diff options
33 files changed, 8233 insertions, 1258 deletions
diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index 84e7d91a5c..2f7088614a 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -707,8 +707,9 @@ void tlb_flush_page_all_cpus_synced(CPUState *src, target_ulong addr) tlb_flush_page_by_mmuidx_all_cpus_synced(src, addr, ALL_MMUIDX_BITS); } -static void tlb_flush_page_bits_locked(CPUArchState *env, int midx, - target_ulong page, unsigned bits) +static void tlb_flush_range_locked(CPUArchState *env, int midx, + target_ulong addr, target_ulong len, + unsigned bits) { CPUTLBDesc *d = &env_tlb(env)->d[midx]; CPUTLBDescFast *f = &env_tlb(env)->f[midx]; @@ -718,20 +719,26 @@ static void tlb_flush_page_bits_locked(CPUArchState *env, int midx, * If @bits is smaller than the tlb size, there may be multiple entries * within the TLB; otherwise all addresses that match under @mask hit * the same TLB entry. - * * TODO: Perhaps allow bits to be a few bits less than the size. * For now, just flush the entire TLB. + * + * If @len is larger than the tlb size, then it will take longer to + * test all of the entries in the TLB than it will to flush it all. */ - if (mask < f->mask) { + if (mask < f->mask || len > f->mask) { tlb_debug("forcing full flush midx %d (" - TARGET_FMT_lx "/" TARGET_FMT_lx ")\n", - midx, page, mask); + TARGET_FMT_lx "/" TARGET_FMT_lx "+" TARGET_FMT_lx ")\n", + midx, addr, mask, len); tlb_flush_one_mmuidx_locked(env, midx, get_clock_realtime()); return; } - /* Check if we need to flush due to large pages. */ - if ((page & d->large_page_mask) == d->large_page_addr) { + /* + * Check if we need to flush due to large pages. + * Because large_page_mask contains all 1's from the msb, + * we only need to test the end of the range. + */ + if (((addr + len - 1) & d->large_page_mask) == d->large_page_addr) { tlb_debug("forcing full flush midx %d (" TARGET_FMT_lx "/" TARGET_FMT_lx ")\n", midx, d->large_page_addr, d->large_page_mask); @@ -739,85 +746,67 @@ static void tlb_flush_page_bits_locked(CPUArchState *env, int midx, return; } - if (tlb_flush_entry_mask_locked(tlb_entry(env, midx, page), page, mask)) { - tlb_n_used_entries_dec(env, midx); + for (target_ulong i = 0; i < len; i += TARGET_PAGE_SIZE) { + target_ulong page = addr + i; + CPUTLBEntry *entry = tlb_entry(env, midx, page); + + if (tlb_flush_entry_mask_locked(entry, page, mask)) { + tlb_n_used_entries_dec(env, midx); + } + tlb_flush_vtlb_page_mask_locked(env, midx, page, mask); } - tlb_flush_vtlb_page_mask_locked(env, midx, page, mask); } typedef struct { target_ulong addr; + target_ulong len; uint16_t idxmap; uint16_t bits; -} TLBFlushPageBitsByMMUIdxData; +} TLBFlushRangeData; -static void -tlb_flush_page_bits_by_mmuidx_async_0(CPUState *cpu, - TLBFlushPageBitsByMMUIdxData d) +static void tlb_flush_range_by_mmuidx_async_0(CPUState *cpu, + TLBFlushRangeData d) { CPUArchState *env = cpu->env_ptr; int mmu_idx; assert_cpu_is_self(cpu); - tlb_debug("page addr:" TARGET_FMT_lx "/%u mmu_map:0x%x\n", - d.addr, d.bits, d.idxmap); + tlb_debug("range:" TARGET_FMT_lx "/%u+" TARGET_FMT_lx " mmu_map:0x%x\n", + d.addr, d.bits, d.len, d.idxmap); qemu_spin_lock(&env_tlb(env)->c.lock); for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) { if ((d.idxmap >> mmu_idx) & 1) { - tlb_flush_page_bits_locked(env, mmu_idx, d.addr, d.bits); + tlb_flush_range_locked(env, mmu_idx, d.addr, d.len, d.bits); } } qemu_spin_unlock(&env_tlb(env)->c.lock); - tb_flush_jmp_cache(cpu, d.addr); -} - -static bool encode_pbm_to_runon(run_on_cpu_data *out, - TLBFlushPageBitsByMMUIdxData d) -{ - /* We need 6 bits to hold to hold @bits up to 63. */ - if (d.idxmap <= MAKE_64BIT_MASK(0, TARGET_PAGE_BITS - 6)) { - *out = RUN_ON_CPU_TARGET_PTR(d.addr | (d.idxmap << 6) | d.bits); - return true; + for (target_ulong i = 0; i < d.len; i += TARGET_PAGE_SIZE) { + tb_flush_jmp_cache(cpu, d.addr + i); } - return false; -} - -static TLBFlushPageBitsByMMUIdxData -decode_runon_to_pbm(run_on_cpu_data data) -{ - target_ulong addr_map_bits = (target_ulong) data.target_ptr; - return (TLBFlushPageBitsByMMUIdxData){ - .addr = addr_map_bits & TARGET_PAGE_MASK, - .idxmap = (addr_map_bits & ~TARGET_PAGE_MASK) >> 6, - .bits = addr_map_bits & 0x3f - }; } -static void tlb_flush_page_bits_by_mmuidx_async_1(CPUState *cpu, - run_on_cpu_data runon) +static void tlb_flush_range_by_mmuidx_async_1(CPUState *cpu, + run_on_cpu_data data) { - tlb_flush_page_bits_by_mmuidx_async_0(cpu, decode_runon_to_pbm(runon)); -} - -static void tlb_flush_page_bits_by_mmuidx_async_2(CPUState *cpu, - run_on_cpu_data data) -{ - TLBFlushPageBitsByMMUIdxData *d = data.host_ptr; - tlb_flush_page_bits_by_mmuidx_async_0(cpu, *d); + TLBFlushRangeData *d = data.host_ptr; + tlb_flush_range_by_mmuidx_async_0(cpu, *d); g_free(d); } -void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr, - uint16_t idxmap, unsigned bits) +void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr, + target_ulong len, uint16_t idxmap, + unsigned bits) { - TLBFlushPageBitsByMMUIdxData d; - run_on_cpu_data runon; + TLBFlushRangeData d; - /* If all bits are significant, this devolves to tlb_flush_page. */ - if (bits >= TARGET_LONG_BITS) { + /* + * If all bits are significant, and len is small, + * this devolves to tlb_flush_page. + */ + if (bits >= TARGET_LONG_BITS && len <= TARGET_PAGE_SIZE) { tlb_flush_page_by_mmuidx(cpu, addr, idxmap); return; } @@ -829,34 +818,38 @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr, /* This should already be page aligned */ d.addr = addr & TARGET_PAGE_MASK; + d.len = len; d.idxmap = idxmap; d.bits = bits; if (qemu_cpu_is_self(cpu)) { - tlb_flush_page_bits_by_mmuidx_async_0(cpu, d); - } else if (encode_pbm_to_runon(&runon, d)) { - async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon); + tlb_flush_range_by_mmuidx_async_0(cpu, d); } else { - TLBFlushPageBitsByMMUIdxData *p - = g_new(TLBFlushPageBitsByMMUIdxData, 1); - /* Otherwise allocate a structure, freed by the worker. */ - *p = d; - async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_2, + TLBFlushRangeData *p = g_memdup(&d, sizeof(d)); + async_run_on_cpu(cpu, tlb_flush_range_by_mmuidx_async_1, RUN_ON_CPU_HOST_PTR(p)); } } -void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, - target_ulong addr, - uint16_t idxmap, - unsigned bits) +void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr, + uint16_t idxmap, unsigned bits) +{ + tlb_flush_range_by_mmuidx(cpu, addr, TARGET_PAGE_SIZE, idxmap, bits); +} + +void tlb_flush_range_by_mmuidx_all_cpus(CPUState *src_cpu, + target_ulong addr, target_ulong len, + uint16_t idxmap, unsigned bits) { - TLBFlushPageBitsByMMUIdxData d; - run_on_cpu_data runon; + TLBFlushRangeData d; + CPUState *dst_cpu; - /* If all bits are significant, this devolves to tlb_flush_page. */ - if (bits >= TARGET_LONG_BITS) { + /* + * If all bits are significant, and len is small, + * this devolves to tlb_flush_page. + */ + if (bits >= TARGET_LONG_BITS && len <= TARGET_PAGE_SIZE) { tlb_flush_page_by_mmuidx_all_cpus(src_cpu, addr, idxmap); return; } @@ -868,40 +861,45 @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, /* This should already be page aligned */ d.addr = addr & TARGET_PAGE_MASK; + d.len = len; d.idxmap = idxmap; d.bits = bits; - if (encode_pbm_to_runon(&runon, d)) { - flush_all_helper(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon); - } else { - CPUState *dst_cpu; - TLBFlushPageBitsByMMUIdxData *p; - - /* Allocate a separate data block for each destination cpu. */ - CPU_FOREACH(dst_cpu) { - if (dst_cpu != src_cpu) { - p = g_new(TLBFlushPageBitsByMMUIdxData, 1); - *p = d; - async_run_on_cpu(dst_cpu, - tlb_flush_page_bits_by_mmuidx_async_2, - RUN_ON_CPU_HOST_PTR(p)); - } + /* Allocate a separate data block for each destination cpu. */ + CPU_FOREACH(dst_cpu) { + if (dst_cpu != src_cpu) { + TLBFlushRangeData *p = g_memdup(&d, sizeof(d)); + async_run_on_cpu(dst_cpu, + tlb_flush_range_by_mmuidx_async_1, + RUN_ON_CPU_HOST_PTR(p)); } } - tlb_flush_page_bits_by_mmuidx_async_0(src_cpu, d); + tlb_flush_range_by_mmuidx_async_0(src_cpu, d); } -void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu, - target_ulong addr, - uint16_t idxmap, - unsigned bits) +void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, + target_ulong addr, + uint16_t idxmap, unsigned bits) { - TLBFlushPageBitsByMMUIdxData d; - run_on_cpu_data runon; + tlb_flush_range_by_mmuidx_all_cpus(src_cpu, addr, TARGET_PAGE_SIZE, + idxmap, bits); +} + +void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *src_cpu, + target_ulong addr, + target_ulong len, + uint16_t idxmap, + unsigned bits) +{ + TLBFlushRangeData d, *p; + CPUState *dst_cpu; - /* If all bits are significant, this devolves to tlb_flush_page. */ - if (bits >= TARGET_LONG_BITS) { + /* + * If all bits are significant, and len is small, + * this devolves to tlb_flush_page. + */ + if (bits >= TARGET_LONG_BITS && len <= TARGET_PAGE_SIZE) { tlb_flush_page_by_mmuidx_all_cpus_synced(src_cpu, addr, idxmap); return; } @@ -913,32 +911,31 @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu, /* This should already be page aligned */ d.addr = addr & TARGET_PAGE_MASK; + d.len = len; d.idxmap = idxmap; d.bits = bits; - if (encode_pbm_to_runon(&runon, d)) { - flush_all_helper(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon); - async_safe_run_on_cpu(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1, - runon); - } else { - CPUState *dst_cpu; - TLBFlushPageBitsByMMUIdxData *p; - - /* Allocate a separate data block for each destination cpu. */ - CPU_FOREACH(dst_cpu) { - if (dst_cpu != src_cpu) { - p = g_new(TLBFlushPageBitsByMMUIdxData, 1); - *p = d; - async_run_on_cpu(dst_cpu, tlb_flush_page_bits_by_mmuidx_async_2, - RUN_ON_CPU_HOST_PTR(p)); - } + /* Allocate a separate data block for each destination cpu. */ + CPU_FOREACH(dst_cpu) { + if (dst_cpu != src_cpu) { + p = g_memdup(&d, sizeof(d)); + async_run_on_cpu(dst_cpu, tlb_flush_range_by_mmuidx_async_1, + RUN_ON_CPU_HOST_PTR(p)); } - - p = g_new(TLBFlushPageBitsByMMUIdxData, 1); - *p = d; - async_safe_run_on_cpu(src_cpu, tlb_flush_page_bits_by_mmuidx_async_2, - RUN_ON_CPU_HOST_PTR(p)); } + + p = g_memdup(&d, sizeof(d)); + async_safe_run_on_cpu(src_cpu, tlb_flush_range_by_mmuidx_async_1, + RUN_ON_CPU_HOST_PTR(p)); +} + +void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu, + target_ulong addr, + uint16_t idxmap, + unsigned bits) +{ + tlb_flush_range_by_mmuidx_all_cpus_synced(src_cpu, addr, TARGET_PAGE_SIZE, + idxmap, bits); } /* update the TLBs so that writes to code in the virtual page 'addr' diff --git a/disas/libvixl/vixl/code-buffer.h b/disas/libvixl/vixl/code-buffer.h index f93ebb6b82..b95babbdee 100644 --- a/disas/libvixl/vixl/code-buffer.h +++ b/disas/libvixl/vixl/code-buffer.h @@ -27,7 +27,7 @@ #ifndef VIXL_CODE_BUFFER_H #define VIXL_CODE_BUFFER_H -#include <string.h> +#include <cstring> #include "vixl/globals.h" namespace vixl { diff --git a/disas/libvixl/vixl/globals.h b/disas/libvixl/vixl/globals.h index 7099aa599f..3a71942f1e 100644 --- a/disas/libvixl/vixl/globals.h +++ b/disas/libvixl/vixl/globals.h @@ -40,15 +40,17 @@ #define __STDC_FORMAT_MACROS #endif -#include <stdint.h> +extern "C" { #include <inttypes.h> - -#include <assert.h> -#include <stdarg.h> -#include <stdio.h> #include <stdint.h> -#include <stdlib.h> -#include <stddef.h> +} + +#include <cassert> +#include <cstdarg> +#include <cstddef> +#include <cstdio> +#include <cstdlib> + #include "vixl/platform.h" diff --git a/disas/libvixl/vixl/invalset.h b/disas/libvixl/vixl/invalset.h index ffdc0237b4..2e0871f8c3 100644 --- a/disas/libvixl/vixl/invalset.h +++ b/disas/libvixl/vixl/invalset.h @@ -27,7 +27,7 @@ #ifndef VIXL_INVALSET_H_ #define VIXL_INVALSET_H_ -#include <string.h> +#include <cstring> #include <algorithm> #include <vector> diff --git a/disas/libvixl/vixl/platform.h b/disas/libvixl/vixl/platform.h index ab588f07f5..26a74de81b 100644 --- a/disas/libvixl/vixl/platform.h +++ b/disas/libvixl/vixl/platform.h @@ -28,7 +28,9 @@ #define PLATFORM_H // Define platform specific functionalities. +extern "C" { #include <signal.h> +} namespace vixl { inline void HostBreakpoint() { raise(SIGINT); } diff --git a/disas/libvixl/vixl/utils.cc b/disas/libvixl/vixl/utils.cc index 3b8bd75fba..69304d266d 100644 --- a/disas/libvixl/vixl/utils.cc +++ b/disas/libvixl/vixl/utils.cc @@ -25,7 +25,7 @@ // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. #include "vixl/utils.h" -#include <stdio.h> +#include <cstdio> namespace vixl { diff --git a/disas/libvixl/vixl/utils.h b/disas/libvixl/vixl/utils.h index 5ab134e240..ecb0f1014a 100644 --- a/disas/libvixl/vixl/utils.h +++ b/disas/libvixl/vixl/utils.h @@ -27,8 +27,8 @@ #ifndef VIXL_UTILS_H #define VIXL_UTILS_H -#include <string.h> #include <cmath> +#include <cstring> #include "vixl/globals.h" #include "vixl/compiler-intrinsics.h" diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c index 2e5d0679e7..a1456cb0f4 100644 --- a/hw/arm/armsse.c +++ b/hw/arm/armsse.c @@ -13,6 +13,7 @@ #include "qemu/log.h" #include "qemu/module.h" #include "qemu/bitops.h" +#include "qemu/units.h" #include "qapi/error.h" #include "trace.h" #include "hw/sysbus.h" @@ -59,6 +60,7 @@ struct ARMSSEInfo { const char *cpu_type; uint32_t sse_version; int sram_banks; + uint32_t sram_bank_base; int num_cpus; uint32_t sys_version; uint32_t iidr; @@ -69,6 +71,7 @@ struct ARMSSEInfo { bool has_cpuid; bool has_cpu_pwrctrl; bool has_sse_counter; + bool has_tcms; Property *props; const ARMSSEDeviceInfo *devinfo; const bool *irq_is_common; @@ -102,7 +105,7 @@ static Property sse300_properties[] = { DEFINE_PROP_LINK("memory", ARMSSE, board_memory, TYPE_MEMORY_REGION, MemoryRegion *), DEFINE_PROP_UINT32("EXP_NUMIRQ", ARMSSE, exp_numirq, 64), - DEFINE_PROP_UINT32("SRAM_ADDR_WIDTH", ARMSSE, sram_addr_width, 15), + DEFINE_PROP_UINT32("SRAM_ADDR_WIDTH", ARMSSE, sram_addr_width, 18), DEFINE_PROP_UINT32("init-svtor", ARMSSE, init_svtor, 0x10000000), DEFINE_PROP_BOOL("CPU0_FPU", ARMSSE, cpu_fpu[0], true), DEFINE_PROP_BOOL("CPU0_DSP", ARMSSE, cpu_dsp[0], true), @@ -504,6 +507,7 @@ static const ARMSSEInfo armsse_variants[] = { .sse_version = ARMSSE_IOTKIT, .cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"), .sram_banks = 1, + .sram_bank_base = 0x20000000, .num_cpus = 1, .sys_version = 0x41743, .iidr = 0, @@ -514,6 +518,7 @@ static const ARMSSEInfo armsse_variants[] = { .has_cpuid = false, .has_cpu_pwrctrl = false, .has_sse_counter = false, + .has_tcms = false, .props = iotkit_properties, .devinfo = iotkit_devices, .irq_is_common = sse200_irq_is_common, @@ -523,6 +528,7 @@ static const ARMSSEInfo armsse_variants[] = { .sse_version = ARMSSE_SSE200, .cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"), .sram_banks = 4, + .sram_bank_base = 0x20000000, .num_cpus = 2, .sys_version = 0x22041743, .iidr = 0, @@ -533,6 +539,7 @@ static const ARMSSEInfo armsse_variants[] = { .has_cpuid = true, .has_cpu_pwrctrl = false, .has_sse_counter = false, + .has_tcms = false, .props = sse200_properties, .devinfo = sse200_devices, .irq_is_common = sse200_irq_is_common, @@ -542,6 +549,7 @@ static const ARMSSEInfo armsse_variants[] = { .sse_version = ARMSSE_SSE300, .cpu_type = ARM_CPU_TYPE_NAME("cortex-m55"), .sram_banks = 2, + .sram_bank_base = 0x21000000, .num_cpus = 1, .sys_version = 0x7e00043b, .iidr = 0x74a0043b, @@ -552,6 +560,7 @@ static const ARMSSEInfo armsse_variants[] = { .has_cpuid = true, .has_cpu_pwrctrl = true, .has_sse_counter = true, + .has_tcms = true, .props = sse300_properties, .devinfo = sse300_devices, .irq_is_common = sse300_irq_is_common, @@ -909,7 +918,6 @@ static void armsse_realize(DeviceState *dev, Error **errp) const ARMSSEDeviceInfo *devinfo; int i; MemoryRegion *mr; - Error *err = NULL; SysBusDevice *sbd_apb_ppc0; SysBusDevice *sbd_secctl; DeviceState *dev_apb_ppc0; @@ -918,6 +926,8 @@ static void armsse_realize(DeviceState *dev, Error **errp) DeviceState *dev_splitter; uint32_t addr_width_max; + ERRP_GUARD(); + if (!s->board_memory) { error_setg(errp, "memory property was not set"); return; @@ -1147,10 +1157,9 @@ static void armsse_realize(DeviceState *dev, Error **errp) uint32_t sram_bank_size = 1 << s->sram_addr_width; memory_region_init_ram(&s->sram[i], NULL, ramname, - sram_bank_size, &err); + sram_bank_size, errp); g_free(ramname); - if (err) { - error_propagate(errp, err); + if (*errp) { return; } object_property_set_link(OBJECT(&s->mpc[i]), "downstream", @@ -1161,7 +1170,7 @@ static void armsse_realize(DeviceState *dev, Error **errp) /* Map the upstream end of the MPC into the right place... */ sbd_mpc = SYS_BUS_DEVICE(&s->mpc[i]); memory_region_add_subregion(&s->container, - 0x20000000 + i * sram_bank_size, + info->sram_bank_base + i * sram_bank_size, sysbus_mmio_get_region(sbd_mpc, 1)); /* ...and its register interface */ memory_region_add_subregion(&s->container, 0x50083000 + i * 0x1000, @@ -1210,6 +1219,20 @@ static void armsse_realize(DeviceState *dev, Error **errp) sysbus_mmio_get_region(sbd, 1)); } + if (info->has_tcms) { + /* The SSE-300 has an ITCM at 0x0000_0000 and a DTCM at 0x2000_0000 */ + memory_region_init_ram(&s->itcm, NULL, "sse300-itcm", 512 * KiB, errp); + if (*errp) { + return; + } + memory_region_init_ram(&s->dtcm, NULL, "sse300-dtcm", 512 * KiB, errp); + if (*errp) { + return; + } + memory_region_add_subregion(&s->container, 0x00000000, &s->itcm); + memory_region_add_subregion(&s->container, 0x20000000, &s->dtcm); + } + /* Devices behind APB PPC0: * 0x40000000: timer0 * 0x40001000: timer1 diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index 70aa31a7f6..e23830f4b7 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -123,8 +123,10 @@ struct MPS2TZMachineClass { int numirq; /* Number of external interrupts */ int uart_overflow_irq; /* number of the combined UART overflow IRQ */ uint32_t init_svtor; /* init-svtor setting for SSE */ + uint32_t sram_addr_width; /* SRAM_ADDR_WIDTH setting for SSE */ const RAMInfo *raminfo; const char *armsse_type; + uint32_t boot_ram_size; /* size of ram at address 0; 0 == find in raminfo */ }; struct MPS2TZMachineState { @@ -244,18 +246,12 @@ static const RAMInfo an524_raminfo[] = { { .mpc = 0, .mrindex = 0, }, { - .name = "sram", - .base = 0x20000000, - .size = 32 * 4 * KiB, - .mpc = -1, - .mrindex = 1, - }, { /* We don't model QSPI flash yet; for now expose it as simple ROM */ .name = "QSPI", .base = 0x28000000, .size = 8 * MiB, .mpc = 1, - .mrindex = 2, + .mrindex = 1, .flags = IS_ROM, }, { .name = "DDR", @@ -269,24 +265,12 @@ static const RAMInfo an524_raminfo[] = { { }; static const RAMInfo an547_raminfo[] = { { - .name = "itcm", - .base = 0x00000000, - .size = 512 * KiB, - .mpc = -1, - .mrindex = 0, - }, { .name = "sram", .base = 0x01000000, .size = 2 * MiB, .mpc = 0, .mrindex = 1, }, { - .name = "dtcm", - .base = 0x20000000, - .size = 4 * 128 * KiB, - .mpc = -1, - .mrindex = 2, - }, { .name = "sram 2", .base = 0x21000000, .size = 4 * MiB, @@ -766,6 +750,14 @@ static uint32_t boot_ram_size(MPS2TZMachineState *mms) const RAMInfo *p; MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); + /* + * Use a per-board specification (for when the boot RAM is in + * the SSE and so doesn't have a RAMInfo list entry) + */ + if (mmc->boot_ram_size) { + return mmc->boot_ram_size; + } + for (p = mmc->raminfo; p->name; p++) { if (p->base == boot_mem_base(mms)) { return p->size; @@ -812,6 +804,7 @@ static void mps2tz_common_init(MachineState *machine) OBJECT(system_memory), &error_abort); qdev_prop_set_uint32(iotkitdev, "EXP_NUMIRQ", mmc->numirq); qdev_prop_set_uint32(iotkitdev, "init-svtor", mmc->init_svtor); + qdev_prop_set_uint32(iotkitdev, "SRAM_ADDR_WIDTH", mmc->sram_addr_width); qdev_connect_clock_in(iotkitdev, "MAINCLK", mms->sysclk); qdev_connect_clock_in(iotkitdev, "S32KCLK", mms->s32kclk); sysbus_realize(SYS_BUS_DEVICE(&mms->iotkit), &error_fatal); @@ -1269,8 +1262,10 @@ static void mps2tz_an505_class_init(ObjectClass *oc, void *data) mmc->numirq = 92; mmc->uart_overflow_irq = 47; mmc->init_svtor = 0x10000000; + mmc->sram_addr_width = 15; mmc->raminfo = an505_raminfo; mmc->armsse_type = TYPE_IOTKIT; + mmc->boot_ram_size = 0; mps2tz_set_default_ram_info(mmc); } @@ -1296,8 +1291,10 @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data) mmc->numirq = 92; mmc->uart_overflow_irq = 47; mmc->init_svtor = 0x10000000; + mmc->sram_addr_width = 15; mmc->raminfo = an505_raminfo; /* AN521 is the same as AN505 here */ mmc->armsse_type = TYPE_SSE200; + mmc->boot_ram_size = 0; mps2tz_set_default_ram_info(mmc); } @@ -1323,8 +1320,10 @@ static void mps3tz_an524_class_init(ObjectClass *oc, void *data) mmc->numirq = 95; mmc->uart_overflow_irq = 47; mmc->init_svtor = 0x10000000; + mmc->sram_addr_width = 15; mmc->raminfo = an524_raminfo; mmc->armsse_type = TYPE_SSE200; + mmc->boot_ram_size = 0; mps2tz_set_default_ram_info(mmc); object_class_property_add_str(oc, "remap", mps2_get_remap, mps2_set_remap); @@ -1355,8 +1354,10 @@ static void mps3tz_an547_class_init(ObjectClass *oc, void *data) mmc->numirq = 96; mmc->uart_overflow_irq = 48; mmc->init_svtor = 0x00000000; + mmc->sram_addr_width = 21; mmc->raminfo = an547_raminfo; mmc->armsse_type = TYPE_SSE300; + mmc->boot_ram_size = 512 * KiB; mps2tz_set_default_ram_info(mmc); } diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c index 7bed2ac520..01b60bee49 100644 --- a/hw/arm/smmuv3.c +++ b/hw/arm/smmuv3.c @@ -857,43 +857,45 @@ static void smmuv3_inv_notifiers_iova(SMMUState *s, int asid, dma_addr_t iova, static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd) { - uint8_t scale = 0, num = 0, ttl = 0; - dma_addr_t addr = CMD_ADDR(cmd); + dma_addr_t end, addr = CMD_ADDR(cmd); uint8_t type = CMD_TYPE(cmd); uint16_t vmid = CMD_VMID(cmd); + uint8_t scale = CMD_SCALE(cmd); + uint8_t num = CMD_NUM(cmd); + uint8_t ttl = CMD_TTL(cmd); bool leaf = CMD_LEAF(cmd); uint8_t tg = CMD_TG(cmd); - uint64_t first_page = 0, last_page; - uint64_t num_pages = 1; + uint64_t num_pages; + uint8_t granule; int asid = -1; - if (tg) { - scale = CMD_SCALE(cmd); - num = CMD_NUM(cmd); - ttl = CMD_TTL(cmd); - num_pages = (num + 1) * BIT_ULL(scale); - } - if (type == SMMU_CMD_TLBI_NH_VA) { asid = CMD_ASID(cmd); } - /* Split invalidations into ^2 range invalidations */ - last_page = num_pages - 1; - while (num_pages) { - uint8_t granule = tg * 2 + 10; - uint64_t mask, count; + if (!tg) { + trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, 1, ttl, leaf); + smmuv3_inv_notifiers_iova(s, asid, addr, tg, 1); + smmu_iotlb_inv_iova(s, asid, addr, tg, 1, ttl); + return; + } + + /* RIL in use */ - mask = dma_aligned_pow2_mask(first_page, last_page, 64 - granule); - count = mask + 1; + num_pages = (num + 1) * BIT_ULL(scale); + granule = tg * 2 + 10; + + /* Split invalidations into ^2 range invalidations */ + end = addr + (num_pages << granule) - 1; - trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, count, ttl, leaf); - smmuv3_inv_notifiers_iova(s, asid, addr, tg, count); - smmu_iotlb_inv_iova(s, asid, addr, tg, count, ttl); + while (addr != end + 1) { + uint64_t mask = dma_aligned_pow2_mask(addr, end, 64); - num_pages -= count; - first_page += count; - addr += count * BIT_ULL(granule); + num_pages = (mask + 1) >> granule; + trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, num_pages, ttl, leaf); + smmuv3_inv_notifiers_iova(s, asid, addr, tg, num_pages); + smmu_iotlb_inv_iova(s, asid, addr, tg, num_pages, ttl); + addr += mask + 1; } } diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index 43ef1d7a84..81f94c7f4a 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -1307,27 +1307,16 @@ static void icc_eoir_write(CPUARMState *env, const ARMCPRegInfo *ri, GICv3CPUState *cs = icc_cs_from_env(env); int irq = value & 0xffffff; int grp; + bool is_eoir0 = ri->crm == 8; - if (icv_access(env, ri->crm == 8 ? HCR_FMO : HCR_IMO)) { + if (icv_access(env, is_eoir0 ? HCR_FMO : HCR_IMO)) { icv_eoir_write(env, ri, value); return; } - trace_gicv3_icc_eoir_write(ri->crm == 8 ? 0 : 1, + trace_gicv3_icc_eoir_write(is_eoir0 ? 0 : 1, gicv3_redist_affid(cs), value); - if (ri->crm == 8) { - /* EOIR0 */ - grp = GICV3_G0; - } else { - /* EOIR1 */ - if (arm_is_secure(env)) { - grp = GICV3_G1; - } else { - grp = GICV3_G1NS; - } - } - if (irq >= cs->gic->num_irq) { /* This handles two cases: * 1. If software writes the ID of a spurious interrupt [ie 1020-1023] @@ -1340,8 +1329,35 @@ static void icc_eoir_write(CPUARMState *env, const ARMCPRegInfo *ri, return; } - if (icc_highest_active_group(cs) != grp) { - return; + grp = icc_highest_active_group(cs); + switch (grp) { + case GICV3_G0: + if (!is_eoir0) { + return; + } + if (!(cs->gic->gicd_ctlr & GICD_CTLR_DS) + && arm_feature(env, ARM_FEATURE_EL3) && !arm_is_secure(env)) { + return; + } + break; + case GICV3_G1: + if (is_eoir0) { + return; + } + if (!arm_is_secure(env)) { + return; + } + break; + case GICV3_G1NS: + if (is_eoir0) { + return; + } + if (!arm_is_el3_or_mon(env) && arm_is_secure(env)) { + return; + } + break; + default: + g_assert_not_reached(); } icc_drop_prio(cs, grp); diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index 6b036cae8f..8021adf38f 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -263,6 +263,31 @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced (CPUState *cpu, target_ulong addr, uint16_t idxmap, unsigned bits); /** + * tlb_flush_range_by_mmuidx + * @cpu: CPU whose TLB should be flushed + * @addr: virtual address of the start of the range to be flushed + * @len: length of range to be flushed + * @idxmap: bitmap of mmu indexes to flush + * @bits: number of significant bits in address + * + * For each mmuidx in @idxmap, flush all pages within [@addr,@addr+@len), + * comparing only the low @bits worth of each virtual page. + */ +void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr, + target_ulong len, uint16_t idxmap, + unsigned bits); + +/* Similarly, with broadcast and syncing. */ +void tlb_flush_range_by_mmuidx_all_cpus(CPUState *cpu, target_ulong addr, + target_ulong len, uint16_t idxmap, + unsigned bits); +void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *cpu, + target_ulong addr, + target_ulong len, + uint16_t idxmap, + unsigned bits); + +/** * tlb_set_page_with_attrs: * @cpu: CPU to add this TLB entry for * @vaddr: virtual address of page to add entry for @@ -365,6 +390,25 @@ tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *cpu, target_ulong addr, uint16_t idxmap, unsigned bits) { } +static inline void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr, + target_ulong len, uint16_t idxmap, + unsigned bits) +{ +} +static inline void tlb_flush_range_by_mmuidx_all_cpus(CPUState *cpu, + target_ulong addr, + target_ulong len, + uint16_t idxmap, + unsigned bits) +{ +} +static inline void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *cpu, + target_ulong addr, + target_long len, + uint16_t idxmap, + unsigned bits) +{ +} #endif /** * probe_access: diff --git a/include/hw/arm/armsse.h b/include/hw/arm/armsse.h index 36592be62c..9648e7a419 100644 --- a/include/hw/arm/armsse.h +++ b/include/hw/arm/armsse.h @@ -198,6 +198,8 @@ struct ARMSSE { MemoryRegion alias2; MemoryRegion alias3[SSE_MAX_CPUS]; MemoryRegion sram[MAX_SRAM_BANKS]; + MemoryRegion itcm; + MemoryRegion dtcm; qemu_irq *exp_irqs[SSE_MAX_CPUS]; qemu_irq ppc0_irq; diff --git a/linux-user/elfload.c b/linux-user/elfload.c index 0e832b2649..1ab97e38e0 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -648,8 +648,18 @@ static uint32_t get_elf_hwcap2(void) uint32_t hwcaps = 0; GET_FEATURE_ID(aa64_dcpodp, ARM_HWCAP2_A64_DCPODP); + GET_FEATURE_ID(aa64_sve2, ARM_HWCAP2_A64_SVE2); + GET_FEATURE_ID(aa64_sve2_aes, ARM_HWCAP2_A64_SVEAES); + GET_FEATURE_ID(aa64_sve2_pmull128, ARM_HWCAP2_A64_SVEPMULL); + GET_FEATURE_ID(aa64_sve2_bitperm, ARM_HWCAP2_A64_SVEBITPERM); + GET_FEATURE_ID(aa64_sve2_sha3, ARM_HWCAP2_A64_SVESHA3); + GET_FEATURE_ID(aa64_sve2_sm4, ARM_HWCAP2_A64_SVESM4); GET_FEATURE_ID(aa64_condm_5, ARM_HWCAP2_A64_FLAGM2); GET_FEATURE_ID(aa64_frint, ARM_HWCAP2_A64_FRINT); + GET_FEATURE_ID(aa64_sve_i8mm, ARM_HWCAP2_A64_SVEI8MM); + GET_FEATURE_ID(aa64_sve_f32mm, ARM_HWCAP2_A64_SVEF32MM); + GET_FEATURE_ID(aa64_sve_f64mm, ARM_HWCAP2_A64_SVEF64MM); + GET_FEATURE_ID(aa64_i8mm, ARM_HWCAP2_A64_I8MM); GET_FEATURE_ID(aa64_rndr, ARM_HWCAP2_A64_RNG); GET_FEATURE_ID(aa64_bti, ARM_HWCAP2_A64_BTI); GET_FEATURE_ID(aa64_mte, ARM_HWCAP2_A64_MTE); diff --git a/target/arm/cpu.c b/target/arm/cpu.c index 4eb0d2f85c..7aeb4b1381 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -1503,6 +1503,7 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) t = cpu->isar.id_aa64isar1; t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 0); + t = FIELD_DP64(t, ID_AA64ISAR1, I8MM, 0); cpu->isar.id_aa64isar1 = t; t = cpu->isar.id_aa64pfr0; @@ -1517,6 +1518,7 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) u = cpu->isar.id_isar6; u = FIELD_DP32(u, ID_ISAR6, DP, 0); u = FIELD_DP32(u, ID_ISAR6, FHM, 0); + u = FIELD_DP32(u, ID_ISAR6, I8MM, 0); cpu->isar.id_isar6 = u; if (!arm_feature(env, ARM_FEATURE_M)) { diff --git a/target/arm/cpu.h b/target/arm/cpu.h index 616b393253..04f8be35bf 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -947,6 +947,7 @@ struct ARMCPU { uint64_t id_aa64mmfr2; uint64_t id_aa64dfr0; uint64_t id_aa64dfr1; + uint64_t id_aa64zfr0; } isar; uint64_t midr; uint32_t revidr; @@ -2034,6 +2035,16 @@ FIELD(ID_AA64DFR0, DOUBLELOCK, 36, 4) FIELD(ID_AA64DFR0, TRACEFILT, 40, 4) FIELD(ID_AA64DFR0, MTPMU, 48, 4) +FIELD(ID_AA64ZFR0, SVEVER, 0, 4) +FIELD(ID_AA64ZFR0, AES, 4, 4) +FIELD(ID_AA64ZFR0, BITPERM, 16, 4) +FIELD(ID_AA64ZFR0, BFLOAT16, 20, 4) +FIELD(ID_AA64ZFR0, SHA3, 32, 4) +FIELD(ID_AA64ZFR0, SM4, 40, 4) +FIELD(ID_AA64ZFR0, I8MM, 44, 4) +FIELD(ID_AA64ZFR0, F32MM, 52, 4) +FIELD(ID_AA64ZFR0, F64MM, 56, 4) + FIELD(ID_DFR0, COPDBG, 0, 4) FIELD(ID_DFR0, COPSDBG, 4, 4) FIELD(ID_DFR0, MMAPDBG, 8, 4) @@ -3772,6 +3783,11 @@ static inline bool isar_feature_aa32_predinv(const ARMISARegisters *id) return FIELD_EX32(id->id_isar6, ID_ISAR6, SPECRES) != 0; } +static inline bool isar_feature_aa32_i8mm(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar6, ID_ISAR6, I8MM) != 0; +} + static inline bool isar_feature_aa32_ras(const ARMISARegisters *id) { return FIELD_EX32(id->id_pfr0, ID_PFR0, RAS) != 0; @@ -4071,6 +4087,16 @@ static inline bool isar_feature_aa64_pauth_arch(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, APA) != 0; } +static inline bool isar_feature_aa64_tlbirange(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) == 2; +} + +static inline bool isar_feature_aa64_tlbios(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) != 0; +} + static inline bool isar_feature_aa64_sb(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, SB) != 0; @@ -4195,6 +4221,11 @@ static inline bool isar_feature_aa64_rcpc_8_4(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) >= 2; } +static inline bool isar_feature_aa64_i8mm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, I8MM) != 0; +} + static inline bool isar_feature_aa64_ccidx(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, CCIDX) != 0; @@ -4215,6 +4246,51 @@ static inline bool isar_feature_aa64_ssbs(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SSBS) != 0; } +static inline bool isar_feature_aa64_sve2(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SVEVER) != 0; +} + +static inline bool isar_feature_aa64_sve2_aes(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, AES) != 0; +} + +static inline bool isar_feature_aa64_sve2_pmull128(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, AES) >= 2; +} + +static inline bool isar_feature_aa64_sve2_bitperm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BITPERM) != 0; +} + +static inline bool isar_feature_aa64_sve2_sha3(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SHA3) != 0; +} + +static inline bool isar_feature_aa64_sve2_sm4(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SM4) != 0; +} + +static inline bool isar_feature_aa64_sve_i8mm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, I8MM) != 0; +} + +static inline bool isar_feature_aa64_sve_f32mm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, F32MM) != 0; +} + +static inline bool isar_feature_aa64_sve_f64mm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, F64MM) != 0; +} + /* * Feature tests for "does this exist in either 32-bit or 64-bit?" */ diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index f0a9e968c9..d561dc7acc 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -651,6 +651,7 @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64ISAR0, DP, 1); t = FIELD_DP64(t, ID_AA64ISAR0, FHM, 1); t = FIELD_DP64(t, ID_AA64ISAR0, TS, 2); /* v8.5-CondM */ + t = FIELD_DP64(t, ID_AA64ISAR0, TLB, 2); /* FEAT_TLBIRANGE */ t = FIELD_DP64(t, ID_AA64ISAR0, RNDR, 1); cpu->isar.id_aa64isar0 = t; @@ -662,6 +663,7 @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64ISAR1, SPECRES, 1); t = FIELD_DP64(t, ID_AA64ISAR1, FRINTTS, 1); t = FIELD_DP64(t, ID_AA64ISAR1, LRCPC, 2); /* ARMv8.4-RCPC */ + t = FIELD_DP64(t, ID_AA64ISAR1, I8MM, 1); cpu->isar.id_aa64isar1 = t; t = cpu->isar.id_aa64pfr0; @@ -702,6 +704,17 @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64MMFR2, ST, 1); /* TTST */ cpu->isar.id_aa64mmfr2 = t; + t = cpu->isar.id_aa64zfr0; + t = FIELD_DP64(t, ID_AA64ZFR0, SVEVER, 1); + t = FIELD_DP64(t, ID_AA64ZFR0, AES, 2); /* PMULL */ + t = FIELD_DP64(t, ID_AA64ZFR0, BITPERM, 1); + t = FIELD_DP64(t, ID_AA64ZFR0, SHA3, 1); + t = FIELD_DP64(t, ID_AA64ZFR0, SM4, 1); + t = FIELD_DP64(t, ID_AA64ZFR0, I8MM, 1); + t = FIELD_DP64(t, ID_AA64ZFR0, F32MM, 1); + t = FIELD_DP64(t, ID_AA64ZFR0, F64MM, 1); + cpu->isar.id_aa64zfr0 = t; + /* Replicate the same data to the 32-bit id registers. */ u = cpu->isar.id_isar5; u = FIELD_DP32(u, ID_ISAR5, AES, 2); /* AES + PMULL */ @@ -718,6 +731,7 @@ static void aarch64_max_initfn(Object *obj) u = FIELD_DP32(u, ID_ISAR6, FHM, 1); u = FIELD_DP32(u, ID_ISAR6, SB, 1); u = FIELD_DP32(u, ID_ISAR6, SPECRES, 1); + u = FIELD_DP32(u, ID_ISAR6, I8MM, 1); cpu->isar.id_isar6 = u; u = cpu->isar.id_pfr0; diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index 046e476f65..d3458335ed 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -968,6 +968,7 @@ static void arm_max_initfn(Object *obj) t = FIELD_DP32(t, ID_ISAR6, FHM, 1); t = FIELD_DP32(t, ID_ISAR6, SB, 1); t = FIELD_DP32(t, ID_ISAR6, SPECRES, 1); + t = FIELD_DP32(t, ID_ISAR6, I8MM, 1); cpu->isar.id_isar6 = t; t = cpu->isar.mvfr1; diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index e4cadd2a65..29a14a21f5 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -158,6 +158,128 @@ DEF_HELPER_FLAGS_5(sve_umulh_zpzz_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve_umulh_zpzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sadalp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sadalp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sadalp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uadalp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uadalp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uadalp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_srshl_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_srshl_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_srshl_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_srshl_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_urshl_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_urshl_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_urshl_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_urshl_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqshl_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqshl_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqshl_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqshl_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uqshl_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqshl_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqshl_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqshl_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqrshl_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrshl_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrshl_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrshl_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_shadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_shadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_shadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_shadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uhadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uhadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uhadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uhadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_srhadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_srhadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_srhadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_srhadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_urhadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_urhadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_urhadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_urhadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_shsub_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_shsub_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_shsub_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_shsub_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uhsub_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uhsub_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uhsub_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uhsub_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_sdiv_zpzz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_sdiv_zpzz_d, TCG_CALL_NO_RWG, @@ -204,6 +326,105 @@ DEF_HELPER_FLAGS_5(sve_sel_zpzz_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve_sel_zpzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_addp_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_addp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_addp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_addp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_smaxp_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smaxp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smaxp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smaxp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_umaxp_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umaxp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umaxp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umaxp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sminp_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sminp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sminp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sminp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uminp_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uminp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uminp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uminp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uqadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqsub_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqsub_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqsub_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqsub_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uqsub_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqsub_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqsub_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqsub_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_suqadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_suqadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_suqadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_suqadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_usqadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_usqadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_usqadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_usqadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_asr_zpzw_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_asr_zpzw_h, TCG_CALL_NO_RWG, @@ -440,6 +661,16 @@ DEF_HELPER_FLAGS_4(sve_tbl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_tbl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_tbl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_tbl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_tbl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_tbl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_tbl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_tbx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_tbx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_tbx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_tbx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(sve_sunpk_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_sunpk_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_sunpk_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) @@ -458,16 +689,19 @@ DEF_HELPER_FLAGS_4(sve_zip_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_zip_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_zip_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_zip_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_zip_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_uzp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_uzp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_uzp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_uzp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_uzp_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_trn_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_trn_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_trn_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_trn_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_trn_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_compact_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_compact_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) @@ -488,6 +722,19 @@ DEF_HELPER_FLAGS_4(sve_rbit_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_rbit_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_rbit_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqabs_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqabs_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqabs_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqabs_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_sqneg_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqneg_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqneg_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqneg_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_urecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_ursqrte_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_splice, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_cmpeq_ppzz_b, TCG_CALL_NO_RWG, @@ -679,7 +926,8 @@ DEF_HELPER_FLAGS_4(sve_brkns, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_cntp, TCG_CALL_NO_RWG, i64, ptr, ptr, i32) -DEF_HELPER_FLAGS_3(sve_while, TCG_CALL_NO_RWG, i32, ptr, i32, i32) +DEF_HELPER_FLAGS_3(sve_whilel, TCG_CALL_NO_RWG, i32, ptr, i32, i32) +DEF_HELPER_FLAGS_3(sve_whileg, TCG_CALL_NO_RWG, i32, ptr, i32, i32) DEF_HELPER_FLAGS_4(sve_subri_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(sve_subri_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) @@ -1133,6 +1381,46 @@ DEF_HELPER_FLAGS_5(sve_ftmad_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_ftmad_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_ftmad_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_saddl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_saddl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_saddl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_ssubl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_ssubl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_ssubl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_sabdl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sabdl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sabdl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_uaddl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_uaddl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_uaddl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_usubl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_usubl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_usubl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_uabdl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_uabdl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_uabdl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_saddw_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_saddw_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_saddw_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_ssubw_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_ssubw_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_ssubw_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_uaddw_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_uaddw_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_uaddw_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_usubw_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_usubw_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_usubw_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve_ld1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld2bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld3bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -2073,4 +2361,436 @@ DEF_HELPER_FLAGS_6(sve_stdd_le_zd_mte, TCG_CALL_NO_WG, DEF_HELPER_FLAGS_6(sve_stdd_be_zd_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmull_zzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmull_zzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmull_zzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_smull_zzz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_smull_zzz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_smull_zzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_umull_zzz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_umull_zzz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_umull_zzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve2_pmull_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_pmull_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sshll_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sshll_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sshll_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_ushll_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_ushll_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_ushll_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_eoril_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_eoril_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_eoril_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_eoril_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_bext_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_bext_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_bext_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_bext_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_bdep_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_bdep_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_bdep_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_bdep_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_bgrp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_bgrp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_bgrp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_bgrp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_cadd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_cadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_cadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_cadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_sqcadd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqcadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqcadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqcadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sabal_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sabal_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sabal_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uabal_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uabal_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uabal_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_adcl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_adcl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqxtnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqxtnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqxtnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_uqxtnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqxtnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqxtnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqxtunb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqxtunb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqxtunb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqxtnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqxtnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqxtnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_uqxtnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqxtnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqxtnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqxtunt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqxtunt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqxtunt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_shrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_shrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_shrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_shrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_shrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_shrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_rshrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_rshrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_rshrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_rshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_rshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_rshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqshrunb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqshrunb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqshrunb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqshrunt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqshrunt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqshrunt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqrshrunb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqrshrunb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqrshrunb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqrshrunt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqrshrunt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqrshrunt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqshrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqshrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqshrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqrshrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqrshrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqrshrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqrshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqrshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqrshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_uqshrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqshrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqshrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_uqshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_uqrshrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqrshrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqrshrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_uqrshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqrshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqrshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_addhnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_addhnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_addhnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_addhnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_addhnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_addhnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_raddhnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_raddhnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_raddhnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_raddhnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_raddhnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_raddhnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_subhnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_subhnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_subhnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_subhnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_subhnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_subhnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_rsubhnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_rsubhnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_rsubhnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_rsubhnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_rsubhnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_rsubhnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_match_ppzz_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_match_ppzz_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_nmatch_ppzz_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_nmatch_ppzz_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_histcnt_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_histcnt_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_histseg, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_xar_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_xar_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_xar_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve2_fmaxnmp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_fmaxnmp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_fmaxnmp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve2_fminnmp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_fminnmp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_fminnmp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve2_fmaxp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_fmaxp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_fmaxp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve2_fminp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_fminp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_fminp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_eor3, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_bcax, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_bsl1n, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_bsl2n, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_nbsl, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqdmlal_zzzw_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqdmlal_zzzw_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqdmlal_zzzw_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqdmlsl_zzzw_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqdmlsl_zzzw_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqdmlsl_zzzw_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_smlal_zzzw_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smlal_zzzw_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smlal_zzzw_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_umlal_zzzw_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umlal_zzzw_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umlal_zzzw_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_smlsl_zzzw_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smlsl_zzzw_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smlsl_zzzw_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_umlsl_zzzw_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umlsl_zzzw_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umlsl_zzzw_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_cmla_zzzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_cmla_zzzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_cmla_zzzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_cmla_zzzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(fmmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(fmmla_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqrdmlah_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlah_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlah_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqdmlal_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqdmlal_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqdmlsl_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqdmlsl_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_sqdmull_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmull_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_smlal_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smlal_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smlsl_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smlsl_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umlal_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umlal_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umlsl_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umlsl_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_smull_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_smull_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_umull_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_umull_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_cmla_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_cmla_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_cdot_zzzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_cdot_zzzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_cdot_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_cdot_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_fcvtnt_sh, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_fcvtnt_ds, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_fcvtlt_hs, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_fcvtlt_sd, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(flogb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(flogb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(flogb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_sqshl_zpzi_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqshl_zpzi_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqshl_zpzi_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqshl_zpzi_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_uqshl_zpzi_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_uqshl_zpzi_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_uqshl_zpzi_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_uqshl_zpzi_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_srshr_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_srshr_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_srshr_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_srshr_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_urshr_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_urshr_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_urshr_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_urshr_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_sqshlu_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqshlu_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqshlu_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqshlu_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/helper.c b/target/arm/helper.c index 3b365a78cb..a66c1f0b9e 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -4759,6 +4759,172 @@ static void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri, ARMMMUIdxBit_SE3, bits); } +#ifdef TARGET_AARCH64 +static uint64_t tlbi_aa64_range_get_length(CPUARMState *env, + uint64_t value) +{ + unsigned int page_shift; + unsigned int page_size_granule; + uint64_t num; + uint64_t scale; + uint64_t exponent; + uint64_t length; + + num = extract64(value, 39, 4); + scale = extract64(value, 44, 2); + page_size_granule = extract64(value, 46, 2); + + page_shift = page_size_granule * 2 + 12; + + if (page_size_granule == 0) { + qemu_log_mask(LOG_GUEST_ERROR, "Invalid page size granule %d\n", + page_size_granule); + return 0; + } + + exponent = (5 * scale) + 1; + length = (num + 1) << (exponent + page_shift); + + return length; +} + +static uint64_t tlbi_aa64_range_get_base(CPUARMState *env, uint64_t value, + bool two_ranges) +{ + /* TODO: ARMv8.7 FEAT_LPA2 */ + uint64_t pageaddr; + + if (two_ranges) { + pageaddr = sextract64(value, 0, 37) << TARGET_PAGE_BITS; + } else { + pageaddr = extract64(value, 0, 37) << TARGET_PAGE_BITS; + } + + return pageaddr; +} + +static void do_rvae_write(CPUARMState *env, uint64_t value, + int idxmap, bool synced) +{ + ARMMMUIdx one_idx = ARM_MMU_IDX_A | ctz32(idxmap); + bool two_ranges = regime_has_2_ranges(one_idx); + uint64_t baseaddr, length; + int bits; + + baseaddr = tlbi_aa64_range_get_base(env, value, two_ranges); + length = tlbi_aa64_range_get_length(env, value); + bits = tlbbits_for_regime(env, one_idx, baseaddr); + + if (synced) { + tlb_flush_range_by_mmuidx_all_cpus_synced(env_cpu(env), + baseaddr, + length, + idxmap, + bits); + } else { + tlb_flush_range_by_mmuidx(env_cpu(env), baseaddr, + length, idxmap, bits); + } +} + +static void tlbi_aa64_rvae1_write(CPUARMState *env, + const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA range, EL1&0. + * Currently handles all of RVAE1, RVAAE1, RVAALE1 and RVALE1, + * since we don't support flush-for-specific-ASID-only or + * flush-last-level-only. + */ + + do_rvae_write(env, value, vae1_tlbmask(env), + tlb_force_broadcast(env)); +} + +static void tlbi_aa64_rvae1is_write(CPUARMState *env, + const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA range, Inner/Outer Shareable EL1&0. + * Currently handles all of RVAE1IS, RVAE1OS, RVAAE1IS, RVAAE1OS, + * RVAALE1IS, RVAALE1OS, RVALE1IS and RVALE1OS, since we don't support + * flush-for-specific-ASID-only, flush-last-level-only or inner/outer + * shareable specific flushes. + */ + + do_rvae_write(env, value, vae1_tlbmask(env), true); +} + +static int vae2_tlbmask(CPUARMState *env) +{ + return (arm_is_secure_below_el3(env) + ? ARMMMUIdxBit_SE2 : ARMMMUIdxBit_E2); +} + +static void tlbi_aa64_rvae2_write(CPUARMState *env, + const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA range, EL2. + * Currently handles all of RVAE2 and RVALE2, + * since we don't support flush-for-specific-ASID-only or + * flush-last-level-only. + */ + + do_rvae_write(env, value, vae2_tlbmask(env), + tlb_force_broadcast(env)); + + +} + +static void tlbi_aa64_rvae2is_write(CPUARMState *env, + const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA range, Inner/Outer Shareable, EL2. + * Currently handles all of RVAE2IS, RVAE2OS, RVALE2IS and RVALE2OS, + * since we don't support flush-for-specific-ASID-only, + * flush-last-level-only or inner/outer shareable specific flushes. + */ + + do_rvae_write(env, value, vae2_tlbmask(env), true); + +} + +static void tlbi_aa64_rvae3_write(CPUARMState *env, + const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA range, EL3. + * Currently handles all of RVAE3 and RVALE3, + * since we don't support flush-for-specific-ASID-only or + * flush-last-level-only. + */ + + do_rvae_write(env, value, ARMMMUIdxBit_SE3, + tlb_force_broadcast(env)); +} + +static void tlbi_aa64_rvae3is_write(CPUARMState *env, + const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA range, EL3, Inner/Outer Shareable. + * Currently handles all of RVAE3IS, RVAE3OS, RVALE3IS and RVALE3OS, + * since we don't support flush-for-specific-ASID-only, + * flush-last-level-only or inner/outer specific flushes. + */ + + do_rvae_write(env, value, ARMMMUIdxBit_SE3, true); +} +#endif + static CPAccessResult aa64_zva_access(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) { @@ -6920,6 +7086,158 @@ static const ARMCPRegInfo pauth_reginfo[] = { REGINFO_SENTINEL }; +static const ARMCPRegInfo tlbirange_reginfo[] = { + { .name = "TLBI_RVAE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 1, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVAAE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 3, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVALE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 5, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVAALE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 7, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVAE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 1, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVAAE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 3, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVALE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 5, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVAALE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 7, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVAE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 1, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1_write }, + { .name = "TLBI_RVAAE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 3, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1_write }, + { .name = "TLBI_RVALE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 5, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1_write }, + { .name = "TLBI_RVAALE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 7, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1_write }, + { .name = "TLBI_RIPAS2E1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 2, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_RIPAS2LE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 6, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_RVAE2IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 2, .opc2 = 1, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae2is_write }, + { .name = "TLBI_RVALE2IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 2, .opc2 = 5, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae2is_write }, + { .name = "TLBI_RIPAS2E1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 2, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_RIPAS2LE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 6, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_RVAE2OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 5, .opc2 = 1, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae2is_write }, + { .name = "TLBI_RVALE2OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 5, .opc2 = 5, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae2is_write }, + { .name = "TLBI_RVAE2", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 6, .opc2 = 1, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae2_write }, + { .name = "TLBI_RVALE2", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 6, .opc2 = 5, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae2_write }, + { .name = "TLBI_RVAE3IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 2, .opc2 = 1, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae3is_write }, + { .name = "TLBI_RVALE3IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 2, .opc2 = 5, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae3is_write }, + { .name = "TLBI_RVAE3OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 5, .opc2 = 1, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae3is_write }, + { .name = "TLBI_RVALE3OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 5, .opc2 = 5, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae3is_write }, + { .name = "TLBI_RVAE3", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 6, .opc2 = 1, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae3_write }, + { .name = "TLBI_RVALE3", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 6, .opc2 = 5, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae3_write }, + REGINFO_SENTINEL +}; + +static const ARMCPRegInfo tlbios_reginfo[] = { + { .name = "TLBI_VMALLE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 0, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_vmalle1is_write }, + { .name = "TLBI_ASIDE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 2, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_vmalle1is_write }, + { .name = "TLBI_ALLE2OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 0, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_alle2is_write }, + { .name = "TLBI_ALLE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 4, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_alle1is_write }, + { .name = "TLBI_VMALLS12E1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 6, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_alle1is_write }, + { .name = "TLBI_IPAS2E1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 0, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_RIPAS2E1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 3, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_IPAS2LE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 4, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_RIPAS2LE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 7, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_ALLE3OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 1, .opc2 = 0, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_alle3is_write }, + REGINFO_SENTINEL +}; + static uint64_t rndr_readfn(CPUARMState *env, const ARMCPRegInfo *ri) { Error *err = NULL; @@ -7561,8 +7879,7 @@ void register_cp_regs_for_features(ARMCPU *cpu) .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 4, .opc2 = 4, .access = PL1_R, .type = ARM_CP_CONST, .accessfn = access_aa64_tid3, - /* At present, only SVEver == 0 is defined anyway. */ - .resetvalue = 0 }, + .resetvalue = cpu->isar.id_aa64zfr0 }, { .name = "ID_AA64PFR5_EL1_RESERVED", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 4, .opc2 = 5, .access = PL1_R, .type = ARM_CP_CONST, @@ -8289,6 +8606,12 @@ void register_cp_regs_for_features(ARMCPU *cpu) if (cpu_isar_feature(aa64_rndr, cpu)) { define_arm_cp_regs(cpu, rndr_reginfo); } + if (cpu_isar_feature(aa64_tlbirange, cpu)) { + define_arm_cp_regs(cpu, tlbirange_reginfo); + } + if (cpu_isar_feature(aa64_tlbios, cpu)) { + define_arm_cp_regs(cpu, tlbios_reginfo); + } #ifndef CONFIG_USER_ONLY /* Data Cache clean instructions up to PoP */ if (cpu_isar_feature(aa64_dcpop, cpu)) { diff --git a/target/arm/helper.h b/target/arm/helper.h index ff8148ddc6..23ccb0f72f 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -591,34 +591,60 @@ DEF_HELPER_FLAGS_5(gvec_qrdmlah_s32, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_qrdmlsh_s32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlah_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlah_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlah_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlah_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_sdot_idx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_udot_idx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_sdot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_udot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_usdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_5(gvec_sdot_idx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fcadds, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_5(gvec_udot_idx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fcaddd, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_5(gvec_sdot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) - -DEF_HELPER_FLAGS_5(gvec_fcmlah, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_5(gvec_udot_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sudot_idx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fcmlah_idx, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_5(gvec_usdot_idx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fcmlas, TCG_CALL_NO_RWG, + +DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fcmlas_idx, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_5(gvec_fcadds, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fcmlad, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_5(gvec_fcaddd, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(gvec_fcmlah, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(gvec_fcmlah_idx, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(gvec_fcmlas, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(gvec_fcmlas_idx, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(gvec_fcmlad, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(neon_paddh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(neon_pmaxh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(neon_pminh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) @@ -828,6 +854,16 @@ DEF_HELPER_FLAGS_3(gvec_cgt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_cge0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_cge0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_smulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_smulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_smulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_smulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_umulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_umulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_umulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_umulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_sshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_sshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_ushl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) @@ -926,6 +962,44 @@ DEF_HELPER_FLAGS_5(neon_sqrdmulh_h, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(neon_sqrdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_sqrdmulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqrdmulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqrdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqrdmulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve2_fmlal_zzzw_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_fmlal_zzxw_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_xar_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_smmla_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_ummla_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_usmmla_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "helper-a64.h" #include "helper-sve.h" diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index dff85f6db9..37ceadd9a9 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -647,17 +647,26 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) sve_supported = ioctl(fdarray[0], KVM_CHECK_EXTENSION, KVM_CAP_ARM_SVE) > 0; - kvm_arm_destroy_scratch_host_vcpu(fdarray); - - if (err < 0) { - return false; - } - /* Add feature bits that can't appear until after VCPU init. */ if (sve_supported) { t = ahcf->isar.id_aa64pfr0; t = FIELD_DP64(t, ID_AA64PFR0, SVE, 1); ahcf->isar.id_aa64pfr0 = t; + + /* + * Before v5.1, KVM did not support SVE and did not expose + * ID_AA64ZFR0_EL1 even as RAZ. After v5.1, KVM still does + * not expose the register to "user" requests like this + * unless the host supports SVE. + */ + err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64zfr0, + ARM64_SYS_REG(3, 0, 0, 4, 4)); + } + + kvm_arm_destroy_scratch_host_vcpu(fdarray); + + if (err < 0) { + return false; } /* diff --git a/target/arm/m_helper.c b/target/arm/m_helper.c index d63ae465e1..eda74e5545 100644 --- a/target/arm/m_helper.c +++ b/target/arm/m_helper.c @@ -1597,10 +1597,11 @@ static void do_v7m_exception_exit(ARMCPU *cpu) * We use this limited C variable scope so we don't accidentally * use 'frame_sp_p' after we do something that makes it invalid. */ + bool spsel = env->v7m.control[return_to_secure] & R_V7M_CONTROL_SPSEL_MASK; uint32_t *frame_sp_p = get_v7m_sp_ptr(env, return_to_secure, !return_to_handler, - return_to_sp_process); + spsel); uint32_t frameptr = *frame_sp_p; bool pop_ok = true; ARMMMUIdx mmu_idx; diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode index ca0c699072..cc9f4cdd85 100644 --- a/target/arm/neon-shared.decode +++ b/target/arm/neon-shared.decode @@ -46,8 +46,11 @@ VCMLA 1111 110 rot:2 . 1 . .... .... 1000 . q:1 . 0 .... \ VCADD 1111 110 rot:1 1 . 0 . .... .... 1000 . q:1 . 0 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp size=%vcadd_size -# VUDOT and VSDOT -VDOT 1111 110 00 . 10 .... .... 1101 . q:1 . u:1 .... \ +VSDOT 1111 110 00 . 10 .... .... 1101 . q:1 . 0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp +VUDOT 1111 110 00 . 10 .... .... 1101 . q:1 . 1 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp +VUSDOT 1111 110 01 . 10 .... .... 1101 . q:1 . 0 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp # VFM[AS]L @@ -56,13 +59,26 @@ VFML 1111 110 0 s:1 . 10 .... .... 1000 . 0 . 1 .... \ VFML 1111 110 0 s:1 . 10 .... .... 1000 . 1 . 1 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp q=1 +VSMMLA 1111 1100 0.10 .... .... 1100 .1.0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp +VUMMLA 1111 1100 0.10 .... .... 1100 .1.1 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp +VUSMMLA 1111 1100 1.10 .... .... 1100 .1.0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp + VCMLA_scalar 1111 1110 0 . rot:2 .... .... 1000 . q:1 index:1 0 vm:4 \ vn=%vn_dp vd=%vd_dp size=1 VCMLA_scalar 1111 1110 1 . rot:2 .... .... 1000 . q:1 . 0 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp size=2 index=0 -VDOT_scalar 1111 1110 0 . 10 .... .... 1101 . q:1 index:1 u:1 rm:4 \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp +VSDOT_scalar 1111 1110 0 . 10 .... .... 1101 . q:1 index:1 0 vm:4 \ + vn=%vn_dp vd=%vd_dp +VUDOT_scalar 1111 1110 0 . 10 .... .... 1101 . q:1 index:1 1 vm:4 \ + vn=%vn_dp vd=%vd_dp +VUSDOT_scalar 1111 1110 1 . 00 .... .... 1101 . q:1 index:1 0 vm:4 \ + vn=%vn_dp vd=%vd_dp +VSUDOT_scalar 1111 1110 1 . 00 .... .... 1101 . q:1 index:1 1 vm:4 \ + vn=%vn_dp vd=%vd_dp %vfml_scalar_q0_rm 0:3 5:1 %vfml_scalar_q1_index 5:1 3:1 diff --git a/target/arm/neon_helper.c b/target/arm/neon_helper.c index b637265691..338b9189d5 100644 --- a/target/arm/neon_helper.c +++ b/target/arm/neon_helper.c @@ -11,6 +11,7 @@ #include "cpu.h" #include "exec/helper-proto.h" #include "fpu/softfloat.h" +#include "vec_internal.h" #define SIGNBIT (uint32_t)0x80000000 #define SIGNBIT64 ((uint64_t)1 << 63) @@ -576,496 +577,154 @@ NEON_POP(pmax_s16, neon_s16, 2) NEON_POP(pmax_u16, neon_u16, 2) #undef NEON_FN -#define NEON_FN(dest, src1, src2) do { \ - int8_t tmp; \ - tmp = (int8_t)src2; \ - if (tmp >= (ssize_t)sizeof(src1) * 8 || \ - tmp <= -(ssize_t)sizeof(src1) * 8) { \ - dest = 0; \ - } else if (tmp < 0) { \ - dest = src1 >> -tmp; \ - } else { \ - dest = src1 << tmp; \ - }} while (0) +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int8_t)src2, 16, false, NULL)) NEON_VOP(shl_u16, neon_u16, 2) #undef NEON_FN -#define NEON_FN(dest, src1, src2) do { \ - int8_t tmp; \ - tmp = (int8_t)src2; \ - if (tmp >= (ssize_t)sizeof(src1) * 8) { \ - dest = 0; \ - } else if (tmp <= -(ssize_t)sizeof(src1) * 8) { \ - dest = src1 >> (sizeof(src1) * 8 - 1); \ - } else if (tmp < 0) { \ - dest = src1 >> -tmp; \ - } else { \ - dest = src1 << tmp; \ - }} while (0) +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, (int8_t)src2, 16, false, NULL)) NEON_VOP(shl_s16, neon_s16, 2) #undef NEON_FN -#define NEON_FN(dest, src1, src2) do { \ - int8_t tmp; \ - tmp = (int8_t)src2; \ - if ((tmp >= (ssize_t)sizeof(src1) * 8) \ - || (tmp <= -(ssize_t)sizeof(src1) * 8)) { \ - dest = 0; \ - } else if (tmp < 0) { \ - dest = (src1 + (1 << (-1 - tmp))) >> -tmp; \ - } else { \ - dest = src1 << tmp; \ - }} while (0) +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, (int8_t)src2, 8, true, NULL)) NEON_VOP(rshl_s8, neon_s8, 4) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, (int8_t)src2, 16, true, NULL)) NEON_VOP(rshl_s16, neon_s16, 2) #undef NEON_FN -/* The addition of the rounding constant may overflow, so we use an - * intermediate 64 bit accumulator. */ -uint32_t HELPER(neon_rshl_s32)(uint32_t valop, uint32_t shiftop) +uint32_t HELPER(neon_rshl_s32)(uint32_t val, uint32_t shift) { - int32_t dest; - int32_t val = (int32_t)valop; - int8_t shift = (int8_t)shiftop; - if ((shift >= 32) || (shift <= -32)) { - dest = 0; - } else if (shift < 0) { - int64_t big_dest = ((int64_t)val + (1 << (-1 - shift))); - dest = big_dest >> -shift; - } else { - dest = val << shift; - } - return dest; + return do_sqrshl_bhs(val, (int8_t)shift, 32, true, NULL); } -/* Handling addition overflow with 64 bit input values is more - * tricky than with 32 bit values. */ -uint64_t HELPER(neon_rshl_s64)(uint64_t valop, uint64_t shiftop) -{ - int8_t shift = (int8_t)shiftop; - int64_t val = valop; - if ((shift >= 64) || (shift <= -64)) { - val = 0; - } else if (shift < 0) { - val >>= (-shift - 1); - if (val == INT64_MAX) { - /* In this case, it means that the rounding constant is 1, - * and the addition would overflow. Return the actual - * result directly. */ - val = 0x4000000000000000LL; - } else { - val++; - val >>= 1; - } - } else { - val <<= shift; - } - return val; +uint64_t HELPER(neon_rshl_s64)(uint64_t val, uint64_t shift) +{ + return do_sqrshl_d(val, (int8_t)shift, true, NULL); } -#define NEON_FN(dest, src1, src2) do { \ - int8_t tmp; \ - tmp = (int8_t)src2; \ - if (tmp >= (ssize_t)sizeof(src1) * 8 || \ - tmp < -(ssize_t)sizeof(src1) * 8) { \ - dest = 0; \ - } else if (tmp == -(ssize_t)sizeof(src1) * 8) { \ - dest = src1 >> (-tmp - 1); \ - } else if (tmp < 0) { \ - dest = (src1 + (1 << (-1 - tmp))) >> -tmp; \ - } else { \ - dest = src1 << tmp; \ - }} while (0) +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int8_t)src2, 8, true, NULL)) NEON_VOP(rshl_u8, neon_u8, 4) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int8_t)src2, 16, true, NULL)) NEON_VOP(rshl_u16, neon_u16, 2) #undef NEON_FN -/* The addition of the rounding constant may overflow, so we use an - * intermediate 64 bit accumulator. */ -uint32_t HELPER(neon_rshl_u32)(uint32_t val, uint32_t shiftop) +uint32_t HELPER(neon_rshl_u32)(uint32_t val, uint32_t shift) { - uint32_t dest; - int8_t shift = (int8_t)shiftop; - if (shift >= 32 || shift < -32) { - dest = 0; - } else if (shift == -32) { - dest = val >> 31; - } else if (shift < 0) { - uint64_t big_dest = ((uint64_t)val + (1 << (-1 - shift))); - dest = big_dest >> -shift; - } else { - dest = val << shift; - } - return dest; + return do_uqrshl_bhs(val, (int8_t)shift, 32, true, NULL); } -/* Handling addition overflow with 64 bit input values is more - * tricky than with 32 bit values. */ -uint64_t HELPER(neon_rshl_u64)(uint64_t val, uint64_t shiftop) -{ - int8_t shift = (uint8_t)shiftop; - if (shift >= 64 || shift < -64) { - val = 0; - } else if (shift == -64) { - /* Rounding a 1-bit result just preserves that bit. */ - val >>= 63; - } else if (shift < 0) { - val >>= (-shift - 1); - if (val == UINT64_MAX) { - /* In this case, it means that the rounding constant is 1, - * and the addition would overflow. Return the actual - * result directly. */ - val = 0x8000000000000000ULL; - } else { - val++; - val >>= 1; - } - } else { - val <<= shift; - } - return val; +uint64_t HELPER(neon_rshl_u64)(uint64_t val, uint64_t shift) +{ + return do_uqrshl_d(val, (int8_t)shift, true, NULL); } -#define NEON_FN(dest, src1, src2) do { \ - int8_t tmp; \ - tmp = (int8_t)src2; \ - if (tmp >= (ssize_t)sizeof(src1) * 8) { \ - if (src1) { \ - SET_QC(); \ - dest = ~0; \ - } else { \ - dest = 0; \ - } \ - } else if (tmp <= -(ssize_t)sizeof(src1) * 8) { \ - dest = 0; \ - } else if (tmp < 0) { \ - dest = src1 >> -tmp; \ - } else { \ - dest = src1 << tmp; \ - if ((dest >> tmp) != src1) { \ - SET_QC(); \ - dest = ~0; \ - } \ - }} while (0) +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int8_t)src2, 8, false, env->vfp.qc)) NEON_VOP_ENV(qshl_u8, neon_u8, 4) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int8_t)src2, 16, false, env->vfp.qc)) NEON_VOP_ENV(qshl_u16, neon_u16, 2) -NEON_VOP_ENV(qshl_u32, neon_u32, 1) #undef NEON_FN -uint64_t HELPER(neon_qshl_u64)(CPUARMState *env, uint64_t val, uint64_t shiftop) -{ - int8_t shift = (int8_t)shiftop; - if (shift >= 64) { - if (val) { - val = ~(uint64_t)0; - SET_QC(); - } - } else if (shift <= -64) { - val = 0; - } else if (shift < 0) { - val >>= -shift; - } else { - uint64_t tmp = val; - val <<= shift; - if ((val >> shift) != tmp) { - SET_QC(); - val = ~(uint64_t)0; - } - } - return val; +uint32_t HELPER(neon_qshl_u32)(CPUARMState *env, uint32_t val, uint32_t shift) +{ + return do_uqrshl_bhs(val, (int8_t)shift, 32, false, env->vfp.qc); } -#define NEON_FN(dest, src1, src2) do { \ - int8_t tmp; \ - tmp = (int8_t)src2; \ - if (tmp >= (ssize_t)sizeof(src1) * 8) { \ - if (src1) { \ - SET_QC(); \ - dest = (uint32_t)(1 << (sizeof(src1) * 8 - 1)); \ - if (src1 > 0) { \ - dest--; \ - } \ - } else { \ - dest = src1; \ - } \ - } else if (tmp <= -(ssize_t)sizeof(src1) * 8) { \ - dest = src1 >> 31; \ - } else if (tmp < 0) { \ - dest = src1 >> -tmp; \ - } else { \ - dest = src1 << tmp; \ - if ((dest >> tmp) != src1) { \ - SET_QC(); \ - dest = (uint32_t)(1 << (sizeof(src1) * 8 - 1)); \ - if (src1 > 0) { \ - dest--; \ - } \ - } \ - }} while (0) +uint64_t HELPER(neon_qshl_u64)(CPUARMState *env, uint64_t val, uint64_t shift) +{ + return do_uqrshl_d(val, (int8_t)shift, false, env->vfp.qc); +} + +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, (int8_t)src2, 8, false, env->vfp.qc)) NEON_VOP_ENV(qshl_s8, neon_s8, 4) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, (int8_t)src2, 16, false, env->vfp.qc)) NEON_VOP_ENV(qshl_s16, neon_s16, 2) -NEON_VOP_ENV(qshl_s32, neon_s32, 1) #undef NEON_FN -uint64_t HELPER(neon_qshl_s64)(CPUARMState *env, uint64_t valop, uint64_t shiftop) -{ - int8_t shift = (uint8_t)shiftop; - int64_t val = valop; - if (shift >= 64) { - if (val) { - SET_QC(); - val = (val >> 63) ^ ~SIGNBIT64; - } - } else if (shift <= -64) { - val >>= 63; - } else if (shift < 0) { - val >>= -shift; - } else { - int64_t tmp = val; - val <<= shift; - if ((val >> shift) != tmp) { - SET_QC(); - val = (tmp >> 63) ^ ~SIGNBIT64; - } - } - return val; +uint32_t HELPER(neon_qshl_s32)(CPUARMState *env, uint32_t val, uint32_t shift) +{ + return do_sqrshl_bhs(val, (int8_t)shift, 32, false, env->vfp.qc); } -#define NEON_FN(dest, src1, src2) do { \ - if (src1 & (1 << (sizeof(src1) * 8 - 1))) { \ - SET_QC(); \ - dest = 0; \ - } else { \ - int8_t tmp; \ - tmp = (int8_t)src2; \ - if (tmp >= (ssize_t)sizeof(src1) * 8) { \ - if (src1) { \ - SET_QC(); \ - dest = ~0; \ - } else { \ - dest = 0; \ - } \ - } else if (tmp <= -(ssize_t)sizeof(src1) * 8) { \ - dest = 0; \ - } else if (tmp < 0) { \ - dest = src1 >> -tmp; \ - } else { \ - dest = src1 << tmp; \ - if ((dest >> tmp) != src1) { \ - SET_QC(); \ - dest = ~0; \ - } \ - } \ - }} while (0) -NEON_VOP_ENV(qshlu_s8, neon_u8, 4) -NEON_VOP_ENV(qshlu_s16, neon_u16, 2) +uint64_t HELPER(neon_qshl_s64)(CPUARMState *env, uint64_t val, uint64_t shift) +{ + return do_sqrshl_d(val, (int8_t)shift, false, env->vfp.qc); +} + +#define NEON_FN(dest, src1, src2) \ + (dest = do_suqrshl_bhs(src1, (int8_t)src2, 8, false, env->vfp.qc)) +NEON_VOP_ENV(qshlu_s8, neon_s8, 4) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_suqrshl_bhs(src1, (int8_t)src2, 16, false, env->vfp.qc)) +NEON_VOP_ENV(qshlu_s16, neon_s16, 2) #undef NEON_FN -uint32_t HELPER(neon_qshlu_s32)(CPUARMState *env, uint32_t valop, uint32_t shiftop) +uint32_t HELPER(neon_qshlu_s32)(CPUARMState *env, uint32_t val, uint32_t shift) { - if ((int32_t)valop < 0) { - SET_QC(); - return 0; - } - return helper_neon_qshl_u32(env, valop, shiftop); + return do_suqrshl_bhs(val, (int8_t)shift, 32, false, env->vfp.qc); } -uint64_t HELPER(neon_qshlu_s64)(CPUARMState *env, uint64_t valop, uint64_t shiftop) +uint64_t HELPER(neon_qshlu_s64)(CPUARMState *env, uint64_t val, uint64_t shift) { - if ((int64_t)valop < 0) { - SET_QC(); - return 0; - } - return helper_neon_qshl_u64(env, valop, shiftop); + return do_suqrshl_d(val, (int8_t)shift, false, env->vfp.qc); } -#define NEON_FN(dest, src1, src2) do { \ - int8_t tmp; \ - tmp = (int8_t)src2; \ - if (tmp >= (ssize_t)sizeof(src1) * 8) { \ - if (src1) { \ - SET_QC(); \ - dest = ~0; \ - } else { \ - dest = 0; \ - } \ - } else if (tmp < -(ssize_t)sizeof(src1) * 8) { \ - dest = 0; \ - } else if (tmp == -(ssize_t)sizeof(src1) * 8) { \ - dest = src1 >> (sizeof(src1) * 8 - 1); \ - } else if (tmp < 0) { \ - dest = (src1 + (1 << (-1 - tmp))) >> -tmp; \ - } else { \ - dest = src1 << tmp; \ - if ((dest >> tmp) != src1) { \ - SET_QC(); \ - dest = ~0; \ - } \ - }} while (0) +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int8_t)src2, 8, true, env->vfp.qc)) NEON_VOP_ENV(qrshl_u8, neon_u8, 4) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int8_t)src2, 16, true, env->vfp.qc)) NEON_VOP_ENV(qrshl_u16, neon_u16, 2) #undef NEON_FN -/* The addition of the rounding constant may overflow, so we use an - * intermediate 64 bit accumulator. */ -uint32_t HELPER(neon_qrshl_u32)(CPUARMState *env, uint32_t val, uint32_t shiftop) +uint32_t HELPER(neon_qrshl_u32)(CPUARMState *env, uint32_t val, uint32_t shift) { - uint32_t dest; - int8_t shift = (int8_t)shiftop; - if (shift >= 32) { - if (val) { - SET_QC(); - dest = ~0; - } else { - dest = 0; - } - } else if (shift < -32) { - dest = 0; - } else if (shift == -32) { - dest = val >> 31; - } else if (shift < 0) { - uint64_t big_dest = ((uint64_t)val + (1 << (-1 - shift))); - dest = big_dest >> -shift; - } else { - dest = val << shift; - if ((dest >> shift) != val) { - SET_QC(); - dest = ~0; - } - } - return dest; + return do_uqrshl_bhs(val, (int8_t)shift, 32, true, env->vfp.qc); } -/* Handling addition overflow with 64 bit input values is more - * tricky than with 32 bit values. */ -uint64_t HELPER(neon_qrshl_u64)(CPUARMState *env, uint64_t val, uint64_t shiftop) -{ - int8_t shift = (int8_t)shiftop; - if (shift >= 64) { - if (val) { - SET_QC(); - val = ~0; - } - } else if (shift < -64) { - val = 0; - } else if (shift == -64) { - val >>= 63; - } else if (shift < 0) { - val >>= (-shift - 1); - if (val == UINT64_MAX) { - /* In this case, it means that the rounding constant is 1, - * and the addition would overflow. Return the actual - * result directly. */ - val = 0x8000000000000000ULL; - } else { - val++; - val >>= 1; - } - } else { \ - uint64_t tmp = val; - val <<= shift; - if ((val >> shift) != tmp) { - SET_QC(); - val = ~0; - } - } - return val; +uint64_t HELPER(neon_qrshl_u64)(CPUARMState *env, uint64_t val, uint64_t shift) +{ + return do_uqrshl_d(val, (int8_t)shift, true, env->vfp.qc); } -#define NEON_FN(dest, src1, src2) do { \ - int8_t tmp; \ - tmp = (int8_t)src2; \ - if (tmp >= (ssize_t)sizeof(src1) * 8) { \ - if (src1) { \ - SET_QC(); \ - dest = (typeof(dest))(1 << (sizeof(src1) * 8 - 1)); \ - if (src1 > 0) { \ - dest--; \ - } \ - } else { \ - dest = 0; \ - } \ - } else if (tmp <= -(ssize_t)sizeof(src1) * 8) { \ - dest = 0; \ - } else if (tmp < 0) { \ - dest = (src1 + (1 << (-1 - tmp))) >> -tmp; \ - } else { \ - dest = src1 << tmp; \ - if ((dest >> tmp) != src1) { \ - SET_QC(); \ - dest = (uint32_t)(1 << (sizeof(src1) * 8 - 1)); \ - if (src1 > 0) { \ - dest--; \ - } \ - } \ - }} while (0) +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, (int8_t)src2, 8, true, env->vfp.qc)) NEON_VOP_ENV(qrshl_s8, neon_s8, 4) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, (int8_t)src2, 16, true, env->vfp.qc)) NEON_VOP_ENV(qrshl_s16, neon_s16, 2) #undef NEON_FN -/* The addition of the rounding constant may overflow, so we use an - * intermediate 64 bit accumulator. */ -uint32_t HELPER(neon_qrshl_s32)(CPUARMState *env, uint32_t valop, uint32_t shiftop) +uint32_t HELPER(neon_qrshl_s32)(CPUARMState *env, uint32_t val, uint32_t shift) { - int32_t dest; - int32_t val = (int32_t)valop; - int8_t shift = (int8_t)shiftop; - if (shift >= 32) { - if (val) { - SET_QC(); - dest = (val >> 31) ^ ~SIGNBIT; - } else { - dest = 0; - } - } else if (shift <= -32) { - dest = 0; - } else if (shift < 0) { - int64_t big_dest = ((int64_t)val + (1 << (-1 - shift))); - dest = big_dest >> -shift; - } else { - dest = val << shift; - if ((dest >> shift) != val) { - SET_QC(); - dest = (val >> 31) ^ ~SIGNBIT; - } - } - return dest; + return do_sqrshl_bhs(val, (int8_t)shift, 32, true, env->vfp.qc); } -/* Handling addition overflow with 64 bit input values is more - * tricky than with 32 bit values. */ -uint64_t HELPER(neon_qrshl_s64)(CPUARMState *env, uint64_t valop, uint64_t shiftop) -{ - int8_t shift = (uint8_t)shiftop; - int64_t val = valop; - - if (shift >= 64) { - if (val) { - SET_QC(); - val = (val >> 63) ^ ~SIGNBIT64; - } - } else if (shift <= -64) { - val = 0; - } else if (shift < 0) { - val >>= (-shift - 1); - if (val == INT64_MAX) { - /* In this case, it means that the rounding constant is 1, - * and the addition would overflow. Return the actual - * result directly. */ - val = 0x4000000000000000ULL; - } else { - val++; - val >>= 1; - } - } else { - int64_t tmp = val; - val <<= shift; - if ((val >> shift) != tmp) { - SET_QC(); - val = (tmp >> 63) ^ ~SIGNBIT64; - } - } - return val; +uint64_t HELPER(neon_qrshl_s64)(CPUARMState *env, uint64_t val, uint64_t shift) +{ + return do_sqrshl_d(val, (int8_t)shift, true, env->vfp.qc); } uint32_t HELPER(neon_add_u8)(uint32_t a, uint32_t b) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index 5c90603358..cb077bfde9 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -30,6 +30,8 @@ %size_23 23:2 %dtype_23_13 23:2 13:2 %index3_22_19 22:1 19:2 +%index3_19_11 19:2 11:1 +%index2_20_11 20:1 11:1 # A combination of tsz:imm3 -- extract esize. %tszimm_esz 22:2 5:5 !function=tszimm_esz @@ -65,11 +67,15 @@ &rr_dbm rd rn dbm &rrri rd rn rm imm &rri_esz rd rn imm esz +&rrri_esz rd rn rm imm esz &rrr_esz rd rn rm esz +&rrx_esz rd rn rm index esz &rpr_esz rd pg rn esz &rpr_s rd pg rn s &rprr_s rd pg rn rm s &rprr_esz rd pg rn rm esz +&rrrr_esz rd ra rn rm esz +&rrxr_esz rd rn rm ra index esz &rprrr_esz rd pg rn rm ra esz &rpri_esz rd pg rn imm esz &ptrue rd esz pat s @@ -112,6 +118,8 @@ @pd_pn_pm ........ esz:2 .. rm:4 ....... rn:4 . rd:4 &rrr_esz @rdn_rm ........ esz:2 ...... ...... rm:5 rd:5 \ &rrr_esz rn=%reg_movprfx +@rdn_rm_e0 ........ .. ...... ...... rm:5 rd:5 \ + &rrr_esz rn=%reg_movprfx esz=0 @rdn_sh_i8u ........ esz:2 ...... ...... ..... rd:5 \ &rri_esz rn=%reg_movprfx imm=%sh8_i8u @rdn_i8u ........ esz:2 ...... ... imm:8 rd:5 \ @@ -119,6 +127,16 @@ @rdn_i8s ........ esz:2 ...... ... imm:s8 rd:5 \ &rri_esz rn=%reg_movprfx +# Four operand, vector element size +@rda_rn_rm ........ esz:2 . rm:5 ... ... rn:5 rd:5 \ + &rrrr_esz ra=%reg_movprfx + +# Four operand with unused vector element size +@rda_rn_rm_e0 ........ ... rm:5 ... ... rn:5 rd:5 \ + &rrrr_esz esz=0 ra=%reg_movprfx +@rdn_ra_rm_e0 ........ ... rm:5 ... ... ra:5 rd:5 \ + &rrrr_esz esz=0 rn=%reg_movprfx + # Three operand with "memory" size, aka immediate left shift @rd_rn_msz_rm ........ ... rm:5 .... imm:2 rn:5 rd:5 &rrri @@ -137,6 +155,7 @@ &rprrr_esz rn=%reg_movprfx @rdn_pg_rm_ra ........ esz:2 . ra:5 ... pg:3 rm:5 rd:5 \ &rprrr_esz rn=%reg_movprfx +@rd_pg_rn_rm ........ esz:2 . rm:5 ... pg:3 rn:5 rd:5 &rprr_esz # One register operand, with governing predicate, vector element size @rd_pg_rn ........ esz:2 ... ... ... pg:3 rn:5 rd:5 &rpr_esz @@ -234,6 +253,32 @@ @rpri_scatter_store ....... msz:2 .. imm:5 ... pg:3 rn:5 rd:5 \ &rpri_scatter_store +# Two registers and a scalar by N-bit index +@rrx_3 ........ .. . .. rm:3 ...... rn:5 rd:5 \ + &rrx_esz index=%index3_22_19 +@rrx_2 ........ .. . index:2 rm:3 ...... rn:5 rd:5 &rrx_esz +@rrx_1 ........ .. . index:1 rm:4 ...... rn:5 rd:5 &rrx_esz + +# Two registers and a scalar by N-bit index, alternate +@rrx_3a ........ .. . .. rm:3 ...... rn:5 rd:5 \ + &rrx_esz index=%index3_19_11 +@rrx_2a ........ .. . . rm:4 ...... rn:5 rd:5 \ + &rrx_esz index=%index2_20_11 + +# Three registers and a scalar by N-bit index +@rrxr_3 ........ .. . .. rm:3 ...... rn:5 rd:5 \ + &rrxr_esz ra=%reg_movprfx index=%index3_22_19 +@rrxr_2 ........ .. . index:2 rm:3 ...... rn:5 rd:5 \ + &rrxr_esz ra=%reg_movprfx +@rrxr_1 ........ .. . index:1 rm:4 ...... rn:5 rd:5 \ + &rrxr_esz ra=%reg_movprfx + +# Three registers and a scalar by N-bit index, alternate +@rrxr_3a ........ .. ... rm:3 ...... rn:5 rd:5 \ + &rrxr_esz ra=%reg_movprfx index=%index3_19_11 +@rrxr_2a ........ .. .. rm:4 ...... rn:5 rd:5 \ + &rrxr_esz ra=%reg_movprfx index=%index2_20_11 + ########################################################################### # Instruction patterns. Grouped according to the SVE encodingindex.xhtml. @@ -297,6 +342,11 @@ ASR_zpzi 00000100 .. 000 000 100 ... .. ... ..... @rdn_pg_tszimm_shr LSR_zpzi 00000100 .. 000 001 100 ... .. ... ..... @rdn_pg_tszimm_shr LSL_zpzi 00000100 .. 000 011 100 ... .. ... ..... @rdn_pg_tszimm_shl ASRD 00000100 .. 000 100 100 ... .. ... ..... @rdn_pg_tszimm_shr +SQSHL_zpzi 00000100 .. 000 110 100 ... .. ... ..... @rdn_pg_tszimm_shl +UQSHL_zpzi 00000100 .. 000 111 100 ... .. ... ..... @rdn_pg_tszimm_shl +SRSHR 00000100 .. 001 100 100 ... .. ... ..... @rdn_pg_tszimm_shr +URSHR 00000100 .. 001 101 100 ... .. ... ..... @rdn_pg_tszimm_shr +SQSHLU 00000100 .. 001 111 100 ... .. ... ..... @rdn_pg_tszimm_shl # SVE bitwise shift by vector (predicated) ASR_zpzz 00000100 .. 010 000 100 ... ..... ..... @rdn_pg_rm @@ -374,6 +424,17 @@ ORR_zzz 00000100 01 1 ..... 001 100 ..... ..... @rd_rn_rm_e0 EOR_zzz 00000100 10 1 ..... 001 100 ..... ..... @rd_rn_rm_e0 BIC_zzz 00000100 11 1 ..... 001 100 ..... ..... @rd_rn_rm_e0 +XAR 00000100 .. 1 ..... 001 101 rm:5 rd:5 &rrri_esz \ + rn=%reg_movprfx esz=%tszimm16_esz imm=%tszimm16_shr + +# SVE2 bitwise ternary operations +EOR3 00000100 00 1 ..... 001 110 ..... ..... @rdn_ra_rm_e0 +BSL 00000100 00 1 ..... 001 111 ..... ..... @rdn_ra_rm_e0 +BCAX 00000100 01 1 ..... 001 110 ..... ..... @rdn_ra_rm_e0 +BSL1N 00000100 01 1 ..... 001 111 ..... ..... @rdn_ra_rm_e0 +BSL2N 00000100 10 1 ..... 001 111 ..... ..... @rdn_ra_rm_e0 +NBSL 00000100 11 1 ..... 001 111 ..... ..... @rdn_ra_rm_e0 + ### SVE Index Generation Group # SVE index generation (immediate start, immediate increment) @@ -472,10 +533,14 @@ CPY_z_i 00000101 .. 01 .... 00 . ........ ..... @rdn_pg4 imm=%sh8_i8s ### SVE Permute - Extract Group -# SVE extract vector (immediate offset) +# SVE extract vector (destructive) EXT 00000101 001 ..... 000 ... rm:5 rd:5 \ &rrri rn=%reg_movprfx imm=%imm8_16_10 +# SVE2 extract vector (constructive) +EXT_sve2 00000101 011 ..... 000 ... rn:5 rd:5 \ + &rri imm=%imm8_16_10 + ### SVE Permute - Unpredicated Group # SVE broadcast general register @@ -500,6 +565,11 @@ TBL 00000101 .. 1 ..... 001100 ..... ..... @rd_rn_rm # SVE unpack vector elements UNPK 00000101 esz:2 1100 u:1 h:1 001110 rn:5 rd:5 +# SVE2 Table Lookup (three sources) + +TBL_sve2 00000101 .. 1 ..... 001010 ..... ..... @rd_rn_rm +TBX 00000101 .. 1 ..... 001011 ..... ..... @rd_rn_rm + ### SVE Permute - Predicates Group # SVE permute predicate elements @@ -527,6 +597,14 @@ UZP2_z 00000101 .. 1 ..... 011 011 ..... ..... @rd_rn_rm TRN1_z 00000101 .. 1 ..... 011 100 ..... ..... @rd_rn_rm TRN2_z 00000101 .. 1 ..... 011 101 ..... ..... @rd_rn_rm +# SVE2 permute vector segments +ZIP1_q 00000101 10 1 ..... 000 000 ..... ..... @rd_rn_rm_e0 +ZIP2_q 00000101 10 1 ..... 000 001 ..... ..... @rd_rn_rm_e0 +UZP1_q 00000101 10 1 ..... 000 010 ..... ..... @rd_rn_rm_e0 +UZP2_q 00000101 10 1 ..... 000 011 ..... ..... @rd_rn_rm_e0 +TRN1_q 00000101 10 1 ..... 000 110 ..... ..... @rd_rn_rm_e0 +TRN2_q 00000101 10 1 ..... 000 111 ..... ..... @rd_rn_rm_e0 + ### SVE Permute - Predicated Group # SVE compress active elements @@ -566,9 +644,12 @@ REVH 00000101 .. 1001 01 100 ... ..... ..... @rd_pg_rn REVW 00000101 .. 1001 10 100 ... ..... ..... @rd_pg_rn RBIT 00000101 .. 1001 11 100 ... ..... ..... @rd_pg_rn -# SVE vector splice (predicated) +# SVE vector splice (predicated, destructive) SPLICE 00000101 .. 101 100 100 ... ..... ..... @rdn_pg_rm +# SVE2 vector splice (predicated, constructive) +SPLICE_sve2 00000101 .. 101 101 100 ... ..... ..... @rd_pg_rn + ### SVE Select Vectors Group # SVE select vector elements (predicated) @@ -695,7 +776,10 @@ SINCDECP_z 00100101 .. 1010 d:1 u:1 10000 00 .... ..... @incdec2_pred CTERM 00100101 1 sf:1 1 rm:5 001000 rn:5 ne:1 0000 # SVE integer compare scalar count and limit -WHILE 00100101 esz:2 1 rm:5 000 sf:1 u:1 1 rn:5 eq:1 rd:4 +WHILE 00100101 esz:2 1 rm:5 000 sf:1 u:1 lt:1 rn:5 eq:1 rd:4 + +# SVE2 pointer conflict compare +WHILE_ptr 00100101 esz:2 1 rm:5 001 100 rn:5 rw:1 rd:4 ### SVE Integer Wide Immediate - Unpredicated Group @@ -724,13 +808,114 @@ UMIN_zzi 00100101 .. 101 011 110 ........ ..... @rdn_i8u MUL_zzi 00100101 .. 110 000 110 ........ ..... @rdn_i8s # SVE integer dot product (unpredicated) -DOT_zzz 01000100 1 sz:1 0 rm:5 00000 u:1 rn:5 rd:5 ra=%reg_movprfx +DOT_zzzz 01000100 1 sz:1 0 rm:5 00000 u:1 rn:5 rd:5 \ + ra=%reg_movprfx + +# SVE2 complex dot product (vectors) +CDOT_zzzz 01000100 esz:2 0 rm:5 0001 rot:2 rn:5 rd:5 ra=%reg_movprfx + +#### SVE Multiply - Indexed # SVE integer dot product (indexed) -DOT_zzx 01000100 101 index:2 rm:3 00000 u:1 rn:5 rd:5 \ - sz=0 ra=%reg_movprfx -DOT_zzx 01000100 111 index:1 rm:4 00000 u:1 rn:5 rd:5 \ - sz=1 ra=%reg_movprfx +SDOT_zzxw_s 01000100 10 1 ..... 000000 ..... ..... @rrxr_2 esz=2 +SDOT_zzxw_d 01000100 11 1 ..... 000000 ..... ..... @rrxr_1 esz=3 +UDOT_zzxw_s 01000100 10 1 ..... 000001 ..... ..... @rrxr_2 esz=2 +UDOT_zzxw_d 01000100 11 1 ..... 000001 ..... ..... @rrxr_1 esz=3 + +# SVE2 integer multiply-add (indexed) +MLA_zzxz_h 01000100 0. 1 ..... 000010 ..... ..... @rrxr_3 esz=1 +MLA_zzxz_s 01000100 10 1 ..... 000010 ..... ..... @rrxr_2 esz=2 +MLA_zzxz_d 01000100 11 1 ..... 000010 ..... ..... @rrxr_1 esz=3 +MLS_zzxz_h 01000100 0. 1 ..... 000011 ..... ..... @rrxr_3 esz=1 +MLS_zzxz_s 01000100 10 1 ..... 000011 ..... ..... @rrxr_2 esz=2 +MLS_zzxz_d 01000100 11 1 ..... 000011 ..... ..... @rrxr_1 esz=3 + +# SVE2 saturating multiply-add high (indexed) +SQRDMLAH_zzxz_h 01000100 0. 1 ..... 000100 ..... ..... @rrxr_3 esz=1 +SQRDMLAH_zzxz_s 01000100 10 1 ..... 000100 ..... ..... @rrxr_2 esz=2 +SQRDMLAH_zzxz_d 01000100 11 1 ..... 000100 ..... ..... @rrxr_1 esz=3 +SQRDMLSH_zzxz_h 01000100 0. 1 ..... 000101 ..... ..... @rrxr_3 esz=1 +SQRDMLSH_zzxz_s 01000100 10 1 ..... 000101 ..... ..... @rrxr_2 esz=2 +SQRDMLSH_zzxz_d 01000100 11 1 ..... 000101 ..... ..... @rrxr_1 esz=3 + +# SVE mixed sign dot product (indexed) +USDOT_zzxw_s 01000100 10 1 ..... 000110 ..... ..... @rrxr_2 esz=2 +SUDOT_zzxw_s 01000100 10 1 ..... 000111 ..... ..... @rrxr_2 esz=2 + +# SVE2 saturating multiply-add (indexed) +SQDMLALB_zzxw_s 01000100 10 1 ..... 0010.0 ..... ..... @rrxr_3a esz=2 +SQDMLALB_zzxw_d 01000100 11 1 ..... 0010.0 ..... ..... @rrxr_2a esz=3 +SQDMLALT_zzxw_s 01000100 10 1 ..... 0010.1 ..... ..... @rrxr_3a esz=2 +SQDMLALT_zzxw_d 01000100 11 1 ..... 0010.1 ..... ..... @rrxr_2a esz=3 +SQDMLSLB_zzxw_s 01000100 10 1 ..... 0011.0 ..... ..... @rrxr_3a esz=2 +SQDMLSLB_zzxw_d 01000100 11 1 ..... 0011.0 ..... ..... @rrxr_2a esz=3 +SQDMLSLT_zzxw_s 01000100 10 1 ..... 0011.1 ..... ..... @rrxr_3a esz=2 +SQDMLSLT_zzxw_d 01000100 11 1 ..... 0011.1 ..... ..... @rrxr_2a esz=3 + +# SVE2 complex integer dot product (indexed) +CDOT_zzxw_s 01000100 10 1 index:2 rm:3 0100 rot:2 rn:5 rd:5 \ + ra=%reg_movprfx +CDOT_zzxw_d 01000100 11 1 index:1 rm:4 0100 rot:2 rn:5 rd:5 \ + ra=%reg_movprfx + +# SVE2 complex integer multiply-add (indexed) +CMLA_zzxz_h 01000100 10 1 index:2 rm:3 0110 rot:2 rn:5 rd:5 \ + ra=%reg_movprfx +CMLA_zzxz_s 01000100 11 1 index:1 rm:4 0110 rot:2 rn:5 rd:5 \ + ra=%reg_movprfx + +# SVE2 complex saturating integer multiply-add (indexed) +SQRDCMLAH_zzxz_h 01000100 10 1 index:2 rm:3 0111 rot:2 rn:5 rd:5 \ + ra=%reg_movprfx +SQRDCMLAH_zzxz_s 01000100 11 1 index:1 rm:4 0111 rot:2 rn:5 rd:5 \ + ra=%reg_movprfx + +# SVE2 multiply-add long (indexed) +SMLALB_zzxw_s 01000100 10 1 ..... 1000.0 ..... ..... @rrxr_3a esz=2 +SMLALB_zzxw_d 01000100 11 1 ..... 1000.0 ..... ..... @rrxr_2a esz=3 +SMLALT_zzxw_s 01000100 10 1 ..... 1000.1 ..... ..... @rrxr_3a esz=2 +SMLALT_zzxw_d 01000100 11 1 ..... 1000.1 ..... ..... @rrxr_2a esz=3 +UMLALB_zzxw_s 01000100 10 1 ..... 1001.0 ..... ..... @rrxr_3a esz=2 +UMLALB_zzxw_d 01000100 11 1 ..... 1001.0 ..... ..... @rrxr_2a esz=3 +UMLALT_zzxw_s 01000100 10 1 ..... 1001.1 ..... ..... @rrxr_3a esz=2 +UMLALT_zzxw_d 01000100 11 1 ..... 1001.1 ..... ..... @rrxr_2a esz=3 +SMLSLB_zzxw_s 01000100 10 1 ..... 1010.0 ..... ..... @rrxr_3a esz=2 +SMLSLB_zzxw_d 01000100 11 1 ..... 1010.0 ..... ..... @rrxr_2a esz=3 +SMLSLT_zzxw_s 01000100 10 1 ..... 1010.1 ..... ..... @rrxr_3a esz=2 +SMLSLT_zzxw_d 01000100 11 1 ..... 1010.1 ..... ..... @rrxr_2a esz=3 +UMLSLB_zzxw_s 01000100 10 1 ..... 1011.0 ..... ..... @rrxr_3a esz=2 +UMLSLB_zzxw_d 01000100 11 1 ..... 1011.0 ..... ..... @rrxr_2a esz=3 +UMLSLT_zzxw_s 01000100 10 1 ..... 1011.1 ..... ..... @rrxr_3a esz=2 +UMLSLT_zzxw_d 01000100 11 1 ..... 1011.1 ..... ..... @rrxr_2a esz=3 + +# SVE2 integer multiply long (indexed) +SMULLB_zzx_s 01000100 10 1 ..... 1100.0 ..... ..... @rrx_3a esz=2 +SMULLB_zzx_d 01000100 11 1 ..... 1100.0 ..... ..... @rrx_2a esz=3 +SMULLT_zzx_s 01000100 10 1 ..... 1100.1 ..... ..... @rrx_3a esz=2 +SMULLT_zzx_d 01000100 11 1 ..... 1100.1 ..... ..... @rrx_2a esz=3 +UMULLB_zzx_s 01000100 10 1 ..... 1101.0 ..... ..... @rrx_3a esz=2 +UMULLB_zzx_d 01000100 11 1 ..... 1101.0 ..... ..... @rrx_2a esz=3 +UMULLT_zzx_s 01000100 10 1 ..... 1101.1 ..... ..... @rrx_3a esz=2 +UMULLT_zzx_d 01000100 11 1 ..... 1101.1 ..... ..... @rrx_2a esz=3 + +# SVE2 saturating multiply (indexed) +SQDMULLB_zzx_s 01000100 10 1 ..... 1110.0 ..... ..... @rrx_3a esz=2 +SQDMULLB_zzx_d 01000100 11 1 ..... 1110.0 ..... ..... @rrx_2a esz=3 +SQDMULLT_zzx_s 01000100 10 1 ..... 1110.1 ..... ..... @rrx_3a esz=2 +SQDMULLT_zzx_d 01000100 11 1 ..... 1110.1 ..... ..... @rrx_2a esz=3 + +# SVE2 saturating multiply high (indexed) +SQDMULH_zzx_h 01000100 0. 1 ..... 111100 ..... ..... @rrx_3 esz=1 +SQDMULH_zzx_s 01000100 10 1 ..... 111100 ..... ..... @rrx_2 esz=2 +SQDMULH_zzx_d 01000100 11 1 ..... 111100 ..... ..... @rrx_1 esz=3 +SQRDMULH_zzx_h 01000100 0. 1 ..... 111101 ..... ..... @rrx_3 esz=1 +SQRDMULH_zzx_s 01000100 10 1 ..... 111101 ..... ..... @rrx_2 esz=2 +SQRDMULH_zzx_d 01000100 11 1 ..... 111101 ..... ..... @rrx_1 esz=3 + +# SVE2 integer multiply (indexed) +MUL_zzx_h 01000100 0. 1 ..... 111110 ..... ..... @rrx_3 esz=1 +MUL_zzx_s 01000100 10 1 ..... 111110 ..... ..... @rrx_2 esz=2 +MUL_zzx_d 01000100 11 1 ..... 111110 ..... ..... @rrx_1 esz=3 # SVE floating-point complex add (predicated) FCADD 01100100 esz:2 00000 rot:1 100 pg:3 rm:5 rd:5 \ @@ -749,20 +934,19 @@ FCMLA_zzxz 01100100 11 1 index:1 rm:4 0001 rot:2 rn:5 rd:5 \ ### SVE FP Multiply-Add Indexed Group # SVE floating-point multiply-add (indexed) -FMLA_zzxz 01100100 0.1 .. rm:3 00000 sub:1 rn:5 rd:5 \ - ra=%reg_movprfx index=%index3_22_19 esz=1 -FMLA_zzxz 01100100 101 index:2 rm:3 00000 sub:1 rn:5 rd:5 \ - ra=%reg_movprfx esz=2 -FMLA_zzxz 01100100 111 index:1 rm:4 00000 sub:1 rn:5 rd:5 \ - ra=%reg_movprfx esz=3 +FMLA_zzxz 01100100 0. 1 ..... 000000 ..... ..... @rrxr_3 esz=1 +FMLA_zzxz 01100100 10 1 ..... 000000 ..... ..... @rrxr_2 esz=2 +FMLA_zzxz 01100100 11 1 ..... 000000 ..... ..... @rrxr_1 esz=3 +FMLS_zzxz 01100100 0. 1 ..... 000001 ..... ..... @rrxr_3 esz=1 +FMLS_zzxz 01100100 10 1 ..... 000001 ..... ..... @rrxr_2 esz=2 +FMLS_zzxz 01100100 11 1 ..... 000001 ..... ..... @rrxr_1 esz=3 ### SVE FP Multiply Indexed Group # SVE floating-point multiply (indexed) -FMUL_zzx 01100100 0.1 .. rm:3 001000 rn:5 rd:5 \ - index=%index3_22_19 esz=1 -FMUL_zzx 01100100 101 index:2 rm:3 001000 rn:5 rd:5 esz=2 -FMUL_zzx 01100100 111 index:1 rm:4 001000 rn:5 rd:5 esz=3 +FMUL_zzx 01100100 0. 1 ..... 001000 ..... ..... @rrx_3 esz=1 +FMUL_zzx 01100100 10 1 ..... 001000 ..... ..... @rrx_2 esz=2 +FMUL_zzx 01100100 11 1 ..... 001000 ..... ..... @rrx_1 esz=3 ### SVE FP Fast Reduction Group @@ -957,11 +1141,15 @@ LD_zpri 1010010 .. nreg:2 0.... 111 ... ..... ..... @rpri_load_msz # SVE load and broadcast quadword (scalar plus scalar) LD1RQ_zprr 1010010 .. 00 ..... 000 ... ..... ..... \ @rprr_load_msz nreg=0 +LD1RO_zprr 1010010 .. 01 ..... 000 ... ..... ..... \ + @rprr_load_msz nreg=0 # SVE load and broadcast quadword (scalar plus immediate) # LD1RQB, LD1RQH, LD1RQS, LD1RQD LD1RQ_zpri 1010010 .. 00 0.... 001 ... ..... ..... \ @rpri_load_msz nreg=0 +LD1RO_zpri 1010010 .. 01 0.... 001 ... ..... ..... \ + @rpri_load_msz nreg=0 # SVE 32-bit gather prefetch (scalar plus 32-bit scaled offsets) PRF 1000010 00 -1 ----- 0-- --- ----- 0 ---- @@ -1090,3 +1278,353 @@ ST1_zprz 1110010 .. 00 ..... 100 ... ..... ..... \ @rprr_scatter_store xs=0 esz=3 scale=0 ST1_zprz 1110010 .. 00 ..... 110 ... ..... ..... \ @rprr_scatter_store xs=1 esz=3 scale=0 + +#### SVE2 Support + +### SVE2 Integer Multiply - Unpredicated + +# SVE2 integer multiply vectors (unpredicated) +MUL_zzz 00000100 .. 1 ..... 0110 00 ..... ..... @rd_rn_rm +SMULH_zzz 00000100 .. 1 ..... 0110 10 ..... ..... @rd_rn_rm +UMULH_zzz 00000100 .. 1 ..... 0110 11 ..... ..... @rd_rn_rm +PMUL_zzz 00000100 00 1 ..... 0110 01 ..... ..... @rd_rn_rm_e0 + +# SVE2 signed saturating doubling multiply high (unpredicated) +SQDMULH_zzz 00000100 .. 1 ..... 0111 00 ..... ..... @rd_rn_rm +SQRDMULH_zzz 00000100 .. 1 ..... 0111 01 ..... ..... @rd_rn_rm + +### SVE2 Integer - Predicated + +SADALP_zpzz 01000100 .. 000 100 101 ... ..... ..... @rdm_pg_rn +UADALP_zpzz 01000100 .. 000 101 101 ... ..... ..... @rdm_pg_rn + +### SVE2 integer unary operations (predicated) + +URECPE 01000100 .. 000 000 101 ... ..... ..... @rd_pg_rn +URSQRTE 01000100 .. 000 001 101 ... ..... ..... @rd_pg_rn +SQABS 01000100 .. 001 000 101 ... ..... ..... @rd_pg_rn +SQNEG 01000100 .. 001 001 101 ... ..... ..... @rd_pg_rn + +### SVE2 saturating/rounding bitwise shift left (predicated) + +SRSHL 01000100 .. 000 010 100 ... ..... ..... @rdn_pg_rm +URSHL 01000100 .. 000 011 100 ... ..... ..... @rdn_pg_rm +SRSHL 01000100 .. 000 110 100 ... ..... ..... @rdm_pg_rn # SRSHLR +URSHL 01000100 .. 000 111 100 ... ..... ..... @rdm_pg_rn # URSHLR + +SQSHL 01000100 .. 001 000 100 ... ..... ..... @rdn_pg_rm +UQSHL 01000100 .. 001 001 100 ... ..... ..... @rdn_pg_rm +SQSHL 01000100 .. 001 100 100 ... ..... ..... @rdm_pg_rn # SQSHLR +UQSHL 01000100 .. 001 101 100 ... ..... ..... @rdm_pg_rn # UQSHLR + +SQRSHL 01000100 .. 001 010 100 ... ..... ..... @rdn_pg_rm +UQRSHL 01000100 .. 001 011 100 ... ..... ..... @rdn_pg_rm +SQRSHL 01000100 .. 001 110 100 ... ..... ..... @rdm_pg_rn # SQRSHLR +UQRSHL 01000100 .. 001 111 100 ... ..... ..... @rdm_pg_rn # UQRSHLR + +### SVE2 integer halving add/subtract (predicated) + +SHADD 01000100 .. 010 000 100 ... ..... ..... @rdn_pg_rm +UHADD 01000100 .. 010 001 100 ... ..... ..... @rdn_pg_rm +SHSUB 01000100 .. 010 010 100 ... ..... ..... @rdn_pg_rm +UHSUB 01000100 .. 010 011 100 ... ..... ..... @rdn_pg_rm +SRHADD 01000100 .. 010 100 100 ... ..... ..... @rdn_pg_rm +URHADD 01000100 .. 010 101 100 ... ..... ..... @rdn_pg_rm +SHSUB 01000100 .. 010 110 100 ... ..... ..... @rdm_pg_rn # SHSUBR +UHSUB 01000100 .. 010 111 100 ... ..... ..... @rdm_pg_rn # UHSUBR + +### SVE2 integer pairwise arithmetic + +ADDP 01000100 .. 010 001 101 ... ..... ..... @rdn_pg_rm +SMAXP 01000100 .. 010 100 101 ... ..... ..... @rdn_pg_rm +UMAXP 01000100 .. 010 101 101 ... ..... ..... @rdn_pg_rm +SMINP 01000100 .. 010 110 101 ... ..... ..... @rdn_pg_rm +UMINP 01000100 .. 010 111 101 ... ..... ..... @rdn_pg_rm + +### SVE2 saturating add/subtract (predicated) + +SQADD_zpzz 01000100 .. 011 000 100 ... ..... ..... @rdn_pg_rm +UQADD_zpzz 01000100 .. 011 001 100 ... ..... ..... @rdn_pg_rm +SQSUB_zpzz 01000100 .. 011 010 100 ... ..... ..... @rdn_pg_rm +UQSUB_zpzz 01000100 .. 011 011 100 ... ..... ..... @rdn_pg_rm +SUQADD 01000100 .. 011 100 100 ... ..... ..... @rdn_pg_rm +USQADD 01000100 .. 011 101 100 ... ..... ..... @rdn_pg_rm +SQSUB_zpzz 01000100 .. 011 110 100 ... ..... ..... @rdm_pg_rn # SQSUBR +UQSUB_zpzz 01000100 .. 011 111 100 ... ..... ..... @rdm_pg_rn # UQSUBR + +#### SVE2 Widening Integer Arithmetic + +## SVE2 integer add/subtract long + +SADDLB 01000101 .. 0 ..... 00 0000 ..... ..... @rd_rn_rm +SADDLT 01000101 .. 0 ..... 00 0001 ..... ..... @rd_rn_rm +UADDLB 01000101 .. 0 ..... 00 0010 ..... ..... @rd_rn_rm +UADDLT 01000101 .. 0 ..... 00 0011 ..... ..... @rd_rn_rm + +SSUBLB 01000101 .. 0 ..... 00 0100 ..... ..... @rd_rn_rm +SSUBLT 01000101 .. 0 ..... 00 0101 ..... ..... @rd_rn_rm +USUBLB 01000101 .. 0 ..... 00 0110 ..... ..... @rd_rn_rm +USUBLT 01000101 .. 0 ..... 00 0111 ..... ..... @rd_rn_rm + +SABDLB 01000101 .. 0 ..... 00 1100 ..... ..... @rd_rn_rm +SABDLT 01000101 .. 0 ..... 00 1101 ..... ..... @rd_rn_rm +UABDLB 01000101 .. 0 ..... 00 1110 ..... ..... @rd_rn_rm +UABDLT 01000101 .. 0 ..... 00 1111 ..... ..... @rd_rn_rm + +## SVE2 integer add/subtract interleaved long + +SADDLBT 01000101 .. 0 ..... 1000 00 ..... ..... @rd_rn_rm +SSUBLBT 01000101 .. 0 ..... 1000 10 ..... ..... @rd_rn_rm +SSUBLTB 01000101 .. 0 ..... 1000 11 ..... ..... @rd_rn_rm + +## SVE2 integer add/subtract wide + +SADDWB 01000101 .. 0 ..... 010 000 ..... ..... @rd_rn_rm +SADDWT 01000101 .. 0 ..... 010 001 ..... ..... @rd_rn_rm +UADDWB 01000101 .. 0 ..... 010 010 ..... ..... @rd_rn_rm +UADDWT 01000101 .. 0 ..... 010 011 ..... ..... @rd_rn_rm + +SSUBWB 01000101 .. 0 ..... 010 100 ..... ..... @rd_rn_rm +SSUBWT 01000101 .. 0 ..... 010 101 ..... ..... @rd_rn_rm +USUBWB 01000101 .. 0 ..... 010 110 ..... ..... @rd_rn_rm +USUBWT 01000101 .. 0 ..... 010 111 ..... ..... @rd_rn_rm + +## SVE2 integer multiply long + +SQDMULLB_zzz 01000101 .. 0 ..... 011 000 ..... ..... @rd_rn_rm +SQDMULLT_zzz 01000101 .. 0 ..... 011 001 ..... ..... @rd_rn_rm +PMULLB 01000101 .. 0 ..... 011 010 ..... ..... @rd_rn_rm +PMULLT 01000101 .. 0 ..... 011 011 ..... ..... @rd_rn_rm +SMULLB_zzz 01000101 .. 0 ..... 011 100 ..... ..... @rd_rn_rm +SMULLT_zzz 01000101 .. 0 ..... 011 101 ..... ..... @rd_rn_rm +UMULLB_zzz 01000101 .. 0 ..... 011 110 ..... ..... @rd_rn_rm +UMULLT_zzz 01000101 .. 0 ..... 011 111 ..... ..... @rd_rn_rm + +## SVE2 bitwise shift left long + +# Note bit23 == 0 is handled by esz > 0 in do_sve2_shll_tb. +SSHLLB 01000101 .. 0 ..... 1010 00 ..... ..... @rd_rn_tszimm_shl +SSHLLT 01000101 .. 0 ..... 1010 01 ..... ..... @rd_rn_tszimm_shl +USHLLB 01000101 .. 0 ..... 1010 10 ..... ..... @rd_rn_tszimm_shl +USHLLT 01000101 .. 0 ..... 1010 11 ..... ..... @rd_rn_tszimm_shl + +## SVE2 bitwise exclusive-or interleaved + +EORBT 01000101 .. 0 ..... 10010 0 ..... ..... @rd_rn_rm +EORTB 01000101 .. 0 ..... 10010 1 ..... ..... @rd_rn_rm + +## SVE integer matrix multiply accumulate + +SMMLA 01000101 00 0 ..... 10011 0 ..... ..... @rda_rn_rm_e0 +USMMLA 01000101 10 0 ..... 10011 0 ..... ..... @rda_rn_rm_e0 +UMMLA 01000101 11 0 ..... 10011 0 ..... ..... @rda_rn_rm_e0 + +## SVE2 bitwise permute + +BEXT 01000101 .. 0 ..... 1011 00 ..... ..... @rd_rn_rm +BDEP 01000101 .. 0 ..... 1011 01 ..... ..... @rd_rn_rm +BGRP 01000101 .. 0 ..... 1011 10 ..... ..... @rd_rn_rm + +#### SVE2 Accumulate + +## SVE2 complex integer add + +CADD_rot90 01000101 .. 00000 0 11011 0 ..... ..... @rdn_rm +CADD_rot270 01000101 .. 00000 0 11011 1 ..... ..... @rdn_rm +SQCADD_rot90 01000101 .. 00000 1 11011 0 ..... ..... @rdn_rm +SQCADD_rot270 01000101 .. 00000 1 11011 1 ..... ..... @rdn_rm + +## SVE2 integer absolute difference and accumulate long + +SABALB 01000101 .. 0 ..... 1100 00 ..... ..... @rda_rn_rm +SABALT 01000101 .. 0 ..... 1100 01 ..... ..... @rda_rn_rm +UABALB 01000101 .. 0 ..... 1100 10 ..... ..... @rda_rn_rm +UABALT 01000101 .. 0 ..... 1100 11 ..... ..... @rda_rn_rm + +## SVE2 integer add/subtract long with carry + +# ADC and SBC decoded via size in helper dispatch. +ADCLB 01000101 .. 0 ..... 11010 0 ..... ..... @rda_rn_rm +ADCLT 01000101 .. 0 ..... 11010 1 ..... ..... @rda_rn_rm + +## SVE2 bitwise shift right and accumulate + +# TODO: Use @rda and %reg_movprfx here. +SSRA 01000101 .. 0 ..... 1110 00 ..... ..... @rd_rn_tszimm_shr +USRA 01000101 .. 0 ..... 1110 01 ..... ..... @rd_rn_tszimm_shr +SRSRA 01000101 .. 0 ..... 1110 10 ..... ..... @rd_rn_tszimm_shr +URSRA 01000101 .. 0 ..... 1110 11 ..... ..... @rd_rn_tszimm_shr + +## SVE2 bitwise shift and insert + +SRI 01000101 .. 0 ..... 11110 0 ..... ..... @rd_rn_tszimm_shr +SLI 01000101 .. 0 ..... 11110 1 ..... ..... @rd_rn_tszimm_shl + +## SVE2 integer absolute difference and accumulate + +# TODO: Use @rda and %reg_movprfx here. +SABA 01000101 .. 0 ..... 11111 0 ..... ..... @rd_rn_rm +UABA 01000101 .. 0 ..... 11111 1 ..... ..... @rd_rn_rm + +#### SVE2 Narrowing + +## SVE2 saturating extract narrow + +# Bits 23, 18-16 are zero, limited in the translator via esz < 3 & imm == 0. +SQXTNB 01000101 .. 1 ..... 010 000 ..... ..... @rd_rn_tszimm_shl +SQXTNT 01000101 .. 1 ..... 010 001 ..... ..... @rd_rn_tszimm_shl +UQXTNB 01000101 .. 1 ..... 010 010 ..... ..... @rd_rn_tszimm_shl +UQXTNT 01000101 .. 1 ..... 010 011 ..... ..... @rd_rn_tszimm_shl +SQXTUNB 01000101 .. 1 ..... 010 100 ..... ..... @rd_rn_tszimm_shl +SQXTUNT 01000101 .. 1 ..... 010 101 ..... ..... @rd_rn_tszimm_shl + +## SVE2 bitwise shift right narrow + +# Bit 23 == 0 is handled by esz > 0 in the translator. +SQSHRUNB 01000101 .. 1 ..... 00 0000 ..... ..... @rd_rn_tszimm_shr +SQSHRUNT 01000101 .. 1 ..... 00 0001 ..... ..... @rd_rn_tszimm_shr +SQRSHRUNB 01000101 .. 1 ..... 00 0010 ..... ..... @rd_rn_tszimm_shr +SQRSHRUNT 01000101 .. 1 ..... 00 0011 ..... ..... @rd_rn_tszimm_shr +SHRNB 01000101 .. 1 ..... 00 0100 ..... ..... @rd_rn_tszimm_shr +SHRNT 01000101 .. 1 ..... 00 0101 ..... ..... @rd_rn_tszimm_shr +RSHRNB 01000101 .. 1 ..... 00 0110 ..... ..... @rd_rn_tszimm_shr +RSHRNT 01000101 .. 1 ..... 00 0111 ..... ..... @rd_rn_tszimm_shr +SQSHRNB 01000101 .. 1 ..... 00 1000 ..... ..... @rd_rn_tszimm_shr +SQSHRNT 01000101 .. 1 ..... 00 1001 ..... ..... @rd_rn_tszimm_shr +SQRSHRNB 01000101 .. 1 ..... 00 1010 ..... ..... @rd_rn_tszimm_shr +SQRSHRNT 01000101 .. 1 ..... 00 1011 ..... ..... @rd_rn_tszimm_shr +UQSHRNB 01000101 .. 1 ..... 00 1100 ..... ..... @rd_rn_tszimm_shr +UQSHRNT 01000101 .. 1 ..... 00 1101 ..... ..... @rd_rn_tszimm_shr +UQRSHRNB 01000101 .. 1 ..... 00 1110 ..... ..... @rd_rn_tszimm_shr +UQRSHRNT 01000101 .. 1 ..... 00 1111 ..... ..... @rd_rn_tszimm_shr + +## SVE2 integer add/subtract narrow high part + +ADDHNB 01000101 .. 1 ..... 011 000 ..... ..... @rd_rn_rm +ADDHNT 01000101 .. 1 ..... 011 001 ..... ..... @rd_rn_rm +RADDHNB 01000101 .. 1 ..... 011 010 ..... ..... @rd_rn_rm +RADDHNT 01000101 .. 1 ..... 011 011 ..... ..... @rd_rn_rm +SUBHNB 01000101 .. 1 ..... 011 100 ..... ..... @rd_rn_rm +SUBHNT 01000101 .. 1 ..... 011 101 ..... ..... @rd_rn_rm +RSUBHNB 01000101 .. 1 ..... 011 110 ..... ..... @rd_rn_rm +RSUBHNT 01000101 .. 1 ..... 011 111 ..... ..... @rd_rn_rm + +### SVE2 Character Match + +MATCH 01000101 .. 1 ..... 100 ... ..... 0 .... @pd_pg_rn_rm +NMATCH 01000101 .. 1 ..... 100 ... ..... 1 .... @pd_pg_rn_rm + +### SVE2 Histogram Computation + +HISTCNT 01000101 .. 1 ..... 110 ... ..... ..... @rd_pg_rn_rm +HISTSEG 01000101 .. 1 ..... 101 000 ..... ..... @rd_rn_rm + +## SVE2 floating-point pairwise operations + +FADDP 01100100 .. 010 00 0 100 ... ..... ..... @rdn_pg_rm +FMAXNMP 01100100 .. 010 10 0 100 ... ..... ..... @rdn_pg_rm +FMINNMP 01100100 .. 010 10 1 100 ... ..... ..... @rdn_pg_rm +FMAXP 01100100 .. 010 11 0 100 ... ..... ..... @rdn_pg_rm +FMINP 01100100 .. 010 11 1 100 ... ..... ..... @rdn_pg_rm + +#### SVE Integer Multiply-Add (unpredicated) + +## SVE2 saturating multiply-add long + +SQDMLALB_zzzw 01000100 .. 0 ..... 0110 00 ..... ..... @rda_rn_rm +SQDMLALT_zzzw 01000100 .. 0 ..... 0110 01 ..... ..... @rda_rn_rm +SQDMLSLB_zzzw 01000100 .. 0 ..... 0110 10 ..... ..... @rda_rn_rm +SQDMLSLT_zzzw 01000100 .. 0 ..... 0110 11 ..... ..... @rda_rn_rm + +## SVE2 saturating multiply-add interleaved long + +SQDMLALBT 01000100 .. 0 ..... 00001 0 ..... ..... @rda_rn_rm +SQDMLSLBT 01000100 .. 0 ..... 00001 1 ..... ..... @rda_rn_rm + +## SVE2 saturating multiply-add high + +SQRDMLAH_zzzz 01000100 .. 0 ..... 01110 0 ..... ..... @rda_rn_rm +SQRDMLSH_zzzz 01000100 .. 0 ..... 01110 1 ..... ..... @rda_rn_rm + +## SVE2 integer multiply-add long + +SMLALB_zzzw 01000100 .. 0 ..... 010 000 ..... ..... @rda_rn_rm +SMLALT_zzzw 01000100 .. 0 ..... 010 001 ..... ..... @rda_rn_rm +UMLALB_zzzw 01000100 .. 0 ..... 010 010 ..... ..... @rda_rn_rm +UMLALT_zzzw 01000100 .. 0 ..... 010 011 ..... ..... @rda_rn_rm +SMLSLB_zzzw 01000100 .. 0 ..... 010 100 ..... ..... @rda_rn_rm +SMLSLT_zzzw 01000100 .. 0 ..... 010 101 ..... ..... @rda_rn_rm +UMLSLB_zzzw 01000100 .. 0 ..... 010 110 ..... ..... @rda_rn_rm +UMLSLT_zzzw 01000100 .. 0 ..... 010 111 ..... ..... @rda_rn_rm + +## SVE2 complex integer multiply-add + +CMLA_zzzz 01000100 esz:2 0 rm:5 0010 rot:2 rn:5 rd:5 ra=%reg_movprfx +SQRDCMLAH_zzzz 01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5 ra=%reg_movprfx + +## SVE mixed sign dot product + +USDOT_zzzz 01000100 .. 0 ..... 011 110 ..... ..... @rda_rn_rm + +### SVE2 floating point matrix multiply accumulate + +FMMLA 01100100 .. 1 ..... 111001 ..... ..... @rda_rn_rm + +### SVE2 Memory Gather Load Group + +# SVE2 64-bit gather non-temporal load +# (scalar plus unpacked 32-bit unscaled offsets) +LDNT1_zprz 1100010 msz:2 00 rm:5 1 u:1 0 pg:3 rn:5 rd:5 \ + &rprr_gather_load xs=0 esz=3 scale=0 ff=0 + +# SVE2 32-bit gather non-temporal load (scalar plus 32-bit unscaled offsets) +LDNT1_zprz 1000010 msz:2 00 rm:5 10 u:1 pg:3 rn:5 rd:5 \ + &rprr_gather_load xs=0 esz=2 scale=0 ff=0 + +### SVE2 Memory Store Group + +# SVE2 64-bit scatter non-temporal store (vector plus scalar) +STNT1_zprz 1110010 .. 00 ..... 001 ... ..... ..... \ + @rprr_scatter_store xs=2 esz=3 scale=0 + +# SVE2 32-bit scatter non-temporal store (vector plus scalar) +STNT1_zprz 1110010 .. 10 ..... 001 ... ..... ..... \ + @rprr_scatter_store xs=0 esz=2 scale=0 + +### SVE2 Crypto Extensions + +# SVE2 crypto unary operations +# AESMC and AESIMC +AESMC 01000101 00 10000011100 decrypt:1 00000 rd:5 + +# SVE2 crypto destructive binary operations +AESE 01000101 00 10001 0 11100 0 ..... ..... @rdn_rm_e0 +AESD 01000101 00 10001 0 11100 1 ..... ..... @rdn_rm_e0 +SM4E 01000101 00 10001 1 11100 0 ..... ..... @rdn_rm_e0 + +# SVE2 crypto constructive binary operations +SM4EKEY 01000101 00 1 ..... 11110 0 ..... ..... @rd_rn_rm_e0 +RAX1 01000101 00 1 ..... 11110 1 ..... ..... @rd_rn_rm_e0 + +### SVE2 floating-point convert precision odd elements +FCVTXNT_ds 01100100 00 0010 10 101 ... ..... ..... @rd_pg_rn_e0 +FCVTX_ds 01100101 00 0010 10 101 ... ..... ..... @rd_pg_rn_e0 +FCVTNT_sh 01100100 10 0010 00 101 ... ..... ..... @rd_pg_rn_e0 +FCVTLT_hs 01100100 10 0010 01 101 ... ..... ..... @rd_pg_rn_e0 +FCVTNT_ds 01100100 11 0010 10 101 ... ..... ..... @rd_pg_rn_e0 +FCVTLT_sd 01100100 11 0010 11 101 ... ..... ..... @rd_pg_rn_e0 + +### SVE2 floating-point convert to integer +FLOGB 01100101 00 011 esz:2 0101 pg:3 rn:5 rd:5 &rpr_esz + +### SVE2 floating-point multiply-add long (vectors) +FMLALB_zzzw 01100100 10 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_e0 +FMLALT_zzzw 01100100 10 1 ..... 10 0 00 1 ..... ..... @rda_rn_rm_e0 +FMLSLB_zzzw 01100100 10 1 ..... 10 1 00 0 ..... ..... @rda_rn_rm_e0 +FMLSLT_zzzw 01100100 10 1 ..... 10 1 00 1 ..... ..... @rda_rn_rm_e0 + +### SVE2 floating-point multiply-add long (indexed) +FMLALB_zzxw 01100100 10 1 ..... 0100.0 ..... ..... @rrxr_3a esz=2 +FMLALT_zzxw 01100100 10 1 ..... 0100.1 ..... ..... @rrxr_3a esz=2 +FMLSLB_zzxw 01100100 10 1 ..... 0110.0 ..... ..... @rrxr_3a esz=2 +FMLSLT_zzxw 01100100 10 1 ..... 0110.1 ..... ..... @rrxr_3a esz=2 diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index c068dfa0d5..40af3024df 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -26,24 +26,9 @@ #include "tcg/tcg-gvec-desc.h" #include "fpu/softfloat.h" #include "tcg/tcg.h" +#include "vec_internal.h" -/* Note that vector data is stored in host-endian 64-bit chunks, - so addressing units smaller than that needs a host-endian fixup. */ -#ifdef HOST_WORDS_BIGENDIAN -#define H1(x) ((x) ^ 7) -#define H1_2(x) ((x) ^ 6) -#define H1_4(x) ((x) ^ 4) -#define H2(x) ((x) ^ 3) -#define H4(x) ((x) ^ 1) -#else -#define H1(x) (x) -#define H1_2(x) (x) -#define H1_4(x) (x) -#define H2(x) (x) -#define H4(x) (x) -#endif - /* Return a value for NZCV as per the ARM PredTest pseudofunction. * * The return value has bit 31 set if N is set, bit 1 set if Z is clear, @@ -517,9 +502,429 @@ DO_ZPZZ_D(sve_asr_zpzz_d, int64_t, DO_ASR) DO_ZPZZ_D(sve_lsr_zpzz_d, uint64_t, DO_LSR) DO_ZPZZ_D(sve_lsl_zpzz_d, uint64_t, DO_LSL) +static inline uint16_t do_sadalp_h(int16_t n, int16_t m) +{ + int8_t n1 = n, n2 = n >> 8; + return m + n1 + n2; +} + +static inline uint32_t do_sadalp_s(int32_t n, int32_t m) +{ + int16_t n1 = n, n2 = n >> 16; + return m + n1 + n2; +} + +static inline uint64_t do_sadalp_d(int64_t n, int64_t m) +{ + int32_t n1 = n, n2 = n >> 32; + return m + n1 + n2; +} + +DO_ZPZZ(sve2_sadalp_zpzz_h, int16_t, H1_2, do_sadalp_h) +DO_ZPZZ(sve2_sadalp_zpzz_s, int32_t, H1_4, do_sadalp_s) +DO_ZPZZ_D(sve2_sadalp_zpzz_d, int64_t, do_sadalp_d) + +static inline uint16_t do_uadalp_h(uint16_t n, uint16_t m) +{ + uint8_t n1 = n, n2 = n >> 8; + return m + n1 + n2; +} + +static inline uint32_t do_uadalp_s(uint32_t n, uint32_t m) +{ + uint16_t n1 = n, n2 = n >> 16; + return m + n1 + n2; +} + +static inline uint64_t do_uadalp_d(uint64_t n, uint64_t m) +{ + uint32_t n1 = n, n2 = n >> 32; + return m + n1 + n2; +} + +DO_ZPZZ(sve2_uadalp_zpzz_h, uint16_t, H1_2, do_uadalp_h) +DO_ZPZZ(sve2_uadalp_zpzz_s, uint32_t, H1_4, do_uadalp_s) +DO_ZPZZ_D(sve2_uadalp_zpzz_d, uint64_t, do_uadalp_d) + +#define do_srshl_b(n, m) do_sqrshl_bhs(n, m, 8, true, NULL) +#define do_srshl_h(n, m) do_sqrshl_bhs(n, m, 16, true, NULL) +#define do_srshl_s(n, m) do_sqrshl_bhs(n, m, 32, true, NULL) +#define do_srshl_d(n, m) do_sqrshl_d(n, m, true, NULL) + +DO_ZPZZ(sve2_srshl_zpzz_b, int8_t, H1, do_srshl_b) +DO_ZPZZ(sve2_srshl_zpzz_h, int16_t, H1_2, do_srshl_h) +DO_ZPZZ(sve2_srshl_zpzz_s, int32_t, H1_4, do_srshl_s) +DO_ZPZZ_D(sve2_srshl_zpzz_d, int64_t, do_srshl_d) + +#define do_urshl_b(n, m) do_uqrshl_bhs(n, (int8_t)m, 8, true, NULL) +#define do_urshl_h(n, m) do_uqrshl_bhs(n, (int16_t)m, 16, true, NULL) +#define do_urshl_s(n, m) do_uqrshl_bhs(n, m, 32, true, NULL) +#define do_urshl_d(n, m) do_uqrshl_d(n, m, true, NULL) + +DO_ZPZZ(sve2_urshl_zpzz_b, uint8_t, H1, do_urshl_b) +DO_ZPZZ(sve2_urshl_zpzz_h, uint16_t, H1_2, do_urshl_h) +DO_ZPZZ(sve2_urshl_zpzz_s, uint32_t, H1_4, do_urshl_s) +DO_ZPZZ_D(sve2_urshl_zpzz_d, uint64_t, do_urshl_d) + +/* + * Unlike the NEON and AdvSIMD versions, there is no QC bit to set. + * We pass in a pointer to a dummy saturation field to trigger + * the saturating arithmetic but discard the information about + * whether it has occurred. + */ +#define do_sqshl_b(n, m) \ + ({ uint32_t discard; do_sqrshl_bhs(n, m, 8, false, &discard); }) +#define do_sqshl_h(n, m) \ + ({ uint32_t discard; do_sqrshl_bhs(n, m, 16, false, &discard); }) +#define do_sqshl_s(n, m) \ + ({ uint32_t discard; do_sqrshl_bhs(n, m, 32, false, &discard); }) +#define do_sqshl_d(n, m) \ + ({ uint32_t discard; do_sqrshl_d(n, m, false, &discard); }) + +DO_ZPZZ(sve2_sqshl_zpzz_b, int8_t, H1_2, do_sqshl_b) +DO_ZPZZ(sve2_sqshl_zpzz_h, int16_t, H1_2, do_sqshl_h) +DO_ZPZZ(sve2_sqshl_zpzz_s, int32_t, H1_4, do_sqshl_s) +DO_ZPZZ_D(sve2_sqshl_zpzz_d, int64_t, do_sqshl_d) + +#define do_uqshl_b(n, m) \ + ({ uint32_t discard; do_uqrshl_bhs(n, (int8_t)m, 8, false, &discard); }) +#define do_uqshl_h(n, m) \ + ({ uint32_t discard; do_uqrshl_bhs(n, (int16_t)m, 16, false, &discard); }) +#define do_uqshl_s(n, m) \ + ({ uint32_t discard; do_uqrshl_bhs(n, m, 32, false, &discard); }) +#define do_uqshl_d(n, m) \ + ({ uint32_t discard; do_uqrshl_d(n, m, false, &discard); }) + +DO_ZPZZ(sve2_uqshl_zpzz_b, uint8_t, H1_2, do_uqshl_b) +DO_ZPZZ(sve2_uqshl_zpzz_h, uint16_t, H1_2, do_uqshl_h) +DO_ZPZZ(sve2_uqshl_zpzz_s, uint32_t, H1_4, do_uqshl_s) +DO_ZPZZ_D(sve2_uqshl_zpzz_d, uint64_t, do_uqshl_d) + +#define do_sqrshl_b(n, m) \ + ({ uint32_t discard; do_sqrshl_bhs(n, m, 8, true, &discard); }) +#define do_sqrshl_h(n, m) \ + ({ uint32_t discard; do_sqrshl_bhs(n, m, 16, true, &discard); }) +#define do_sqrshl_s(n, m) \ + ({ uint32_t discard; do_sqrshl_bhs(n, m, 32, true, &discard); }) +#define do_sqrshl_d(n, m) \ + ({ uint32_t discard; do_sqrshl_d(n, m, true, &discard); }) + +DO_ZPZZ(sve2_sqrshl_zpzz_b, int8_t, H1_2, do_sqrshl_b) +DO_ZPZZ(sve2_sqrshl_zpzz_h, int16_t, H1_2, do_sqrshl_h) +DO_ZPZZ(sve2_sqrshl_zpzz_s, int32_t, H1_4, do_sqrshl_s) +DO_ZPZZ_D(sve2_sqrshl_zpzz_d, int64_t, do_sqrshl_d) + +#undef do_sqrshl_d + +#define do_uqrshl_b(n, m) \ + ({ uint32_t discard; do_uqrshl_bhs(n, (int8_t)m, 8, true, &discard); }) +#define do_uqrshl_h(n, m) \ + ({ uint32_t discard; do_uqrshl_bhs(n, (int16_t)m, 16, true, &discard); }) +#define do_uqrshl_s(n, m) \ + ({ uint32_t discard; do_uqrshl_bhs(n, m, 32, true, &discard); }) +#define do_uqrshl_d(n, m) \ + ({ uint32_t discard; do_uqrshl_d(n, m, true, &discard); }) + +DO_ZPZZ(sve2_uqrshl_zpzz_b, uint8_t, H1_2, do_uqrshl_b) +DO_ZPZZ(sve2_uqrshl_zpzz_h, uint16_t, H1_2, do_uqrshl_h) +DO_ZPZZ(sve2_uqrshl_zpzz_s, uint32_t, H1_4, do_uqrshl_s) +DO_ZPZZ_D(sve2_uqrshl_zpzz_d, uint64_t, do_uqrshl_d) + +#undef do_uqrshl_d + +#define DO_HADD_BHS(n, m) (((int64_t)n + m) >> 1) +#define DO_HADD_D(n, m) ((n >> 1) + (m >> 1) + (n & m & 1)) + +DO_ZPZZ(sve2_shadd_zpzz_b, int8_t, H1, DO_HADD_BHS) +DO_ZPZZ(sve2_shadd_zpzz_h, int16_t, H1_2, DO_HADD_BHS) +DO_ZPZZ(sve2_shadd_zpzz_s, int32_t, H1_4, DO_HADD_BHS) +DO_ZPZZ_D(sve2_shadd_zpzz_d, int64_t, DO_HADD_D) + +DO_ZPZZ(sve2_uhadd_zpzz_b, uint8_t, H1, DO_HADD_BHS) +DO_ZPZZ(sve2_uhadd_zpzz_h, uint16_t, H1_2, DO_HADD_BHS) +DO_ZPZZ(sve2_uhadd_zpzz_s, uint32_t, H1_4, DO_HADD_BHS) +DO_ZPZZ_D(sve2_uhadd_zpzz_d, uint64_t, DO_HADD_D) + +#define DO_RHADD_BHS(n, m) (((int64_t)n + m + 1) >> 1) +#define DO_RHADD_D(n, m) ((n >> 1) + (m >> 1) + ((n | m) & 1)) + +DO_ZPZZ(sve2_srhadd_zpzz_b, int8_t, H1, DO_RHADD_BHS) +DO_ZPZZ(sve2_srhadd_zpzz_h, int16_t, H1_2, DO_RHADD_BHS) +DO_ZPZZ(sve2_srhadd_zpzz_s, int32_t, H1_4, DO_RHADD_BHS) +DO_ZPZZ_D(sve2_srhadd_zpzz_d, int64_t, DO_RHADD_D) + +DO_ZPZZ(sve2_urhadd_zpzz_b, uint8_t, H1, DO_RHADD_BHS) +DO_ZPZZ(sve2_urhadd_zpzz_h, uint16_t, H1_2, DO_RHADD_BHS) +DO_ZPZZ(sve2_urhadd_zpzz_s, uint32_t, H1_4, DO_RHADD_BHS) +DO_ZPZZ_D(sve2_urhadd_zpzz_d, uint64_t, DO_RHADD_D) + +#define DO_HSUB_BHS(n, m) (((int64_t)n - m) >> 1) +#define DO_HSUB_D(n, m) ((n >> 1) - (m >> 1) - (~n & m & 1)) + +DO_ZPZZ(sve2_shsub_zpzz_b, int8_t, H1, DO_HSUB_BHS) +DO_ZPZZ(sve2_shsub_zpzz_h, int16_t, H1_2, DO_HSUB_BHS) +DO_ZPZZ(sve2_shsub_zpzz_s, int32_t, H1_4, DO_HSUB_BHS) +DO_ZPZZ_D(sve2_shsub_zpzz_d, int64_t, DO_HSUB_D) + +DO_ZPZZ(sve2_uhsub_zpzz_b, uint8_t, H1, DO_HSUB_BHS) +DO_ZPZZ(sve2_uhsub_zpzz_h, uint16_t, H1_2, DO_HSUB_BHS) +DO_ZPZZ(sve2_uhsub_zpzz_s, uint32_t, H1_4, DO_HSUB_BHS) +DO_ZPZZ_D(sve2_uhsub_zpzz_d, uint64_t, DO_HSUB_D) + +static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max) +{ + return val >= max ? max : val <= min ? min : val; +} + +#define DO_SQADD_B(n, m) do_sat_bhs((int64_t)n + m, INT8_MIN, INT8_MAX) +#define DO_SQADD_H(n, m) do_sat_bhs((int64_t)n + m, INT16_MIN, INT16_MAX) +#define DO_SQADD_S(n, m) do_sat_bhs((int64_t)n + m, INT32_MIN, INT32_MAX) + +static inline int64_t do_sqadd_d(int64_t n, int64_t m) +{ + int64_t r = n + m; + if (((r ^ n) & ~(n ^ m)) < 0) { + /* Signed overflow. */ + return r < 0 ? INT64_MAX : INT64_MIN; + } + return r; +} + +DO_ZPZZ(sve2_sqadd_zpzz_b, int8_t, H1, DO_SQADD_B) +DO_ZPZZ(sve2_sqadd_zpzz_h, int16_t, H1_2, DO_SQADD_H) +DO_ZPZZ(sve2_sqadd_zpzz_s, int32_t, H1_4, DO_SQADD_S) +DO_ZPZZ_D(sve2_sqadd_zpzz_d, int64_t, do_sqadd_d) + +#define DO_UQADD_B(n, m) do_sat_bhs((int64_t)n + m, 0, UINT8_MAX) +#define DO_UQADD_H(n, m) do_sat_bhs((int64_t)n + m, 0, UINT16_MAX) +#define DO_UQADD_S(n, m) do_sat_bhs((int64_t)n + m, 0, UINT32_MAX) + +static inline uint64_t do_uqadd_d(uint64_t n, uint64_t m) +{ + uint64_t r = n + m; + return r < n ? UINT64_MAX : r; +} + +DO_ZPZZ(sve2_uqadd_zpzz_b, uint8_t, H1, DO_UQADD_B) +DO_ZPZZ(sve2_uqadd_zpzz_h, uint16_t, H1_2, DO_UQADD_H) +DO_ZPZZ(sve2_uqadd_zpzz_s, uint32_t, H1_4, DO_UQADD_S) +DO_ZPZZ_D(sve2_uqadd_zpzz_d, uint64_t, do_uqadd_d) + +#define DO_SQSUB_B(n, m) do_sat_bhs((int64_t)n - m, INT8_MIN, INT8_MAX) +#define DO_SQSUB_H(n, m) do_sat_bhs((int64_t)n - m, INT16_MIN, INT16_MAX) +#define DO_SQSUB_S(n, m) do_sat_bhs((int64_t)n - m, INT32_MIN, INT32_MAX) + +static inline int64_t do_sqsub_d(int64_t n, int64_t m) +{ + int64_t r = n - m; + if (((r ^ n) & (n ^ m)) < 0) { + /* Signed overflow. */ + return r < 0 ? INT64_MAX : INT64_MIN; + } + return r; +} + +DO_ZPZZ(sve2_sqsub_zpzz_b, int8_t, H1, DO_SQSUB_B) +DO_ZPZZ(sve2_sqsub_zpzz_h, int16_t, H1_2, DO_SQSUB_H) +DO_ZPZZ(sve2_sqsub_zpzz_s, int32_t, H1_4, DO_SQSUB_S) +DO_ZPZZ_D(sve2_sqsub_zpzz_d, int64_t, do_sqsub_d) + +#define DO_UQSUB_B(n, m) do_sat_bhs((int64_t)n - m, 0, UINT8_MAX) +#define DO_UQSUB_H(n, m) do_sat_bhs((int64_t)n - m, 0, UINT16_MAX) +#define DO_UQSUB_S(n, m) do_sat_bhs((int64_t)n - m, 0, UINT32_MAX) + +static inline uint64_t do_uqsub_d(uint64_t n, uint64_t m) +{ + return n > m ? n - m : 0; +} + +DO_ZPZZ(sve2_uqsub_zpzz_b, uint8_t, H1, DO_UQSUB_B) +DO_ZPZZ(sve2_uqsub_zpzz_h, uint16_t, H1_2, DO_UQSUB_H) +DO_ZPZZ(sve2_uqsub_zpzz_s, uint32_t, H1_4, DO_UQSUB_S) +DO_ZPZZ_D(sve2_uqsub_zpzz_d, uint64_t, do_uqsub_d) + +#define DO_SUQADD_B(n, m) \ + do_sat_bhs((int64_t)(int8_t)n + m, INT8_MIN, INT8_MAX) +#define DO_SUQADD_H(n, m) \ + do_sat_bhs((int64_t)(int16_t)n + m, INT16_MIN, INT16_MAX) +#define DO_SUQADD_S(n, m) \ + do_sat_bhs((int64_t)(int32_t)n + m, INT32_MIN, INT32_MAX) + +static inline int64_t do_suqadd_d(int64_t n, uint64_t m) +{ + uint64_t r = n + m; + + if (n < 0) { + /* Note that m - abs(n) cannot underflow. */ + if (r > INT64_MAX) { + /* Result is either very large positive or negative. */ + if (m > -n) { + /* m > abs(n), so r is a very large positive. */ + return INT64_MAX; + } + /* Result is negative. */ + } + } else { + /* Both inputs are positive: check for overflow. */ + if (r < m || r > INT64_MAX) { + return INT64_MAX; + } + } + return r; +} + +DO_ZPZZ(sve2_suqadd_zpzz_b, uint8_t, H1, DO_SUQADD_B) +DO_ZPZZ(sve2_suqadd_zpzz_h, uint16_t, H1_2, DO_SUQADD_H) +DO_ZPZZ(sve2_suqadd_zpzz_s, uint32_t, H1_4, DO_SUQADD_S) +DO_ZPZZ_D(sve2_suqadd_zpzz_d, uint64_t, do_suqadd_d) + +#define DO_USQADD_B(n, m) \ + do_sat_bhs((int64_t)n + (int8_t)m, 0, UINT8_MAX) +#define DO_USQADD_H(n, m) \ + do_sat_bhs((int64_t)n + (int16_t)m, 0, UINT16_MAX) +#define DO_USQADD_S(n, m) \ + do_sat_bhs((int64_t)n + (int32_t)m, 0, UINT32_MAX) + +static inline uint64_t do_usqadd_d(uint64_t n, int64_t m) +{ + uint64_t r = n + m; + + if (m < 0) { + return n < -m ? 0 : r; + } + return r < n ? UINT64_MAX : r; +} + +DO_ZPZZ(sve2_usqadd_zpzz_b, uint8_t, H1, DO_USQADD_B) +DO_ZPZZ(sve2_usqadd_zpzz_h, uint16_t, H1_2, DO_USQADD_H) +DO_ZPZZ(sve2_usqadd_zpzz_s, uint32_t, H1_4, DO_USQADD_S) +DO_ZPZZ_D(sve2_usqadd_zpzz_d, uint64_t, do_usqadd_d) + #undef DO_ZPZZ #undef DO_ZPZZ_D +/* + * Three operand expander, operating on element pairs. + * If the slot I is even, the elements from from VN {I, I+1}. + * If the slot I is odd, the elements from from VM {I-1, I}. + * Load all of the input elements in each pair before overwriting output. + */ +#define DO_ZPZZ_PAIR(NAME, TYPE, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + for (i = 0; i < opr_sz; ) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + TYPE n0 = *(TYPE *)(vn + H(i)); \ + TYPE m0 = *(TYPE *)(vm + H(i)); \ + TYPE n1 = *(TYPE *)(vn + H(i + sizeof(TYPE))); \ + TYPE m1 = *(TYPE *)(vm + H(i + sizeof(TYPE))); \ + if (pg & 1) { \ + *(TYPE *)(vd + H(i)) = OP(n0, n1); \ + } \ + i += sizeof(TYPE), pg >>= sizeof(TYPE); \ + if (pg & 1) { \ + *(TYPE *)(vd + H(i)) = OP(m0, m1); \ + } \ + i += sizeof(TYPE), pg >>= sizeof(TYPE); \ + } while (i & 15); \ + } \ +} + +/* Similarly, specialized for 64-bit operands. */ +#define DO_ZPZZ_PAIR_D(NAME, TYPE, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; \ + TYPE *d = vd, *n = vn, *m = vm; \ + uint8_t *pg = vg; \ + for (i = 0; i < opr_sz; i += 2) { \ + TYPE n0 = n[i], n1 = n[i + 1]; \ + TYPE m0 = m[i], m1 = m[i + 1]; \ + if (pg[H1(i)] & 1) { \ + d[i] = OP(n0, n1); \ + } \ + if (pg[H1(i + 1)] & 1) { \ + d[i + 1] = OP(m0, m1); \ + } \ + } \ +} + +DO_ZPZZ_PAIR(sve2_addp_zpzz_b, uint8_t, H1, DO_ADD) +DO_ZPZZ_PAIR(sve2_addp_zpzz_h, uint16_t, H1_2, DO_ADD) +DO_ZPZZ_PAIR(sve2_addp_zpzz_s, uint32_t, H1_4, DO_ADD) +DO_ZPZZ_PAIR_D(sve2_addp_zpzz_d, uint64_t, DO_ADD) + +DO_ZPZZ_PAIR(sve2_umaxp_zpzz_b, uint8_t, H1, DO_MAX) +DO_ZPZZ_PAIR(sve2_umaxp_zpzz_h, uint16_t, H1_2, DO_MAX) +DO_ZPZZ_PAIR(sve2_umaxp_zpzz_s, uint32_t, H1_4, DO_MAX) +DO_ZPZZ_PAIR_D(sve2_umaxp_zpzz_d, uint64_t, DO_MAX) + +DO_ZPZZ_PAIR(sve2_uminp_zpzz_b, uint8_t, H1, DO_MIN) +DO_ZPZZ_PAIR(sve2_uminp_zpzz_h, uint16_t, H1_2, DO_MIN) +DO_ZPZZ_PAIR(sve2_uminp_zpzz_s, uint32_t, H1_4, DO_MIN) +DO_ZPZZ_PAIR_D(sve2_uminp_zpzz_d, uint64_t, DO_MIN) + +DO_ZPZZ_PAIR(sve2_smaxp_zpzz_b, int8_t, H1, DO_MAX) +DO_ZPZZ_PAIR(sve2_smaxp_zpzz_h, int16_t, H1_2, DO_MAX) +DO_ZPZZ_PAIR(sve2_smaxp_zpzz_s, int32_t, H1_4, DO_MAX) +DO_ZPZZ_PAIR_D(sve2_smaxp_zpzz_d, int64_t, DO_MAX) + +DO_ZPZZ_PAIR(sve2_sminp_zpzz_b, int8_t, H1, DO_MIN) +DO_ZPZZ_PAIR(sve2_sminp_zpzz_h, int16_t, H1_2, DO_MIN) +DO_ZPZZ_PAIR(sve2_sminp_zpzz_s, int32_t, H1_4, DO_MIN) +DO_ZPZZ_PAIR_D(sve2_sminp_zpzz_d, int64_t, DO_MIN) + +#undef DO_ZPZZ_PAIR +#undef DO_ZPZZ_PAIR_D + +#define DO_ZPZZ_PAIR_FP(NAME, TYPE, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, \ + void *status, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + for (i = 0; i < opr_sz; ) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + TYPE n0 = *(TYPE *)(vn + H(i)); \ + TYPE m0 = *(TYPE *)(vm + H(i)); \ + TYPE n1 = *(TYPE *)(vn + H(i + sizeof(TYPE))); \ + TYPE m1 = *(TYPE *)(vm + H(i + sizeof(TYPE))); \ + if (pg & 1) { \ + *(TYPE *)(vd + H(i)) = OP(n0, n1, status); \ + } \ + i += sizeof(TYPE), pg >>= sizeof(TYPE); \ + if (pg & 1) { \ + *(TYPE *)(vd + H(i)) = OP(m0, m1, status); \ + } \ + i += sizeof(TYPE), pg >>= sizeof(TYPE); \ + } while (i & 15); \ + } \ +} + +DO_ZPZZ_PAIR_FP(sve2_faddp_zpzz_h, float16, H1_2, float16_add) +DO_ZPZZ_PAIR_FP(sve2_faddp_zpzz_s, float32, H1_4, float32_add) +DO_ZPZZ_PAIR_FP(sve2_faddp_zpzz_d, float64, , float64_add) + +DO_ZPZZ_PAIR_FP(sve2_fmaxnmp_zpzz_h, float16, H1_2, float16_maxnum) +DO_ZPZZ_PAIR_FP(sve2_fmaxnmp_zpzz_s, float32, H1_4, float32_maxnum) +DO_ZPZZ_PAIR_FP(sve2_fmaxnmp_zpzz_d, float64, , float64_maxnum) + +DO_ZPZZ_PAIR_FP(sve2_fminnmp_zpzz_h, float16, H1_2, float16_minnum) +DO_ZPZZ_PAIR_FP(sve2_fminnmp_zpzz_s, float32, H1_4, float32_minnum) +DO_ZPZZ_PAIR_FP(sve2_fminnmp_zpzz_d, float64, , float64_minnum) + +DO_ZPZZ_PAIR_FP(sve2_fmaxp_zpzz_h, float16, H1_2, float16_max) +DO_ZPZZ_PAIR_FP(sve2_fmaxp_zpzz_s, float32, H1_4, float32_max) +DO_ZPZZ_PAIR_FP(sve2_fmaxp_zpzz_d, float64, , float64_max) + +DO_ZPZZ_PAIR_FP(sve2_fminp_zpzz_h, float16, H1_2, float16_min) +DO_ZPZZ_PAIR_FP(sve2_fminp_zpzz_s, float32, H1_4, float32_min) +DO_ZPZZ_PAIR_FP(sve2_fminp_zpzz_d, float64, , float64_min) + +#undef DO_ZPZZ_PAIR_FP + /* Three-operand expander, controlled by a predicate, in which the * third operand is "wide". That is, for D = N op M, the same 64-bit * value of M is used with all of the narrower values of N. @@ -684,6 +1089,27 @@ DO_ZPZ(sve_rbit_h, uint16_t, H1_2, revbit16) DO_ZPZ(sve_rbit_s, uint32_t, H1_4, revbit32) DO_ZPZ_D(sve_rbit_d, uint64_t, revbit64) +#define DO_SQABS(X) \ + ({ __typeof(X) x_ = (X), min_ = 1ull << (sizeof(X) * 8 - 1); \ + x_ >= 0 ? x_ : x_ == min_ ? -min_ - 1 : -x_; }) + +DO_ZPZ(sve2_sqabs_b, int8_t, H1, DO_SQABS) +DO_ZPZ(sve2_sqabs_h, int16_t, H1_2, DO_SQABS) +DO_ZPZ(sve2_sqabs_s, int32_t, H1_4, DO_SQABS) +DO_ZPZ_D(sve2_sqabs_d, int64_t, DO_SQABS) + +#define DO_SQNEG(X) \ + ({ __typeof(X) x_ = (X), min_ = 1ull << (sizeof(X) * 8 - 1); \ + x_ == min_ ? -min_ - 1 : -x_; }) + +DO_ZPZ(sve2_sqneg_b, uint8_t, H1, DO_SQNEG) +DO_ZPZ(sve2_sqneg_h, uint16_t, H1_2, DO_SQNEG) +DO_ZPZ(sve2_sqneg_s, uint32_t, H1_4, DO_SQNEG) +DO_ZPZ_D(sve2_sqneg_d, uint64_t, DO_SQNEG) + +DO_ZPZ(sve2_urecpe_s, uint32_t, H1_4, helper_recpe_u32) +DO_ZPZ(sve2_ursqrte_s, uint32_t, H1_4, helper_rsqrte_u32) + /* Three-operand expander, unpredicated, in which the third operand is "wide". */ #define DO_ZZW(NAME, TYPE, TYPEW, H, OP) \ @@ -726,6 +1152,709 @@ DO_ZZW(sve_lsl_zzw_s, uint32_t, uint64_t, H1_4, DO_LSL) #undef DO_ZPZ #undef DO_ZPZ_D +/* + * Three-operand expander, unpredicated, in which the two inputs are + * selected from the top or bottom half of the wide column. + */ +#define DO_ZZZ_TB(NAME, TYPEW, TYPEN, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + int sel1 = extract32(desc, SIMD_DATA_SHIFT, 1) * sizeof(TYPEN); \ + int sel2 = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(TYPEN); \ + for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEN *)(vn + HN(i + sel1)); \ + TYPEW mm = *(TYPEN *)(vm + HN(i + sel2)); \ + *(TYPEW *)(vd + HW(i)) = OP(nn, mm); \ + } \ +} + +DO_ZZZ_TB(sve2_saddl_h, int16_t, int8_t, H1_2, H1, DO_ADD) +DO_ZZZ_TB(sve2_saddl_s, int32_t, int16_t, H1_4, H1_2, DO_ADD) +DO_ZZZ_TB(sve2_saddl_d, int64_t, int32_t, , H1_4, DO_ADD) + +DO_ZZZ_TB(sve2_ssubl_h, int16_t, int8_t, H1_2, H1, DO_SUB) +DO_ZZZ_TB(sve2_ssubl_s, int32_t, int16_t, H1_4, H1_2, DO_SUB) +DO_ZZZ_TB(sve2_ssubl_d, int64_t, int32_t, , H1_4, DO_SUB) + +DO_ZZZ_TB(sve2_sabdl_h, int16_t, int8_t, H1_2, H1, DO_ABD) +DO_ZZZ_TB(sve2_sabdl_s, int32_t, int16_t, H1_4, H1_2, DO_ABD) +DO_ZZZ_TB(sve2_sabdl_d, int64_t, int32_t, , H1_4, DO_ABD) + +DO_ZZZ_TB(sve2_uaddl_h, uint16_t, uint8_t, H1_2, H1, DO_ADD) +DO_ZZZ_TB(sve2_uaddl_s, uint32_t, uint16_t, H1_4, H1_2, DO_ADD) +DO_ZZZ_TB(sve2_uaddl_d, uint64_t, uint32_t, , H1_4, DO_ADD) + +DO_ZZZ_TB(sve2_usubl_h, uint16_t, uint8_t, H1_2, H1, DO_SUB) +DO_ZZZ_TB(sve2_usubl_s, uint32_t, uint16_t, H1_4, H1_2, DO_SUB) +DO_ZZZ_TB(sve2_usubl_d, uint64_t, uint32_t, , H1_4, DO_SUB) + +DO_ZZZ_TB(sve2_uabdl_h, uint16_t, uint8_t, H1_2, H1, DO_ABD) +DO_ZZZ_TB(sve2_uabdl_s, uint32_t, uint16_t, H1_4, H1_2, DO_ABD) +DO_ZZZ_TB(sve2_uabdl_d, uint64_t, uint32_t, , H1_4, DO_ABD) + +DO_ZZZ_TB(sve2_smull_zzz_h, int16_t, int8_t, H1_2, H1, DO_MUL) +DO_ZZZ_TB(sve2_smull_zzz_s, int32_t, int16_t, H1_4, H1_2, DO_MUL) +DO_ZZZ_TB(sve2_smull_zzz_d, int64_t, int32_t, , H1_4, DO_MUL) + +DO_ZZZ_TB(sve2_umull_zzz_h, uint16_t, uint8_t, H1_2, H1, DO_MUL) +DO_ZZZ_TB(sve2_umull_zzz_s, uint32_t, uint16_t, H1_4, H1_2, DO_MUL) +DO_ZZZ_TB(sve2_umull_zzz_d, uint64_t, uint32_t, , H1_4, DO_MUL) + +/* Note that the multiply cannot overflow, but the doubling can. */ +static inline int16_t do_sqdmull_h(int16_t n, int16_t m) +{ + int16_t val = n * m; + return DO_SQADD_H(val, val); +} + +static inline int32_t do_sqdmull_s(int32_t n, int32_t m) +{ + int32_t val = n * m; + return DO_SQADD_S(val, val); +} + +static inline int64_t do_sqdmull_d(int64_t n, int64_t m) +{ + int64_t val = n * m; + return do_sqadd_d(val, val); +} + +DO_ZZZ_TB(sve2_sqdmull_zzz_h, int16_t, int8_t, H1_2, H1, do_sqdmull_h) +DO_ZZZ_TB(sve2_sqdmull_zzz_s, int32_t, int16_t, H1_4, H1_2, do_sqdmull_s) +DO_ZZZ_TB(sve2_sqdmull_zzz_d, int64_t, int32_t, , H1_4, do_sqdmull_d) + +#undef DO_ZZZ_TB + +#define DO_ZZZ_WTB(NAME, TYPEW, TYPEN, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + int sel2 = extract32(desc, SIMD_DATA_SHIFT, 1) * sizeof(TYPEN); \ + for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEW *)(vn + HW(i)); \ + TYPEW mm = *(TYPEN *)(vm + HN(i + sel2)); \ + *(TYPEW *)(vd + HW(i)) = OP(nn, mm); \ + } \ +} + +DO_ZZZ_WTB(sve2_saddw_h, int16_t, int8_t, H1_2, H1, DO_ADD) +DO_ZZZ_WTB(sve2_saddw_s, int32_t, int16_t, H1_4, H1_2, DO_ADD) +DO_ZZZ_WTB(sve2_saddw_d, int64_t, int32_t, , H1_4, DO_ADD) + +DO_ZZZ_WTB(sve2_ssubw_h, int16_t, int8_t, H1_2, H1, DO_SUB) +DO_ZZZ_WTB(sve2_ssubw_s, int32_t, int16_t, H1_4, H1_2, DO_SUB) +DO_ZZZ_WTB(sve2_ssubw_d, int64_t, int32_t, , H1_4, DO_SUB) + +DO_ZZZ_WTB(sve2_uaddw_h, uint16_t, uint8_t, H1_2, H1, DO_ADD) +DO_ZZZ_WTB(sve2_uaddw_s, uint32_t, uint16_t, H1_4, H1_2, DO_ADD) +DO_ZZZ_WTB(sve2_uaddw_d, uint64_t, uint32_t, , H1_4, DO_ADD) + +DO_ZZZ_WTB(sve2_usubw_h, uint16_t, uint8_t, H1_2, H1, DO_SUB) +DO_ZZZ_WTB(sve2_usubw_s, uint32_t, uint16_t, H1_4, H1_2, DO_SUB) +DO_ZZZ_WTB(sve2_usubw_d, uint64_t, uint32_t, , H1_4, DO_SUB) + +#undef DO_ZZZ_WTB + +#define DO_ZZZ_NTB(NAME, TYPE, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + intptr_t sel1 = extract32(desc, SIMD_DATA_SHIFT, 1) * sizeof(TYPE); \ + intptr_t sel2 = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(TYPE); \ + for (i = 0; i < opr_sz; i += 2 * sizeof(TYPE)) { \ + TYPE nn = *(TYPE *)(vn + H(i + sel1)); \ + TYPE mm = *(TYPE *)(vm + H(i + sel2)); \ + *(TYPE *)(vd + H(i + sel1)) = OP(nn, mm); \ + } \ +} + +DO_ZZZ_NTB(sve2_eoril_b, uint8_t, H1, DO_EOR) +DO_ZZZ_NTB(sve2_eoril_h, uint16_t, H1_2, DO_EOR) +DO_ZZZ_NTB(sve2_eoril_s, uint32_t, H1_4, DO_EOR) +DO_ZZZ_NTB(sve2_eoril_d, uint64_t, , DO_EOR) + +#undef DO_ZZZ_NTB + +#define DO_ZZZW_ACC(NAME, TYPEW, TYPEN, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + intptr_t sel1 = simd_data(desc) * sizeof(TYPEN); \ + for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEN *)(vn + HN(i + sel1)); \ + TYPEW mm = *(TYPEN *)(vm + HN(i + sel1)); \ + TYPEW aa = *(TYPEW *)(va + HW(i)); \ + *(TYPEW *)(vd + HW(i)) = OP(nn, mm) + aa; \ + } \ +} + +DO_ZZZW_ACC(sve2_sabal_h, int16_t, int8_t, H1_2, H1, DO_ABD) +DO_ZZZW_ACC(sve2_sabal_s, int32_t, int16_t, H1_4, H1_2, DO_ABD) +DO_ZZZW_ACC(sve2_sabal_d, int64_t, int32_t, , H1_4, DO_ABD) + +DO_ZZZW_ACC(sve2_uabal_h, uint16_t, uint8_t, H1_2, H1, DO_ABD) +DO_ZZZW_ACC(sve2_uabal_s, uint32_t, uint16_t, H1_4, H1_2, DO_ABD) +DO_ZZZW_ACC(sve2_uabal_d, uint64_t, uint32_t, , H1_4, DO_ABD) + +DO_ZZZW_ACC(sve2_smlal_zzzw_h, int16_t, int8_t, H1_2, H1, DO_MUL) +DO_ZZZW_ACC(sve2_smlal_zzzw_s, int32_t, int16_t, H1_4, H1_2, DO_MUL) +DO_ZZZW_ACC(sve2_smlal_zzzw_d, int64_t, int32_t, , H1_4, DO_MUL) + +DO_ZZZW_ACC(sve2_umlal_zzzw_h, uint16_t, uint8_t, H1_2, H1, DO_MUL) +DO_ZZZW_ACC(sve2_umlal_zzzw_s, uint32_t, uint16_t, H1_4, H1_2, DO_MUL) +DO_ZZZW_ACC(sve2_umlal_zzzw_d, uint64_t, uint32_t, , H1_4, DO_MUL) + +#define DO_NMUL(N, M) -(N * M) + +DO_ZZZW_ACC(sve2_smlsl_zzzw_h, int16_t, int8_t, H1_2, H1, DO_NMUL) +DO_ZZZW_ACC(sve2_smlsl_zzzw_s, int32_t, int16_t, H1_4, H1_2, DO_NMUL) +DO_ZZZW_ACC(sve2_smlsl_zzzw_d, int64_t, int32_t, , H1_4, DO_NMUL) + +DO_ZZZW_ACC(sve2_umlsl_zzzw_h, uint16_t, uint8_t, H1_2, H1, DO_NMUL) +DO_ZZZW_ACC(sve2_umlsl_zzzw_s, uint32_t, uint16_t, H1_4, H1_2, DO_NMUL) +DO_ZZZW_ACC(sve2_umlsl_zzzw_d, uint64_t, uint32_t, , H1_4, DO_NMUL) + +#undef DO_ZZZW_ACC + +#define DO_XTNB(NAME, TYPE, OP) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + for (i = 0; i < opr_sz; i += sizeof(TYPE)) { \ + TYPE nn = *(TYPE *)(vn + i); \ + nn = OP(nn) & MAKE_64BIT_MASK(0, sizeof(TYPE) * 4); \ + *(TYPE *)(vd + i) = nn; \ + } \ +} + +#define DO_XTNT(NAME, TYPE, TYPEN, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc), odd = H(sizeof(TYPEN)); \ + for (i = 0; i < opr_sz; i += sizeof(TYPE)) { \ + TYPE nn = *(TYPE *)(vn + i); \ + *(TYPEN *)(vd + i + odd) = OP(nn); \ + } \ +} + +#define DO_SQXTN_H(n) do_sat_bhs(n, INT8_MIN, INT8_MAX) +#define DO_SQXTN_S(n) do_sat_bhs(n, INT16_MIN, INT16_MAX) +#define DO_SQXTN_D(n) do_sat_bhs(n, INT32_MIN, INT32_MAX) + +DO_XTNB(sve2_sqxtnb_h, int16_t, DO_SQXTN_H) +DO_XTNB(sve2_sqxtnb_s, int32_t, DO_SQXTN_S) +DO_XTNB(sve2_sqxtnb_d, int64_t, DO_SQXTN_D) + +DO_XTNT(sve2_sqxtnt_h, int16_t, int8_t, H1, DO_SQXTN_H) +DO_XTNT(sve2_sqxtnt_s, int32_t, int16_t, H1_2, DO_SQXTN_S) +DO_XTNT(sve2_sqxtnt_d, int64_t, int32_t, H1_4, DO_SQXTN_D) + +#define DO_UQXTN_H(n) do_sat_bhs(n, 0, UINT8_MAX) +#define DO_UQXTN_S(n) do_sat_bhs(n, 0, UINT16_MAX) +#define DO_UQXTN_D(n) do_sat_bhs(n, 0, UINT32_MAX) + +DO_XTNB(sve2_uqxtnb_h, uint16_t, DO_UQXTN_H) +DO_XTNB(sve2_uqxtnb_s, uint32_t, DO_UQXTN_S) +DO_XTNB(sve2_uqxtnb_d, uint64_t, DO_UQXTN_D) + +DO_XTNT(sve2_uqxtnt_h, uint16_t, uint8_t, H1, DO_UQXTN_H) +DO_XTNT(sve2_uqxtnt_s, uint32_t, uint16_t, H1_2, DO_UQXTN_S) +DO_XTNT(sve2_uqxtnt_d, uint64_t, uint32_t, H1_4, DO_UQXTN_D) + +DO_XTNB(sve2_sqxtunb_h, int16_t, DO_UQXTN_H) +DO_XTNB(sve2_sqxtunb_s, int32_t, DO_UQXTN_S) +DO_XTNB(sve2_sqxtunb_d, int64_t, DO_UQXTN_D) + +DO_XTNT(sve2_sqxtunt_h, int16_t, int8_t, H1, DO_UQXTN_H) +DO_XTNT(sve2_sqxtunt_s, int32_t, int16_t, H1_2, DO_UQXTN_S) +DO_XTNT(sve2_sqxtunt_d, int64_t, int32_t, H1_4, DO_UQXTN_D) + +#undef DO_XTNB +#undef DO_XTNT + +void HELPER(sve2_adcl_s)(void *vd, void *vn, void *vm, void *va, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int sel = H4(extract32(desc, SIMD_DATA_SHIFT, 1)); + uint32_t inv = -extract32(desc, SIMD_DATA_SHIFT + 1, 1); + uint32_t *a = va, *n = vn; + uint64_t *d = vd, *m = vm; + + for (i = 0; i < opr_sz / 8; ++i) { + uint32_t e1 = a[2 * i + H4(0)]; + uint32_t e2 = n[2 * i + sel] ^ inv; + uint64_t c = extract64(m[i], 32, 1); + /* Compute and store the entire 33-bit result at once. */ + d[i] = c + e1 + e2; + } +} + +void HELPER(sve2_adcl_d)(void *vd, void *vn, void *vm, void *va, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int sel = extract32(desc, SIMD_DATA_SHIFT, 1); + uint64_t inv = -(uint64_t)extract32(desc, SIMD_DATA_SHIFT + 1, 1); + uint64_t *d = vd, *a = va, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 8; i += 2) { + Int128 e1 = int128_make64(a[i]); + Int128 e2 = int128_make64(n[i + sel] ^ inv); + Int128 c = int128_make64(m[i + 1] & 1); + Int128 r = int128_add(int128_add(e1, e2), c); + d[i + 0] = int128_getlo(r); + d[i + 1] = int128_gethi(r); + } +} + +#define DO_SQDMLAL(NAME, TYPEW, TYPEN, HW, HN, DMUL_OP, SUM_OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + int sel1 = extract32(desc, SIMD_DATA_SHIFT, 1) * sizeof(TYPEN); \ + int sel2 = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(TYPEN); \ + for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEN *)(vn + HN(i + sel1)); \ + TYPEW mm = *(TYPEN *)(vm + HN(i + sel2)); \ + TYPEW aa = *(TYPEW *)(va + HW(i)); \ + *(TYPEW *)(vd + HW(i)) = SUM_OP(aa, DMUL_OP(nn, mm)); \ + } \ +} + +DO_SQDMLAL(sve2_sqdmlal_zzzw_h, int16_t, int8_t, H1_2, H1, + do_sqdmull_h, DO_SQADD_H) +DO_SQDMLAL(sve2_sqdmlal_zzzw_s, int32_t, int16_t, H1_4, H1_2, + do_sqdmull_s, DO_SQADD_S) +DO_SQDMLAL(sve2_sqdmlal_zzzw_d, int64_t, int32_t, , H1_4, + do_sqdmull_d, do_sqadd_d) + +DO_SQDMLAL(sve2_sqdmlsl_zzzw_h, int16_t, int8_t, H1_2, H1, + do_sqdmull_h, DO_SQSUB_H) +DO_SQDMLAL(sve2_sqdmlsl_zzzw_s, int32_t, int16_t, H1_4, H1_2, + do_sqdmull_s, DO_SQSUB_S) +DO_SQDMLAL(sve2_sqdmlsl_zzzw_d, int64_t, int32_t, , H1_4, + do_sqdmull_d, do_sqsub_d) + +#undef DO_SQDMLAL + +#define DO_CMLA_FUNC(NAME, TYPE, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc) / sizeof(TYPE); \ + int rot = simd_data(desc); \ + int sel_a = rot & 1, sel_b = sel_a ^ 1; \ + bool sub_r = rot == 1 || rot == 2; \ + bool sub_i = rot >= 2; \ + TYPE *d = vd, *n = vn, *m = vm, *a = va; \ + for (i = 0; i < opr_sz; i += 2) { \ + TYPE elt1_a = n[H(i + sel_a)]; \ + TYPE elt2_a = m[H(i + sel_a)]; \ + TYPE elt2_b = m[H(i + sel_b)]; \ + d[H(i)] = OP(elt1_a, elt2_a, a[H(i)], sub_r); \ + d[H(i + 1)] = OP(elt1_a, elt2_b, a[H(i + 1)], sub_i); \ + } \ +} + +#define DO_CMLA(N, M, A, S) (A + (N * M) * (S ? -1 : 1)) + +DO_CMLA_FUNC(sve2_cmla_zzzz_b, uint8_t, H1, DO_CMLA) +DO_CMLA_FUNC(sve2_cmla_zzzz_h, uint16_t, H2, DO_CMLA) +DO_CMLA_FUNC(sve2_cmla_zzzz_s, uint32_t, H4, DO_CMLA) +DO_CMLA_FUNC(sve2_cmla_zzzz_d, uint64_t, , DO_CMLA) + +#define DO_SQRDMLAH_B(N, M, A, S) \ + do_sqrdmlah_b(N, M, A, S, true) +#define DO_SQRDMLAH_H(N, M, A, S) \ + ({ uint32_t discard; do_sqrdmlah_h(N, M, A, S, true, &discard); }) +#define DO_SQRDMLAH_S(N, M, A, S) \ + ({ uint32_t discard; do_sqrdmlah_s(N, M, A, S, true, &discard); }) +#define DO_SQRDMLAH_D(N, M, A, S) \ + do_sqrdmlah_d(N, M, A, S, true) + +DO_CMLA_FUNC(sve2_sqrdcmlah_zzzz_b, int8_t, H1, DO_SQRDMLAH_B) +DO_CMLA_FUNC(sve2_sqrdcmlah_zzzz_h, int16_t, H2, DO_SQRDMLAH_H) +DO_CMLA_FUNC(sve2_sqrdcmlah_zzzz_s, int32_t, H4, DO_SQRDMLAH_S) +DO_CMLA_FUNC(sve2_sqrdcmlah_zzzz_d, int64_t, , DO_SQRDMLAH_D) + +#define DO_CMLA_IDX_FUNC(NAME, TYPE, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t i, j, oprsz = simd_oprsz(desc); \ + int rot = extract32(desc, SIMD_DATA_SHIFT, 2); \ + int idx = extract32(desc, SIMD_DATA_SHIFT + 2, 2) * 2; \ + int sel_a = rot & 1, sel_b = sel_a ^ 1; \ + bool sub_r = rot == 1 || rot == 2; \ + bool sub_i = rot >= 2; \ + TYPE *d = vd, *n = vn, *m = vm, *a = va; \ + for (i = 0; i < oprsz / sizeof(TYPE); i += 16 / sizeof(TYPE)) { \ + TYPE elt2_a = m[H(i + idx + sel_a)]; \ + TYPE elt2_b = m[H(i + idx + sel_b)]; \ + for (j = 0; j < 16 / sizeof(TYPE); j += 2) { \ + TYPE elt1_a = n[H(i + j + sel_a)]; \ + d[H2(i + j)] = OP(elt1_a, elt2_a, a[H(i + j)], sub_r); \ + d[H2(i + j + 1)] = OP(elt1_a, elt2_b, a[H(i + j + 1)], sub_i); \ + } \ + } \ +} + +DO_CMLA_IDX_FUNC(sve2_cmla_idx_h, int16_t, H2, DO_CMLA) +DO_CMLA_IDX_FUNC(sve2_cmla_idx_s, int32_t, H4, DO_CMLA) + +DO_CMLA_IDX_FUNC(sve2_sqrdcmlah_idx_h, int16_t, H2, DO_SQRDMLAH_H) +DO_CMLA_IDX_FUNC(sve2_sqrdcmlah_idx_s, int32_t, H4, DO_SQRDMLAH_S) + +#undef DO_CMLA +#undef DO_CMLA_FUNC +#undef DO_CMLA_IDX_FUNC +#undef DO_SQRDMLAH_B +#undef DO_SQRDMLAH_H +#undef DO_SQRDMLAH_S +#undef DO_SQRDMLAH_D + +/* Note N and M are 4 elements bundled into one unit. */ +static int32_t do_cdot_s(uint32_t n, uint32_t m, int32_t a, + int sel_a, int sel_b, int sub_i) +{ + for (int i = 0; i <= 1; i++) { + int32_t elt1_r = (int8_t)(n >> (16 * i)); + int32_t elt1_i = (int8_t)(n >> (16 * i + 8)); + int32_t elt2_a = (int8_t)(m >> (16 * i + 8 * sel_a)); + int32_t elt2_b = (int8_t)(m >> (16 * i + 8 * sel_b)); + + a += elt1_r * elt2_a + elt1_i * elt2_b * sub_i; + } + return a; +} + +static int64_t do_cdot_d(uint64_t n, uint64_t m, int64_t a, + int sel_a, int sel_b, int sub_i) +{ + for (int i = 0; i <= 1; i++) { + int64_t elt1_r = (int16_t)(n >> (32 * i + 0)); + int64_t elt1_i = (int16_t)(n >> (32 * i + 16)); + int64_t elt2_a = (int16_t)(m >> (32 * i + 16 * sel_a)); + int64_t elt2_b = (int16_t)(m >> (32 * i + 16 * sel_b)); + + a += elt1_r * elt2_a + elt1_i * elt2_b * sub_i; + } + return a; +} + +void HELPER(sve2_cdot_zzzz_s)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + int opr_sz = simd_oprsz(desc); + int rot = simd_data(desc); + int sel_a = rot & 1; + int sel_b = sel_a ^ 1; + int sub_i = (rot == 0 || rot == 3 ? -1 : 1); + uint32_t *d = vd, *n = vn, *m = vm, *a = va; + + for (int e = 0; e < opr_sz / 4; e++) { + d[e] = do_cdot_s(n[e], m[e], a[e], sel_a, sel_b, sub_i); + } +} + +void HELPER(sve2_cdot_zzzz_d)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + int opr_sz = simd_oprsz(desc); + int rot = simd_data(desc); + int sel_a = rot & 1; + int sel_b = sel_a ^ 1; + int sub_i = (rot == 0 || rot == 3 ? -1 : 1); + uint64_t *d = vd, *n = vn, *m = vm, *a = va; + + for (int e = 0; e < opr_sz / 8; e++) { + d[e] = do_cdot_d(n[e], m[e], a[e], sel_a, sel_b, sub_i); + } +} + +void HELPER(sve2_cdot_idx_s)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + int opr_sz = simd_oprsz(desc); + int rot = extract32(desc, SIMD_DATA_SHIFT, 2); + int idx = H4(extract32(desc, SIMD_DATA_SHIFT + 2, 2)); + int sel_a = rot & 1; + int sel_b = sel_a ^ 1; + int sub_i = (rot == 0 || rot == 3 ? -1 : 1); + uint32_t *d = vd, *n = vn, *m = vm, *a = va; + + for (int seg = 0; seg < opr_sz / 4; seg += 4) { + uint32_t seg_m = m[seg + idx]; + for (int e = 0; e < 4; e++) { + d[seg + e] = do_cdot_s(n[seg + e], seg_m, a[seg + e], + sel_a, sel_b, sub_i); + } + } +} + +void HELPER(sve2_cdot_idx_d)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + int seg, opr_sz = simd_oprsz(desc); + int rot = extract32(desc, SIMD_DATA_SHIFT, 2); + int idx = extract32(desc, SIMD_DATA_SHIFT + 2, 2); + int sel_a = rot & 1; + int sel_b = sel_a ^ 1; + int sub_i = (rot == 0 || rot == 3 ? -1 : 1); + uint64_t *d = vd, *n = vn, *m = vm, *a = va; + + for (seg = 0; seg < opr_sz / 8; seg += 2) { + uint64_t seg_m = m[seg + idx]; + for (int e = 0; e < 2; e++) { + d[seg + e] = do_cdot_d(n[seg + e], seg_m, a[seg + e], + sel_a, sel_b, sub_i); + } + } +} + +#define DO_ZZXZ(NAME, TYPE, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE); \ + intptr_t i, j, idx = simd_data(desc); \ + TYPE *d = vd, *a = va, *n = vn, *m = (TYPE *)vm + H(idx); \ + for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \ + TYPE mm = m[i]; \ + for (j = 0; j < segment; j++) { \ + d[i + j] = OP(n[i + j], mm, a[i + j]); \ + } \ + } \ +} + +#define DO_SQRDMLAH_H(N, M, A) \ + ({ uint32_t discard; do_sqrdmlah_h(N, M, A, false, true, &discard); }) +#define DO_SQRDMLAH_S(N, M, A) \ + ({ uint32_t discard; do_sqrdmlah_s(N, M, A, false, true, &discard); }) +#define DO_SQRDMLAH_D(N, M, A) do_sqrdmlah_d(N, M, A, false, true) + +DO_ZZXZ(sve2_sqrdmlah_idx_h, int16_t, H2, DO_SQRDMLAH_H) +DO_ZZXZ(sve2_sqrdmlah_idx_s, int32_t, H4, DO_SQRDMLAH_S) +DO_ZZXZ(sve2_sqrdmlah_idx_d, int64_t, , DO_SQRDMLAH_D) + +#define DO_SQRDMLSH_H(N, M, A) \ + ({ uint32_t discard; do_sqrdmlah_h(N, M, A, true, true, &discard); }) +#define DO_SQRDMLSH_S(N, M, A) \ + ({ uint32_t discard; do_sqrdmlah_s(N, M, A, true, true, &discard); }) +#define DO_SQRDMLSH_D(N, M, A) do_sqrdmlah_d(N, M, A, true, true) + +DO_ZZXZ(sve2_sqrdmlsh_idx_h, int16_t, H2, DO_SQRDMLSH_H) +DO_ZZXZ(sve2_sqrdmlsh_idx_s, int32_t, H4, DO_SQRDMLSH_S) +DO_ZZXZ(sve2_sqrdmlsh_idx_d, int64_t, , DO_SQRDMLSH_D) + +#undef DO_ZZXZ + +#define DO_ZZXW(NAME, TYPEW, TYPEN, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t i, j, oprsz = simd_oprsz(desc); \ + intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 1) * sizeof(TYPEN); \ + intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 1, 3) * sizeof(TYPEN); \ + for (i = 0; i < oprsz; i += 16) { \ + TYPEW mm = *(TYPEN *)(vm + HN(i + idx)); \ + for (j = 0; j < 16; j += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEN *)(vn + HN(i + j + sel)); \ + TYPEW aa = *(TYPEW *)(va + HW(i + j)); \ + *(TYPEW *)(vd + HW(i + j)) = OP(nn, mm, aa); \ + } \ + } \ +} + +#define DO_MLA(N, M, A) (A + N * M) + +DO_ZZXW(sve2_smlal_idx_s, int32_t, int16_t, H1_4, H1_2, DO_MLA) +DO_ZZXW(sve2_smlal_idx_d, int64_t, int32_t, , H1_4, DO_MLA) +DO_ZZXW(sve2_umlal_idx_s, uint32_t, uint16_t, H1_4, H1_2, DO_MLA) +DO_ZZXW(sve2_umlal_idx_d, uint64_t, uint32_t, , H1_4, DO_MLA) + +#define DO_MLS(N, M, A) (A - N * M) + +DO_ZZXW(sve2_smlsl_idx_s, int32_t, int16_t, H1_4, H1_2, DO_MLS) +DO_ZZXW(sve2_smlsl_idx_d, int64_t, int32_t, , H1_4, DO_MLS) +DO_ZZXW(sve2_umlsl_idx_s, uint32_t, uint16_t, H1_4, H1_2, DO_MLS) +DO_ZZXW(sve2_umlsl_idx_d, uint64_t, uint32_t, , H1_4, DO_MLS) + +#define DO_SQDMLAL_S(N, M, A) DO_SQADD_S(A, do_sqdmull_s(N, M)) +#define DO_SQDMLAL_D(N, M, A) do_sqadd_d(A, do_sqdmull_d(N, M)) + +DO_ZZXW(sve2_sqdmlal_idx_s, int32_t, int16_t, H1_4, H1_2, DO_SQDMLAL_S) +DO_ZZXW(sve2_sqdmlal_idx_d, int64_t, int32_t, , H1_4, DO_SQDMLAL_D) + +#define DO_SQDMLSL_S(N, M, A) DO_SQSUB_S(A, do_sqdmull_s(N, M)) +#define DO_SQDMLSL_D(N, M, A) do_sqsub_d(A, do_sqdmull_d(N, M)) + +DO_ZZXW(sve2_sqdmlsl_idx_s, int32_t, int16_t, H1_4, H1_2, DO_SQDMLSL_S) +DO_ZZXW(sve2_sqdmlsl_idx_d, int64_t, int32_t, , H1_4, DO_SQDMLSL_D) + +#undef DO_MLA +#undef DO_MLS +#undef DO_ZZXW + +#define DO_ZZX(NAME, TYPEW, TYPEN, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, j, oprsz = simd_oprsz(desc); \ + intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 1) * sizeof(TYPEN); \ + intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 1, 3) * sizeof(TYPEN); \ + for (i = 0; i < oprsz; i += 16) { \ + TYPEW mm = *(TYPEN *)(vm + HN(i + idx)); \ + for (j = 0; j < 16; j += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEN *)(vn + HN(i + j + sel)); \ + *(TYPEW *)(vd + HW(i + j)) = OP(nn, mm); \ + } \ + } \ +} + +DO_ZZX(sve2_sqdmull_idx_s, int32_t, int16_t, H1_4, H1_2, do_sqdmull_s) +DO_ZZX(sve2_sqdmull_idx_d, int64_t, int32_t, , H1_4, do_sqdmull_d) + +DO_ZZX(sve2_smull_idx_s, int32_t, int16_t, H1_4, H1_2, DO_MUL) +DO_ZZX(sve2_smull_idx_d, int64_t, int32_t, , H1_4, DO_MUL) + +DO_ZZX(sve2_umull_idx_s, uint32_t, uint16_t, H1_4, H1_2, DO_MUL) +DO_ZZX(sve2_umull_idx_d, uint64_t, uint32_t, , H1_4, DO_MUL) + +#undef DO_ZZX + +#define DO_BITPERM(NAME, TYPE, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + for (i = 0; i < opr_sz; i += sizeof(TYPE)) { \ + TYPE nn = *(TYPE *)(vn + i); \ + TYPE mm = *(TYPE *)(vm + i); \ + *(TYPE *)(vd + i) = OP(nn, mm, sizeof(TYPE) * 8); \ + } \ +} + +static uint64_t bitextract(uint64_t data, uint64_t mask, int n) +{ + uint64_t res = 0; + int db, rb = 0; + + for (db = 0; db < n; ++db) { + if ((mask >> db) & 1) { + res |= ((data >> db) & 1) << rb; + ++rb; + } + } + return res; +} + +DO_BITPERM(sve2_bext_b, uint8_t, bitextract) +DO_BITPERM(sve2_bext_h, uint16_t, bitextract) +DO_BITPERM(sve2_bext_s, uint32_t, bitextract) +DO_BITPERM(sve2_bext_d, uint64_t, bitextract) + +static uint64_t bitdeposit(uint64_t data, uint64_t mask, int n) +{ + uint64_t res = 0; + int rb, db = 0; + + for (rb = 0; rb < n; ++rb) { + if ((mask >> rb) & 1) { + res |= ((data >> db) & 1) << rb; + ++db; + } + } + return res; +} + +DO_BITPERM(sve2_bdep_b, uint8_t, bitdeposit) +DO_BITPERM(sve2_bdep_h, uint16_t, bitdeposit) +DO_BITPERM(sve2_bdep_s, uint32_t, bitdeposit) +DO_BITPERM(sve2_bdep_d, uint64_t, bitdeposit) + +static uint64_t bitgroup(uint64_t data, uint64_t mask, int n) +{ + uint64_t resm = 0, resu = 0; + int db, rbm = 0, rbu = 0; + + for (db = 0; db < n; ++db) { + uint64_t val = (data >> db) & 1; + if ((mask >> db) & 1) { + resm |= val << rbm++; + } else { + resu |= val << rbu++; + } + } + + return resm | (resu << rbm); +} + +DO_BITPERM(sve2_bgrp_b, uint8_t, bitgroup) +DO_BITPERM(sve2_bgrp_h, uint16_t, bitgroup) +DO_BITPERM(sve2_bgrp_s, uint32_t, bitgroup) +DO_BITPERM(sve2_bgrp_d, uint64_t, bitgroup) + +#undef DO_BITPERM + +#define DO_CADD(NAME, TYPE, H, ADD_OP, SUB_OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + int sub_r = simd_data(desc); \ + if (sub_r) { \ + for (i = 0; i < opr_sz; i += 2 * sizeof(TYPE)) { \ + TYPE acc_r = *(TYPE *)(vn + H(i)); \ + TYPE acc_i = *(TYPE *)(vn + H(i + sizeof(TYPE))); \ + TYPE el2_r = *(TYPE *)(vm + H(i)); \ + TYPE el2_i = *(TYPE *)(vm + H(i + sizeof(TYPE))); \ + acc_r = ADD_OP(acc_r, el2_i); \ + acc_i = SUB_OP(acc_i, el2_r); \ + *(TYPE *)(vd + H(i)) = acc_r; \ + *(TYPE *)(vd + H(i + sizeof(TYPE))) = acc_i; \ + } \ + } else { \ + for (i = 0; i < opr_sz; i += 2 * sizeof(TYPE)) { \ + TYPE acc_r = *(TYPE *)(vn + H(i)); \ + TYPE acc_i = *(TYPE *)(vn + H(i + sizeof(TYPE))); \ + TYPE el2_r = *(TYPE *)(vm + H(i)); \ + TYPE el2_i = *(TYPE *)(vm + H(i + sizeof(TYPE))); \ + acc_r = SUB_OP(acc_r, el2_i); \ + acc_i = ADD_OP(acc_i, el2_r); \ + *(TYPE *)(vd + H(i)) = acc_r; \ + *(TYPE *)(vd + H(i + sizeof(TYPE))) = acc_i; \ + } \ + } \ +} + +DO_CADD(sve2_cadd_b, int8_t, H1, DO_ADD, DO_SUB) +DO_CADD(sve2_cadd_h, int16_t, H1_2, DO_ADD, DO_SUB) +DO_CADD(sve2_cadd_s, int32_t, H1_4, DO_ADD, DO_SUB) +DO_CADD(sve2_cadd_d, int64_t, , DO_ADD, DO_SUB) + +DO_CADD(sve2_sqcadd_b, int8_t, H1, DO_SQADD_B, DO_SQSUB_B) +DO_CADD(sve2_sqcadd_h, int16_t, H1_2, DO_SQADD_H, DO_SQSUB_H) +DO_CADD(sve2_sqcadd_s, int32_t, H1_4, DO_SQADD_S, DO_SQSUB_S) +DO_CADD(sve2_sqcadd_d, int64_t, , do_sqadd_d, do_sqsub_d) + +#undef DO_CADD + +#define DO_ZZI_SHLL(NAME, TYPEW, TYPEN, HW, HN) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + intptr_t sel = (simd_data(desc) & 1) * sizeof(TYPEN); \ + int shift = simd_data(desc) >> 1; \ + for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEN *)(vn + HN(i + sel)); \ + *(TYPEW *)(vd + HW(i)) = nn << shift; \ + } \ +} + +DO_ZZI_SHLL(sve2_sshll_h, int16_t, int8_t, H1_2, H1) +DO_ZZI_SHLL(sve2_sshll_s, int32_t, int16_t, H1_4, H1_2) +DO_ZZI_SHLL(sve2_sshll_d, int64_t, int32_t, , H1_4) + +DO_ZZI_SHLL(sve2_ushll_h, uint16_t, uint8_t, H1_2, H1) +DO_ZZI_SHLL(sve2_ushll_s, uint32_t, uint16_t, H1_4, H1_2) +DO_ZZI_SHLL(sve2_ushll_d, uint64_t, uint32_t, , H1_4) + +#undef DO_ZZI_SHLL + /* Two-operand reduction expander, controlled by a predicate. * The difference between TYPERED and TYPERET has to do with * sign-extension. E.g. for SMAX, TYPERED must be signed, @@ -1052,6 +2181,27 @@ void HELPER(NAME)(void *vd, void *vn, void *vg, uint32_t desc) \ when N is negative, add 2**M-1. */ #define DO_ASRD(N, M) ((N + (N < 0 ? ((__typeof(N))1 << M) - 1 : 0)) >> M) +static inline uint64_t do_urshr(uint64_t x, unsigned sh) +{ + if (likely(sh < 64)) { + return (x >> sh) + ((x >> (sh - 1)) & 1); + } else if (sh == 64) { + return x >> 63; + } else { + return 0; + } +} + +static inline int64_t do_srshr(int64_t x, unsigned sh) +{ + if (likely(sh < 64)) { + return (x >> sh) + ((x >> (sh - 1)) & 1); + } else { + /* Rounding the sign bit always produces 0. */ + return 0; + } +} + DO_ZPZI(sve_asr_zpzi_b, int8_t, H1, DO_SHR) DO_ZPZI(sve_asr_zpzi_h, int16_t, H1_2, DO_SHR) DO_ZPZI(sve_asr_zpzi_s, int32_t, H1_4, DO_SHR) @@ -1072,12 +2222,225 @@ DO_ZPZI(sve_asrd_h, int16_t, H1_2, DO_ASRD) DO_ZPZI(sve_asrd_s, int32_t, H1_4, DO_ASRD) DO_ZPZI_D(sve_asrd_d, int64_t, DO_ASRD) -#undef DO_SHR -#undef DO_SHL +/* SVE2 bitwise shift by immediate */ +DO_ZPZI(sve2_sqshl_zpzi_b, int8_t, H1, do_sqshl_b) +DO_ZPZI(sve2_sqshl_zpzi_h, int16_t, H1_2, do_sqshl_h) +DO_ZPZI(sve2_sqshl_zpzi_s, int32_t, H1_4, do_sqshl_s) +DO_ZPZI_D(sve2_sqshl_zpzi_d, int64_t, do_sqshl_d) + +DO_ZPZI(sve2_uqshl_zpzi_b, uint8_t, H1, do_uqshl_b) +DO_ZPZI(sve2_uqshl_zpzi_h, uint16_t, H1_2, do_uqshl_h) +DO_ZPZI(sve2_uqshl_zpzi_s, uint32_t, H1_4, do_uqshl_s) +DO_ZPZI_D(sve2_uqshl_zpzi_d, uint64_t, do_uqshl_d) + +DO_ZPZI(sve2_srshr_b, int8_t, H1, do_srshr) +DO_ZPZI(sve2_srshr_h, int16_t, H1_2, do_srshr) +DO_ZPZI(sve2_srshr_s, int32_t, H1_4, do_srshr) +DO_ZPZI_D(sve2_srshr_d, int64_t, do_srshr) + +DO_ZPZI(sve2_urshr_b, uint8_t, H1, do_urshr) +DO_ZPZI(sve2_urshr_h, uint16_t, H1_2, do_urshr) +DO_ZPZI(sve2_urshr_s, uint32_t, H1_4, do_urshr) +DO_ZPZI_D(sve2_urshr_d, uint64_t, do_urshr) + +#define do_suqrshl_b(n, m) \ + ({ uint32_t discard; do_suqrshl_bhs(n, (int8_t)m, 8, false, &discard); }) +#define do_suqrshl_h(n, m) \ + ({ uint32_t discard; do_suqrshl_bhs(n, (int16_t)m, 16, false, &discard); }) +#define do_suqrshl_s(n, m) \ + ({ uint32_t discard; do_suqrshl_bhs(n, m, 32, false, &discard); }) +#define do_suqrshl_d(n, m) \ + ({ uint32_t discard; do_suqrshl_d(n, m, false, &discard); }) + +DO_ZPZI(sve2_sqshlu_b, int8_t, H1, do_suqrshl_b) +DO_ZPZI(sve2_sqshlu_h, int16_t, H1_2, do_suqrshl_h) +DO_ZPZI(sve2_sqshlu_s, int32_t, H1_4, do_suqrshl_s) +DO_ZPZI_D(sve2_sqshlu_d, int64_t, do_suqrshl_d) + #undef DO_ASRD #undef DO_ZPZI #undef DO_ZPZI_D +#define DO_SHRNB(NAME, TYPEW, TYPEN, OP) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + int shift = simd_data(desc); \ + for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEW *)(vn + i); \ + *(TYPEW *)(vd + i) = (TYPEN)OP(nn, shift); \ + } \ +} + +#define DO_SHRNT(NAME, TYPEW, TYPEN, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + int shift = simd_data(desc); \ + for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEW *)(vn + HW(i)); \ + *(TYPEN *)(vd + HN(i + sizeof(TYPEN))) = OP(nn, shift); \ + } \ +} + +DO_SHRNB(sve2_shrnb_h, uint16_t, uint8_t, DO_SHR) +DO_SHRNB(sve2_shrnb_s, uint32_t, uint16_t, DO_SHR) +DO_SHRNB(sve2_shrnb_d, uint64_t, uint32_t, DO_SHR) + +DO_SHRNT(sve2_shrnt_h, uint16_t, uint8_t, H1_2, H1, DO_SHR) +DO_SHRNT(sve2_shrnt_s, uint32_t, uint16_t, H1_4, H1_2, DO_SHR) +DO_SHRNT(sve2_shrnt_d, uint64_t, uint32_t, , H1_4, DO_SHR) + +DO_SHRNB(sve2_rshrnb_h, uint16_t, uint8_t, do_urshr) +DO_SHRNB(sve2_rshrnb_s, uint32_t, uint16_t, do_urshr) +DO_SHRNB(sve2_rshrnb_d, uint64_t, uint32_t, do_urshr) + +DO_SHRNT(sve2_rshrnt_h, uint16_t, uint8_t, H1_2, H1, do_urshr) +DO_SHRNT(sve2_rshrnt_s, uint32_t, uint16_t, H1_4, H1_2, do_urshr) +DO_SHRNT(sve2_rshrnt_d, uint64_t, uint32_t, , H1_4, do_urshr) + +#define DO_SQSHRUN_H(x, sh) do_sat_bhs((int64_t)(x) >> sh, 0, UINT8_MAX) +#define DO_SQSHRUN_S(x, sh) do_sat_bhs((int64_t)(x) >> sh, 0, UINT16_MAX) +#define DO_SQSHRUN_D(x, sh) \ + do_sat_bhs((int64_t)(x) >> (sh < 64 ? sh : 63), 0, UINT32_MAX) + +DO_SHRNB(sve2_sqshrunb_h, int16_t, uint8_t, DO_SQSHRUN_H) +DO_SHRNB(sve2_sqshrunb_s, int32_t, uint16_t, DO_SQSHRUN_S) +DO_SHRNB(sve2_sqshrunb_d, int64_t, uint32_t, DO_SQSHRUN_D) + +DO_SHRNT(sve2_sqshrunt_h, int16_t, uint8_t, H1_2, H1, DO_SQSHRUN_H) +DO_SHRNT(sve2_sqshrunt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQSHRUN_S) +DO_SHRNT(sve2_sqshrunt_d, int64_t, uint32_t, , H1_4, DO_SQSHRUN_D) + +#define DO_SQRSHRUN_H(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT8_MAX) +#define DO_SQRSHRUN_S(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT16_MAX) +#define DO_SQRSHRUN_D(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT32_MAX) + +DO_SHRNB(sve2_sqrshrunb_h, int16_t, uint8_t, DO_SQRSHRUN_H) +DO_SHRNB(sve2_sqrshrunb_s, int32_t, uint16_t, DO_SQRSHRUN_S) +DO_SHRNB(sve2_sqrshrunb_d, int64_t, uint32_t, DO_SQRSHRUN_D) + +DO_SHRNT(sve2_sqrshrunt_h, int16_t, uint8_t, H1_2, H1, DO_SQRSHRUN_H) +DO_SHRNT(sve2_sqrshrunt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQRSHRUN_S) +DO_SHRNT(sve2_sqrshrunt_d, int64_t, uint32_t, , H1_4, DO_SQRSHRUN_D) + +#define DO_SQSHRN_H(x, sh) do_sat_bhs(x >> sh, INT8_MIN, INT8_MAX) +#define DO_SQSHRN_S(x, sh) do_sat_bhs(x >> sh, INT16_MIN, INT16_MAX) +#define DO_SQSHRN_D(x, sh) do_sat_bhs(x >> sh, INT32_MIN, INT32_MAX) + +DO_SHRNB(sve2_sqshrnb_h, int16_t, uint8_t, DO_SQSHRN_H) +DO_SHRNB(sve2_sqshrnb_s, int32_t, uint16_t, DO_SQSHRN_S) +DO_SHRNB(sve2_sqshrnb_d, int64_t, uint32_t, DO_SQSHRN_D) + +DO_SHRNT(sve2_sqshrnt_h, int16_t, uint8_t, H1_2, H1, DO_SQSHRN_H) +DO_SHRNT(sve2_sqshrnt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQSHRN_S) +DO_SHRNT(sve2_sqshrnt_d, int64_t, uint32_t, , H1_4, DO_SQSHRN_D) + +#define DO_SQRSHRN_H(x, sh) do_sat_bhs(do_srshr(x, sh), INT8_MIN, INT8_MAX) +#define DO_SQRSHRN_S(x, sh) do_sat_bhs(do_srshr(x, sh), INT16_MIN, INT16_MAX) +#define DO_SQRSHRN_D(x, sh) do_sat_bhs(do_srshr(x, sh), INT32_MIN, INT32_MAX) + +DO_SHRNB(sve2_sqrshrnb_h, int16_t, uint8_t, DO_SQRSHRN_H) +DO_SHRNB(sve2_sqrshrnb_s, int32_t, uint16_t, DO_SQRSHRN_S) +DO_SHRNB(sve2_sqrshrnb_d, int64_t, uint32_t, DO_SQRSHRN_D) + +DO_SHRNT(sve2_sqrshrnt_h, int16_t, uint8_t, H1_2, H1, DO_SQRSHRN_H) +DO_SHRNT(sve2_sqrshrnt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQRSHRN_S) +DO_SHRNT(sve2_sqrshrnt_d, int64_t, uint32_t, , H1_4, DO_SQRSHRN_D) + +#define DO_UQSHRN_H(x, sh) MIN(x >> sh, UINT8_MAX) +#define DO_UQSHRN_S(x, sh) MIN(x >> sh, UINT16_MAX) +#define DO_UQSHRN_D(x, sh) MIN(x >> sh, UINT32_MAX) + +DO_SHRNB(sve2_uqshrnb_h, uint16_t, uint8_t, DO_UQSHRN_H) +DO_SHRNB(sve2_uqshrnb_s, uint32_t, uint16_t, DO_UQSHRN_S) +DO_SHRNB(sve2_uqshrnb_d, uint64_t, uint32_t, DO_UQSHRN_D) + +DO_SHRNT(sve2_uqshrnt_h, uint16_t, uint8_t, H1_2, H1, DO_UQSHRN_H) +DO_SHRNT(sve2_uqshrnt_s, uint32_t, uint16_t, H1_4, H1_2, DO_UQSHRN_S) +DO_SHRNT(sve2_uqshrnt_d, uint64_t, uint32_t, , H1_4, DO_UQSHRN_D) + +#define DO_UQRSHRN_H(x, sh) MIN(do_urshr(x, sh), UINT8_MAX) +#define DO_UQRSHRN_S(x, sh) MIN(do_urshr(x, sh), UINT16_MAX) +#define DO_UQRSHRN_D(x, sh) MIN(do_urshr(x, sh), UINT32_MAX) + +DO_SHRNB(sve2_uqrshrnb_h, uint16_t, uint8_t, DO_UQRSHRN_H) +DO_SHRNB(sve2_uqrshrnb_s, uint32_t, uint16_t, DO_UQRSHRN_S) +DO_SHRNB(sve2_uqrshrnb_d, uint64_t, uint32_t, DO_UQRSHRN_D) + +DO_SHRNT(sve2_uqrshrnt_h, uint16_t, uint8_t, H1_2, H1, DO_UQRSHRN_H) +DO_SHRNT(sve2_uqrshrnt_s, uint32_t, uint16_t, H1_4, H1_2, DO_UQRSHRN_S) +DO_SHRNT(sve2_uqrshrnt_d, uint64_t, uint32_t, , H1_4, DO_UQRSHRN_D) + +#undef DO_SHRNB +#undef DO_SHRNT + +#define DO_BINOPNB(NAME, TYPEW, TYPEN, SHIFT, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEW *)(vn + i); \ + TYPEW mm = *(TYPEW *)(vm + i); \ + *(TYPEW *)(vd + i) = (TYPEN)OP(nn, mm, SHIFT); \ + } \ +} + +#define DO_BINOPNT(NAME, TYPEW, TYPEN, SHIFT, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEW *)(vn + HW(i)); \ + TYPEW mm = *(TYPEW *)(vm + HW(i)); \ + *(TYPEN *)(vd + HN(i + sizeof(TYPEN))) = OP(nn, mm, SHIFT); \ + } \ +} + +#define DO_ADDHN(N, M, SH) ((N + M) >> SH) +#define DO_RADDHN(N, M, SH) ((N + M + ((__typeof(N))1 << (SH - 1))) >> SH) +#define DO_SUBHN(N, M, SH) ((N - M) >> SH) +#define DO_RSUBHN(N, M, SH) ((N - M + ((__typeof(N))1 << (SH - 1))) >> SH) + +DO_BINOPNB(sve2_addhnb_h, uint16_t, uint8_t, 8, DO_ADDHN) +DO_BINOPNB(sve2_addhnb_s, uint32_t, uint16_t, 16, DO_ADDHN) +DO_BINOPNB(sve2_addhnb_d, uint64_t, uint32_t, 32, DO_ADDHN) + +DO_BINOPNT(sve2_addhnt_h, uint16_t, uint8_t, 8, H1_2, H1, DO_ADDHN) +DO_BINOPNT(sve2_addhnt_s, uint32_t, uint16_t, 16, H1_4, H1_2, DO_ADDHN) +DO_BINOPNT(sve2_addhnt_d, uint64_t, uint32_t, 32, , H1_4, DO_ADDHN) + +DO_BINOPNB(sve2_raddhnb_h, uint16_t, uint8_t, 8, DO_RADDHN) +DO_BINOPNB(sve2_raddhnb_s, uint32_t, uint16_t, 16, DO_RADDHN) +DO_BINOPNB(sve2_raddhnb_d, uint64_t, uint32_t, 32, DO_RADDHN) + +DO_BINOPNT(sve2_raddhnt_h, uint16_t, uint8_t, 8, H1_2, H1, DO_RADDHN) +DO_BINOPNT(sve2_raddhnt_s, uint32_t, uint16_t, 16, H1_4, H1_2, DO_RADDHN) +DO_BINOPNT(sve2_raddhnt_d, uint64_t, uint32_t, 32, , H1_4, DO_RADDHN) + +DO_BINOPNB(sve2_subhnb_h, uint16_t, uint8_t, 8, DO_SUBHN) +DO_BINOPNB(sve2_subhnb_s, uint32_t, uint16_t, 16, DO_SUBHN) +DO_BINOPNB(sve2_subhnb_d, uint64_t, uint32_t, 32, DO_SUBHN) + +DO_BINOPNT(sve2_subhnt_h, uint16_t, uint8_t, 8, H1_2, H1, DO_SUBHN) +DO_BINOPNT(sve2_subhnt_s, uint32_t, uint16_t, 16, H1_4, H1_2, DO_SUBHN) +DO_BINOPNT(sve2_subhnt_d, uint64_t, uint32_t, 32, , H1_4, DO_SUBHN) + +DO_BINOPNB(sve2_rsubhnb_h, uint16_t, uint8_t, 8, DO_RSUBHN) +DO_BINOPNB(sve2_rsubhnb_s, uint32_t, uint16_t, 16, DO_RSUBHN) +DO_BINOPNB(sve2_rsubhnb_d, uint64_t, uint32_t, 32, DO_RSUBHN) + +DO_BINOPNT(sve2_rsubhnt_h, uint16_t, uint8_t, 8, H1_2, H1, DO_RSUBHN) +DO_BINOPNT(sve2_rsubhnt_s, uint32_t, uint16_t, 16, H1_4, H1_2, DO_RSUBHN) +DO_BINOPNT(sve2_rsubhnt_d, uint64_t, uint32_t, 32, , H1_4, DO_RSUBHN) + +#undef DO_RSUBHN +#undef DO_SUBHN +#undef DO_RADDHN +#undef DO_ADDHN + +#undef DO_BINOPNB + /* Fully general four-operand expander, controlled by a predicate. */ #define DO_ZPZZZ(NAME, TYPE, H, OP) \ @@ -1356,13 +2719,7 @@ void HELPER(sve_sqaddi_b)(void *d, void *a, int32_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(int8_t)) { - int r = *(int8_t *)(a + i) + b; - if (r > INT8_MAX) { - r = INT8_MAX; - } else if (r < INT8_MIN) { - r = INT8_MIN; - } - *(int8_t *)(d + i) = r; + *(int8_t *)(d + i) = DO_SQADD_B(b, *(int8_t *)(a + i)); } } @@ -1371,13 +2728,7 @@ void HELPER(sve_sqaddi_h)(void *d, void *a, int32_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(int16_t)) { - int r = *(int16_t *)(a + i) + b; - if (r > INT16_MAX) { - r = INT16_MAX; - } else if (r < INT16_MIN) { - r = INT16_MIN; - } - *(int16_t *)(d + i) = r; + *(int16_t *)(d + i) = DO_SQADD_H(b, *(int16_t *)(a + i)); } } @@ -1386,13 +2737,7 @@ void HELPER(sve_sqaddi_s)(void *d, void *a, int64_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(int32_t)) { - int64_t r = *(int32_t *)(a + i) + b; - if (r > INT32_MAX) { - r = INT32_MAX; - } else if (r < INT32_MIN) { - r = INT32_MIN; - } - *(int32_t *)(d + i) = r; + *(int32_t *)(d + i) = DO_SQADD_S(b, *(int32_t *)(a + i)); } } @@ -1401,13 +2746,7 @@ void HELPER(sve_sqaddi_d)(void *d, void *a, int64_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(int64_t)) { - int64_t ai = *(int64_t *)(a + i); - int64_t r = ai + b; - if (((r ^ ai) & ~(ai ^ b)) < 0) { - /* Signed overflow. */ - r = (r < 0 ? INT64_MAX : INT64_MIN); - } - *(int64_t *)(d + i) = r; + *(int64_t *)(d + i) = do_sqadd_d(b, *(int64_t *)(a + i)); } } @@ -1420,13 +2759,7 @@ void HELPER(sve_uqaddi_b)(void *d, void *a, int32_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(uint8_t)) { - int r = *(uint8_t *)(a + i) + b; - if (r > UINT8_MAX) { - r = UINT8_MAX; - } else if (r < 0) { - r = 0; - } - *(uint8_t *)(d + i) = r; + *(uint8_t *)(d + i) = DO_UQADD_B(b, *(uint8_t *)(a + i)); } } @@ -1435,13 +2768,7 @@ void HELPER(sve_uqaddi_h)(void *d, void *a, int32_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(uint16_t)) { - int r = *(uint16_t *)(a + i) + b; - if (r > UINT16_MAX) { - r = UINT16_MAX; - } else if (r < 0) { - r = 0; - } - *(uint16_t *)(d + i) = r; + *(uint16_t *)(d + i) = DO_UQADD_H(b, *(uint16_t *)(a + i)); } } @@ -1450,13 +2777,7 @@ void HELPER(sve_uqaddi_s)(void *d, void *a, int64_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(uint32_t)) { - int64_t r = *(uint32_t *)(a + i) + b; - if (r > UINT32_MAX) { - r = UINT32_MAX; - } else if (r < 0) { - r = 0; - } - *(uint32_t *)(d + i) = r; + *(uint32_t *)(d + i) = DO_UQADD_S(b, *(uint32_t *)(a + i)); } } @@ -1465,11 +2786,7 @@ void HELPER(sve_uqaddi_d)(void *d, void *a, uint64_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(uint64_t)) { - uint64_t r = *(uint64_t *)(a + i) + b; - if (r < b) { - r = UINT64_MAX; - } - *(uint64_t *)(d + i) = r; + *(uint64_t *)(d + i) = do_uqadd_d(b, *(uint64_t *)(a + i)); } } @@ -1478,8 +2795,7 @@ void HELPER(sve_uqsubi_d)(void *d, void *a, uint64_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(uint64_t)) { - uint64_t ai = *(uint64_t *)(a + i); - *(uint64_t *)(d + i) = (ai < b ? 0 : ai - b); + *(uint64_t *)(d + i) = do_uqsub_d(*(uint64_t *)(a + i), b); } } @@ -1772,28 +3088,80 @@ void HELPER(sve_rev_d)(void *vd, void *vn, uint32_t desc) } } -#define DO_TBL(NAME, TYPE, H) \ -void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ -{ \ - intptr_t i, opr_sz = simd_oprsz(desc); \ - uintptr_t elem = opr_sz / sizeof(TYPE); \ - TYPE *d = vd, *n = vn, *m = vm; \ - ARMVectorReg tmp; \ - if (unlikely(vd == vn)) { \ - n = memcpy(&tmp, vn, opr_sz); \ - } \ - for (i = 0; i < elem; i++) { \ - TYPE j = m[H(i)]; \ - d[H(i)] = j < elem ? n[H(j)] : 0; \ - } \ +typedef void tb_impl_fn(void *, void *, void *, void *, uintptr_t, bool); + +static inline void do_tbl1(void *vd, void *vn, void *vm, uint32_t desc, + bool is_tbx, tb_impl_fn *fn) +{ + ARMVectorReg scratch; + uintptr_t oprsz = simd_oprsz(desc); + + if (unlikely(vd == vn)) { + vn = memcpy(&scratch, vn, oprsz); + } + + fn(vd, vn, NULL, vm, oprsz, is_tbx); +} + +static inline void do_tbl2(void *vd, void *vn0, void *vn1, void *vm, + uint32_t desc, bool is_tbx, tb_impl_fn *fn) +{ + ARMVectorReg scratch; + uintptr_t oprsz = simd_oprsz(desc); + + if (unlikely(vd == vn0)) { + vn0 = memcpy(&scratch, vn0, oprsz); + if (vd == vn1) { + vn1 = vn0; + } + } else if (unlikely(vd == vn1)) { + vn1 = memcpy(&scratch, vn1, oprsz); + } + + fn(vd, vn0, vn1, vm, oprsz, is_tbx); +} + +#define DO_TB(SUFF, TYPE, H) \ +static inline void do_tb_##SUFF(void *vd, void *vt0, void *vt1, \ + void *vm, uintptr_t oprsz, bool is_tbx) \ +{ \ + TYPE *d = vd, *tbl0 = vt0, *tbl1 = vt1, *indexes = vm; \ + uintptr_t i, nelem = oprsz / sizeof(TYPE); \ + for (i = 0; i < nelem; ++i) { \ + TYPE index = indexes[H1(i)], val = 0; \ + if (index < nelem) { \ + val = tbl0[H(index)]; \ + } else { \ + index -= nelem; \ + if (tbl1 && index < nelem) { \ + val = tbl1[H(index)]; \ + } else if (is_tbx) { \ + continue; \ + } \ + } \ + d[H(i)] = val; \ + } \ +} \ +void HELPER(sve_tbl_##SUFF)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + do_tbl1(vd, vn, vm, desc, false, do_tb_##SUFF); \ +} \ +void HELPER(sve2_tbl_##SUFF)(void *vd, void *vn0, void *vn1, \ + void *vm, uint32_t desc) \ +{ \ + do_tbl2(vd, vn0, vn1, vm, desc, false, do_tb_##SUFF); \ +} \ +void HELPER(sve2_tbx_##SUFF)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + do_tbl1(vd, vn, vm, desc, true, do_tb_##SUFF); \ } -DO_TBL(sve_tbl_b, uint8_t, H1) -DO_TBL(sve_tbl_h, uint16_t, H2) -DO_TBL(sve_tbl_s, uint32_t, H4) -DO_TBL(sve_tbl_d, uint64_t, ) +DO_TB(b, uint8_t, H1) +DO_TB(h, uint16_t, H2) +DO_TB(s, uint32_t, H4) +DO_TB(d, uint64_t, ) -#undef TBL +#undef DO_TB #define DO_UNPK(NAME, TYPED, TYPES, HD, HS) \ void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ @@ -2143,36 +3511,45 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ *(TYPE *)(vd + H(2 * i + 0)) = *(TYPE *)(vn + H(i)); \ *(TYPE *)(vd + H(2 * i + sizeof(TYPE))) = *(TYPE *)(vm + H(i)); \ } \ + if (sizeof(TYPE) == 16 && unlikely(oprsz & 16)) { \ + memset(vd + oprsz - 16, 0, 16); \ + } \ } DO_ZIP(sve_zip_b, uint8_t, H1) DO_ZIP(sve_zip_h, uint16_t, H1_2) DO_ZIP(sve_zip_s, uint32_t, H1_4) DO_ZIP(sve_zip_d, uint64_t, ) +DO_ZIP(sve2_zip_q, Int128, ) #define DO_UZP(NAME, TYPE, H) \ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ { \ intptr_t oprsz = simd_oprsz(desc); \ - intptr_t oprsz_2 = oprsz / 2; \ intptr_t odd_ofs = simd_data(desc); \ - intptr_t i; \ + intptr_t i, p; \ ARMVectorReg tmp_m; \ if (unlikely((vm - vd) < (uintptr_t)oprsz)) { \ vm = memcpy(&tmp_m, vm, oprsz); \ } \ - for (i = 0; i < oprsz_2; i += sizeof(TYPE)) { \ - *(TYPE *)(vd + H(i)) = *(TYPE *)(vn + H(2 * i + odd_ofs)); \ - } \ - for (i = 0; i < oprsz_2; i += sizeof(TYPE)) { \ - *(TYPE *)(vd + H(oprsz_2 + i)) = *(TYPE *)(vm + H(2 * i + odd_ofs)); \ - } \ + i = 0, p = odd_ofs; \ + do { \ + *(TYPE *)(vd + H(i)) = *(TYPE *)(vn + H(p)); \ + i += sizeof(TYPE), p += 2 * sizeof(TYPE); \ + } while (p < oprsz); \ + p -= oprsz; \ + do { \ + *(TYPE *)(vd + H(i)) = *(TYPE *)(vm + H(p)); \ + i += sizeof(TYPE), p += 2 * sizeof(TYPE); \ + } while (p < oprsz); \ + tcg_debug_assert(i == oprsz); \ } DO_UZP(sve_uzp_b, uint8_t, H1) DO_UZP(sve_uzp_h, uint16_t, H1_2) DO_UZP(sve_uzp_s, uint32_t, H1_4) DO_UZP(sve_uzp_d, uint64_t, ) +DO_UZP(sve2_uzp_q, Int128, ) #define DO_TRN(NAME, TYPE, H) \ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ @@ -2186,12 +3563,16 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ *(TYPE *)(vd + H(i + 0)) = ae; \ *(TYPE *)(vd + H(i + sizeof(TYPE))) = be; \ } \ + if (sizeof(TYPE) == 16 && unlikely(oprsz & 16)) { \ + memset(vd + oprsz - 16, 0, 16); \ + } \ } DO_TRN(sve_trn_b, uint8_t, H1) DO_TRN(sve_trn_h, uint16_t, H1_2) DO_TRN(sve_trn_s, uint32_t, H1_4) DO_TRN(sve_trn_d, uint64_t, ) +DO_TRN(sve2_trn_q, Int128, ) #undef DO_ZIP #undef DO_UZP @@ -2848,7 +4229,7 @@ uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc) return sum; } -uint32_t HELPER(sve_while)(void *vd, uint32_t count, uint32_t pred_desc) +uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc) { intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); @@ -2874,6 +4255,42 @@ uint32_t HELPER(sve_while)(void *vd, uint32_t count, uint32_t pred_desc) return predtest_ones(d, oprsz, esz_mask); } +uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc) +{ + intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); + intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); + uint64_t esz_mask = pred_esz_masks[esz]; + ARMPredicateReg *d = vd; + intptr_t i, invcount, oprbits; + uint64_t bits; + + if (count == 0) { + return do_zero(d, oprsz); + } + + oprbits = oprsz * 8; + tcg_debug_assert(count <= oprbits); + + bits = esz_mask; + if (oprbits & 63) { + bits &= MAKE_64BIT_MASK(0, oprbits & 63); + } + + invcount = oprbits - count; + for (i = (oprsz - 1) / 8; i > invcount / 64; --i) { + d->p[i] = bits; + bits = esz_mask; + } + + d->p[i] = bits & MAKE_64BIT_MASK(invcount & 63, 64); + + while (--i >= 0) { + d->p[i] = 0; + } + + return predtest_ones(d, oprsz, esz_mask); +} + /* Recursive reduction on a function; * C.f. the ARM ARM function ReducePredicated. * @@ -3344,6 +4761,94 @@ DO_ZPZ_FP(sve_ucvt_dh, uint64_t, , uint64_to_float16) DO_ZPZ_FP(sve_ucvt_ds, uint64_t, , uint64_to_float32) DO_ZPZ_FP(sve_ucvt_dd, uint64_t, , uint64_to_float64) +static int16_t do_float16_logb_as_int(float16 a, float_status *s) +{ + /* Extract frac to the top of the uint32_t. */ + uint32_t frac = (uint32_t)a << (16 + 6); + int16_t exp = extract32(a, 10, 5); + + if (unlikely(exp == 0)) { + if (frac != 0) { + if (!get_flush_inputs_to_zero(s)) { + /* denormal: bias - fractional_zeros */ + return -15 - clz32(frac); + } + /* flush to zero */ + float_raise(float_flag_input_denormal, s); + } + } else if (unlikely(exp == 0x1f)) { + if (frac == 0) { + return INT16_MAX; /* infinity */ + } + } else { + /* normal: exp - bias */ + return exp - 15; + } + /* nan or zero */ + float_raise(float_flag_invalid, s); + return INT16_MIN; +} + +static int32_t do_float32_logb_as_int(float32 a, float_status *s) +{ + /* Extract frac to the top of the uint32_t. */ + uint32_t frac = a << 9; + int32_t exp = extract32(a, 23, 8); + + if (unlikely(exp == 0)) { + if (frac != 0) { + if (!get_flush_inputs_to_zero(s)) { + /* denormal: bias - fractional_zeros */ + return -127 - clz32(frac); + } + /* flush to zero */ + float_raise(float_flag_input_denormal, s); + } + } else if (unlikely(exp == 0xff)) { + if (frac == 0) { + return INT32_MAX; /* infinity */ + } + } else { + /* normal: exp - bias */ + return exp - 127; + } + /* nan or zero */ + float_raise(float_flag_invalid, s); + return INT32_MIN; +} + +static int64_t do_float64_logb_as_int(float64 a, float_status *s) +{ + /* Extract frac to the top of the uint64_t. */ + uint64_t frac = a << 12; + int64_t exp = extract64(a, 52, 11); + + if (unlikely(exp == 0)) { + if (frac != 0) { + if (!get_flush_inputs_to_zero(s)) { + /* denormal: bias - fractional_zeros */ + return -1023 - clz64(frac); + } + /* flush to zero */ + float_raise(float_flag_input_denormal, s); + } + } else if (unlikely(exp == 0x7ff)) { + if (frac == 0) { + return INT64_MAX; /* infinity */ + } + } else { + /* normal: exp - bias */ + return exp - 1023; + } + /* nan or zero */ + float_raise(float_flag_invalid, s); + return INT64_MIN; +} + +DO_ZPZ_FP(flogb_h, float16, H1_2, do_float16_logb_as_int) +DO_ZPZ_FP(flogb_s, float32, H1_4, do_float32_logb_as_int) +DO_ZPZ_FP(flogb_d, float64, , do_float64_logb_as_int) + #undef DO_ZPZ_FP static void do_fmla_zpzzz_h(void *vd, void *vn, void *vm, void *va, void *vg, @@ -5859,3 +7364,404 @@ DO_ST1_ZPZ_D(dd_be, zd, MO_64) #undef DO_ST1_ZPZ_S #undef DO_ST1_ZPZ_D + +void HELPER(sve2_eor3)(void *vd, void *vn, void *vm, void *vk, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn, *m = vm, *k = vk; + + for (i = 0; i < opr_sz; ++i) { + d[i] = n[i] ^ m[i] ^ k[i]; + } +} + +void HELPER(sve2_bcax)(void *vd, void *vn, void *vm, void *vk, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn, *m = vm, *k = vk; + + for (i = 0; i < opr_sz; ++i) { + d[i] = n[i] ^ (m[i] & ~k[i]); + } +} + +void HELPER(sve2_bsl1n)(void *vd, void *vn, void *vm, void *vk, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn, *m = vm, *k = vk; + + for (i = 0; i < opr_sz; ++i) { + d[i] = (~n[i] & k[i]) | (m[i] & ~k[i]); + } +} + +void HELPER(sve2_bsl2n)(void *vd, void *vn, void *vm, void *vk, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn, *m = vm, *k = vk; + + for (i = 0; i < opr_sz; ++i) { + d[i] = (n[i] & k[i]) | (~m[i] & ~k[i]); + } +} + +void HELPER(sve2_nbsl)(void *vd, void *vn, void *vm, void *vk, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn, *m = vm, *k = vk; + + for (i = 0; i < opr_sz; ++i) { + d[i] = ~((n[i] & k[i]) | (m[i] & ~k[i])); + } +} + +/* + * Returns true if m0 or m1 contains the low uint8_t/uint16_t in n. + * See hasless(v,1) from + * https://graphics.stanford.edu/~seander/bithacks.html#ZeroInWord + */ +static inline bool do_match2(uint64_t n, uint64_t m0, uint64_t m1, int esz) +{ + int bits = 8 << esz; + uint64_t ones = dup_const(esz, 1); + uint64_t signs = ones << (bits - 1); + uint64_t cmp0, cmp1; + + cmp1 = dup_const(esz, n); + cmp0 = cmp1 ^ m0; + cmp1 = cmp1 ^ m1; + cmp0 = (cmp0 - ones) & ~cmp0; + cmp1 = (cmp1 - ones) & ~cmp1; + return (cmp0 | cmp1) & signs; +} + +static inline uint32_t do_match(void *vd, void *vn, void *vm, void *vg, + uint32_t desc, int esz, bool nmatch) +{ + uint16_t esz_mask = pred_esz_masks[esz]; + intptr_t opr_sz = simd_oprsz(desc); + uint32_t flags = PREDTEST_INIT; + intptr_t i, j, k; + + for (i = 0; i < opr_sz; i += 16) { + uint64_t m0 = *(uint64_t *)(vm + i); + uint64_t m1 = *(uint64_t *)(vm + i + 8); + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)) & esz_mask; + uint16_t out = 0; + + for (j = 0; j < 16; j += 8) { + uint64_t n = *(uint64_t *)(vn + i + j); + + for (k = 0; k < 8; k += 1 << esz) { + if (pg & (1 << (j + k))) { + bool o = do_match2(n >> (k * 8), m0, m1, esz); + out |= (o ^ nmatch) << (j + k); + } + } + } + *(uint16_t *)(vd + H1_2(i >> 3)) = out; + flags = iter_predtest_fwd(out, pg, flags); + } + return flags; +} + +#define DO_PPZZ_MATCH(NAME, ESZ, INV) \ +uint32_t HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) \ +{ \ + return do_match(vd, vn, vm, vg, desc, ESZ, INV); \ +} + +DO_PPZZ_MATCH(sve2_match_ppzz_b, MO_8, false) +DO_PPZZ_MATCH(sve2_match_ppzz_h, MO_16, false) + +DO_PPZZ_MATCH(sve2_nmatch_ppzz_b, MO_8, true) +DO_PPZZ_MATCH(sve2_nmatch_ppzz_h, MO_16, true) + +#undef DO_PPZZ_MATCH + +void HELPER(sve2_histcnt_s)(void *vd, void *vn, void *vm, void *vg, + uint32_t desc) +{ + ARMVectorReg scratch; + intptr_t i, j; + intptr_t opr_sz = simd_oprsz(desc); + uint32_t *d = vd, *n = vn, *m = vm; + uint8_t *pg = vg; + + if (d == n) { + n = memcpy(&scratch, n, opr_sz); + if (d == m) { + m = n; + } + } else if (d == m) { + m = memcpy(&scratch, m, opr_sz); + } + + for (i = 0; i < opr_sz; i += 4) { + uint64_t count = 0; + uint8_t pred; + + pred = pg[H1(i >> 3)] >> (i & 7); + if (pred & 1) { + uint32_t nn = n[H4(i >> 2)]; + + for (j = 0; j <= i; j += 4) { + pred = pg[H1(j >> 3)] >> (j & 7); + if ((pred & 1) && nn == m[H4(j >> 2)]) { + ++count; + } + } + } + d[H4(i >> 2)] = count; + } +} + +void HELPER(sve2_histcnt_d)(void *vd, void *vn, void *vm, void *vg, + uint32_t desc) +{ + ARMVectorReg scratch; + intptr_t i, j; + intptr_t opr_sz = simd_oprsz(desc); + uint64_t *d = vd, *n = vn, *m = vm; + uint8_t *pg = vg; + + if (d == n) { + n = memcpy(&scratch, n, opr_sz); + if (d == m) { + m = n; + } + } else if (d == m) { + m = memcpy(&scratch, m, opr_sz); + } + + for (i = 0; i < opr_sz / 8; ++i) { + uint64_t count = 0; + if (pg[H1(i)] & 1) { + uint64_t nn = n[i]; + for (j = 0; j <= i; ++j) { + if ((pg[H1(j)] & 1) && nn == m[j]) { + ++count; + } + } + } + d[i] = count; + } +} + +/* + * Returns the number of bytes in m0 and m1 that match n. + * Unlike do_match2 we don't just need true/false, we need an exact count. + * This requires two extra logical operations. + */ +static inline uint64_t do_histseg_cnt(uint8_t n, uint64_t m0, uint64_t m1) +{ + const uint64_t mask = dup_const(MO_8, 0x7f); + uint64_t cmp0, cmp1; + + cmp1 = dup_const(MO_8, n); + cmp0 = cmp1 ^ m0; + cmp1 = cmp1 ^ m1; + + /* + * 1: clear msb of each byte to avoid carry to next byte (& mask) + * 2: carry in to msb if byte != 0 (+ mask) + * 3: set msb if cmp has msb set (| cmp) + * 4: set ~msb to ignore them (| mask) + * We now have 0xff for byte != 0 or 0x7f for byte == 0. + * 5: invert, resulting in 0x80 if and only if byte == 0. + */ + cmp0 = ~(((cmp0 & mask) + mask) | cmp0 | mask); + cmp1 = ~(((cmp1 & mask) + mask) | cmp1 | mask); + + /* + * Combine the two compares in a way that the bits do + * not overlap, and so preserves the count of set bits. + * If the host has an efficient instruction for ctpop, + * then ctpop(x) + ctpop(y) has the same number of + * operations as ctpop(x | (y >> 1)). If the host does + * not have an efficient ctpop, then we only want to + * use it once. + */ + return ctpop64(cmp0 | (cmp1 >> 1)); +} + +void HELPER(sve2_histseg)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, j; + intptr_t opr_sz = simd_oprsz(desc); + + for (i = 0; i < opr_sz; i += 16) { + uint64_t n0 = *(uint64_t *)(vn + i); + uint64_t m0 = *(uint64_t *)(vm + i); + uint64_t n1 = *(uint64_t *)(vn + i + 8); + uint64_t m1 = *(uint64_t *)(vm + i + 8); + uint64_t out0 = 0; + uint64_t out1 = 0; + + for (j = 0; j < 64; j += 8) { + uint64_t cnt0 = do_histseg_cnt(n0 >> j, m0, m1); + uint64_t cnt1 = do_histseg_cnt(n1 >> j, m0, m1); + out0 |= cnt0 << j; + out1 |= cnt1 << j; + } + + *(uint64_t *)(vd + i) = out0; + *(uint64_t *)(vd + i + 8) = out1; + } +} + +void HELPER(sve2_xar_b)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + int shr = simd_data(desc); + int shl = 8 - shr; + uint64_t mask = dup_const(MO_8, 0xff >> shr); + uint64_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz; ++i) { + uint64_t t = n[i] ^ m[i]; + d[i] = ((t >> shr) & mask) | ((t << shl) & ~mask); + } +} + +void HELPER(sve2_xar_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + int shr = simd_data(desc); + int shl = 16 - shr; + uint64_t mask = dup_const(MO_16, 0xffff >> shr); + uint64_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz; ++i) { + uint64_t t = n[i] ^ m[i]; + d[i] = ((t >> shr) & mask) | ((t << shl) & ~mask); + } +} + +void HELPER(sve2_xar_s)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 4; + int shr = simd_data(desc); + uint32_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz; ++i) { + d[i] = ror32(n[i] ^ m[i], shr); + } +} + +void HELPER(fmmla_s)(void *vd, void *vn, void *vm, void *va, + void *status, uint32_t desc) +{ + intptr_t s, opr_sz = simd_oprsz(desc) / (sizeof(float32) * 4); + + for (s = 0; s < opr_sz; ++s) { + float32 *n = vn + s * sizeof(float32) * 4; + float32 *m = vm + s * sizeof(float32) * 4; + float32 *a = va + s * sizeof(float32) * 4; + float32 *d = vd + s * sizeof(float32) * 4; + float32 n00 = n[H4(0)], n01 = n[H4(1)]; + float32 n10 = n[H4(2)], n11 = n[H4(3)]; + float32 m00 = m[H4(0)], m01 = m[H4(1)]; + float32 m10 = m[H4(2)], m11 = m[H4(3)]; + float32 p0, p1; + + /* i = 0, j = 0 */ + p0 = float32_mul(n00, m00, status); + p1 = float32_mul(n01, m01, status); + d[H4(0)] = float32_add(a[H4(0)], float32_add(p0, p1, status), status); + + /* i = 0, j = 1 */ + p0 = float32_mul(n00, m10, status); + p1 = float32_mul(n01, m11, status); + d[H4(1)] = float32_add(a[H4(1)], float32_add(p0, p1, status), status); + + /* i = 1, j = 0 */ + p0 = float32_mul(n10, m00, status); + p1 = float32_mul(n11, m01, status); + d[H4(2)] = float32_add(a[H4(2)], float32_add(p0, p1, status), status); + + /* i = 1, j = 1 */ + p0 = float32_mul(n10, m10, status); + p1 = float32_mul(n11, m11, status); + d[H4(3)] = float32_add(a[H4(3)], float32_add(p0, p1, status), status); + } +} + +void HELPER(fmmla_d)(void *vd, void *vn, void *vm, void *va, + void *status, uint32_t desc) +{ + intptr_t s, opr_sz = simd_oprsz(desc) / (sizeof(float64) * 4); + + for (s = 0; s < opr_sz; ++s) { + float64 *n = vn + s * sizeof(float64) * 4; + float64 *m = vm + s * sizeof(float64) * 4; + float64 *a = va + s * sizeof(float64) * 4; + float64 *d = vd + s * sizeof(float64) * 4; + float64 n00 = n[0], n01 = n[1], n10 = n[2], n11 = n[3]; + float64 m00 = m[0], m01 = m[1], m10 = m[2], m11 = m[3]; + float64 p0, p1; + + /* i = 0, j = 0 */ + p0 = float64_mul(n00, m00, status); + p1 = float64_mul(n01, m01, status); + d[0] = float64_add(a[0], float64_add(p0, p1, status), status); + + /* i = 0, j = 1 */ + p0 = float64_mul(n00, m10, status); + p1 = float64_mul(n01, m11, status); + d[1] = float64_add(a[1], float64_add(p0, p1, status), status); + + /* i = 1, j = 0 */ + p0 = float64_mul(n10, m00, status); + p1 = float64_mul(n11, m01, status); + d[2] = float64_add(a[2], float64_add(p0, p1, status), status); + + /* i = 1, j = 1 */ + p0 = float64_mul(n10, m10, status); + p1 = float64_mul(n11, m11, status); + d[3] = float64_add(a[3], float64_add(p0, p1, status), status); + } +} + +#define DO_FCVTNT(NAME, TYPEW, TYPEN, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vg, void *status, uint32_t desc) \ +{ \ + intptr_t i = simd_oprsz(desc); \ + uint64_t *g = vg; \ + do { \ + uint64_t pg = g[(i - 1) >> 6]; \ + do { \ + i -= sizeof(TYPEW); \ + if (likely((pg >> (i & 63)) & 1)) { \ + TYPEW nn = *(TYPEW *)(vn + HW(i)); \ + *(TYPEN *)(vd + HN(i + sizeof(TYPEN))) = OP(nn, status); \ + } \ + } while (i & 63); \ + } while (i != 0); \ +} + +DO_FCVTNT(sve2_fcvtnt_sh, uint32_t, uint16_t, H1_4, H1_2, sve_f32_to_f16) +DO_FCVTNT(sve2_fcvtnt_ds, uint64_t, uint32_t, , H1_4, float64_to_float32) + +#define DO_FCVTLT(NAME, TYPEW, TYPEN, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vg, void *status, uint32_t desc) \ +{ \ + intptr_t i = simd_oprsz(desc); \ + uint64_t *g = vg; \ + do { \ + uint64_t pg = g[(i - 1) >> 6]; \ + do { \ + i -= sizeof(TYPEW); \ + if (likely((pg >> (i & 63)) & 1)) { \ + TYPEN nn = *(TYPEN *)(vn + HN(i + sizeof(TYPEN))); \ + *(TYPEW *)(vd + HW(i)) = OP(nn, status); \ + } \ + } while (i & 63); \ + } while (i != 0); \ +} + +DO_FCVTLT(sve2_fcvtlt_hs, uint32_t, uint16_t, H1_4, H1_2, sve_f16_to_f32) +DO_FCVTLT(sve2_fcvtlt_sd, uint64_t, uint32_t, , H1_4, float32_to_float64) + +#undef DO_FCVTLT +#undef DO_FCVTNT diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index 0c80d0b505..ceac0ee2bd 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -683,6 +683,34 @@ static void gen_gvec_op3_qc(DisasContext *s, bool is_q, int rd, int rn, tcg_temp_free_ptr(qc_ptr); } +/* Expand a 4-operand operation using an out-of-line helper. */ +static void gen_gvec_op4_ool(DisasContext *s, bool is_q, int rd, int rn, + int rm, int ra, int data, gen_helper_gvec_4 *fn) +{ + tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + vec_full_reg_offset(s, ra), + is_q ? 16 : 8, vec_full_reg_size(s), data, fn); +} + +/* + * Expand a 4-operand + fpstatus pointer + simd data value operation using + * an out-of-line helper. + */ +static void gen_gvec_op4_fpst(DisasContext *s, bool is_q, int rd, int rn, + int rm, int ra, bool is_fp16, int data, + gen_helper_gvec_4_ptr *fn) +{ + TCGv_ptr fpst = fpstatus_ptr(is_fp16 ? FPST_FPCR_F16 : FPST_FPCR); + tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + vec_full_reg_offset(s, ra), fpst, + is_q ? 16 : 8, vec_full_reg_size(s), data, fn); + tcg_temp_free_ptr(fpst); +} + /* Set ZF and NF based on a 64 bit result. This is alas fiddlier * than the 32 bit equivalent. */ @@ -12147,6 +12175,22 @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) } feature = dc_isar_feature(aa64_dp, s); break; + case 0x03: /* USDOT */ + if (size != MO_32) { + unallocated_encoding(s); + return; + } + feature = dc_isar_feature(aa64_i8mm, s); + break; + case 0x04: /* SMMLA */ + case 0x14: /* UMMLA */ + case 0x05: /* USMMLA */ + if (!is_q || size != MO_32) { + unallocated_encoding(s); + return; + } + feature = dc_isar_feature(aa64_i8mm, s); + break; case 0x18: /* FCMLA, #0 */ case 0x19: /* FCMLA, #90 */ case 0x1a: /* FCMLA, #180 */ @@ -12183,10 +12227,23 @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) return; case 0x2: /* SDOT / UDOT */ - gen_gvec_op3_ool(s, is_q, rd, rn, rm, 0, + gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b); return; + case 0x3: /* USDOT */ + gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, gen_helper_gvec_usdot_b); + return; + + case 0x04: /* SMMLA, UMMLA */ + gen_gvec_op4_ool(s, 1, rd, rn, rm, rd, 0, + u ? gen_helper_gvec_ummla_b + : gen_helper_gvec_smmla_b); + return; + case 0x05: /* USMMLA */ + gen_gvec_op4_ool(s, 1, rd, rn, rm, rd, 0, gen_helper_gvec_usmmla_b); + return; + case 0x8: /* FCMLA, #0 */ case 0x9: /* FCMLA, #90 */ case 0xa: /* FCMLA, #180 */ @@ -12194,15 +12251,15 @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) rot = extract32(opcode, 0, 2); switch (size) { case 1: - gen_gvec_op3_fpst(s, is_q, rd, rn, rm, true, rot, + gen_gvec_op4_fpst(s, is_q, rd, rn, rm, rd, true, rot, gen_helper_gvec_fcmlah); break; case 2: - gen_gvec_op3_fpst(s, is_q, rd, rn, rm, false, rot, + gen_gvec_op4_fpst(s, is_q, rd, rn, rm, rd, false, rot, gen_helper_gvec_fcmlas); break; case 3: - gen_gvec_op3_fpst(s, is_q, rd, rn, rm, false, rot, + gen_gvec_op4_fpst(s, is_q, rd, rn, rm, rd, false, rot, gen_helper_gvec_fcmlad); break; default: @@ -13332,6 +13389,13 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) return; } break; + case 0x0f: /* SUDOT, USDOT */ + if (is_scalar || (size & 1) || !dc_isar_feature(aa64_i8mm, s)) { + unallocated_encoding(s); + return; + } + size = MO_32; + break; case 0x11: /* FCMLA #0 */ case 0x13: /* FCMLA #90 */ case 0x15: /* FCMLA #180 */ @@ -13442,10 +13506,17 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) switch (16 * u + opcode) { case 0x0e: /* SDOT */ case 0x1e: /* UDOT */ - gen_gvec_op3_ool(s, is_q, rd, rn, rm, index, + gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index, u ? gen_helper_gvec_udot_idx_b : gen_helper_gvec_sdot_idx_b); return; + case 0x0f: /* SUDOT, USDOT */ + gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index, + extract32(insn, 23, 1) + ? gen_helper_gvec_usdot_idx_b + : gen_helper_gvec_sudot_idx_b); + return; + case 0x11: /* FCMLA #0 */ case 0x13: /* FCMLA #90 */ case 0x15: /* FCMLA #180 */ @@ -13453,9 +13524,10 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) { int rot = extract32(insn, 13, 2); int data = (index << 2) | rot; - tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd), + tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, rd), vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), fpst, + vec_full_reg_offset(s, rm), + vec_full_reg_offset(s, rd), fpst, is_q ? 16 : 8, vec_full_reg_size(s), data, size == MO_64 ? gen_helper_gvec_fcmlas_idx @@ -14349,8 +14421,6 @@ static void disas_crypto_xar(DisasContext *s, uint32_t insn) int imm6 = extract32(insn, 10, 6); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - TCGv_i64 tcg_op1, tcg_op2, tcg_res[2]; - int pass; if (!dc_isar_feature(aa64_sha3, s)) { unallocated_encoding(s); @@ -14361,25 +14431,10 @@ static void disas_crypto_xar(DisasContext *s, uint32_t insn) return; } - tcg_op1 = tcg_temp_new_i64(); - tcg_op2 = tcg_temp_new_i64(); - tcg_res[0] = tcg_temp_new_i64(); - tcg_res[1] = tcg_temp_new_i64(); - - for (pass = 0; pass < 2; pass++) { - read_vec_element(s, tcg_op1, rn, pass, MO_64); - read_vec_element(s, tcg_op2, rm, pass, MO_64); - - tcg_gen_xor_i64(tcg_res[pass], tcg_op1, tcg_op2); - tcg_gen_rotri_i64(tcg_res[pass], tcg_res[pass], imm6); - } - write_vec_element(s, tcg_res[0], rd, 0, MO_64); - write_vec_element(s, tcg_res[1], rd, 1, MO_64); - - tcg_temp_free_i64(tcg_op1); - tcg_temp_free_i64(tcg_op2); - tcg_temp_free_i64(tcg_res[0]); - tcg_temp_free_i64(tcg_res[1]); + gen_gvec_xar(MO_64, vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), imm6, 16, + vec_full_reg_size(s)); } /* Crypto three-reg imm2 diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index 89437276e7..58f50abca4 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -120,5 +120,8 @@ bool disas_sve(DisasContext *, uint32_t); void gen_gvec_rax1(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_xar(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, int64_t shift, + uint32_t opr_sz, uint32_t max_sz); #endif /* TARGET_ARM_TRANSLATE_A64_H */ diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c index 658bd275da..9e990b41ed 100644 --- a/target/arm/translate-neon.c +++ b/target/arm/translate-neon.c @@ -151,24 +151,51 @@ static void neon_store_element64(int reg, int ele, MemOp size, TCGv_i64 var) } } -static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a) +static bool do_neon_ddda(DisasContext *s, int q, int vd, int vn, int vm, + int data, gen_helper_gvec_4 *fn_gvec) { - int opr_sz; - TCGv_ptr fpst; - gen_helper_gvec_3_ptr *fn_gvec_ptr; + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (((vd | vn | vm) & 0x10) && !dc_isar_feature(aa32_simd_r32, s)) { + return false; + } - if (!dc_isar_feature(aa32_vcma, s) - || (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s))) { + /* + * UNDEF accesses to odd registers for each bit of Q. + * Q will be 0b111 for all Q-reg instructions, otherwise + * when we have mixed Q- and D-reg inputs. + */ + if (((vd & 1) * 4 | (vn & 1) * 2 | (vm & 1)) & q) { return false; } + if (!vfp_access_check(s)) { + return true; + } + + int opr_sz = q ? 16 : 8; + tcg_gen_gvec_4_ool(vfp_reg_offset(1, vd), + vfp_reg_offset(1, vn), + vfp_reg_offset(1, vm), + vfp_reg_offset(1, vd), + opr_sz, opr_sz, data, fn_gvec); + return true; +} + +static bool do_neon_ddda_fpst(DisasContext *s, int q, int vd, int vn, int vm, + int data, ARMFPStatusFlavour fp_flavour, + gen_helper_gvec_4_ptr *fn_gvec_ptr) +{ /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && - ((a->vd | a->vn | a->vm) & 0x10)) { + if (((vd | vn | vm) & 0x10) && !dc_isar_feature(aa32_simd_r32, s)) { return false; } - if ((a->vn | a->vm | a->vd) & a->q) { + /* + * UNDEF accesses to odd registers for each bit of Q. + * Q will be 0b111 for all Q-reg instructions, otherwise + * when we have mixed Q- and D-reg inputs. + */ + if (((vd & 1) * 4 | (vn & 1) * 2 | (vm & 1)) & q) { return false; } @@ -176,19 +203,34 @@ static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a) return true; } - opr_sz = (1 + a->q) * 8; - fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD); - fn_gvec_ptr = (a->size == MO_16) ? - gen_helper_gvec_fcmlah : gen_helper_gvec_fcmlas; - tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), - vfp_reg_offset(1, a->vn), - vfp_reg_offset(1, a->vm), - fpst, opr_sz, opr_sz, a->rot, - fn_gvec_ptr); + int opr_sz = q ? 16 : 8; + TCGv_ptr fpst = fpstatus_ptr(fp_flavour); + + tcg_gen_gvec_4_ptr(vfp_reg_offset(1, vd), + vfp_reg_offset(1, vn), + vfp_reg_offset(1, vm), + vfp_reg_offset(1, vd), + fpst, opr_sz, opr_sz, data, fn_gvec_ptr); tcg_temp_free_ptr(fpst); return true; } +static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a) +{ + if (!dc_isar_feature(aa32_vcma, s)) { + return false; + } + if (a->size == MO_16) { + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + return do_neon_ddda_fpst(s, a->q * 7, a->vd, a->vn, a->vm, a->rot, + FPST_STD_F16, gen_helper_gvec_fcmlah); + } + return do_neon_ddda_fpst(s, a->q * 7, a->vd, a->vn, a->vm, a->rot, + FPST_STD, gen_helper_gvec_fcmlas); +} + static bool trans_VCADD(DisasContext *s, arg_VCADD *a) { int opr_sz; @@ -227,36 +269,31 @@ static bool trans_VCADD(DisasContext *s, arg_VCADD *a) return true; } -static bool trans_VDOT(DisasContext *s, arg_VDOT *a) +static bool trans_VSDOT(DisasContext *s, arg_VSDOT *a) { - int opr_sz; - gen_helper_gvec_3 *fn_gvec; - if (!dc_isar_feature(aa32_dp, s)) { return false; } + return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0, + gen_helper_gvec_sdot_b); +} - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && - ((a->vd | a->vn | a->vm) & 0x10)) { +static bool trans_VUDOT(DisasContext *s, arg_VUDOT *a) +{ + if (!dc_isar_feature(aa32_dp, s)) { return false; } + return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0, + gen_helper_gvec_udot_b); +} - if ((a->vn | a->vm | a->vd) & a->q) { +static bool trans_VUSDOT(DisasContext *s, arg_VUSDOT *a) +{ + if (!dc_isar_feature(aa32_i8mm, s)) { return false; } - - if (!vfp_access_check(s)) { - return true; - } - - opr_sz = (1 + a->q) * 8; - fn_gvec = a->u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b; - tcg_gen_gvec_3_ool(vfp_reg_offset(1, a->vd), - vfp_reg_offset(1, a->vn), - vfp_reg_offset(1, a->vm), - opr_sz, opr_sz, 0, fn_gvec); - return true; + return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0, + gen_helper_gvec_usdot_b); } static bool trans_VFML(DisasContext *s, arg_VFML *a) @@ -292,77 +329,56 @@ static bool trans_VFML(DisasContext *s, arg_VFML *a) static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a) { - gen_helper_gvec_3_ptr *fn_gvec_ptr; - int opr_sz; - TCGv_ptr fpst; + int data = (a->index << 2) | a->rot; if (!dc_isar_feature(aa32_vcma, s)) { return false; } - if (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s)) { - return false; - } - - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && - ((a->vd | a->vn | a->vm) & 0x10)) { - return false; + if (a->size == MO_16) { + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + return do_neon_ddda_fpst(s, a->q * 6, a->vd, a->vn, a->vm, data, + FPST_STD_F16, gen_helper_gvec_fcmlah_idx); } + return do_neon_ddda_fpst(s, a->q * 6, a->vd, a->vn, a->vm, data, + FPST_STD, gen_helper_gvec_fcmlas_idx); +} - if ((a->vd | a->vn) & a->q) { +static bool trans_VSDOT_scalar(DisasContext *s, arg_VSDOT_scalar *a) +{ + if (!dc_isar_feature(aa32_dp, s)) { return false; } - - if (!vfp_access_check(s)) { - return true; - } - - fn_gvec_ptr = (a->size == MO_16) ? - gen_helper_gvec_fcmlah_idx : gen_helper_gvec_fcmlas_idx; - opr_sz = (1 + a->q) * 8; - fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD); - tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), - vfp_reg_offset(1, a->vn), - vfp_reg_offset(1, a->vm), - fpst, opr_sz, opr_sz, - (a->index << 2) | a->rot, fn_gvec_ptr); - tcg_temp_free_ptr(fpst); - return true; + return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index, + gen_helper_gvec_sdot_idx_b); } -static bool trans_VDOT_scalar(DisasContext *s, arg_VDOT_scalar *a) +static bool trans_VUDOT_scalar(DisasContext *s, arg_VUDOT_scalar *a) { - gen_helper_gvec_3 *fn_gvec; - int opr_sz; - TCGv_ptr fpst; - if (!dc_isar_feature(aa32_dp, s)) { return false; } + return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index, + gen_helper_gvec_udot_idx_b); +} - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && - ((a->vd | a->vn) & 0x10)) { +static bool trans_VUSDOT_scalar(DisasContext *s, arg_VUSDOT_scalar *a) +{ + if (!dc_isar_feature(aa32_i8mm, s)) { return false; } + return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index, + gen_helper_gvec_usdot_idx_b); +} - if ((a->vd | a->vn) & a->q) { +static bool trans_VSUDOT_scalar(DisasContext *s, arg_VSUDOT_scalar *a) +{ + if (!dc_isar_feature(aa32_i8mm, s)) { return false; } - - if (!vfp_access_check(s)) { - return true; - } - - fn_gvec = a->u ? gen_helper_gvec_udot_idx_b : gen_helper_gvec_sdot_idx_b; - opr_sz = (1 + a->q) * 8; - fpst = fpstatus_ptr(FPST_STD); - tcg_gen_gvec_3_ool(vfp_reg_offset(1, a->vd), - vfp_reg_offset(1, a->vn), - vfp_reg_offset(1, a->rm), - opr_sz, opr_sz, a->index, fn_gvec); - tcg_temp_free_ptr(fpst); - return true; + return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index, + gen_helper_gvec_sudot_idx_b); } static bool trans_VFML_scalar(DisasContext *s, arg_VFML_scalar *a) @@ -4020,3 +4036,30 @@ static bool trans_VTRN(DisasContext *s, arg_2misc *a) tcg_temp_free_i32(tmp2); return true; } + +static bool trans_VSMMLA(DisasContext *s, arg_VSMMLA *a) +{ + if (!dc_isar_feature(aa32_i8mm, s)) { + return false; + } + return do_neon_ddda(s, 7, a->vd, a->vn, a->vm, 0, + gen_helper_gvec_smmla_b); +} + +static bool trans_VUMMLA(DisasContext *s, arg_VUMMLA *a) +{ + if (!dc_isar_feature(aa32_i8mm, s)) { + return false; + } + return do_neon_ddda(s, 7, a->vd, a->vn, a->vm, 0, + gen_helper_gvec_ummla_b); +} + +static bool trans_VUSMMLA(DisasContext *s, arg_VUSMMLA *a) +{ + if (!dc_isar_feature(aa32_i8mm, s)) { + return false; + } + return do_neon_ddda(s, 7, a->vd, a->vn, a->vm, 0, + gen_helper_gvec_usmmla_b); +} diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index 864ed669c4..9574efe957 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -163,6 +163,18 @@ static void gen_gvec_ool_zzz(DisasContext *s, gen_helper_gvec_3 *fn, vsz, vsz, data, fn); } +/* Invoke an out-of-line helper on 4 Zregs. */ +static void gen_gvec_ool_zzzz(DisasContext *s, gen_helper_gvec_4 *fn, + int rd, int rn, int rm, int ra, int data) +{ + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + vec_full_reg_offset(s, ra), + vsz, vsz, data, fn); +} + /* Invoke an out-of-line helper on 2 Zregs and a predicate. */ static void gen_gvec_ool_zzp(DisasContext *s, gen_helper_gvec_3 *fn, int rd, int rn, int pg, int data) @@ -205,6 +217,17 @@ static void gen_gvec_fn_zzz(DisasContext *s, GVecGen3Fn *gvec_fn, vec_full_reg_offset(s, rm), vsz, vsz); } +/* Invoke a vector expander on four Zregs. */ +static void gen_gvec_fn_zzzz(DisasContext *s, GVecGen4Fn *gvec_fn, + int esz, int rd, int rn, int rm, int ra) +{ + unsigned vsz = vec_full_reg_size(s); + gvec_fn(esz, vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + vec_full_reg_offset(s, ra), vsz, vsz); +} + /* Invoke a vector move on two Zregs. */ static bool do_mov_z(DisasContext *s, int rd, int rn) { @@ -317,6 +340,312 @@ static bool trans_BIC_zzz(DisasContext *s, arg_rrr_esz *a) return do_zzz_fn(s, a, tcg_gen_gvec_andc); } +static void gen_xar8_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + uint64_t mask = dup_const(MO_8, 0xff >> sh); + + tcg_gen_xor_i64(t, n, m); + tcg_gen_shri_i64(d, t, sh); + tcg_gen_shli_i64(t, t, 8 - sh); + tcg_gen_andi_i64(d, d, mask); + tcg_gen_andi_i64(t, t, ~mask); + tcg_gen_or_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_xar16_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + uint64_t mask = dup_const(MO_16, 0xffff >> sh); + + tcg_gen_xor_i64(t, n, m); + tcg_gen_shri_i64(d, t, sh); + tcg_gen_shli_i64(t, t, 16 - sh); + tcg_gen_andi_i64(d, d, mask); + tcg_gen_andi_i64(t, t, ~mask); + tcg_gen_or_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_xar_i32(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, int32_t sh) +{ + tcg_gen_xor_i32(d, n, m); + tcg_gen_rotri_i32(d, d, sh); +} + +static void gen_xar_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, int64_t sh) +{ + tcg_gen_xor_i64(d, n, m); + tcg_gen_rotri_i64(d, d, sh); +} + +static void gen_xar_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, int64_t sh) +{ + tcg_gen_xor_vec(vece, d, n, m); + tcg_gen_rotri_vec(vece, d, d, sh); +} + +void gen_gvec_xar(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, int64_t shift, + uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop[] = { INDEX_op_rotli_vec, 0 }; + static const GVecGen3i ops[4] = { + { .fni8 = gen_xar8_i64, + .fniv = gen_xar_vec, + .fno = gen_helper_sve2_xar_b, + .opt_opc = vecop, + .vece = MO_8 }, + { .fni8 = gen_xar16_i64, + .fniv = gen_xar_vec, + .fno = gen_helper_sve2_xar_h, + .opt_opc = vecop, + .vece = MO_16 }, + { .fni4 = gen_xar_i32, + .fniv = gen_xar_vec, + .fno = gen_helper_sve2_xar_s, + .opt_opc = vecop, + .vece = MO_32 }, + { .fni8 = gen_xar_i64, + .fniv = gen_xar_vec, + .fno = gen_helper_gvec_xar_d, + .opt_opc = vecop, + .vece = MO_64 } + }; + int esize = 8 << vece; + + /* The SVE2 range is 1 .. esize; the AdvSIMD range is 0 .. esize-1. */ + tcg_debug_assert(shift >= 0); + tcg_debug_assert(shift <= esize); + shift &= esize - 1; + + if (shift == 0) { + /* xar with no rotate devolves to xor. */ + tcg_gen_gvec_xor(vece, rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz); + } else { + tcg_gen_gvec_3i(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, + shift, &ops[vece]); + } +} + +static bool trans_XAR(DisasContext *s, arg_rrri_esz *a) +{ + if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + gen_gvec_xar(a->esz, vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), a->imm, vsz, vsz); + } + return true; +} + +static bool do_sve2_zzzz_fn(DisasContext *s, arg_rrrr_esz *a, GVecGen4Fn *fn) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_fn_zzzz(s, fn, a->esz, a->rd, a->rn, a->rm, a->ra); + } + return true; +} + +static void gen_eor3_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) +{ + tcg_gen_xor_i64(d, n, m); + tcg_gen_xor_i64(d, d, k); +} + +static void gen_eor3_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, TCGv_vec k) +{ + tcg_gen_xor_vec(vece, d, n, m); + tcg_gen_xor_vec(vece, d, d, k); +} + +static void gen_eor3(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen4 op = { + .fni8 = gen_eor3_i64, + .fniv = gen_eor3_vec, + .fno = gen_helper_sve2_eor3, + .vece = MO_64, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + }; + tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); +} + +static bool trans_EOR3(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sve2_zzzz_fn(s, a, gen_eor3); +} + +static void gen_bcax_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) +{ + tcg_gen_andc_i64(d, m, k); + tcg_gen_xor_i64(d, d, n); +} + +static void gen_bcax_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, TCGv_vec k) +{ + tcg_gen_andc_vec(vece, d, m, k); + tcg_gen_xor_vec(vece, d, d, n); +} + +static void gen_bcax(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen4 op = { + .fni8 = gen_bcax_i64, + .fniv = gen_bcax_vec, + .fno = gen_helper_sve2_bcax, + .vece = MO_64, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + }; + tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); +} + +static bool trans_BCAX(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sve2_zzzz_fn(s, a, gen_bcax); +} + +static void gen_bsl(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + /* BSL differs from the generic bitsel in argument ordering. */ + tcg_gen_gvec_bitsel(vece, d, a, n, m, oprsz, maxsz); +} + +static bool trans_BSL(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sve2_zzzz_fn(s, a, gen_bsl); +} + +static void gen_bsl1n_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) +{ + tcg_gen_andc_i64(n, k, n); + tcg_gen_andc_i64(m, m, k); + tcg_gen_or_i64(d, n, m); +} + +static void gen_bsl1n_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, TCGv_vec k) +{ + if (TCG_TARGET_HAS_bitsel_vec) { + tcg_gen_not_vec(vece, n, n); + tcg_gen_bitsel_vec(vece, d, k, n, m); + } else { + tcg_gen_andc_vec(vece, n, k, n); + tcg_gen_andc_vec(vece, m, m, k); + tcg_gen_or_vec(vece, d, n, m); + } +} + +static void gen_bsl1n(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen4 op = { + .fni8 = gen_bsl1n_i64, + .fniv = gen_bsl1n_vec, + .fno = gen_helper_sve2_bsl1n, + .vece = MO_64, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + }; + tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); +} + +static bool trans_BSL1N(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sve2_zzzz_fn(s, a, gen_bsl1n); +} + +static void gen_bsl2n_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) +{ + /* + * Z[dn] = (n & k) | (~m & ~k) + * = | ~(m | k) + */ + tcg_gen_and_i64(n, n, k); + if (TCG_TARGET_HAS_orc_i64) { + tcg_gen_or_i64(m, m, k); + tcg_gen_orc_i64(d, n, m); + } else { + tcg_gen_nor_i64(m, m, k); + tcg_gen_or_i64(d, n, m); + } +} + +static void gen_bsl2n_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, TCGv_vec k) +{ + if (TCG_TARGET_HAS_bitsel_vec) { + tcg_gen_not_vec(vece, m, m); + tcg_gen_bitsel_vec(vece, d, k, n, m); + } else { + tcg_gen_and_vec(vece, n, n, k); + tcg_gen_or_vec(vece, m, m, k); + tcg_gen_orc_vec(vece, d, n, m); + } +} + +static void gen_bsl2n(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen4 op = { + .fni8 = gen_bsl2n_i64, + .fniv = gen_bsl2n_vec, + .fno = gen_helper_sve2_bsl2n, + .vece = MO_64, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + }; + tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); +} + +static bool trans_BSL2N(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sve2_zzzz_fn(s, a, gen_bsl2n); +} + +static void gen_nbsl_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) +{ + tcg_gen_and_i64(n, n, k); + tcg_gen_andc_i64(m, m, k); + tcg_gen_nor_i64(d, n, m); +} + +static void gen_nbsl_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, TCGv_vec k) +{ + tcg_gen_bitsel_vec(vece, d, k, n, m); + tcg_gen_not_vec(vece, d, d); +} + +static void gen_nbsl(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen4 op = { + .fni8 = gen_nbsl_i64, + .fniv = gen_nbsl_vec, + .fno = gen_helper_sve2_nbsl, + .vece = MO_64, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + }; + tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); +} + +static bool trans_NBSL(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sve2_zzzz_fn(s, a, gen_nbsl); +} + /* *** SVE Integer Arithmetic - Unpredicated Group */ @@ -715,6 +1044,66 @@ static bool trans_ASRD(DisasContext *s, arg_rpri_esz *a) } } +static bool trans_SQSHL_zpzi(DisasContext *s, arg_rpri_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_sqshl_zpzi_b, gen_helper_sve2_sqshl_zpzi_h, + gen_helper_sve2_sqshl_zpzi_s, gen_helper_sve2_sqshl_zpzi_d, + }; + if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_zpzi_ool(s, a, fns[a->esz]); +} + +static bool trans_UQSHL_zpzi(DisasContext *s, arg_rpri_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_uqshl_zpzi_b, gen_helper_sve2_uqshl_zpzi_h, + gen_helper_sve2_uqshl_zpzi_s, gen_helper_sve2_uqshl_zpzi_d, + }; + if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_zpzi_ool(s, a, fns[a->esz]); +} + +static bool trans_SRSHR(DisasContext *s, arg_rpri_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_srshr_b, gen_helper_sve2_srshr_h, + gen_helper_sve2_srshr_s, gen_helper_sve2_srshr_d, + }; + if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_zpzi_ool(s, a, fns[a->esz]); +} + +static bool trans_URSHR(DisasContext *s, arg_rpri_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_urshr_b, gen_helper_sve2_urshr_h, + gen_helper_sve2_urshr_s, gen_helper_sve2_urshr_d, + }; + if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_zpzi_ool(s, a, fns[a->esz]); +} + +static bool trans_SQSHLU(DisasContext *s, arg_rpri_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_sqshlu_b, gen_helper_sve2_sqshlu_h, + gen_helper_sve2_sqshlu_s, gen_helper_sve2_sqshlu_d, + }; + if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_zpzi_ool(s, a, fns[a->esz]); +} + /* *** SVE Bitwise Shift - Predicated Group */ @@ -1937,18 +2326,18 @@ static bool trans_CPY_z_i(DisasContext *s, arg_CPY_z_i *a) *** SVE Permute Extract Group */ -static bool trans_EXT(DisasContext *s, arg_EXT *a) +static bool do_EXT(DisasContext *s, int rd, int rn, int rm, int imm) { if (!sve_access_check(s)) { return true; } unsigned vsz = vec_full_reg_size(s); - unsigned n_ofs = a->imm >= vsz ? 0 : a->imm; + unsigned n_ofs = imm >= vsz ? 0 : imm; unsigned n_siz = vsz - n_ofs; - unsigned d = vec_full_reg_offset(s, a->rd); - unsigned n = vec_full_reg_offset(s, a->rn); - unsigned m = vec_full_reg_offset(s, a->rm); + unsigned d = vec_full_reg_offset(s, rd); + unsigned n = vec_full_reg_offset(s, rn); + unsigned m = vec_full_reg_offset(s, rm); /* Use host vector move insns if we have appropriate sizes * and no unfortunate overlap. @@ -1967,6 +2356,19 @@ static bool trans_EXT(DisasContext *s, arg_EXT *a) return true; } +static bool trans_EXT(DisasContext *s, arg_EXT *a) +{ + return do_EXT(s, a->rd, a->rn, a->rm, a->imm); +} + +static bool trans_EXT_sve2(DisasContext *s, arg_rri *a) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_EXT(s, a->rd, a->rn, (a->rn + 1) % 32, a->imm); +} + /* *** SVE Permute - Unpredicated Group */ @@ -2075,6 +2477,39 @@ static bool trans_TBL(DisasContext *s, arg_rrr_esz *a) return true; } +static bool trans_TBL_sve2(DisasContext *s, arg_rrr_esz *a) +{ + static gen_helper_gvec_4 * const fns[4] = { + gen_helper_sve2_tbl_b, gen_helper_sve2_tbl_h, + gen_helper_sve2_tbl_s, gen_helper_sve2_tbl_d + }; + + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn, + (a->rn + 1) % 32, a->rm, 0); + } + return true; +} + +static bool trans_TBX(DisasContext *s, arg_rrr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_tbx_b, gen_helper_sve2_tbx_h, + gen_helper_sve2_tbx_s, gen_helper_sve2_tbx_d + }; + + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzz(s, fns[a->esz], a->rd, a->rn, a->rm, 0); + } + return true; +} + static bool trans_UNPK(DisasContext *s, arg_UNPK *a) { static gen_helper_gvec_2 * const fns[4][2] = { @@ -2249,6 +2684,32 @@ static bool trans_ZIP2_z(DisasContext *s, arg_rrr_esz *a) return do_zip(s, a, true); } +static bool do_zip_q(DisasContext *s, arg_rrr_esz *a, bool high) +{ + if (!dc_isar_feature(aa64_sve_f64mm, s)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + unsigned high_ofs = high ? QEMU_ALIGN_DOWN(vsz, 32) / 2 : 0; + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn) + high_ofs, + vec_full_reg_offset(s, a->rm) + high_ofs, + vsz, vsz, 0, gen_helper_sve2_zip_q); + } + return true; +} + +static bool trans_ZIP1_q(DisasContext *s, arg_rrr_esz *a) +{ + return do_zip_q(s, a, false); +} + +static bool trans_ZIP2_q(DisasContext *s, arg_rrr_esz *a) +{ + return do_zip_q(s, a, true); +} + static gen_helper_gvec_3 * const uzp_fns[4] = { gen_helper_sve_uzp_b, gen_helper_sve_uzp_h, gen_helper_sve_uzp_s, gen_helper_sve_uzp_d, @@ -2264,6 +2725,22 @@ static bool trans_UZP2_z(DisasContext *s, arg_rrr_esz *a) return do_zzz_data_ool(s, a, 1 << a->esz, uzp_fns[a->esz]); } +static bool trans_UZP1_q(DisasContext *s, arg_rrr_esz *a) +{ + if (!dc_isar_feature(aa64_sve_f64mm, s)) { + return false; + } + return do_zzz_data_ool(s, a, 0, gen_helper_sve2_uzp_q); +} + +static bool trans_UZP2_q(DisasContext *s, arg_rrr_esz *a) +{ + if (!dc_isar_feature(aa64_sve_f64mm, s)) { + return false; + } + return do_zzz_data_ool(s, a, 16, gen_helper_sve2_uzp_q); +} + static gen_helper_gvec_3 * const trn_fns[4] = { gen_helper_sve_trn_b, gen_helper_sve_trn_h, gen_helper_sve_trn_s, gen_helper_sve_trn_d, @@ -2279,6 +2756,22 @@ static bool trans_TRN2_z(DisasContext *s, arg_rrr_esz *a) return do_zzz_data_ool(s, a, 1 << a->esz, trn_fns[a->esz]); } +static bool trans_TRN1_q(DisasContext *s, arg_rrr_esz *a) +{ + if (!dc_isar_feature(aa64_sve_f64mm, s)) { + return false; + } + return do_zzz_data_ool(s, a, 0, gen_helper_sve2_trn_q); +} + +static bool trans_TRN2_q(DisasContext *s, arg_rrr_esz *a) +{ + if (!dc_isar_feature(aa64_sve_f64mm, s)) { + return false; + } + return do_zzz_data_ool(s, a, 16, gen_helper_sve2_trn_q); +} + /* *** SVE Permute Vector - Predicated Group */ @@ -2684,6 +3177,18 @@ static bool trans_SPLICE(DisasContext *s, arg_rprr_esz *a) return true; } +static bool trans_SPLICE_sve2(DisasContext *s, arg_rpr_esz *a) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzzp(s, gen_helper_sve_splice, + a->rd, a->rn, (a->rn + 1) % 32, a->pg, a->esz); + } + return true; +} + /* *** SVE Integer Compare - Vectors Group */ @@ -3100,7 +3605,14 @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) unsigned vsz = vec_full_reg_size(s); unsigned desc = 0; TCGCond cond; + uint64_t maxval; + /* Note that GE/HS has a->eq == 0 and GT/HI has a->eq == 1. */ + bool eq = a->eq == a->lt; + /* The greater-than conditions are all SVE2. */ + if (!a->lt && !dc_isar_feature(aa64_sve2, s)) { + return false; + } if (!sve_access_check(s)) { return true; } @@ -3123,22 +3635,42 @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) */ t0 = tcg_temp_new_i64(); t1 = tcg_temp_new_i64(); - tcg_gen_sub_i64(t0, op1, op0); + + if (a->lt) { + tcg_gen_sub_i64(t0, op1, op0); + if (a->u) { + maxval = a->sf ? UINT64_MAX : UINT32_MAX; + cond = eq ? TCG_COND_LEU : TCG_COND_LTU; + } else { + maxval = a->sf ? INT64_MAX : INT32_MAX; + cond = eq ? TCG_COND_LE : TCG_COND_LT; + } + } else { + tcg_gen_sub_i64(t0, op0, op1); + if (a->u) { + maxval = 0; + cond = eq ? TCG_COND_GEU : TCG_COND_GTU; + } else { + maxval = a->sf ? INT64_MIN : INT32_MIN; + cond = eq ? TCG_COND_GE : TCG_COND_GT; + } + } tmax = tcg_const_i64(vsz >> a->esz); - if (a->eq) { + if (eq) { /* Equality means one more iteration. */ tcg_gen_addi_i64(t0, t0, 1); - /* If op1 is max (un)signed integer (and the only time the addition - * above could overflow), then we produce an all-true predicate by - * setting the count to the vector length. This is because the - * pseudocode is described as an increment + compare loop, and the - * max integer would always compare true. + /* + * For the less-than while, if op1 is maxval (and the only time + * the addition above could overflow), then we produce an all-true + * predicate by setting the count to the vector length. This is + * because the pseudocode is described as an increment + compare + * loop, and the maximum integer would always compare true. + * Similarly, the greater-than while has the same issue with the + * minimum integer due to the decrement + compare loop. */ - tcg_gen_movi_i64(t1, (a->sf - ? (a->u ? UINT64_MAX : INT64_MAX) - : (a->u ? UINT32_MAX : INT32_MAX))); + tcg_gen_movi_i64(t1, maxval); tcg_gen_movcond_i64(TCG_COND_EQ, t0, op1, t1, tmax, t0); } @@ -3147,9 +3679,6 @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) tcg_temp_free_i64(tmax); /* Set the count to zero if the condition is false. */ - cond = (a->u - ? (a->eq ? TCG_COND_LEU : TCG_COND_LTU) - : (a->eq ? TCG_COND_LE : TCG_COND_LT)); tcg_gen_movi_i64(t1, 0); tcg_gen_movcond_i64(cond, t0, op0, op1, t0, t1); tcg_temp_free_i64(t1); @@ -3169,7 +3698,78 @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) ptr = tcg_temp_new_ptr(); tcg_gen_addi_ptr(ptr, cpu_env, pred_full_reg_offset(s, a->rd)); - gen_helper_sve_while(t2, ptr, t2, t3); + if (a->lt) { + gen_helper_sve_whilel(t2, ptr, t2, t3); + } else { + gen_helper_sve_whileg(t2, ptr, t2, t3); + } + do_pred_flags(t2); + + tcg_temp_free_ptr(ptr); + tcg_temp_free_i32(t2); + tcg_temp_free_i32(t3); + return true; +} + +static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a) +{ + TCGv_i64 op0, op1, diff, t1, tmax; + TCGv_i32 t2, t3; + TCGv_ptr ptr; + unsigned vsz = vec_full_reg_size(s); + unsigned desc = 0; + + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + op0 = read_cpu_reg(s, a->rn, 1); + op1 = read_cpu_reg(s, a->rm, 1); + + tmax = tcg_const_i64(vsz); + diff = tcg_temp_new_i64(); + + if (a->rw) { + /* WHILERW */ + /* diff = abs(op1 - op0), noting that op0/1 are unsigned. */ + t1 = tcg_temp_new_i64(); + tcg_gen_sub_i64(diff, op0, op1); + tcg_gen_sub_i64(t1, op1, op0); + tcg_gen_movcond_i64(TCG_COND_GEU, diff, op0, op1, diff, t1); + tcg_temp_free_i64(t1); + /* Round down to a multiple of ESIZE. */ + tcg_gen_andi_i64(diff, diff, -1 << a->esz); + /* If op1 == op0, diff == 0, and the condition is always true. */ + tcg_gen_movcond_i64(TCG_COND_EQ, diff, op0, op1, tmax, diff); + } else { + /* WHILEWR */ + tcg_gen_sub_i64(diff, op1, op0); + /* Round down to a multiple of ESIZE. */ + tcg_gen_andi_i64(diff, diff, -1 << a->esz); + /* If op0 >= op1, diff <= 0, the condition is always true. */ + tcg_gen_movcond_i64(TCG_COND_GEU, diff, op0, op1, tmax, diff); + } + + /* Bound to the maximum. */ + tcg_gen_umin_i64(diff, diff, tmax); + tcg_temp_free_i64(tmax); + + /* Since we're bounded, pass as a 32-bit type. */ + t2 = tcg_temp_new_i32(); + tcg_gen_extrl_i64_i32(t2, diff); + tcg_temp_free_i64(diff); + + desc = FIELD_DP32(desc, PREDDESC, OPRSZ, vsz / 8); + desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz); + t3 = tcg_const_i32(desc); + + ptr = tcg_temp_new_ptr(); + tcg_gen_addi_ptr(ptr, cpu_env, pred_full_reg_offset(s, a->rd)); + + gen_helper_sve_whilel(t2, ptr, t2, t3); do_pred_flags(t2); tcg_temp_free_ptr(ptr); @@ -3351,38 +3951,221 @@ DO_ZZI(UMIN, umin) #undef DO_ZZI -static bool trans_DOT_zzz(DisasContext *s, arg_DOT_zzz *a) +static bool trans_DOT_zzzz(DisasContext *s, arg_DOT_zzzz *a) { - static gen_helper_gvec_3 * const fns[2][2] = { + static gen_helper_gvec_4 * const fns[2][2] = { { gen_helper_gvec_sdot_b, gen_helper_gvec_sdot_h }, { gen_helper_gvec_udot_b, gen_helper_gvec_udot_h } }; if (sve_access_check(s)) { - gen_gvec_ool_zzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm, 0); + gen_gvec_ool_zzzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm, a->ra, 0); } return true; } -static bool trans_DOT_zzx(DisasContext *s, arg_DOT_zzx *a) +/* + * SVE Multiply - Indexed + */ + +static bool do_zzxz_ool(DisasContext *s, arg_rrxr_esz *a, + gen_helper_gvec_4 *fn) { - static gen_helper_gvec_3 * const fns[2][2] = { - { gen_helper_gvec_sdot_idx_b, gen_helper_gvec_sdot_idx_h }, - { gen_helper_gvec_udot_idx_b, gen_helper_gvec_udot_idx_h } - }; + if (fn == NULL) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, a->index); + } + return true; +} + +#define DO_RRXR(NAME, FUNC) \ + static bool NAME(DisasContext *s, arg_rrxr_esz *a) \ + { return do_zzxz_ool(s, a, FUNC); } +DO_RRXR(trans_SDOT_zzxw_s, gen_helper_gvec_sdot_idx_b) +DO_RRXR(trans_SDOT_zzxw_d, gen_helper_gvec_sdot_idx_h) +DO_RRXR(trans_UDOT_zzxw_s, gen_helper_gvec_udot_idx_b) +DO_RRXR(trans_UDOT_zzxw_d, gen_helper_gvec_udot_idx_h) + +static bool trans_SUDOT_zzxw_s(DisasContext *s, arg_rrxr_esz *a) +{ + if (!dc_isar_feature(aa64_sve_i8mm, s)) { + return false; + } + return do_zzxz_ool(s, a, gen_helper_gvec_sudot_idx_b); +} + +static bool trans_USDOT_zzxw_s(DisasContext *s, arg_rrxr_esz *a) +{ + if (!dc_isar_feature(aa64_sve_i8mm, s)) { + return false; + } + return do_zzxz_ool(s, a, gen_helper_gvec_usdot_idx_b); +} + +#undef DO_RRXR + +static bool do_sve2_zzz_data(DisasContext *s, int rd, int rn, int rm, int data, + gen_helper_gvec_3 *fn) +{ + if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + vsz, vsz, data, fn); + } + return true; +} + +#define DO_SVE2_RRX(NAME, FUNC) \ + static bool NAME(DisasContext *s, arg_rrx_esz *a) \ + { return do_sve2_zzz_data(s, a->rd, a->rn, a->rm, a->index, FUNC); } + +DO_SVE2_RRX(trans_MUL_zzx_h, gen_helper_gvec_mul_idx_h) +DO_SVE2_RRX(trans_MUL_zzx_s, gen_helper_gvec_mul_idx_s) +DO_SVE2_RRX(trans_MUL_zzx_d, gen_helper_gvec_mul_idx_d) + +DO_SVE2_RRX(trans_SQDMULH_zzx_h, gen_helper_sve2_sqdmulh_idx_h) +DO_SVE2_RRX(trans_SQDMULH_zzx_s, gen_helper_sve2_sqdmulh_idx_s) +DO_SVE2_RRX(trans_SQDMULH_zzx_d, gen_helper_sve2_sqdmulh_idx_d) + +DO_SVE2_RRX(trans_SQRDMULH_zzx_h, gen_helper_sve2_sqrdmulh_idx_h) +DO_SVE2_RRX(trans_SQRDMULH_zzx_s, gen_helper_sve2_sqrdmulh_idx_s) +DO_SVE2_RRX(trans_SQRDMULH_zzx_d, gen_helper_sve2_sqrdmulh_idx_d) + +#undef DO_SVE2_RRX + +#define DO_SVE2_RRX_TB(NAME, FUNC, TOP) \ + static bool NAME(DisasContext *s, arg_rrx_esz *a) \ + { \ + return do_sve2_zzz_data(s, a->rd, a->rn, a->rm, \ + (a->index << 1) | TOP, FUNC); \ + } + +DO_SVE2_RRX_TB(trans_SQDMULLB_zzx_s, gen_helper_sve2_sqdmull_idx_s, false) +DO_SVE2_RRX_TB(trans_SQDMULLB_zzx_d, gen_helper_sve2_sqdmull_idx_d, false) +DO_SVE2_RRX_TB(trans_SQDMULLT_zzx_s, gen_helper_sve2_sqdmull_idx_s, true) +DO_SVE2_RRX_TB(trans_SQDMULLT_zzx_d, gen_helper_sve2_sqdmull_idx_d, true) + +DO_SVE2_RRX_TB(trans_SMULLB_zzx_s, gen_helper_sve2_smull_idx_s, false) +DO_SVE2_RRX_TB(trans_SMULLB_zzx_d, gen_helper_sve2_smull_idx_d, false) +DO_SVE2_RRX_TB(trans_SMULLT_zzx_s, gen_helper_sve2_smull_idx_s, true) +DO_SVE2_RRX_TB(trans_SMULLT_zzx_d, gen_helper_sve2_smull_idx_d, true) + +DO_SVE2_RRX_TB(trans_UMULLB_zzx_s, gen_helper_sve2_umull_idx_s, false) +DO_SVE2_RRX_TB(trans_UMULLB_zzx_d, gen_helper_sve2_umull_idx_d, false) +DO_SVE2_RRX_TB(trans_UMULLT_zzx_s, gen_helper_sve2_umull_idx_s, true) +DO_SVE2_RRX_TB(trans_UMULLT_zzx_d, gen_helper_sve2_umull_idx_d, true) + +#undef DO_SVE2_RRX_TB + +static bool do_sve2_zzzz_data(DisasContext *s, int rd, int rn, int rm, int ra, + int data, gen_helper_gvec_4 *fn) +{ + if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) { + return false; + } if (sve_access_check(s)) { - gen_gvec_ool_zzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm, a->index); + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + vec_full_reg_offset(s, ra), + vsz, vsz, data, fn); } return true; } +#define DO_SVE2_RRXR(NAME, FUNC) \ + static bool NAME(DisasContext *s, arg_rrxr_esz *a) \ + { return do_sve2_zzzz_data(s, a->rd, a->rn, a->rm, a->ra, a->index, FUNC); } + +DO_SVE2_RRXR(trans_MLA_zzxz_h, gen_helper_gvec_mla_idx_h) +DO_SVE2_RRXR(trans_MLA_zzxz_s, gen_helper_gvec_mla_idx_s) +DO_SVE2_RRXR(trans_MLA_zzxz_d, gen_helper_gvec_mla_idx_d) + +DO_SVE2_RRXR(trans_MLS_zzxz_h, gen_helper_gvec_mls_idx_h) +DO_SVE2_RRXR(trans_MLS_zzxz_s, gen_helper_gvec_mls_idx_s) +DO_SVE2_RRXR(trans_MLS_zzxz_d, gen_helper_gvec_mls_idx_d) + +DO_SVE2_RRXR(trans_SQRDMLAH_zzxz_h, gen_helper_sve2_sqrdmlah_idx_h) +DO_SVE2_RRXR(trans_SQRDMLAH_zzxz_s, gen_helper_sve2_sqrdmlah_idx_s) +DO_SVE2_RRXR(trans_SQRDMLAH_zzxz_d, gen_helper_sve2_sqrdmlah_idx_d) + +DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_h, gen_helper_sve2_sqrdmlsh_idx_h) +DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_s, gen_helper_sve2_sqrdmlsh_idx_s) +DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_d, gen_helper_sve2_sqrdmlsh_idx_d) + +#undef DO_SVE2_RRXR + +#define DO_SVE2_RRXR_TB(NAME, FUNC, TOP) \ + static bool NAME(DisasContext *s, arg_rrxr_esz *a) \ + { \ + return do_sve2_zzzz_data(s, a->rd, a->rn, a->rm, a->rd, \ + (a->index << 1) | TOP, FUNC); \ + } + +DO_SVE2_RRXR_TB(trans_SQDMLALB_zzxw_s, gen_helper_sve2_sqdmlal_idx_s, false) +DO_SVE2_RRXR_TB(trans_SQDMLALB_zzxw_d, gen_helper_sve2_sqdmlal_idx_d, false) +DO_SVE2_RRXR_TB(trans_SQDMLALT_zzxw_s, gen_helper_sve2_sqdmlal_idx_s, true) +DO_SVE2_RRXR_TB(trans_SQDMLALT_zzxw_d, gen_helper_sve2_sqdmlal_idx_d, true) + +DO_SVE2_RRXR_TB(trans_SQDMLSLB_zzxw_s, gen_helper_sve2_sqdmlsl_idx_s, false) +DO_SVE2_RRXR_TB(trans_SQDMLSLB_zzxw_d, gen_helper_sve2_sqdmlsl_idx_d, false) +DO_SVE2_RRXR_TB(trans_SQDMLSLT_zzxw_s, gen_helper_sve2_sqdmlsl_idx_s, true) +DO_SVE2_RRXR_TB(trans_SQDMLSLT_zzxw_d, gen_helper_sve2_sqdmlsl_idx_d, true) + +DO_SVE2_RRXR_TB(trans_SMLALB_zzxw_s, gen_helper_sve2_smlal_idx_s, false) +DO_SVE2_RRXR_TB(trans_SMLALB_zzxw_d, gen_helper_sve2_smlal_idx_d, false) +DO_SVE2_RRXR_TB(trans_SMLALT_zzxw_s, gen_helper_sve2_smlal_idx_s, true) +DO_SVE2_RRXR_TB(trans_SMLALT_zzxw_d, gen_helper_sve2_smlal_idx_d, true) + +DO_SVE2_RRXR_TB(trans_UMLALB_zzxw_s, gen_helper_sve2_umlal_idx_s, false) +DO_SVE2_RRXR_TB(trans_UMLALB_zzxw_d, gen_helper_sve2_umlal_idx_d, false) +DO_SVE2_RRXR_TB(trans_UMLALT_zzxw_s, gen_helper_sve2_umlal_idx_s, true) +DO_SVE2_RRXR_TB(trans_UMLALT_zzxw_d, gen_helper_sve2_umlal_idx_d, true) + +DO_SVE2_RRXR_TB(trans_SMLSLB_zzxw_s, gen_helper_sve2_smlsl_idx_s, false) +DO_SVE2_RRXR_TB(trans_SMLSLB_zzxw_d, gen_helper_sve2_smlsl_idx_d, false) +DO_SVE2_RRXR_TB(trans_SMLSLT_zzxw_s, gen_helper_sve2_smlsl_idx_s, true) +DO_SVE2_RRXR_TB(trans_SMLSLT_zzxw_d, gen_helper_sve2_smlsl_idx_d, true) + +DO_SVE2_RRXR_TB(trans_UMLSLB_zzxw_s, gen_helper_sve2_umlsl_idx_s, false) +DO_SVE2_RRXR_TB(trans_UMLSLB_zzxw_d, gen_helper_sve2_umlsl_idx_d, false) +DO_SVE2_RRXR_TB(trans_UMLSLT_zzxw_s, gen_helper_sve2_umlsl_idx_s, true) +DO_SVE2_RRXR_TB(trans_UMLSLT_zzxw_d, gen_helper_sve2_umlsl_idx_d, true) + +#undef DO_SVE2_RRXR_TB + +#define DO_SVE2_RRXR_ROT(NAME, FUNC) \ + static bool trans_##NAME(DisasContext *s, arg_##NAME *a) \ + { \ + return do_sve2_zzzz_data(s, a->rd, a->rn, a->rm, a->ra, \ + (a->index << 2) | a->rot, FUNC); \ + } + +DO_SVE2_RRXR_ROT(CMLA_zzxz_h, gen_helper_sve2_cmla_idx_h) +DO_SVE2_RRXR_ROT(CMLA_zzxz_s, gen_helper_sve2_cmla_idx_s) + +DO_SVE2_RRXR_ROT(SQRDCMLAH_zzxz_h, gen_helper_sve2_sqrdcmlah_idx_h) +DO_SVE2_RRXR_ROT(SQRDCMLAH_zzxz_s, gen_helper_sve2_sqrdcmlah_idx_s) + +DO_SVE2_RRXR_ROT(CDOT_zzxw_s, gen_helper_sve2_cdot_idx_s) +DO_SVE2_RRXR_ROT(CDOT_zzxw_d, gen_helper_sve2_cdot_idx_d) + +#undef DO_SVE2_RRXR_ROT /* *** SVE Floating Point Multiply-Add Indexed Group */ -static bool trans_FMLA_zzxz(DisasContext *s, arg_FMLA_zzxz *a) +static bool do_FMLA_zzxz(DisasContext *s, arg_rrxr_esz *a, bool sub) { static gen_helper_gvec_4_ptr * const fns[3] = { gen_helper_gvec_fmla_idx_h, @@ -3397,13 +4180,23 @@ static bool trans_FMLA_zzxz(DisasContext *s, arg_FMLA_zzxz *a) vec_full_reg_offset(s, a->rn), vec_full_reg_offset(s, a->rm), vec_full_reg_offset(s, a->ra), - status, vsz, vsz, (a->index << 1) | a->sub, + status, vsz, vsz, (a->index << 1) | sub, fns[a->esz - 1]); tcg_temp_free_ptr(status); } return true; } +static bool trans_FMLA_zzxz(DisasContext *s, arg_FMLA_zzxz *a) +{ + return do_FMLA_zzxz(s, a, false); +} + +static bool trans_FMLS_zzxz(DisasContext *s, arg_FMLA_zzxz *a) +{ + return do_FMLA_zzxz(s, a, true); +} + /* *** SVE Floating Point Multiply Indexed Group */ @@ -3933,7 +4726,7 @@ static bool trans_FCMLA_zpzzz(DisasContext *s, arg_FCMLA_zpzzz *a) static bool trans_FCMLA_zzxz(DisasContext *s, arg_FCMLA_zzxz *a) { - static gen_helper_gvec_3_ptr * const fns[2] = { + static gen_helper_gvec_4_ptr * const fns[2] = { gen_helper_gvec_fcmlah_idx, gen_helper_gvec_fcmlas_idx, }; @@ -3943,9 +4736,10 @@ static bool trans_FCMLA_zzxz(DisasContext *s, arg_FCMLA_zzxz *a) if (sve_access_check(s)) { unsigned vsz = vec_full_reg_size(s); TCGv_ptr status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); - tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd), + tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd), vec_full_reg_offset(s, a->rn), vec_full_reg_offset(s, a->rm), + vec_full_reg_offset(s, a->ra), status, vsz, vsz, a->index * 4 + a->rot, fns[a->esz - 1]); @@ -4101,11 +4895,9 @@ static bool trans_FRINTX(DisasContext *s, arg_rpr_esz *a) return do_zpz_ptr(s, a->rd, a->rn, a->pg, a->esz == MO_16, fns[a->esz - 1]); } -static bool do_frint_mode(DisasContext *s, arg_rpr_esz *a, int mode) +static bool do_frint_mode(DisasContext *s, arg_rpr_esz *a, + int mode, gen_helper_gvec_3_ptr *fn) { - if (a->esz == 0) { - return false; - } if (sve_access_check(s)) { unsigned vsz = vec_full_reg_size(s); TCGv_i32 tmode = tcg_const_i32(mode); @@ -4116,7 +4908,7 @@ static bool do_frint_mode(DisasContext *s, arg_rpr_esz *a, int mode) tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd), vec_full_reg_offset(s, a->rn), pred_full_reg_offset(s, a->pg), - status, vsz, vsz, 0, frint_fns[a->esz - 1]); + status, vsz, vsz, 0, fn); gen_helper_set_rmode(tmode, tmode, status); tcg_temp_free_i32(tmode); @@ -4127,27 +4919,42 @@ static bool do_frint_mode(DisasContext *s, arg_rpr_esz *a, int mode) static bool trans_FRINTN(DisasContext *s, arg_rpr_esz *a) { - return do_frint_mode(s, a, float_round_nearest_even); + if (a->esz == 0) { + return false; + } + return do_frint_mode(s, a, float_round_nearest_even, frint_fns[a->esz - 1]); } static bool trans_FRINTP(DisasContext *s, arg_rpr_esz *a) { - return do_frint_mode(s, a, float_round_up); + if (a->esz == 0) { + return false; + } + return do_frint_mode(s, a, float_round_up, frint_fns[a->esz - 1]); } static bool trans_FRINTM(DisasContext *s, arg_rpr_esz *a) { - return do_frint_mode(s, a, float_round_down); + if (a->esz == 0) { + return false; + } + return do_frint_mode(s, a, float_round_down, frint_fns[a->esz - 1]); } static bool trans_FRINTZ(DisasContext *s, arg_rpr_esz *a) { - return do_frint_mode(s, a, float_round_to_zero); + if (a->esz == 0) { + return false; + } + return do_frint_mode(s, a, float_round_to_zero, frint_fns[a->esz - 1]); } static bool trans_FRINTA(DisasContext *s, arg_rpr_esz *a) { - return do_frint_mode(s, a, float_round_ties_away); + if (a->esz == 0) { + return false; + } + return do_frint_mode(s, a, float_round_ties_away, frint_fns[a->esz - 1]); } static bool trans_FRECPX(DisasContext *s, arg_rpr_esz *a) @@ -4526,128 +5333,130 @@ static void do_mem_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, tcg_temp_free_i32(t_desc); } +/* Indexed by [mte][be][dtype][nreg] */ +static gen_helper_gvec_mem * const ldr_fns[2][2][16][4] = { + { /* mte inactive, little-endian */ + { { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r, + gen_helper_sve_ld3bb_r, gen_helper_sve_ld4bb_r }, + { gen_helper_sve_ld1bhu_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bsu_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bdu_r, NULL, NULL, NULL }, + + { gen_helper_sve_ld1sds_le_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hh_le_r, gen_helper_sve_ld2hh_le_r, + gen_helper_sve_ld3hh_le_r, gen_helper_sve_ld4hh_le_r }, + { gen_helper_sve_ld1hsu_le_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hdu_le_r, NULL, NULL, NULL }, + + { gen_helper_sve_ld1hds_le_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hss_le_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1ss_le_r, gen_helper_sve_ld2ss_le_r, + gen_helper_sve_ld3ss_le_r, gen_helper_sve_ld4ss_le_r }, + { gen_helper_sve_ld1sdu_le_r, NULL, NULL, NULL }, + + { gen_helper_sve_ld1bds_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bss_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bhs_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1dd_le_r, gen_helper_sve_ld2dd_le_r, + gen_helper_sve_ld3dd_le_r, gen_helper_sve_ld4dd_le_r } }, + + /* mte inactive, big-endian */ + { { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r, + gen_helper_sve_ld3bb_r, gen_helper_sve_ld4bb_r }, + { gen_helper_sve_ld1bhu_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bsu_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bdu_r, NULL, NULL, NULL }, + + { gen_helper_sve_ld1sds_be_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hh_be_r, gen_helper_sve_ld2hh_be_r, + gen_helper_sve_ld3hh_be_r, gen_helper_sve_ld4hh_be_r }, + { gen_helper_sve_ld1hsu_be_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hdu_be_r, NULL, NULL, NULL }, + + { gen_helper_sve_ld1hds_be_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hss_be_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1ss_be_r, gen_helper_sve_ld2ss_be_r, + gen_helper_sve_ld3ss_be_r, gen_helper_sve_ld4ss_be_r }, + { gen_helper_sve_ld1sdu_be_r, NULL, NULL, NULL }, + + { gen_helper_sve_ld1bds_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bss_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bhs_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1dd_be_r, gen_helper_sve_ld2dd_be_r, + gen_helper_sve_ld3dd_be_r, gen_helper_sve_ld4dd_be_r } } }, + + { /* mte active, little-endian */ + { { gen_helper_sve_ld1bb_r_mte, + gen_helper_sve_ld2bb_r_mte, + gen_helper_sve_ld3bb_r_mte, + gen_helper_sve_ld4bb_r_mte }, + { gen_helper_sve_ld1bhu_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1bsu_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1bdu_r_mte, NULL, NULL, NULL }, + + { gen_helper_sve_ld1sds_le_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1hh_le_r_mte, + gen_helper_sve_ld2hh_le_r_mte, + gen_helper_sve_ld3hh_le_r_mte, + gen_helper_sve_ld4hh_le_r_mte }, + { gen_helper_sve_ld1hsu_le_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1hdu_le_r_mte, NULL, NULL, NULL }, + + { gen_helper_sve_ld1hds_le_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1hss_le_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1ss_le_r_mte, + gen_helper_sve_ld2ss_le_r_mte, + gen_helper_sve_ld3ss_le_r_mte, + gen_helper_sve_ld4ss_le_r_mte }, + { gen_helper_sve_ld1sdu_le_r_mte, NULL, NULL, NULL }, + + { gen_helper_sve_ld1bds_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1bss_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1bhs_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1dd_le_r_mte, + gen_helper_sve_ld2dd_le_r_mte, + gen_helper_sve_ld3dd_le_r_mte, + gen_helper_sve_ld4dd_le_r_mte } }, + + /* mte active, big-endian */ + { { gen_helper_sve_ld1bb_r_mte, + gen_helper_sve_ld2bb_r_mte, + gen_helper_sve_ld3bb_r_mte, + gen_helper_sve_ld4bb_r_mte }, + { gen_helper_sve_ld1bhu_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1bsu_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1bdu_r_mte, NULL, NULL, NULL }, + + { gen_helper_sve_ld1sds_be_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1hh_be_r_mte, + gen_helper_sve_ld2hh_be_r_mte, + gen_helper_sve_ld3hh_be_r_mte, + gen_helper_sve_ld4hh_be_r_mte }, + { gen_helper_sve_ld1hsu_be_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1hdu_be_r_mte, NULL, NULL, NULL }, + + { gen_helper_sve_ld1hds_be_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1hss_be_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1ss_be_r_mte, + gen_helper_sve_ld2ss_be_r_mte, + gen_helper_sve_ld3ss_be_r_mte, + gen_helper_sve_ld4ss_be_r_mte }, + { gen_helper_sve_ld1sdu_be_r_mte, NULL, NULL, NULL }, + + { gen_helper_sve_ld1bds_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1bss_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1bhs_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1dd_be_r_mte, + gen_helper_sve_ld2dd_be_r_mte, + gen_helper_sve_ld3dd_be_r_mte, + gen_helper_sve_ld4dd_be_r_mte } } }, +}; + static void do_ld_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, int dtype, int nreg) { - static gen_helper_gvec_mem * const fns[2][2][16][4] = { - { /* mte inactive, little-endian */ - { { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r, - gen_helper_sve_ld3bb_r, gen_helper_sve_ld4bb_r }, - { gen_helper_sve_ld1bhu_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1bsu_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1bdu_r, NULL, NULL, NULL }, - - { gen_helper_sve_ld1sds_le_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1hh_le_r, gen_helper_sve_ld2hh_le_r, - gen_helper_sve_ld3hh_le_r, gen_helper_sve_ld4hh_le_r }, - { gen_helper_sve_ld1hsu_le_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1hdu_le_r, NULL, NULL, NULL }, - - { gen_helper_sve_ld1hds_le_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1hss_le_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1ss_le_r, gen_helper_sve_ld2ss_le_r, - gen_helper_sve_ld3ss_le_r, gen_helper_sve_ld4ss_le_r }, - { gen_helper_sve_ld1sdu_le_r, NULL, NULL, NULL }, - - { gen_helper_sve_ld1bds_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1bss_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1bhs_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1dd_le_r, gen_helper_sve_ld2dd_le_r, - gen_helper_sve_ld3dd_le_r, gen_helper_sve_ld4dd_le_r } }, - - /* mte inactive, big-endian */ - { { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r, - gen_helper_sve_ld3bb_r, gen_helper_sve_ld4bb_r }, - { gen_helper_sve_ld1bhu_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1bsu_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1bdu_r, NULL, NULL, NULL }, - - { gen_helper_sve_ld1sds_be_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1hh_be_r, gen_helper_sve_ld2hh_be_r, - gen_helper_sve_ld3hh_be_r, gen_helper_sve_ld4hh_be_r }, - { gen_helper_sve_ld1hsu_be_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1hdu_be_r, NULL, NULL, NULL }, - - { gen_helper_sve_ld1hds_be_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1hss_be_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1ss_be_r, gen_helper_sve_ld2ss_be_r, - gen_helper_sve_ld3ss_be_r, gen_helper_sve_ld4ss_be_r }, - { gen_helper_sve_ld1sdu_be_r, NULL, NULL, NULL }, - - { gen_helper_sve_ld1bds_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1bss_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1bhs_r, NULL, NULL, NULL }, - { gen_helper_sve_ld1dd_be_r, gen_helper_sve_ld2dd_be_r, - gen_helper_sve_ld3dd_be_r, gen_helper_sve_ld4dd_be_r } } }, - - { /* mte active, little-endian */ - { { gen_helper_sve_ld1bb_r_mte, - gen_helper_sve_ld2bb_r_mte, - gen_helper_sve_ld3bb_r_mte, - gen_helper_sve_ld4bb_r_mte }, - { gen_helper_sve_ld1bhu_r_mte, NULL, NULL, NULL }, - { gen_helper_sve_ld1bsu_r_mte, NULL, NULL, NULL }, - { gen_helper_sve_ld1bdu_r_mte, NULL, NULL, NULL }, - - { gen_helper_sve_ld1sds_le_r_mte, NULL, NULL, NULL }, - { gen_helper_sve_ld1hh_le_r_mte, - gen_helper_sve_ld2hh_le_r_mte, - gen_helper_sve_ld3hh_le_r_mte, - gen_helper_sve_ld4hh_le_r_mte }, - { gen_helper_sve_ld1hsu_le_r_mte, NULL, NULL, NULL }, - { gen_helper_sve_ld1hdu_le_r_mte, NULL, NULL, NULL }, - - { gen_helper_sve_ld1hds_le_r_mte, NULL, NULL, NULL }, - { gen_helper_sve_ld1hss_le_r_mte, NULL, NULL, NULL }, - { gen_helper_sve_ld1ss_le_r_mte, - gen_helper_sve_ld2ss_le_r_mte, - gen_helper_sve_ld3ss_le_r_mte, - gen_helper_sve_ld4ss_le_r_mte }, - { gen_helper_sve_ld1sdu_le_r_mte, NULL, NULL, NULL }, - - { gen_helper_sve_ld1bds_r_mte, NULL, NULL, NULL }, - { gen_helper_sve_ld1bss_r_mte, NULL, NULL, NULL }, - { gen_helper_sve_ld1bhs_r_mte, NULL, NULL, NULL }, - { gen_helper_sve_ld1dd_le_r_mte, - gen_helper_sve_ld2dd_le_r_mte, - gen_helper_sve_ld3dd_le_r_mte, - gen_helper_sve_ld4dd_le_r_mte } }, - - /* mte active, big-endian */ - { { gen_helper_sve_ld1bb_r_mte, - gen_helper_sve_ld2bb_r_mte, - gen_helper_sve_ld3bb_r_mte, - gen_helper_sve_ld4bb_r_mte }, - { gen_helper_sve_ld1bhu_r_mte, NULL, NULL, NULL }, - { gen_helper_sve_ld1bsu_r_mte, NULL, NULL, NULL }, - { gen_helper_sve_ld1bdu_r_mte, NULL, NULL, NULL }, - - { gen_helper_sve_ld1sds_be_r_mte, NULL, NULL, NULL }, - { gen_helper_sve_ld1hh_be_r_mte, - gen_helper_sve_ld2hh_be_r_mte, - gen_helper_sve_ld3hh_be_r_mte, - gen_helper_sve_ld4hh_be_r_mte }, - { gen_helper_sve_ld1hsu_be_r_mte, NULL, NULL, NULL }, - { gen_helper_sve_ld1hdu_be_r_mte, NULL, NULL, NULL }, - - { gen_helper_sve_ld1hds_be_r_mte, NULL, NULL, NULL }, - { gen_helper_sve_ld1hss_be_r_mte, NULL, NULL, NULL }, - { gen_helper_sve_ld1ss_be_r_mte, - gen_helper_sve_ld2ss_be_r_mte, - gen_helper_sve_ld3ss_be_r_mte, - gen_helper_sve_ld4ss_be_r_mte }, - { gen_helper_sve_ld1sdu_be_r_mte, NULL, NULL, NULL }, - - { gen_helper_sve_ld1bds_r_mte, NULL, NULL, NULL }, - { gen_helper_sve_ld1bss_r_mte, NULL, NULL, NULL }, - { gen_helper_sve_ld1bhs_r_mte, NULL, NULL, NULL }, - { gen_helper_sve_ld1dd_be_r_mte, - gen_helper_sve_ld2dd_be_r_mte, - gen_helper_sve_ld3dd_be_r_mte, - gen_helper_sve_ld4dd_be_r_mte } } }, - }; gen_helper_gvec_mem *fn - = fns[s->mte_active[0]][s->be_data == MO_BE][dtype][nreg]; + = ldr_fns[s->mte_active[0]][s->be_data == MO_BE][dtype][nreg]; /* * While there are holes in the table, they are not @@ -4885,23 +5694,13 @@ static bool trans_LDNF1_zpri(DisasContext *s, arg_rpri_load *a) return true; } -static void do_ldrq(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz) +static void do_ldrq(DisasContext *s, int zt, int pg, TCGv_i64 addr, int dtype) { - static gen_helper_gvec_mem * const fns[2][4] = { - { gen_helper_sve_ld1bb_r, gen_helper_sve_ld1hh_le_r, - gen_helper_sve_ld1ss_le_r, gen_helper_sve_ld1dd_le_r }, - { gen_helper_sve_ld1bb_r, gen_helper_sve_ld1hh_be_r, - gen_helper_sve_ld1ss_be_r, gen_helper_sve_ld1dd_be_r }, - }; unsigned vsz = vec_full_reg_size(s); TCGv_ptr t_pg; - TCGv_i32 t_desc; - int desc, poff; + int poff; /* Load the first quadword using the normal predicated load helpers. */ - desc = simd_desc(16, 16, zt); - t_desc = tcg_const_i32(desc); - poff = pred_full_reg_offset(s, pg); if (vsz > 16) { /* @@ -4924,15 +5723,16 @@ static void do_ldrq(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz) t_pg = tcg_temp_new_ptr(); tcg_gen_addi_ptr(t_pg, cpu_env, poff); - fns[s->be_data == MO_BE][msz](cpu_env, t_pg, addr, t_desc); + gen_helper_gvec_mem *fn + = ldr_fns[s->mte_active[0]][s->be_data == MO_BE][dtype][0]; + fn(cpu_env, t_pg, addr, tcg_constant_i32(simd_desc(16, 16, zt))); tcg_temp_free_ptr(t_pg); - tcg_temp_free_i32(t_desc); /* Replicate that first quadword. */ if (vsz > 16) { - unsigned dofs = vec_full_reg_offset(s, zt); - tcg_gen_gvec_dup_mem(4, dofs + 16, dofs, vsz - 16, vsz - 16); + int doff = vec_full_reg_offset(s, zt); + tcg_gen_gvec_dup_mem(4, doff + 16, doff, vsz - 16, vsz - 16); } } @@ -4946,7 +5746,7 @@ static bool trans_LD1RQ_zprr(DisasContext *s, arg_rprr_load *a) TCGv_i64 addr = new_tmp_a64(s); tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), msz); tcg_gen_add_i64(addr, addr, cpu_reg_sp(s, a->rn)); - do_ldrq(s, a->rd, a->pg, addr, msz); + do_ldrq(s, a->rd, a->pg, addr, a->dtype); } return true; } @@ -4956,7 +5756,100 @@ static bool trans_LD1RQ_zpri(DisasContext *s, arg_rpri_load *a) if (sve_access_check(s)) { TCGv_i64 addr = new_tmp_a64(s); tcg_gen_addi_i64(addr, cpu_reg_sp(s, a->rn), a->imm * 16); - do_ldrq(s, a->rd, a->pg, addr, dtype_msz(a->dtype)); + do_ldrq(s, a->rd, a->pg, addr, a->dtype); + } + return true; +} + +static void do_ldro(DisasContext *s, int zt, int pg, TCGv_i64 addr, int dtype) +{ + unsigned vsz = vec_full_reg_size(s); + unsigned vsz_r32; + TCGv_ptr t_pg; + int poff, doff; + + if (vsz < 32) { + /* + * Note that this UNDEFINED check comes after CheckSVEEnabled() + * in the ARM pseudocode, which is the sve_access_check() done + * in our caller. We should not now return false from the caller. + */ + unallocated_encoding(s); + return; + } + + /* Load the first octaword using the normal predicated load helpers. */ + + poff = pred_full_reg_offset(s, pg); + if (vsz > 32) { + /* + * Zero-extend the first 32 bits of the predicate into a temporary. + * This avoids triggering an assert making sure we don't have bits + * set within a predicate beyond VQ, but we have lowered VQ to 2 + * for this load operation. + */ + TCGv_i64 tmp = tcg_temp_new_i64(); +#ifdef HOST_WORDS_BIGENDIAN + poff += 4; +#endif + tcg_gen_ld32u_i64(tmp, cpu_env, poff); + + poff = offsetof(CPUARMState, vfp.preg_tmp); + tcg_gen_st_i64(tmp, cpu_env, poff); + tcg_temp_free_i64(tmp); + } + + t_pg = tcg_temp_new_ptr(); + tcg_gen_addi_ptr(t_pg, cpu_env, poff); + + gen_helper_gvec_mem *fn + = ldr_fns[s->mte_active[0]][s->be_data == MO_BE][dtype][0]; + fn(cpu_env, t_pg, addr, tcg_constant_i32(simd_desc(32, 32, zt))); + + tcg_temp_free_ptr(t_pg); + + /* + * Replicate that first octaword. + * The replication happens in units of 32; if the full vector size + * is not a multiple of 32, the final bits are zeroed. + */ + doff = vec_full_reg_offset(s, zt); + vsz_r32 = QEMU_ALIGN_DOWN(vsz, 32); + if (vsz >= 64) { + tcg_gen_gvec_dup_mem(5, doff + 32, doff, vsz_r32 - 32, vsz_r32 - 32); + } + vsz -= vsz_r32; + if (vsz) { + tcg_gen_gvec_dup_imm(MO_64, doff + vsz_r32, vsz, vsz, 0); + } +} + +static bool trans_LD1RO_zprr(DisasContext *s, arg_rprr_load *a) +{ + if (!dc_isar_feature(aa64_sve_f64mm, s)) { + return false; + } + if (a->rm == 31) { + return false; + } + if (sve_access_check(s)) { + TCGv_i64 addr = new_tmp_a64(s); + tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), dtype_msz(a->dtype)); + tcg_gen_add_i64(addr, addr, cpu_reg_sp(s, a->rn)); + do_ldro(s, a->rd, a->pg, addr, a->dtype); + } + return true; +} + +static bool trans_LD1RO_zpri(DisasContext *s, arg_rpri_load *a) +{ + if (!dc_isar_feature(aa64_sve_f64mm, s)) { + return false; + } + if (sve_access_check(s)) { + TCGv_i64 addr = new_tmp_a64(s); + tcg_gen_addi_i64(addr, cpu_reg_sp(s, a->rn), a->imm * 32); + do_ldro(s, a->rd, a->pg, addr, a->dtype); } return true; } @@ -5591,6 +6484,14 @@ static bool trans_LD1_zpiz(DisasContext *s, arg_LD1_zpiz *a) return true; } +static bool trans_LDNT1_zprz(DisasContext *s, arg_LD1_zprz *a) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return trans_LD1_zprz(s, a); +} + /* Indexed by [mte][be][xs][msz]. */ static gen_helper_gvec_mem_scatter * const scatter_store_fn32[2][2][2][3] = { { /* MTE Inactive */ @@ -5743,6 +6644,14 @@ static bool trans_ST1_zpiz(DisasContext *s, arg_ST1_zpiz *a) return true; } +static bool trans_STNT1_zprz(DisasContext *s, arg_ST1_zprz *a) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return trans_ST1_zprz(s, a); +} + /* * Prefetches */ @@ -5795,3 +6704,1936 @@ static bool trans_MOVPRFX_z(DisasContext *s, arg_rpr_esz *a) { return do_movz_zpz(s, a->rd, a->rn, a->pg, a->esz, false); } + +/* + * SVE2 Integer Multiply - Unpredicated + */ + +static bool trans_MUL_zzz(DisasContext *s, arg_rrr_esz *a) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_fn_zzz(s, tcg_gen_gvec_mul, a->esz, a->rd, a->rn, a->rm); + } + return true; +} + +static bool do_sve2_zzz_ool(DisasContext *s, arg_rrr_esz *a, + gen_helper_gvec_3 *fn) +{ + if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, 0); + } + return true; +} + +static bool trans_SMULH_zzz(DisasContext *s, arg_rrr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_gvec_smulh_b, gen_helper_gvec_smulh_h, + gen_helper_gvec_smulh_s, gen_helper_gvec_smulh_d, + }; + return do_sve2_zzz_ool(s, a, fns[a->esz]); +} + +static bool trans_UMULH_zzz(DisasContext *s, arg_rrr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_gvec_umulh_b, gen_helper_gvec_umulh_h, + gen_helper_gvec_umulh_s, gen_helper_gvec_umulh_d, + }; + return do_sve2_zzz_ool(s, a, fns[a->esz]); +} + +static bool trans_PMUL_zzz(DisasContext *s, arg_rrr_esz *a) +{ + return do_sve2_zzz_ool(s, a, gen_helper_gvec_pmul_b); +} + +static bool trans_SQDMULH_zzz(DisasContext *s, arg_rrr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_sqdmulh_b, gen_helper_sve2_sqdmulh_h, + gen_helper_sve2_sqdmulh_s, gen_helper_sve2_sqdmulh_d, + }; + return do_sve2_zzz_ool(s, a, fns[a->esz]); +} + +static bool trans_SQRDMULH_zzz(DisasContext *s, arg_rrr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_sqrdmulh_b, gen_helper_sve2_sqrdmulh_h, + gen_helper_sve2_sqrdmulh_s, gen_helper_sve2_sqrdmulh_d, + }; + return do_sve2_zzz_ool(s, a, fns[a->esz]); +} + +/* + * SVE2 Integer - Predicated + */ + +static bool do_sve2_zpzz_ool(DisasContext *s, arg_rprr_esz *a, + gen_helper_gvec_4 *fn) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_zpzz_ool(s, a, fn); +} + +static bool trans_SADALP_zpzz(DisasContext *s, arg_rprr_esz *a) +{ + static gen_helper_gvec_4 * const fns[3] = { + gen_helper_sve2_sadalp_zpzz_h, + gen_helper_sve2_sadalp_zpzz_s, + gen_helper_sve2_sadalp_zpzz_d, + }; + if (a->esz == 0) { + return false; + } + return do_sve2_zpzz_ool(s, a, fns[a->esz - 1]); +} + +static bool trans_UADALP_zpzz(DisasContext *s, arg_rprr_esz *a) +{ + static gen_helper_gvec_4 * const fns[3] = { + gen_helper_sve2_uadalp_zpzz_h, + gen_helper_sve2_uadalp_zpzz_s, + gen_helper_sve2_uadalp_zpzz_d, + }; + if (a->esz == 0) { + return false; + } + return do_sve2_zpzz_ool(s, a, fns[a->esz - 1]); +} + +/* + * SVE2 integer unary operations (predicated) + */ + +static bool do_sve2_zpz_ool(DisasContext *s, arg_rpr_esz *a, + gen_helper_gvec_3 *fn) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_zpz_ool(s, a, fn); +} + +static bool trans_URECPE(DisasContext *s, arg_rpr_esz *a) +{ + if (a->esz != 2) { + return false; + } + return do_sve2_zpz_ool(s, a, gen_helper_sve2_urecpe_s); +} + +static bool trans_URSQRTE(DisasContext *s, arg_rpr_esz *a) +{ + if (a->esz != 2) { + return false; + } + return do_sve2_zpz_ool(s, a, gen_helper_sve2_ursqrte_s); +} + +static bool trans_SQABS(DisasContext *s, arg_rpr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_sqabs_b, gen_helper_sve2_sqabs_h, + gen_helper_sve2_sqabs_s, gen_helper_sve2_sqabs_d, + }; + return do_sve2_zpz_ool(s, a, fns[a->esz]); +} + +static bool trans_SQNEG(DisasContext *s, arg_rpr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_sqneg_b, gen_helper_sve2_sqneg_h, + gen_helper_sve2_sqneg_s, gen_helper_sve2_sqneg_d, + }; + return do_sve2_zpz_ool(s, a, fns[a->esz]); +} + +#define DO_SVE2_ZPZZ(NAME, name) \ +static bool trans_##NAME(DisasContext *s, arg_rprr_esz *a) \ +{ \ + static gen_helper_gvec_4 * const fns[4] = { \ + gen_helper_sve2_##name##_zpzz_b, gen_helper_sve2_##name##_zpzz_h, \ + gen_helper_sve2_##name##_zpzz_s, gen_helper_sve2_##name##_zpzz_d, \ + }; \ + return do_sve2_zpzz_ool(s, a, fns[a->esz]); \ +} + +DO_SVE2_ZPZZ(SQSHL, sqshl) +DO_SVE2_ZPZZ(SQRSHL, sqrshl) +DO_SVE2_ZPZZ(SRSHL, srshl) + +DO_SVE2_ZPZZ(UQSHL, uqshl) +DO_SVE2_ZPZZ(UQRSHL, uqrshl) +DO_SVE2_ZPZZ(URSHL, urshl) + +DO_SVE2_ZPZZ(SHADD, shadd) +DO_SVE2_ZPZZ(SRHADD, srhadd) +DO_SVE2_ZPZZ(SHSUB, shsub) + +DO_SVE2_ZPZZ(UHADD, uhadd) +DO_SVE2_ZPZZ(URHADD, urhadd) +DO_SVE2_ZPZZ(UHSUB, uhsub) + +DO_SVE2_ZPZZ(ADDP, addp) +DO_SVE2_ZPZZ(SMAXP, smaxp) +DO_SVE2_ZPZZ(UMAXP, umaxp) +DO_SVE2_ZPZZ(SMINP, sminp) +DO_SVE2_ZPZZ(UMINP, uminp) + +DO_SVE2_ZPZZ(SQADD_zpzz, sqadd) +DO_SVE2_ZPZZ(UQADD_zpzz, uqadd) +DO_SVE2_ZPZZ(SQSUB_zpzz, sqsub) +DO_SVE2_ZPZZ(UQSUB_zpzz, uqsub) +DO_SVE2_ZPZZ(SUQADD, suqadd) +DO_SVE2_ZPZZ(USQADD, usqadd) + +/* + * SVE2 Widening Integer Arithmetic + */ + +static bool do_sve2_zzw_ool(DisasContext *s, arg_rrr_esz *a, + gen_helper_gvec_3 *fn, int data) +{ + if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vsz, vsz, data, fn); + } + return true; +} + +#define DO_SVE2_ZZZ_TB(NAME, name, SEL1, SEL2) \ +static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \ +{ \ + static gen_helper_gvec_3 * const fns[4] = { \ + NULL, gen_helper_sve2_##name##_h, \ + gen_helper_sve2_##name##_s, gen_helper_sve2_##name##_d, \ + }; \ + return do_sve2_zzw_ool(s, a, fns[a->esz], (SEL2 << 1) | SEL1); \ +} + +DO_SVE2_ZZZ_TB(SADDLB, saddl, false, false) +DO_SVE2_ZZZ_TB(SSUBLB, ssubl, false, false) +DO_SVE2_ZZZ_TB(SABDLB, sabdl, false, false) + +DO_SVE2_ZZZ_TB(UADDLB, uaddl, false, false) +DO_SVE2_ZZZ_TB(USUBLB, usubl, false, false) +DO_SVE2_ZZZ_TB(UABDLB, uabdl, false, false) + +DO_SVE2_ZZZ_TB(SADDLT, saddl, true, true) +DO_SVE2_ZZZ_TB(SSUBLT, ssubl, true, true) +DO_SVE2_ZZZ_TB(SABDLT, sabdl, true, true) + +DO_SVE2_ZZZ_TB(UADDLT, uaddl, true, true) +DO_SVE2_ZZZ_TB(USUBLT, usubl, true, true) +DO_SVE2_ZZZ_TB(UABDLT, uabdl, true, true) + +DO_SVE2_ZZZ_TB(SADDLBT, saddl, false, true) +DO_SVE2_ZZZ_TB(SSUBLBT, ssubl, false, true) +DO_SVE2_ZZZ_TB(SSUBLTB, ssubl, true, false) + +DO_SVE2_ZZZ_TB(SQDMULLB_zzz, sqdmull_zzz, false, false) +DO_SVE2_ZZZ_TB(SQDMULLT_zzz, sqdmull_zzz, true, true) + +DO_SVE2_ZZZ_TB(SMULLB_zzz, smull_zzz, false, false) +DO_SVE2_ZZZ_TB(SMULLT_zzz, smull_zzz, true, true) + +DO_SVE2_ZZZ_TB(UMULLB_zzz, umull_zzz, false, false) +DO_SVE2_ZZZ_TB(UMULLT_zzz, umull_zzz, true, true) + +static bool do_eor_tb(DisasContext *s, arg_rrr_esz *a, bool sel1) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_eoril_b, gen_helper_sve2_eoril_h, + gen_helper_sve2_eoril_s, gen_helper_sve2_eoril_d, + }; + return do_sve2_zzw_ool(s, a, fns[a->esz], (!sel1 << 1) | sel1); +} + +static bool trans_EORBT(DisasContext *s, arg_rrr_esz *a) +{ + return do_eor_tb(s, a, false); +} + +static bool trans_EORTB(DisasContext *s, arg_rrr_esz *a) +{ + return do_eor_tb(s, a, true); +} + +static bool do_trans_pmull(DisasContext *s, arg_rrr_esz *a, bool sel) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_gvec_pmull_q, gen_helper_sve2_pmull_h, + NULL, gen_helper_sve2_pmull_d, + }; + if (a->esz == 0 && !dc_isar_feature(aa64_sve2_pmull128, s)) { + return false; + } + return do_sve2_zzw_ool(s, a, fns[a->esz], sel); +} + +static bool trans_PMULLB(DisasContext *s, arg_rrr_esz *a) +{ + return do_trans_pmull(s, a, false); +} + +static bool trans_PMULLT(DisasContext *s, arg_rrr_esz *a) +{ + return do_trans_pmull(s, a, true); +} + +#define DO_SVE2_ZZZ_WTB(NAME, name, SEL2) \ +static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \ +{ \ + static gen_helper_gvec_3 * const fns[4] = { \ + NULL, gen_helper_sve2_##name##_h, \ + gen_helper_sve2_##name##_s, gen_helper_sve2_##name##_d, \ + }; \ + return do_sve2_zzw_ool(s, a, fns[a->esz], SEL2); \ +} + +DO_SVE2_ZZZ_WTB(SADDWB, saddw, false) +DO_SVE2_ZZZ_WTB(SADDWT, saddw, true) +DO_SVE2_ZZZ_WTB(SSUBWB, ssubw, false) +DO_SVE2_ZZZ_WTB(SSUBWT, ssubw, true) + +DO_SVE2_ZZZ_WTB(UADDWB, uaddw, false) +DO_SVE2_ZZZ_WTB(UADDWT, uaddw, true) +DO_SVE2_ZZZ_WTB(USUBWB, usubw, false) +DO_SVE2_ZZZ_WTB(USUBWT, usubw, true) + +static void gen_sshll_vec(unsigned vece, TCGv_vec d, TCGv_vec n, int64_t imm) +{ + int top = imm & 1; + int shl = imm >> 1; + int halfbits = 4 << vece; + + if (top) { + if (shl == halfbits) { + TCGv_vec t = tcg_temp_new_vec_matching(d); + tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(halfbits, halfbits)); + tcg_gen_and_vec(vece, d, n, t); + tcg_temp_free_vec(t); + } else { + tcg_gen_sari_vec(vece, d, n, halfbits); + tcg_gen_shli_vec(vece, d, d, shl); + } + } else { + tcg_gen_shli_vec(vece, d, n, halfbits); + tcg_gen_sari_vec(vece, d, d, halfbits - shl); + } +} + +static void gen_ushll_i64(unsigned vece, TCGv_i64 d, TCGv_i64 n, int imm) +{ + int halfbits = 4 << vece; + int top = imm & 1; + int shl = (imm >> 1); + int shift; + uint64_t mask; + + mask = MAKE_64BIT_MASK(0, halfbits); + mask <<= shl; + mask = dup_const(vece, mask); + + shift = shl - top * halfbits; + if (shift < 0) { + tcg_gen_shri_i64(d, n, -shift); + } else { + tcg_gen_shli_i64(d, n, shift); + } + tcg_gen_andi_i64(d, d, mask); +} + +static void gen_ushll16_i64(TCGv_i64 d, TCGv_i64 n, int64_t imm) +{ + gen_ushll_i64(MO_16, d, n, imm); +} + +static void gen_ushll32_i64(TCGv_i64 d, TCGv_i64 n, int64_t imm) +{ + gen_ushll_i64(MO_32, d, n, imm); +} + +static void gen_ushll64_i64(TCGv_i64 d, TCGv_i64 n, int64_t imm) +{ + gen_ushll_i64(MO_64, d, n, imm); +} + +static void gen_ushll_vec(unsigned vece, TCGv_vec d, TCGv_vec n, int64_t imm) +{ + int halfbits = 4 << vece; + int top = imm & 1; + int shl = imm >> 1; + + if (top) { + if (shl == halfbits) { + TCGv_vec t = tcg_temp_new_vec_matching(d); + tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(halfbits, halfbits)); + tcg_gen_and_vec(vece, d, n, t); + tcg_temp_free_vec(t); + } else { + tcg_gen_shri_vec(vece, d, n, halfbits); + tcg_gen_shli_vec(vece, d, d, shl); + } + } else { + if (shl == 0) { + TCGv_vec t = tcg_temp_new_vec_matching(d); + tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits)); + tcg_gen_and_vec(vece, d, n, t); + tcg_temp_free_vec(t); + } else { + tcg_gen_shli_vec(vece, d, n, halfbits); + tcg_gen_shri_vec(vece, d, d, halfbits - shl); + } + } +} + +static bool do_sve2_shll_tb(DisasContext *s, arg_rri_esz *a, + bool sel, bool uns) +{ + static const TCGOpcode sshll_list[] = { + INDEX_op_shli_vec, INDEX_op_sari_vec, 0 + }; + static const TCGOpcode ushll_list[] = { + INDEX_op_shli_vec, INDEX_op_shri_vec, 0 + }; + static const GVecGen2i ops[2][3] = { + { { .fniv = gen_sshll_vec, + .opt_opc = sshll_list, + .fno = gen_helper_sve2_sshll_h, + .vece = MO_16 }, + { .fniv = gen_sshll_vec, + .opt_opc = sshll_list, + .fno = gen_helper_sve2_sshll_s, + .vece = MO_32 }, + { .fniv = gen_sshll_vec, + .opt_opc = sshll_list, + .fno = gen_helper_sve2_sshll_d, + .vece = MO_64 } }, + { { .fni8 = gen_ushll16_i64, + .fniv = gen_ushll_vec, + .opt_opc = ushll_list, + .fno = gen_helper_sve2_ushll_h, + .vece = MO_16 }, + { .fni8 = gen_ushll32_i64, + .fniv = gen_ushll_vec, + .opt_opc = ushll_list, + .fno = gen_helper_sve2_ushll_s, + .vece = MO_32 }, + { .fni8 = gen_ushll64_i64, + .fniv = gen_ushll_vec, + .opt_opc = ushll_list, + .fno = gen_helper_sve2_ushll_d, + .vece = MO_64 } }, + }; + + if (a->esz < 0 || a->esz > 2 || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_2i(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vsz, vsz, (a->imm << 1) | sel, + &ops[uns][a->esz]); + } + return true; +} + +static bool trans_SSHLLB(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_shll_tb(s, a, false, false); +} + +static bool trans_SSHLLT(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_shll_tb(s, a, true, false); +} + +static bool trans_USHLLB(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_shll_tb(s, a, false, true); +} + +static bool trans_USHLLT(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_shll_tb(s, a, true, true); +} + +static bool trans_BEXT(DisasContext *s, arg_rrr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_bext_b, gen_helper_sve2_bext_h, + gen_helper_sve2_bext_s, gen_helper_sve2_bext_d, + }; + if (!dc_isar_feature(aa64_sve2_bitperm, s)) { + return false; + } + return do_sve2_zzw_ool(s, a, fns[a->esz], 0); +} + +static bool trans_BDEP(DisasContext *s, arg_rrr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_bdep_b, gen_helper_sve2_bdep_h, + gen_helper_sve2_bdep_s, gen_helper_sve2_bdep_d, + }; + if (!dc_isar_feature(aa64_sve2_bitperm, s)) { + return false; + } + return do_sve2_zzw_ool(s, a, fns[a->esz], 0); +} + +static bool trans_BGRP(DisasContext *s, arg_rrr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_bgrp_b, gen_helper_sve2_bgrp_h, + gen_helper_sve2_bgrp_s, gen_helper_sve2_bgrp_d, + }; + if (!dc_isar_feature(aa64_sve2_bitperm, s)) { + return false; + } + return do_sve2_zzw_ool(s, a, fns[a->esz], 0); +} + +static bool do_cadd(DisasContext *s, arg_rrr_esz *a, bool sq, bool rot) +{ + static gen_helper_gvec_3 * const fns[2][4] = { + { gen_helper_sve2_cadd_b, gen_helper_sve2_cadd_h, + gen_helper_sve2_cadd_s, gen_helper_sve2_cadd_d }, + { gen_helper_sve2_sqcadd_b, gen_helper_sve2_sqcadd_h, + gen_helper_sve2_sqcadd_s, gen_helper_sve2_sqcadd_d }, + }; + return do_sve2_zzw_ool(s, a, fns[sq][a->esz], rot); +} + +static bool trans_CADD_rot90(DisasContext *s, arg_rrr_esz *a) +{ + return do_cadd(s, a, false, false); +} + +static bool trans_CADD_rot270(DisasContext *s, arg_rrr_esz *a) +{ + return do_cadd(s, a, false, true); +} + +static bool trans_SQCADD_rot90(DisasContext *s, arg_rrr_esz *a) +{ + return do_cadd(s, a, true, false); +} + +static bool trans_SQCADD_rot270(DisasContext *s, arg_rrr_esz *a) +{ + return do_cadd(s, a, true, true); +} + +static bool do_sve2_zzzz_ool(DisasContext *s, arg_rrrr_esz *a, + gen_helper_gvec_4 *fn, int data) +{ + if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, data); + } + return true; +} + +static bool do_abal(DisasContext *s, arg_rrrr_esz *a, bool uns, bool sel) +{ + static gen_helper_gvec_4 * const fns[2][4] = { + { NULL, gen_helper_sve2_sabal_h, + gen_helper_sve2_sabal_s, gen_helper_sve2_sabal_d }, + { NULL, gen_helper_sve2_uabal_h, + gen_helper_sve2_uabal_s, gen_helper_sve2_uabal_d }, + }; + return do_sve2_zzzz_ool(s, a, fns[uns][a->esz], sel); +} + +static bool trans_SABALB(DisasContext *s, arg_rrrr_esz *a) +{ + return do_abal(s, a, false, false); +} + +static bool trans_SABALT(DisasContext *s, arg_rrrr_esz *a) +{ + return do_abal(s, a, false, true); +} + +static bool trans_UABALB(DisasContext *s, arg_rrrr_esz *a) +{ + return do_abal(s, a, true, false); +} + +static bool trans_UABALT(DisasContext *s, arg_rrrr_esz *a) +{ + return do_abal(s, a, true, true); +} + +static bool do_adcl(DisasContext *s, arg_rrrr_esz *a, bool sel) +{ + static gen_helper_gvec_4 * const fns[2] = { + gen_helper_sve2_adcl_s, + gen_helper_sve2_adcl_d, + }; + /* + * Note that in this case the ESZ field encodes both size and sign. + * Split out 'subtract' into bit 1 of the data field for the helper. + */ + return do_sve2_zzzz_ool(s, a, fns[a->esz & 1], (a->esz & 2) | sel); +} + +static bool trans_ADCLB(DisasContext *s, arg_rrrr_esz *a) +{ + return do_adcl(s, a, false); +} + +static bool trans_ADCLT(DisasContext *s, arg_rrrr_esz *a) +{ + return do_adcl(s, a, true); +} + +static bool do_sve2_fn2i(DisasContext *s, arg_rri_esz *a, GVecGen2iFn *fn) +{ + if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + unsigned rd_ofs = vec_full_reg_offset(s, a->rd); + unsigned rn_ofs = vec_full_reg_offset(s, a->rn); + fn(a->esz, rd_ofs, rn_ofs, a->imm, vsz, vsz); + } + return true; +} + +static bool trans_SSRA(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_fn2i(s, a, gen_gvec_ssra); +} + +static bool trans_USRA(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_fn2i(s, a, gen_gvec_usra); +} + +static bool trans_SRSRA(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_fn2i(s, a, gen_gvec_srsra); +} + +static bool trans_URSRA(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_fn2i(s, a, gen_gvec_ursra); +} + +static bool trans_SRI(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_fn2i(s, a, gen_gvec_sri); +} + +static bool trans_SLI(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_fn2i(s, a, gen_gvec_sli); +} + +static bool do_sve2_fn_zzz(DisasContext *s, arg_rrr_esz *a, GVecGen3Fn *fn) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_fn_zzz(s, fn, a->esz, a->rd, a->rn, a->rm); + } + return true; +} + +static bool trans_SABA(DisasContext *s, arg_rrr_esz *a) +{ + return do_sve2_fn_zzz(s, a, gen_gvec_saba); +} + +static bool trans_UABA(DisasContext *s, arg_rrr_esz *a) +{ + return do_sve2_fn_zzz(s, a, gen_gvec_uaba); +} + +static bool do_sve2_narrow_extract(DisasContext *s, arg_rri_esz *a, + const GVecGen2 ops[3]) +{ + if (a->esz < 0 || a->esz > MO_32 || a->imm != 0 || + !dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_2(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vsz, vsz, &ops[a->esz]); + } + return true; +} + +static const TCGOpcode sqxtn_list[] = { + INDEX_op_shli_vec, INDEX_op_smin_vec, INDEX_op_smax_vec, 0 +}; + +static void gen_sqxtnb_vec(unsigned vece, TCGv_vec d, TCGv_vec n) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + int64_t mask = (1ull << halfbits) - 1; + int64_t min = -1ull << (halfbits - 1); + int64_t max = -min - 1; + + tcg_gen_dupi_vec(vece, t, min); + tcg_gen_smax_vec(vece, d, n, t); + tcg_gen_dupi_vec(vece, t, max); + tcg_gen_smin_vec(vece, d, d, t); + tcg_gen_dupi_vec(vece, t, mask); + tcg_gen_and_vec(vece, d, d, t); + tcg_temp_free_vec(t); +} + +static bool trans_SQXTNB(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2 ops[3] = { + { .fniv = gen_sqxtnb_vec, + .opt_opc = sqxtn_list, + .fno = gen_helper_sve2_sqxtnb_h, + .vece = MO_16 }, + { .fniv = gen_sqxtnb_vec, + .opt_opc = sqxtn_list, + .fno = gen_helper_sve2_sqxtnb_s, + .vece = MO_32 }, + { .fniv = gen_sqxtnb_vec, + .opt_opc = sqxtn_list, + .fno = gen_helper_sve2_sqxtnb_d, + .vece = MO_64 }, + }; + return do_sve2_narrow_extract(s, a, ops); +} + +static void gen_sqxtnt_vec(unsigned vece, TCGv_vec d, TCGv_vec n) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + int64_t mask = (1ull << halfbits) - 1; + int64_t min = -1ull << (halfbits - 1); + int64_t max = -min - 1; + + tcg_gen_dupi_vec(vece, t, min); + tcg_gen_smax_vec(vece, n, n, t); + tcg_gen_dupi_vec(vece, t, max); + tcg_gen_smin_vec(vece, n, n, t); + tcg_gen_shli_vec(vece, n, n, halfbits); + tcg_gen_dupi_vec(vece, t, mask); + tcg_gen_bitsel_vec(vece, d, t, d, n); + tcg_temp_free_vec(t); +} + +static bool trans_SQXTNT(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2 ops[3] = { + { .fniv = gen_sqxtnt_vec, + .opt_opc = sqxtn_list, + .load_dest = true, + .fno = gen_helper_sve2_sqxtnt_h, + .vece = MO_16 }, + { .fniv = gen_sqxtnt_vec, + .opt_opc = sqxtn_list, + .load_dest = true, + .fno = gen_helper_sve2_sqxtnt_s, + .vece = MO_32 }, + { .fniv = gen_sqxtnt_vec, + .opt_opc = sqxtn_list, + .load_dest = true, + .fno = gen_helper_sve2_sqxtnt_d, + .vece = MO_64 }, + }; + return do_sve2_narrow_extract(s, a, ops); +} + +static const TCGOpcode uqxtn_list[] = { + INDEX_op_shli_vec, INDEX_op_umin_vec, 0 +}; + +static void gen_uqxtnb_vec(unsigned vece, TCGv_vec d, TCGv_vec n) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + int64_t max = (1ull << halfbits) - 1; + + tcg_gen_dupi_vec(vece, t, max); + tcg_gen_umin_vec(vece, d, n, t); + tcg_temp_free_vec(t); +} + +static bool trans_UQXTNB(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2 ops[3] = { + { .fniv = gen_uqxtnb_vec, + .opt_opc = uqxtn_list, + .fno = gen_helper_sve2_uqxtnb_h, + .vece = MO_16 }, + { .fniv = gen_uqxtnb_vec, + .opt_opc = uqxtn_list, + .fno = gen_helper_sve2_uqxtnb_s, + .vece = MO_32 }, + { .fniv = gen_uqxtnb_vec, + .opt_opc = uqxtn_list, + .fno = gen_helper_sve2_uqxtnb_d, + .vece = MO_64 }, + }; + return do_sve2_narrow_extract(s, a, ops); +} + +static void gen_uqxtnt_vec(unsigned vece, TCGv_vec d, TCGv_vec n) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + int64_t max = (1ull << halfbits) - 1; + + tcg_gen_dupi_vec(vece, t, max); + tcg_gen_umin_vec(vece, n, n, t); + tcg_gen_shli_vec(vece, n, n, halfbits); + tcg_gen_bitsel_vec(vece, d, t, d, n); + tcg_temp_free_vec(t); +} + +static bool trans_UQXTNT(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2 ops[3] = { + { .fniv = gen_uqxtnt_vec, + .opt_opc = uqxtn_list, + .load_dest = true, + .fno = gen_helper_sve2_uqxtnt_h, + .vece = MO_16 }, + { .fniv = gen_uqxtnt_vec, + .opt_opc = uqxtn_list, + .load_dest = true, + .fno = gen_helper_sve2_uqxtnt_s, + .vece = MO_32 }, + { .fniv = gen_uqxtnt_vec, + .opt_opc = uqxtn_list, + .load_dest = true, + .fno = gen_helper_sve2_uqxtnt_d, + .vece = MO_64 }, + }; + return do_sve2_narrow_extract(s, a, ops); +} + +static const TCGOpcode sqxtun_list[] = { + INDEX_op_shli_vec, INDEX_op_umin_vec, INDEX_op_smax_vec, 0 +}; + +static void gen_sqxtunb_vec(unsigned vece, TCGv_vec d, TCGv_vec n) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + int64_t max = (1ull << halfbits) - 1; + + tcg_gen_dupi_vec(vece, t, 0); + tcg_gen_smax_vec(vece, d, n, t); + tcg_gen_dupi_vec(vece, t, max); + tcg_gen_umin_vec(vece, d, d, t); + tcg_temp_free_vec(t); +} + +static bool trans_SQXTUNB(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2 ops[3] = { + { .fniv = gen_sqxtunb_vec, + .opt_opc = sqxtun_list, + .fno = gen_helper_sve2_sqxtunb_h, + .vece = MO_16 }, + { .fniv = gen_sqxtunb_vec, + .opt_opc = sqxtun_list, + .fno = gen_helper_sve2_sqxtunb_s, + .vece = MO_32 }, + { .fniv = gen_sqxtunb_vec, + .opt_opc = sqxtun_list, + .fno = gen_helper_sve2_sqxtunb_d, + .vece = MO_64 }, + }; + return do_sve2_narrow_extract(s, a, ops); +} + +static void gen_sqxtunt_vec(unsigned vece, TCGv_vec d, TCGv_vec n) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + int64_t max = (1ull << halfbits) - 1; + + tcg_gen_dupi_vec(vece, t, 0); + tcg_gen_smax_vec(vece, n, n, t); + tcg_gen_dupi_vec(vece, t, max); + tcg_gen_umin_vec(vece, n, n, t); + tcg_gen_shli_vec(vece, n, n, halfbits); + tcg_gen_bitsel_vec(vece, d, t, d, n); + tcg_temp_free_vec(t); +} + +static bool trans_SQXTUNT(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2 ops[3] = { + { .fniv = gen_sqxtunt_vec, + .opt_opc = sqxtun_list, + .load_dest = true, + .fno = gen_helper_sve2_sqxtunt_h, + .vece = MO_16 }, + { .fniv = gen_sqxtunt_vec, + .opt_opc = sqxtun_list, + .load_dest = true, + .fno = gen_helper_sve2_sqxtunt_s, + .vece = MO_32 }, + { .fniv = gen_sqxtunt_vec, + .opt_opc = sqxtun_list, + .load_dest = true, + .fno = gen_helper_sve2_sqxtunt_d, + .vece = MO_64 }, + }; + return do_sve2_narrow_extract(s, a, ops); +} + +static bool do_sve2_shr_narrow(DisasContext *s, arg_rri_esz *a, + const GVecGen2i ops[3]) +{ + if (a->esz < 0 || a->esz > MO_32 || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + assert(a->imm > 0 && a->imm <= (8 << a->esz)); + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_2i(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vsz, vsz, a->imm, &ops[a->esz]); + } + return true; +} + +static void gen_shrnb_i64(unsigned vece, TCGv_i64 d, TCGv_i64 n, int shr) +{ + int halfbits = 4 << vece; + uint64_t mask = dup_const(vece, MAKE_64BIT_MASK(0, halfbits)); + + tcg_gen_shri_i64(d, n, shr); + tcg_gen_andi_i64(d, d, mask); +} + +static void gen_shrnb16_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr) +{ + gen_shrnb_i64(MO_16, d, n, shr); +} + +static void gen_shrnb32_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr) +{ + gen_shrnb_i64(MO_32, d, n, shr); +} + +static void gen_shrnb64_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr) +{ + gen_shrnb_i64(MO_64, d, n, shr); +} + +static void gen_shrnb_vec(unsigned vece, TCGv_vec d, TCGv_vec n, int64_t shr) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + uint64_t mask = MAKE_64BIT_MASK(0, halfbits); + + tcg_gen_shri_vec(vece, n, n, shr); + tcg_gen_dupi_vec(vece, t, mask); + tcg_gen_and_vec(vece, d, n, t); + tcg_temp_free_vec(t); +} + +static bool trans_SHRNB(DisasContext *s, arg_rri_esz *a) +{ + static const TCGOpcode vec_list[] = { INDEX_op_shri_vec, 0 }; + static const GVecGen2i ops[3] = { + { .fni8 = gen_shrnb16_i64, + .fniv = gen_shrnb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_shrnb_h, + .vece = MO_16 }, + { .fni8 = gen_shrnb32_i64, + .fniv = gen_shrnb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_shrnb_s, + .vece = MO_32 }, + { .fni8 = gen_shrnb64_i64, + .fniv = gen_shrnb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_shrnb_d, + .vece = MO_64 }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static void gen_shrnt_i64(unsigned vece, TCGv_i64 d, TCGv_i64 n, int shr) +{ + int halfbits = 4 << vece; + uint64_t mask = dup_const(vece, MAKE_64BIT_MASK(0, halfbits)); + + tcg_gen_shli_i64(n, n, halfbits - shr); + tcg_gen_andi_i64(n, n, ~mask); + tcg_gen_andi_i64(d, d, mask); + tcg_gen_or_i64(d, d, n); +} + +static void gen_shrnt16_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr) +{ + gen_shrnt_i64(MO_16, d, n, shr); +} + +static void gen_shrnt32_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr) +{ + gen_shrnt_i64(MO_32, d, n, shr); +} + +static void gen_shrnt64_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr) +{ + tcg_gen_shri_i64(n, n, shr); + tcg_gen_deposit_i64(d, d, n, 32, 32); +} + +static void gen_shrnt_vec(unsigned vece, TCGv_vec d, TCGv_vec n, int64_t shr) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + uint64_t mask = MAKE_64BIT_MASK(0, halfbits); + + tcg_gen_shli_vec(vece, n, n, halfbits - shr); + tcg_gen_dupi_vec(vece, t, mask); + tcg_gen_bitsel_vec(vece, d, t, d, n); + tcg_temp_free_vec(t); +} + +static bool trans_SHRNT(DisasContext *s, arg_rri_esz *a) +{ + static const TCGOpcode vec_list[] = { INDEX_op_shli_vec, 0 }; + static const GVecGen2i ops[3] = { + { .fni8 = gen_shrnt16_i64, + .fniv = gen_shrnt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_shrnt_h, + .vece = MO_16 }, + { .fni8 = gen_shrnt32_i64, + .fniv = gen_shrnt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_shrnt_s, + .vece = MO_32 }, + { .fni8 = gen_shrnt64_i64, + .fniv = gen_shrnt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_shrnt_d, + .vece = MO_64 }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static bool trans_RSHRNB(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2i ops[3] = { + { .fno = gen_helper_sve2_rshrnb_h }, + { .fno = gen_helper_sve2_rshrnb_s }, + { .fno = gen_helper_sve2_rshrnb_d }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static bool trans_RSHRNT(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2i ops[3] = { + { .fno = gen_helper_sve2_rshrnt_h }, + { .fno = gen_helper_sve2_rshrnt_s }, + { .fno = gen_helper_sve2_rshrnt_d }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static void gen_sqshrunb_vec(unsigned vece, TCGv_vec d, + TCGv_vec n, int64_t shr) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + + tcg_gen_sari_vec(vece, n, n, shr); + tcg_gen_dupi_vec(vece, t, 0); + tcg_gen_smax_vec(vece, n, n, t); + tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits)); + tcg_gen_umin_vec(vece, d, n, t); + tcg_temp_free_vec(t); +} + +static bool trans_SQSHRUNB(DisasContext *s, arg_rri_esz *a) +{ + static const TCGOpcode vec_list[] = { + INDEX_op_sari_vec, INDEX_op_smax_vec, INDEX_op_umin_vec, 0 + }; + static const GVecGen2i ops[3] = { + { .fniv = gen_sqshrunb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_sqshrunb_h, + .vece = MO_16 }, + { .fniv = gen_sqshrunb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_sqshrunb_s, + .vece = MO_32 }, + { .fniv = gen_sqshrunb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_sqshrunb_d, + .vece = MO_64 }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static void gen_sqshrunt_vec(unsigned vece, TCGv_vec d, + TCGv_vec n, int64_t shr) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + + tcg_gen_sari_vec(vece, n, n, shr); + tcg_gen_dupi_vec(vece, t, 0); + tcg_gen_smax_vec(vece, n, n, t); + tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits)); + tcg_gen_umin_vec(vece, n, n, t); + tcg_gen_shli_vec(vece, n, n, halfbits); + tcg_gen_bitsel_vec(vece, d, t, d, n); + tcg_temp_free_vec(t); +} + +static bool trans_SQSHRUNT(DisasContext *s, arg_rri_esz *a) +{ + static const TCGOpcode vec_list[] = { + INDEX_op_shli_vec, INDEX_op_sari_vec, + INDEX_op_smax_vec, INDEX_op_umin_vec, 0 + }; + static const GVecGen2i ops[3] = { + { .fniv = gen_sqshrunt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_sqshrunt_h, + .vece = MO_16 }, + { .fniv = gen_sqshrunt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_sqshrunt_s, + .vece = MO_32 }, + { .fniv = gen_sqshrunt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_sqshrunt_d, + .vece = MO_64 }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static bool trans_SQRSHRUNB(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2i ops[3] = { + { .fno = gen_helper_sve2_sqrshrunb_h }, + { .fno = gen_helper_sve2_sqrshrunb_s }, + { .fno = gen_helper_sve2_sqrshrunb_d }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static bool trans_SQRSHRUNT(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2i ops[3] = { + { .fno = gen_helper_sve2_sqrshrunt_h }, + { .fno = gen_helper_sve2_sqrshrunt_s }, + { .fno = gen_helper_sve2_sqrshrunt_d }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static void gen_sqshrnb_vec(unsigned vece, TCGv_vec d, + TCGv_vec n, int64_t shr) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + int64_t max = MAKE_64BIT_MASK(0, halfbits - 1); + int64_t min = -max - 1; + + tcg_gen_sari_vec(vece, n, n, shr); + tcg_gen_dupi_vec(vece, t, min); + tcg_gen_smax_vec(vece, n, n, t); + tcg_gen_dupi_vec(vece, t, max); + tcg_gen_smin_vec(vece, n, n, t); + tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits)); + tcg_gen_and_vec(vece, d, n, t); + tcg_temp_free_vec(t); +} + +static bool trans_SQSHRNB(DisasContext *s, arg_rri_esz *a) +{ + static const TCGOpcode vec_list[] = { + INDEX_op_sari_vec, INDEX_op_smax_vec, INDEX_op_smin_vec, 0 + }; + static const GVecGen2i ops[3] = { + { .fniv = gen_sqshrnb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_sqshrnb_h, + .vece = MO_16 }, + { .fniv = gen_sqshrnb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_sqshrnb_s, + .vece = MO_32 }, + { .fniv = gen_sqshrnb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_sqshrnb_d, + .vece = MO_64 }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static void gen_sqshrnt_vec(unsigned vece, TCGv_vec d, + TCGv_vec n, int64_t shr) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + int64_t max = MAKE_64BIT_MASK(0, halfbits - 1); + int64_t min = -max - 1; + + tcg_gen_sari_vec(vece, n, n, shr); + tcg_gen_dupi_vec(vece, t, min); + tcg_gen_smax_vec(vece, n, n, t); + tcg_gen_dupi_vec(vece, t, max); + tcg_gen_smin_vec(vece, n, n, t); + tcg_gen_shli_vec(vece, n, n, halfbits); + tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits)); + tcg_gen_bitsel_vec(vece, d, t, d, n); + tcg_temp_free_vec(t); +} + +static bool trans_SQSHRNT(DisasContext *s, arg_rri_esz *a) +{ + static const TCGOpcode vec_list[] = { + INDEX_op_shli_vec, INDEX_op_sari_vec, + INDEX_op_smax_vec, INDEX_op_smin_vec, 0 + }; + static const GVecGen2i ops[3] = { + { .fniv = gen_sqshrnt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_sqshrnt_h, + .vece = MO_16 }, + { .fniv = gen_sqshrnt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_sqshrnt_s, + .vece = MO_32 }, + { .fniv = gen_sqshrnt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_sqshrnt_d, + .vece = MO_64 }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static bool trans_SQRSHRNB(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2i ops[3] = { + { .fno = gen_helper_sve2_sqrshrnb_h }, + { .fno = gen_helper_sve2_sqrshrnb_s }, + { .fno = gen_helper_sve2_sqrshrnb_d }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static bool trans_SQRSHRNT(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2i ops[3] = { + { .fno = gen_helper_sve2_sqrshrnt_h }, + { .fno = gen_helper_sve2_sqrshrnt_s }, + { .fno = gen_helper_sve2_sqrshrnt_d }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static void gen_uqshrnb_vec(unsigned vece, TCGv_vec d, + TCGv_vec n, int64_t shr) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + + tcg_gen_shri_vec(vece, n, n, shr); + tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits)); + tcg_gen_umin_vec(vece, d, n, t); + tcg_temp_free_vec(t); +} + +static bool trans_UQSHRNB(DisasContext *s, arg_rri_esz *a) +{ + static const TCGOpcode vec_list[] = { + INDEX_op_shri_vec, INDEX_op_umin_vec, 0 + }; + static const GVecGen2i ops[3] = { + { .fniv = gen_uqshrnb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_uqshrnb_h, + .vece = MO_16 }, + { .fniv = gen_uqshrnb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_uqshrnb_s, + .vece = MO_32 }, + { .fniv = gen_uqshrnb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_uqshrnb_d, + .vece = MO_64 }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static void gen_uqshrnt_vec(unsigned vece, TCGv_vec d, + TCGv_vec n, int64_t shr) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + + tcg_gen_shri_vec(vece, n, n, shr); + tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits)); + tcg_gen_umin_vec(vece, n, n, t); + tcg_gen_shli_vec(vece, n, n, halfbits); + tcg_gen_bitsel_vec(vece, d, t, d, n); + tcg_temp_free_vec(t); +} + +static bool trans_UQSHRNT(DisasContext *s, arg_rri_esz *a) +{ + static const TCGOpcode vec_list[] = { + INDEX_op_shli_vec, INDEX_op_shri_vec, INDEX_op_umin_vec, 0 + }; + static const GVecGen2i ops[3] = { + { .fniv = gen_uqshrnt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_uqshrnt_h, + .vece = MO_16 }, + { .fniv = gen_uqshrnt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_uqshrnt_s, + .vece = MO_32 }, + { .fniv = gen_uqshrnt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_uqshrnt_d, + .vece = MO_64 }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static bool trans_UQRSHRNB(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2i ops[3] = { + { .fno = gen_helper_sve2_uqrshrnb_h }, + { .fno = gen_helper_sve2_uqrshrnb_s }, + { .fno = gen_helper_sve2_uqrshrnb_d }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static bool trans_UQRSHRNT(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2i ops[3] = { + { .fno = gen_helper_sve2_uqrshrnt_h }, + { .fno = gen_helper_sve2_uqrshrnt_s }, + { .fno = gen_helper_sve2_uqrshrnt_d }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +#define DO_SVE2_ZZZ_NARROW(NAME, name) \ +static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \ +{ \ + static gen_helper_gvec_3 * const fns[4] = { \ + NULL, gen_helper_sve2_##name##_h, \ + gen_helper_sve2_##name##_s, gen_helper_sve2_##name##_d, \ + }; \ + return do_sve2_zzz_ool(s, a, fns[a->esz]); \ +} + +DO_SVE2_ZZZ_NARROW(ADDHNB, addhnb) +DO_SVE2_ZZZ_NARROW(ADDHNT, addhnt) +DO_SVE2_ZZZ_NARROW(RADDHNB, raddhnb) +DO_SVE2_ZZZ_NARROW(RADDHNT, raddhnt) + +DO_SVE2_ZZZ_NARROW(SUBHNB, subhnb) +DO_SVE2_ZZZ_NARROW(SUBHNT, subhnt) +DO_SVE2_ZZZ_NARROW(RSUBHNB, rsubhnb) +DO_SVE2_ZZZ_NARROW(RSUBHNT, rsubhnt) + +static bool do_sve2_ppzz_flags(DisasContext *s, arg_rprr_esz *a, + gen_helper_gvec_flags_4 *fn) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_ppzz_flags(s, a, fn); +} + +#define DO_SVE2_PPZZ_MATCH(NAME, name) \ +static bool trans_##NAME(DisasContext *s, arg_rprr_esz *a) \ +{ \ + static gen_helper_gvec_flags_4 * const fns[4] = { \ + gen_helper_sve2_##name##_ppzz_b, gen_helper_sve2_##name##_ppzz_h, \ + NULL, NULL \ + }; \ + return do_sve2_ppzz_flags(s, a, fns[a->esz]); \ +} + +DO_SVE2_PPZZ_MATCH(MATCH, match) +DO_SVE2_PPZZ_MATCH(NMATCH, nmatch) + +static bool trans_HISTCNT(DisasContext *s, arg_rprr_esz *a) +{ + static gen_helper_gvec_4 * const fns[2] = { + gen_helper_sve2_histcnt_s, gen_helper_sve2_histcnt_d + }; + if (a->esz < 2) { + return false; + } + return do_sve2_zpzz_ool(s, a, fns[a->esz - 2]); +} + +static bool trans_HISTSEG(DisasContext *s, arg_rrr_esz *a) +{ + if (a->esz != 0) { + return false; + } + return do_sve2_zzz_ool(s, a, gen_helper_sve2_histseg); +} + +static bool do_sve2_zpzz_fp(DisasContext *s, arg_rprr_esz *a, + gen_helper_gvec_4_ptr *fn) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_zpzz_fp(s, a, fn); +} + +#define DO_SVE2_ZPZZ_FP(NAME, name) \ +static bool trans_##NAME(DisasContext *s, arg_rprr_esz *a) \ +{ \ + static gen_helper_gvec_4_ptr * const fns[4] = { \ + NULL, gen_helper_sve2_##name##_zpzz_h, \ + gen_helper_sve2_##name##_zpzz_s, gen_helper_sve2_##name##_zpzz_d \ + }; \ + return do_sve2_zpzz_fp(s, a, fns[a->esz]); \ +} + +DO_SVE2_ZPZZ_FP(FADDP, faddp) +DO_SVE2_ZPZZ_FP(FMAXNMP, fmaxnmp) +DO_SVE2_ZPZZ_FP(FMINNMP, fminnmp) +DO_SVE2_ZPZZ_FP(FMAXP, fmaxp) +DO_SVE2_ZPZZ_FP(FMINP, fminp) + +/* + * SVE Integer Multiply-Add (unpredicated) + */ + +static bool trans_FMMLA(DisasContext *s, arg_rrrr_esz *a) +{ + gen_helper_gvec_4_ptr *fn; + + switch (a->esz) { + case MO_32: + if (!dc_isar_feature(aa64_sve_f32mm, s)) { + return false; + } + fn = gen_helper_fmmla_s; + break; + case MO_64: + if (!dc_isar_feature(aa64_sve_f64mm, s)) { + return false; + } + fn = gen_helper_fmmla_d; + break; + default: + return false; + } + + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr status = fpstatus_ptr(FPST_FPCR); + tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vec_full_reg_offset(s, a->ra), + status, vsz, vsz, 0, fn); + tcg_temp_free_ptr(status); + } + return true; +} + +static bool do_sqdmlal_zzzw(DisasContext *s, arg_rrrr_esz *a, + bool sel1, bool sel2) +{ + static gen_helper_gvec_4 * const fns[] = { + NULL, gen_helper_sve2_sqdmlal_zzzw_h, + gen_helper_sve2_sqdmlal_zzzw_s, gen_helper_sve2_sqdmlal_zzzw_d, + }; + return do_sve2_zzzz_ool(s, a, fns[a->esz], (sel2 << 1) | sel1); +} + +static bool do_sqdmlsl_zzzw(DisasContext *s, arg_rrrr_esz *a, + bool sel1, bool sel2) +{ + static gen_helper_gvec_4 * const fns[] = { + NULL, gen_helper_sve2_sqdmlsl_zzzw_h, + gen_helper_sve2_sqdmlsl_zzzw_s, gen_helper_sve2_sqdmlsl_zzzw_d, + }; + return do_sve2_zzzz_ool(s, a, fns[a->esz], (sel2 << 1) | sel1); +} + +static bool trans_SQDMLALB_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sqdmlal_zzzw(s, a, false, false); +} + +static bool trans_SQDMLALT_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sqdmlal_zzzw(s, a, true, true); +} + +static bool trans_SQDMLALBT(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sqdmlal_zzzw(s, a, false, true); +} + +static bool trans_SQDMLSLB_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sqdmlsl_zzzw(s, a, false, false); +} + +static bool trans_SQDMLSLT_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sqdmlsl_zzzw(s, a, true, true); +} + +static bool trans_SQDMLSLBT(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sqdmlsl_zzzw(s, a, false, true); +} + +static bool trans_SQRDMLAH_zzzz(DisasContext *s, arg_rrrr_esz *a) +{ + static gen_helper_gvec_4 * const fns[] = { + gen_helper_sve2_sqrdmlah_b, gen_helper_sve2_sqrdmlah_h, + gen_helper_sve2_sqrdmlah_s, gen_helper_sve2_sqrdmlah_d, + }; + return do_sve2_zzzz_ool(s, a, fns[a->esz], 0); +} + +static bool trans_SQRDMLSH_zzzz(DisasContext *s, arg_rrrr_esz *a) +{ + static gen_helper_gvec_4 * const fns[] = { + gen_helper_sve2_sqrdmlsh_b, gen_helper_sve2_sqrdmlsh_h, + gen_helper_sve2_sqrdmlsh_s, gen_helper_sve2_sqrdmlsh_d, + }; + return do_sve2_zzzz_ool(s, a, fns[a->esz], 0); +} + +static bool do_smlal_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) +{ + static gen_helper_gvec_4 * const fns[] = { + NULL, gen_helper_sve2_smlal_zzzw_h, + gen_helper_sve2_smlal_zzzw_s, gen_helper_sve2_smlal_zzzw_d, + }; + return do_sve2_zzzz_ool(s, a, fns[a->esz], sel); +} + +static bool trans_SMLALB_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_smlal_zzzw(s, a, false); +} + +static bool trans_SMLALT_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_smlal_zzzw(s, a, true); +} + +static bool do_umlal_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) +{ + static gen_helper_gvec_4 * const fns[] = { + NULL, gen_helper_sve2_umlal_zzzw_h, + gen_helper_sve2_umlal_zzzw_s, gen_helper_sve2_umlal_zzzw_d, + }; + return do_sve2_zzzz_ool(s, a, fns[a->esz], sel); +} + +static bool trans_UMLALB_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_umlal_zzzw(s, a, false); +} + +static bool trans_UMLALT_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_umlal_zzzw(s, a, true); +} + +static bool do_smlsl_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) +{ + static gen_helper_gvec_4 * const fns[] = { + NULL, gen_helper_sve2_smlsl_zzzw_h, + gen_helper_sve2_smlsl_zzzw_s, gen_helper_sve2_smlsl_zzzw_d, + }; + return do_sve2_zzzz_ool(s, a, fns[a->esz], sel); +} + +static bool trans_SMLSLB_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_smlsl_zzzw(s, a, false); +} + +static bool trans_SMLSLT_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_smlsl_zzzw(s, a, true); +} + +static bool do_umlsl_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) +{ + static gen_helper_gvec_4 * const fns[] = { + NULL, gen_helper_sve2_umlsl_zzzw_h, + gen_helper_sve2_umlsl_zzzw_s, gen_helper_sve2_umlsl_zzzw_d, + }; + return do_sve2_zzzz_ool(s, a, fns[a->esz], sel); +} + +static bool trans_UMLSLB_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_umlsl_zzzw(s, a, false); +} + +static bool trans_UMLSLT_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_umlsl_zzzw(s, a, true); +} + +static bool trans_CMLA_zzzz(DisasContext *s, arg_CMLA_zzzz *a) +{ + static gen_helper_gvec_4 * const fns[] = { + gen_helper_sve2_cmla_zzzz_b, gen_helper_sve2_cmla_zzzz_h, + gen_helper_sve2_cmla_zzzz_s, gen_helper_sve2_cmla_zzzz_d, + }; + + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot); + } + return true; +} + +static bool trans_CDOT_zzzz(DisasContext *s, arg_CMLA_zzzz *a) +{ + if (!dc_isar_feature(aa64_sve2, s) || a->esz < MO_32) { + return false; + } + if (sve_access_check(s)) { + gen_helper_gvec_4 *fn = (a->esz == MO_32 + ? gen_helper_sve2_cdot_zzzz_s + : gen_helper_sve2_cdot_zzzz_d); + gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, a->rot); + } + return true; +} + +static bool trans_SQRDCMLAH_zzzz(DisasContext *s, arg_SQRDCMLAH_zzzz *a) +{ + static gen_helper_gvec_4 * const fns[] = { + gen_helper_sve2_sqrdcmlah_zzzz_b, gen_helper_sve2_sqrdcmlah_zzzz_h, + gen_helper_sve2_sqrdcmlah_zzzz_s, gen_helper_sve2_sqrdcmlah_zzzz_d, + }; + + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot); + } + return true; +} + +static bool trans_USDOT_zzzz(DisasContext *s, arg_USDOT_zzzz *a) +{ + if (a->esz != 2 || !dc_isar_feature(aa64_sve_i8mm, s)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_4_ool(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vec_full_reg_offset(s, a->ra), + vsz, vsz, 0, gen_helper_gvec_usdot_b); + } + return true; +} + +static bool trans_AESMC(DisasContext *s, arg_AESMC *a) +{ + if (!dc_isar_feature(aa64_sve2_aes, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zz(s, gen_helper_crypto_aesmc, a->rd, a->rd, a->decrypt); + } + return true; +} + +static bool do_aese(DisasContext *s, arg_rrr_esz *a, bool decrypt) +{ + if (!dc_isar_feature(aa64_sve2_aes, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzz(s, gen_helper_crypto_aese, + a->rd, a->rn, a->rm, decrypt); + } + return true; +} + +static bool trans_AESE(DisasContext *s, arg_rrr_esz *a) +{ + return do_aese(s, a, false); +} + +static bool trans_AESD(DisasContext *s, arg_rrr_esz *a) +{ + return do_aese(s, a, true); +} + +static bool do_sm4(DisasContext *s, arg_rrr_esz *a, gen_helper_gvec_3 *fn) +{ + if (!dc_isar_feature(aa64_sve2_sm4, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, 0); + } + return true; +} + +static bool trans_SM4E(DisasContext *s, arg_rrr_esz *a) +{ + return do_sm4(s, a, gen_helper_crypto_sm4e); +} + +static bool trans_SM4EKEY(DisasContext *s, arg_rrr_esz *a) +{ + return do_sm4(s, a, gen_helper_crypto_sm4ekey); +} + +static bool trans_RAX1(DisasContext *s, arg_rrr_esz *a) +{ + if (!dc_isar_feature(aa64_sve2_sha3, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_fn_zzz(s, gen_gvec_rax1, MO_64, a->rd, a->rn, a->rm); + } + return true; +} + +static bool trans_FCVTNT_sh(DisasContext *s, arg_rpr_esz *a) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve2_fcvtnt_sh); +} + +static bool trans_FCVTNT_ds(DisasContext *s, arg_rpr_esz *a) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve2_fcvtnt_ds); +} + +static bool trans_FCVTLT_hs(DisasContext *s, arg_rpr_esz *a) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve2_fcvtlt_hs); +} + +static bool trans_FCVTLT_sd(DisasContext *s, arg_rpr_esz *a) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve2_fcvtlt_sd); +} + +static bool trans_FCVTX_ds(DisasContext *s, arg_rpr_esz *a) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_frint_mode(s, a, float_round_to_odd, gen_helper_sve_fcvt_ds); +} + +static bool trans_FCVTXNT_ds(DisasContext *s, arg_rpr_esz *a) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_frint_mode(s, a, float_round_to_odd, gen_helper_sve2_fcvtnt_ds); +} + +static bool trans_FLOGB(DisasContext *s, arg_rpr_esz *a) +{ + static gen_helper_gvec_3_ptr * const fns[] = { + NULL, gen_helper_flogb_h, + gen_helper_flogb_s, gen_helper_flogb_d + }; + + if (!dc_isar_feature(aa64_sve2, s) || fns[a->esz] == NULL) { + return false; + } + if (sve_access_check(s)) { + TCGv_ptr status = + fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + unsigned vsz = vec_full_reg_size(s); + + tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + pred_full_reg_offset(s, a->pg), + status, vsz, vsz, 0, fns[a->esz]); + tcg_temp_free_ptr(status); + } + return true; +} + +static bool do_FMLAL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sub, bool sel) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vec_full_reg_offset(s, a->ra), + cpu_env, vsz, vsz, (sel << 1) | sub, + gen_helper_sve2_fmlal_zzzw_s); + } + return true; +} + +static bool trans_FMLALB_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_FMLAL_zzzw(s, a, false, false); +} + +static bool trans_FMLALT_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_FMLAL_zzzw(s, a, false, true); +} + +static bool trans_FMLSLB_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_FMLAL_zzzw(s, a, true, false); +} + +static bool trans_FMLSLT_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_FMLAL_zzzw(s, a, true, true); +} + +static bool do_FMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sub, bool sel) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vec_full_reg_offset(s, a->ra), + cpu_env, vsz, vsz, + (a->index << 2) | (sel << 1) | sub, + gen_helper_sve2_fmlal_zzxw_s); + } + return true; +} + +static bool trans_FMLALB_zzxw(DisasContext *s, arg_rrxr_esz *a) +{ + return do_FMLAL_zzxw(s, a, false, false); +} + +static bool trans_FMLALT_zzxw(DisasContext *s, arg_rrxr_esz *a) +{ + return do_FMLAL_zzxw(s, a, false, true); +} + +static bool trans_FMLSLB_zzxw(DisasContext *s, arg_rrxr_esz *a) +{ + return do_FMLAL_zzxw(s, a, true, false); +} + +static bool trans_FMLSLT_zzxw(DisasContext *s, arg_rrxr_esz *a) +{ + return do_FMLAL_zzxw(s, a, true, true); +} + +static bool do_i8mm_zzzz_ool(DisasContext *s, arg_rrrr_esz *a, + gen_helper_gvec_4 *fn, int data) +{ + if (!dc_isar_feature(aa64_sve_i8mm, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, data); + } + return true; +} + +static bool trans_SMMLA(DisasContext *s, arg_rrrr_esz *a) +{ + return do_i8mm_zzzz_ool(s, a, gen_helper_gvec_smmla_b, 0); +} + +static bool trans_USMMLA(DisasContext *s, arg_rrrr_esz *a) +{ + return do_i8mm_zzzz_ool(s, a, gen_helper_gvec_usmmla_b, 0); +} + +static bool trans_UMMLA(DisasContext *s, arg_rrrr_esz *a) +{ + return do_i8mm_zzzz_ool(s, a, gen_helper_gvec_ummla_b, 0); +} diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index 3fbeae87cb..e84b438340 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -22,33 +22,82 @@ #include "exec/helper-proto.h" #include "tcg/tcg-gvec-desc.h" #include "fpu/softfloat.h" +#include "qemu/int128.h" #include "vec_internal.h" -/* Note that vector data is stored in host-endian 64-bit chunks, - so addressing units smaller than that needs a host-endian fixup. */ -#ifdef HOST_WORDS_BIGENDIAN -#define H1(x) ((x) ^ 7) -#define H2(x) ((x) ^ 3) -#define H4(x) ((x) ^ 1) -#else -#define H1(x) (x) -#define H2(x) (x) -#define H4(x) (x) -#endif - -/* Signed saturating rounding doubling multiply-accumulate high half, 16-bit */ -static int16_t do_sqrdmlah_h(int16_t src1, int16_t src2, int16_t src3, - bool neg, bool round, uint32_t *sat) +/* Signed saturating rounding doubling multiply-accumulate high half, 8-bit */ +int8_t do_sqrdmlah_b(int8_t src1, int8_t src2, int8_t src3, + bool neg, bool round) { /* * Simplify: - * = ((a3 << 16) + ((e1 * e2) << 1) + (1 << 15)) >> 16 - * = ((a3 << 15) + (e1 * e2) + (1 << 14)) >> 15 + * = ((a3 << 8) + ((e1 * e2) << 1) + (round << 7)) >> 8 + * = ((a3 << 7) + (e1 * e2) + (round << 6)) >> 7 */ int32_t ret = (int32_t)src1 * src2; if (neg) { ret = -ret; } + ret += ((int32_t)src3 << 7) + (round << 6); + ret >>= 7; + + if (ret != (int8_t)ret) { + ret = (ret < 0 ? INT8_MIN : INT8_MAX); + } + return ret; +} + +void HELPER(sve2_sqrdmlah_b)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int8_t *d = vd, *n = vn, *m = vm, *a = va; + + for (i = 0; i < opr_sz; ++i) { + d[i] = do_sqrdmlah_b(n[i], m[i], a[i], false, true); + } +} + +void HELPER(sve2_sqrdmlsh_b)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int8_t *d = vd, *n = vn, *m = vm, *a = va; + + for (i = 0; i < opr_sz; ++i) { + d[i] = do_sqrdmlah_b(n[i], m[i], a[i], true, true); + } +} + +void HELPER(sve2_sqdmulh_b)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int8_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz; ++i) { + d[i] = do_sqrdmlah_b(n[i], m[i], 0, false, false); + } +} + +void HELPER(sve2_sqrdmulh_b)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int8_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz; ++i) { + d[i] = do_sqrdmlah_b(n[i], m[i], 0, false, true); + } +} + +/* Signed saturating rounding doubling multiply-accumulate high half, 16-bit */ +int16_t do_sqrdmlah_h(int16_t src1, int16_t src2, int16_t src3, + bool neg, bool round, uint32_t *sat) +{ + /* Simplify similarly to do_sqrdmlah_b above. */ + int32_t ret = (int32_t)src1 * src2; + if (neg) { + ret = -ret; + } ret += ((int32_t)src3 << 15) + (round << 14); ret >>= 15; @@ -133,11 +182,87 @@ void HELPER(neon_sqrdmulh_h)(void *vd, void *vn, void *vm, clear_tail(d, opr_sz, simd_maxsz(desc)); } +void HELPER(sve2_sqrdmlah_h)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int16_t *d = vd, *n = vn, *m = vm, *a = va; + uint32_t discard; + + for (i = 0; i < opr_sz / 2; ++i) { + d[i] = do_sqrdmlah_h(n[i], m[i], a[i], false, true, &discard); + } +} + +void HELPER(sve2_sqrdmlsh_h)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int16_t *d = vd, *n = vn, *m = vm, *a = va; + uint32_t discard; + + for (i = 0; i < opr_sz / 2; ++i) { + d[i] = do_sqrdmlah_h(n[i], m[i], a[i], true, true, &discard); + } +} + +void HELPER(sve2_sqdmulh_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int16_t *d = vd, *n = vn, *m = vm; + uint32_t discard; + + for (i = 0; i < opr_sz / 2; ++i) { + d[i] = do_sqrdmlah_h(n[i], m[i], 0, false, false, &discard); + } +} + +void HELPER(sve2_sqrdmulh_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int16_t *d = vd, *n = vn, *m = vm; + uint32_t discard; + + for (i = 0; i < opr_sz / 2; ++i) { + d[i] = do_sqrdmlah_h(n[i], m[i], 0, false, true, &discard); + } +} + +void HELPER(sve2_sqdmulh_idx_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx); + uint32_t discard; + + for (i = 0; i < opr_sz / 2; i += 16 / 2) { + int16_t mm = m[i]; + for (j = 0; j < 16 / 2; ++j) { + d[i + j] = do_sqrdmlah_h(n[i + j], mm, 0, false, false, &discard); + } + } +} + +void HELPER(sve2_sqrdmulh_idx_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx); + uint32_t discard; + + for (i = 0; i < opr_sz / 2; i += 16 / 2) { + int16_t mm = m[i]; + for (j = 0; j < 16 / 2; ++j) { + d[i + j] = do_sqrdmlah_h(n[i + j], mm, 0, false, true, &discard); + } + } +} + /* Signed saturating rounding doubling multiply-accumulate high half, 32-bit */ -static int32_t do_sqrdmlah_s(int32_t src1, int32_t src2, int32_t src3, - bool neg, bool round, uint32_t *sat) +int32_t do_sqrdmlah_s(int32_t src1, int32_t src2, int32_t src3, + bool neg, bool round, uint32_t *sat) { - /* Simplify similarly to int_qrdmlah_s16 above. */ + /* Simplify similarly to do_sqrdmlah_b above. */ int64_t ret = (int64_t)src1 * src2; if (neg) { ret = -ret; @@ -220,197 +345,253 @@ void HELPER(neon_sqrdmulh_s)(void *vd, void *vn, void *vm, clear_tail(d, opr_sz, simd_maxsz(desc)); } -/* Integer 8 and 16-bit dot-product. - * - * Note that for the loops herein, host endianness does not matter - * with respect to the ordering of data within the 64-bit lanes. - * All elements are treated equally, no matter where they are. - */ - -void HELPER(gvec_sdot_b)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(sve2_sqrdmlah_s)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc); - uint32_t *d = vd; - int8_t *n = vn, *m = vm; + int32_t *d = vd, *n = vn, *m = vm, *a = va; + uint32_t discard; for (i = 0; i < opr_sz / 4; ++i) { - d[i] += n[i * 4 + 0] * m[i * 4 + 0] - + n[i * 4 + 1] * m[i * 4 + 1] - + n[i * 4 + 2] * m[i * 4 + 2] - + n[i * 4 + 3] * m[i * 4 + 3]; + d[i] = do_sqrdmlah_s(n[i], m[i], a[i], false, true, &discard); } - clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_udot_b)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(sve2_sqrdmlsh_s)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc); - uint32_t *d = vd; - uint8_t *n = vn, *m = vm; + int32_t *d = vd, *n = vn, *m = vm, *a = va; + uint32_t discard; for (i = 0; i < opr_sz / 4; ++i) { - d[i] += n[i * 4 + 0] * m[i * 4 + 0] - + n[i * 4 + 1] * m[i * 4 + 1] - + n[i * 4 + 2] * m[i * 4 + 2] - + n[i * 4 + 3] * m[i * 4 + 3]; + d[i] = do_sqrdmlah_s(n[i], m[i], a[i], true, true, &discard); } - clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_sdot_h)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(sve2_sqdmulh_s)(void *vd, void *vn, void *vm, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc); - uint64_t *d = vd; - int16_t *n = vn, *m = vm; + int32_t *d = vd, *n = vn, *m = vm; + uint32_t discard; - for (i = 0; i < opr_sz / 8; ++i) { - d[i] += (int64_t)n[i * 4 + 0] * m[i * 4 + 0] - + (int64_t)n[i * 4 + 1] * m[i * 4 + 1] - + (int64_t)n[i * 4 + 2] * m[i * 4 + 2] - + (int64_t)n[i * 4 + 3] * m[i * 4 + 3]; + for (i = 0; i < opr_sz / 4; ++i) { + d[i] = do_sqrdmlah_s(n[i], m[i], 0, false, false, &discard); } - clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_udot_h)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(sve2_sqrdmulh_s)(void *vd, void *vn, void *vm, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc); - uint64_t *d = vd; - uint16_t *n = vn, *m = vm; + int32_t *d = vd, *n = vn, *m = vm; + uint32_t discard; - for (i = 0; i < opr_sz / 8; ++i) { - d[i] += (uint64_t)n[i * 4 + 0] * m[i * 4 + 0] - + (uint64_t)n[i * 4 + 1] * m[i * 4 + 1] - + (uint64_t)n[i * 4 + 2] * m[i * 4 + 2] - + (uint64_t)n[i * 4 + 3] * m[i * 4 + 3]; + for (i = 0; i < opr_sz / 4; ++i) { + d[i] = do_sqrdmlah_s(n[i], m[i], 0, false, true, &discard); } - clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(sve2_sqdmulh_idx_s)(void *vd, void *vn, void *vm, uint32_t desc) { - intptr_t i, segend, opr_sz = simd_oprsz(desc), opr_sz_4 = opr_sz / 4; - intptr_t index = simd_data(desc); - uint32_t *d = vd; - int8_t *n = vn; - int8_t *m_indexed = (int8_t *)vm + H4(index) * 4; + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx); + uint32_t discard; + + for (i = 0; i < opr_sz / 4; i += 16 / 4) { + int32_t mm = m[i]; + for (j = 0; j < 16 / 4; ++j) { + d[i + j] = do_sqrdmlah_s(n[i + j], mm, 0, false, false, &discard); + } + } +} - /* Notice the special case of opr_sz == 8, from aa64/aa32 advsimd. - * Otherwise opr_sz is a multiple of 16. - */ - segend = MIN(4, opr_sz_4); - i = 0; - do { - int8_t m0 = m_indexed[i * 4 + 0]; - int8_t m1 = m_indexed[i * 4 + 1]; - int8_t m2 = m_indexed[i * 4 + 2]; - int8_t m3 = m_indexed[i * 4 + 3]; - - do { - d[i] += n[i * 4 + 0] * m0 - + n[i * 4 + 1] * m1 - + n[i * 4 + 2] * m2 - + n[i * 4 + 3] * m3; - } while (++i < segend); - segend = i + 4; - } while (i < opr_sz_4); +void HELPER(sve2_sqrdmulh_idx_s)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx); + uint32_t discard; + + for (i = 0; i < opr_sz / 4; i += 16 / 4) { + int32_t mm = m[i]; + for (j = 0; j < 16 / 4; ++j) { + d[i + j] = do_sqrdmlah_s(n[i + j], mm, 0, false, true, &discard); + } + } +} - clear_tail(d, opr_sz, simd_maxsz(desc)); +/* Signed saturating rounding doubling multiply-accumulate high half, 64-bit */ +static int64_t do_sat128_d(Int128 r) +{ + int64_t ls = int128_getlo(r); + int64_t hs = int128_gethi(r); + + if (unlikely(hs != (ls >> 63))) { + return hs < 0 ? INT64_MIN : INT64_MAX; + } + return ls; } -void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) +int64_t do_sqrdmlah_d(int64_t n, int64_t m, int64_t a, bool neg, bool round) { - intptr_t i, segend, opr_sz = simd_oprsz(desc), opr_sz_4 = opr_sz / 4; - intptr_t index = simd_data(desc); - uint32_t *d = vd; - uint8_t *n = vn; - uint8_t *m_indexed = (uint8_t *)vm + H4(index) * 4; + uint64_t l, h; + Int128 r, t; - /* Notice the special case of opr_sz == 8, from aa64/aa32 advsimd. - * Otherwise opr_sz is a multiple of 16. - */ - segend = MIN(4, opr_sz_4); - i = 0; - do { - uint8_t m0 = m_indexed[i * 4 + 0]; - uint8_t m1 = m_indexed[i * 4 + 1]; - uint8_t m2 = m_indexed[i * 4 + 2]; - uint8_t m3 = m_indexed[i * 4 + 3]; - - do { - d[i] += n[i * 4 + 0] * m0 - + n[i * 4 + 1] * m1 - + n[i * 4 + 2] * m2 - + n[i * 4 + 3] * m3; - } while (++i < segend); - segend = i + 4; - } while (i < opr_sz_4); + /* As in do_sqrdmlah_b, but with 128-bit arithmetic. */ + muls64(&l, &h, m, n); + r = int128_make128(l, h); + if (neg) { + r = int128_neg(r); + } + if (a) { + t = int128_exts64(a); + t = int128_lshift(t, 63); + r = int128_add(r, t); + } + if (round) { + t = int128_exts64(1ll << 62); + r = int128_add(r, t); + } + r = int128_rshift(r, 63); - clear_tail(d, opr_sz, simd_maxsz(desc)); + return do_sat128_d(r); } -void HELPER(gvec_sdot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(sve2_sqrdmlah_d)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) { - intptr_t i, opr_sz = simd_oprsz(desc), opr_sz_8 = opr_sz / 8; - intptr_t index = simd_data(desc); - uint64_t *d = vd; - int16_t *n = vn; - int16_t *m_indexed = (int16_t *)vm + index * 4; + intptr_t i, opr_sz = simd_oprsz(desc); + int64_t *d = vd, *n = vn, *m = vm, *a = va; - /* This is supported by SVE only, so opr_sz is always a multiple of 16. - * Process the entire segment all at once, writing back the results - * only after we've consumed all of the inputs. - */ - for (i = 0; i < opr_sz_8 ; i += 2) { - uint64_t d0, d1; + for (i = 0; i < opr_sz / 8; ++i) { + d[i] = do_sqrdmlah_d(n[i], m[i], a[i], false, true); + } +} - d0 = n[i * 4 + 0] * (int64_t)m_indexed[i * 4 + 0]; - d0 += n[i * 4 + 1] * (int64_t)m_indexed[i * 4 + 1]; - d0 += n[i * 4 + 2] * (int64_t)m_indexed[i * 4 + 2]; - d0 += n[i * 4 + 3] * (int64_t)m_indexed[i * 4 + 3]; - d1 = n[i * 4 + 4] * (int64_t)m_indexed[i * 4 + 0]; - d1 += n[i * 4 + 5] * (int64_t)m_indexed[i * 4 + 1]; - d1 += n[i * 4 + 6] * (int64_t)m_indexed[i * 4 + 2]; - d1 += n[i * 4 + 7] * (int64_t)m_indexed[i * 4 + 3]; +void HELPER(sve2_sqrdmlsh_d)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int64_t *d = vd, *n = vn, *m = vm, *a = va; - d[i + 0] += d0; - d[i + 1] += d1; + for (i = 0; i < opr_sz / 8; ++i) { + d[i] = do_sqrdmlah_d(n[i], m[i], a[i], true, true); } +} - clear_tail(d, opr_sz, simd_maxsz(desc)); +void HELPER(sve2_sqdmulh_d)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int64_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 8; ++i) { + d[i] = do_sqrdmlah_d(n[i], m[i], 0, false, false); + } } -void HELPER(gvec_udot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(sve2_sqrdmulh_d)(void *vd, void *vn, void *vm, uint32_t desc) { - intptr_t i, opr_sz = simd_oprsz(desc), opr_sz_8 = opr_sz / 8; - intptr_t index = simd_data(desc); - uint64_t *d = vd; - uint16_t *n = vn; - uint16_t *m_indexed = (uint16_t *)vm + index * 4; + intptr_t i, opr_sz = simd_oprsz(desc); + int64_t *d = vd, *n = vn, *m = vm; - /* This is supported by SVE only, so opr_sz is always a multiple of 16. - * Process the entire segment all at once, writing back the results - * only after we've consumed all of the inputs. - */ - for (i = 0; i < opr_sz_8 ; i += 2) { - uint64_t d0, d1; + for (i = 0; i < opr_sz / 8; ++i) { + d[i] = do_sqrdmlah_d(n[i], m[i], 0, false, true); + } +} - d0 = n[i * 4 + 0] * (uint64_t)m_indexed[i * 4 + 0]; - d0 += n[i * 4 + 1] * (uint64_t)m_indexed[i * 4 + 1]; - d0 += n[i * 4 + 2] * (uint64_t)m_indexed[i * 4 + 2]; - d0 += n[i * 4 + 3] * (uint64_t)m_indexed[i * 4 + 3]; - d1 = n[i * 4 + 4] * (uint64_t)m_indexed[i * 4 + 0]; - d1 += n[i * 4 + 5] * (uint64_t)m_indexed[i * 4 + 1]; - d1 += n[i * 4 + 6] * (uint64_t)m_indexed[i * 4 + 2]; - d1 += n[i * 4 + 7] * (uint64_t)m_indexed[i * 4 + 3]; +void HELPER(sve2_sqdmulh_idx_d)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int64_t *d = vd, *n = vn, *m = (int64_t *)vm + idx; - d[i + 0] += d0; - d[i + 1] += d1; + for (i = 0; i < opr_sz / 8; i += 16 / 8) { + int64_t mm = m[i]; + for (j = 0; j < 16 / 8; ++j) { + d[i + j] = do_sqrdmlah_d(n[i + j], mm, 0, false, false); + } } +} - clear_tail(d, opr_sz, simd_maxsz(desc)); +void HELPER(sve2_sqrdmulh_idx_d)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int64_t *d = vd, *n = vn, *m = (int64_t *)vm + idx; + + for (i = 0; i < opr_sz / 8; i += 16 / 8) { + int64_t mm = m[i]; + for (j = 0; j < 16 / 8; ++j) { + d[i + j] = do_sqrdmlah_d(n[i + j], mm, 0, false, true); + } + } } +/* Integer 8 and 16-bit dot-product. + * + * Note that for the loops herein, host endianness does not matter + * with respect to the ordering of data within the quad-width lanes. + * All elements are treated equally, no matter where they are. + */ + +#define DO_DOT(NAME, TYPED, TYPEN, TYPEM) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + TYPED *d = vd, *a = va; \ + TYPEN *n = vn; \ + TYPEM *m = vm; \ + for (i = 0; i < opr_sz / sizeof(TYPED); ++i) { \ + d[i] = (a[i] + \ + (TYPED)n[i * 4 + 0] * m[i * 4 + 0] + \ + (TYPED)n[i * 4 + 1] * m[i * 4 + 1] + \ + (TYPED)n[i * 4 + 2] * m[i * 4 + 2] + \ + (TYPED)n[i * 4 + 3] * m[i * 4 + 3]); \ + } \ + clear_tail(d, opr_sz, simd_maxsz(desc)); \ +} + +DO_DOT(gvec_sdot_b, int32_t, int8_t, int8_t) +DO_DOT(gvec_udot_b, uint32_t, uint8_t, uint8_t) +DO_DOT(gvec_usdot_b, uint32_t, uint8_t, int8_t) +DO_DOT(gvec_sdot_h, int64_t, int16_t, int16_t) +DO_DOT(gvec_udot_h, uint64_t, uint16_t, uint16_t) + +#define DO_DOT_IDX(NAME, TYPED, TYPEN, TYPEM, HD) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t i = 0, opr_sz = simd_oprsz(desc); \ + intptr_t opr_sz_n = opr_sz / sizeof(TYPED); \ + intptr_t segend = MIN(16 / sizeof(TYPED), opr_sz_n); \ + intptr_t index = simd_data(desc); \ + TYPED *d = vd, *a = va; \ + TYPEN *n = vn; \ + TYPEM *m_indexed = (TYPEM *)vm + HD(index) * 4; \ + do { \ + TYPED m0 = m_indexed[i * 4 + 0]; \ + TYPED m1 = m_indexed[i * 4 + 1]; \ + TYPED m2 = m_indexed[i * 4 + 2]; \ + TYPED m3 = m_indexed[i * 4 + 3]; \ + do { \ + d[i] = (a[i] + \ + n[i * 4 + 0] * m0 + \ + n[i * 4 + 1] * m1 + \ + n[i * 4 + 2] * m2 + \ + n[i * 4 + 3] * m3); \ + } while (++i < segend); \ + segend = i + 4; \ + } while (i < opr_sz_n); \ + clear_tail(d, opr_sz, simd_maxsz(desc)); \ +} + +DO_DOT_IDX(gvec_sdot_idx_b, int32_t, int8_t, int8_t, H4) +DO_DOT_IDX(gvec_udot_idx_b, uint32_t, uint8_t, uint8_t, H4) +DO_DOT_IDX(gvec_sudot_idx_b, int32_t, int8_t, uint8_t, H4) +DO_DOT_IDX(gvec_usdot_idx_b, int32_t, uint8_t, int8_t, H4) +DO_DOT_IDX(gvec_sdot_idx_h, int64_t, int16_t, int16_t, ) +DO_DOT_IDX(gvec_udot_idx_h, uint64_t, uint16_t, uint16_t, ) + void HELPER(gvec_fcaddh)(void *vd, void *vn, void *vm, void *vfpst, uint32_t desc) { @@ -495,13 +676,11 @@ void HELPER(gvec_fcaddd)(void *vd, void *vn, void *vm, clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_fcmlah)(void *vd, void *vn, void *vm, +void HELPER(gvec_fcmlah)(void *vd, void *vn, void *vm, void *va, void *vfpst, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); - float16 *d = vd; - float16 *n = vn; - float16 *m = vm; + float16 *d = vd, *n = vn, *m = vm, *a = va; float_status *fpst = vfpst; intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1); uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1); @@ -518,19 +697,17 @@ void HELPER(gvec_fcmlah)(void *vd, void *vn, void *vm, float16 e4 = e2; float16 e3 = m[H2(i + 1 - flip)] ^ neg_imag; - d[H2(i)] = float16_muladd(e2, e1, d[H2(i)], 0, fpst); - d[H2(i + 1)] = float16_muladd(e4, e3, d[H2(i + 1)], 0, fpst); + d[H2(i)] = float16_muladd(e2, e1, a[H2(i)], 0, fpst); + d[H2(i + 1)] = float16_muladd(e4, e3, a[H2(i + 1)], 0, fpst); } clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_fcmlah_idx)(void *vd, void *vn, void *vm, +void HELPER(gvec_fcmlah_idx)(void *vd, void *vn, void *vm, void *va, void *vfpst, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); - float16 *d = vd; - float16 *n = vn; - float16 *m = vm; + float16 *d = vd, *n = vn, *m = vm, *a = va; float_status *fpst = vfpst; intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1); uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1); @@ -554,20 +731,18 @@ void HELPER(gvec_fcmlah_idx)(void *vd, void *vn, void *vm, float16 e2 = n[H2(j + flip)]; float16 e4 = e2; - d[H2(j)] = float16_muladd(e2, e1, d[H2(j)], 0, fpst); - d[H2(j + 1)] = float16_muladd(e4, e3, d[H2(j + 1)], 0, fpst); + d[H2(j)] = float16_muladd(e2, e1, a[H2(j)], 0, fpst); + d[H2(j + 1)] = float16_muladd(e4, e3, a[H2(j + 1)], 0, fpst); } } clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_fcmlas)(void *vd, void *vn, void *vm, +void HELPER(gvec_fcmlas)(void *vd, void *vn, void *vm, void *va, void *vfpst, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); - float32 *d = vd; - float32 *n = vn; - float32 *m = vm; + float32 *d = vd, *n = vn, *m = vm, *a = va; float_status *fpst = vfpst; intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1); uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1); @@ -584,19 +759,17 @@ void HELPER(gvec_fcmlas)(void *vd, void *vn, void *vm, float32 e4 = e2; float32 e3 = m[H4(i + 1 - flip)] ^ neg_imag; - d[H4(i)] = float32_muladd(e2, e1, d[H4(i)], 0, fpst); - d[H4(i + 1)] = float32_muladd(e4, e3, d[H4(i + 1)], 0, fpst); + d[H4(i)] = float32_muladd(e2, e1, a[H4(i)], 0, fpst); + d[H4(i + 1)] = float32_muladd(e4, e3, a[H4(i + 1)], 0, fpst); } clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm, +void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm, void *va, void *vfpst, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); - float32 *d = vd; - float32 *n = vn; - float32 *m = vm; + float32 *d = vd, *n = vn, *m = vm, *a = va; float_status *fpst = vfpst; intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1); uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1); @@ -620,20 +793,18 @@ void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm, float32 e2 = n[H4(j + flip)]; float32 e4 = e2; - d[H4(j)] = float32_muladd(e2, e1, d[H4(j)], 0, fpst); - d[H4(j + 1)] = float32_muladd(e4, e3, d[H4(j + 1)], 0, fpst); + d[H4(j)] = float32_muladd(e2, e1, a[H4(j)], 0, fpst); + d[H4(j + 1)] = float32_muladd(e4, e3, a[H4(j + 1)], 0, fpst); } } clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_fcmlad)(void *vd, void *vn, void *vm, +void HELPER(gvec_fcmlad)(void *vd, void *vn, void *vm, void *va, void *vfpst, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); - float64 *d = vd; - float64 *n = vn; - float64 *m = vm; + float64 *d = vd, *n = vn, *m = vm, *a = va; float_status *fpst = vfpst; intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1); uint64_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1); @@ -650,8 +821,8 @@ void HELPER(gvec_fcmlad)(void *vd, void *vn, void *vm, float64 e4 = e2; float64 e3 = m[i + 1 - flip] ^ neg_imag; - d[i] = float64_muladd(e2, e1, d[i], 0, fpst); - d[i + 1] = float64_muladd(e4, e3, d[i + 1], 0, fpst); + d[i] = float64_muladd(e2, e1, a[i], 0, fpst); + d[i + 1] = float64_muladd(e4, e3, a[i + 1], 0, fpst); } clear_tail(d, opr_sz, simd_maxsz(desc)); } @@ -1497,6 +1668,27 @@ void HELPER(gvec_fmlal_a64)(void *vd, void *vn, void *vm, get_flush_inputs_to_zero(&env->vfp.fp_status_f16)); } +void HELPER(sve2_fmlal_zzzw_s)(void *vd, void *vn, void *vm, void *va, + void *venv, uint32_t desc) +{ + intptr_t i, oprsz = simd_oprsz(desc); + uint16_t negn = extract32(desc, SIMD_DATA_SHIFT, 1) << 15; + intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16); + CPUARMState *env = venv; + float_status *status = &env->vfp.fp_status; + bool fz16 = get_flush_inputs_to_zero(&env->vfp.fp_status_f16); + + for (i = 0; i < oprsz; i += sizeof(float32)) { + float16 nn_16 = *(float16 *)(vn + H1_2(i + sel)) ^ negn; + float16 mm_16 = *(float16 *)(vm + H1_2(i + sel)); + float32 nn = float16_to_float32_by_bits(nn_16, fz16); + float32 mm = float16_to_float32_by_bits(mm_16, fz16); + float32 aa = *(float32 *)(va + H1_4(i)); + + *(float32 *)(vd + H1_4(i)) = float32_muladd(nn, mm, aa, 0, status); + } +} + static void do_fmlal_idx(float32 *d, void *vn, void *vm, float_status *fpst, uint32_t desc, bool fz16) { @@ -1541,6 +1733,32 @@ void HELPER(gvec_fmlal_idx_a64)(void *vd, void *vn, void *vm, get_flush_inputs_to_zero(&env->vfp.fp_status_f16)); } +void HELPER(sve2_fmlal_zzxw_s)(void *vd, void *vn, void *vm, void *va, + void *venv, uint32_t desc) +{ + intptr_t i, j, oprsz = simd_oprsz(desc); + uint16_t negn = extract32(desc, SIMD_DATA_SHIFT, 1) << 15; + intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16); + intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 2, 3) * sizeof(float16); + CPUARMState *env = venv; + float_status *status = &env->vfp.fp_status; + bool fz16 = get_flush_inputs_to_zero(&env->vfp.fp_status_f16); + + for (i = 0; i < oprsz; i += 16) { + float16 mm_16 = *(float16 *)(vm + i + idx); + float32 mm = float16_to_float32_by_bits(mm_16, fz16); + + for (j = 0; j < 16; j += sizeof(float32)) { + float16 nn_16 = *(float16 *)(vn + H1_2(i + j + sel)) ^ negn; + float32 nn = float16_to_float32_by_bits(nn_16, fz16); + float32 aa = *(float32 *)(va + H1_4(i + j)); + + *(float32 *)(vd + H1_4(i + j)) = + float32_muladd(nn, mm, aa, 0, status); + } + } +} + void HELPER(gvec_sshl_b)(void *vd, void *vn, void *vm, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc); @@ -1750,6 +1968,30 @@ void HELPER(sve2_pmull_h)(void *vd, void *vn, void *vm, uint32_t desc) d[i] = pmull_h(nn, mm); } } + +static uint64_t pmull_d(uint64_t op1, uint64_t op2) +{ + uint64_t result = 0; + int i; + + for (i = 0; i < 32; ++i) { + uint64_t mask = -((op1 >> i) & 1); + result ^= (op2 << i) & mask; + } + return result; +} + +void HELPER(sve2_pmull_d)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t sel = H4(simd_data(desc)); + intptr_t i, opr_sz = simd_oprsz(desc); + uint32_t *n = vn, *m = vm; + uint64_t *d = vd; + + for (i = 0; i < opr_sz / 8; ++i) { + d[i] = pmull_d(n[2 * i + sel], m[2 * i + sel]); + } +} #endif #define DO_CMP0(NAME, TYPE, OP) \ @@ -1985,3 +2227,188 @@ void HELPER(simd_tblx)(void *vd, void *vm, void *venv, uint32_t desc) clear_tail(vd, oprsz, simd_maxsz(desc)); } #endif + +/* + * NxN -> N highpart multiply + * + * TODO: expose this as a generic vector operation. + */ + +void HELPER(gvec_smulh_b)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int8_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz; ++i) { + d[i] = ((int32_t)n[i] * m[i]) >> 8; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_smulh_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int16_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 2; ++i) { + d[i] = ((int32_t)n[i] * m[i]) >> 16; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_smulh_s)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int32_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 4; ++i) { + d[i] = ((int64_t)n[i] * m[i]) >> 32; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_smulh_d)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint64_t *d = vd, *n = vn, *m = vm; + uint64_t discard; + + for (i = 0; i < opr_sz / 8; ++i) { + muls64(&discard, &d[i], n[i], m[i]); + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_umulh_b)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint8_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz; ++i) { + d[i] = ((uint32_t)n[i] * m[i]) >> 8; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_umulh_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint16_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 2; ++i) { + d[i] = ((uint32_t)n[i] * m[i]) >> 16; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_umulh_s)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint32_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 4; ++i) { + d[i] = ((uint64_t)n[i] * m[i]) >> 32; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_umulh_d)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint64_t *d = vd, *n = vn, *m = vm; + uint64_t discard; + + for (i = 0; i < opr_sz / 8; ++i) { + mulu64(&discard, &d[i], n[i], m[i]); + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_xar_d)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + int shr = simd_data(desc); + uint64_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz; ++i) { + d[i] = ror64(n[i] ^ m[i], shr); + } + clear_tail(d, opr_sz * 8, simd_maxsz(desc)); +} + +/* + * Integer matrix-multiply accumulate + */ + +static uint32_t do_smmla_b(uint32_t sum, void *vn, void *vm) +{ + int8_t *n = vn, *m = vm; + + for (intptr_t k = 0; k < 8; ++k) { + sum += n[H1(k)] * m[H1(k)]; + } + return sum; +} + +static uint32_t do_ummla_b(uint32_t sum, void *vn, void *vm) +{ + uint8_t *n = vn, *m = vm; + + for (intptr_t k = 0; k < 8; ++k) { + sum += n[H1(k)] * m[H1(k)]; + } + return sum; +} + +static uint32_t do_usmmla_b(uint32_t sum, void *vn, void *vm) +{ + uint8_t *n = vn; + int8_t *m = vm; + + for (intptr_t k = 0; k < 8; ++k) { + sum += n[H1(k)] * m[H1(k)]; + } + return sum; +} + +static void do_mmla_b(void *vd, void *vn, void *vm, void *va, uint32_t desc, + uint32_t (*inner_loop)(uint32_t, void *, void *)) +{ + intptr_t seg, opr_sz = simd_oprsz(desc); + + for (seg = 0; seg < opr_sz; seg += 16) { + uint32_t *d = vd + seg; + uint32_t *a = va + seg; + uint32_t sum0, sum1, sum2, sum3; + + /* + * Process the entire segment at once, writing back the + * results only after we've consumed all of the inputs. + * + * Key to indicies by column: + * i j i j + */ + sum0 = a[H4(0 + 0)]; + sum0 = inner_loop(sum0, vn + seg + 0, vm + seg + 0); + sum1 = a[H4(0 + 1)]; + sum1 = inner_loop(sum1, vn + seg + 0, vm + seg + 8); + sum2 = a[H4(2 + 0)]; + sum2 = inner_loop(sum2, vn + seg + 8, vm + seg + 0); + sum3 = a[H4(2 + 1)]; + sum3 = inner_loop(sum3, vn + seg + 8, vm + seg + 8); + + d[H4(0)] = sum0; + d[H4(1)] = sum1; + d[H4(2)] = sum2; + d[H4(3)] = sum3; + } + clear_tail(vd, opr_sz, simd_maxsz(desc)); +} + +#define DO_MMLA_B(NAME, INNER) \ + void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ + { do_mmla_b(vd, vn, vm, va, desc, INNER); } + +DO_MMLA_B(gvec_smmla_b, do_smmla_b) +DO_MMLA_B(gvec_ummla_b, do_ummla_b) +DO_MMLA_B(gvec_usmmla_b, do_usmmla_b) diff --git a/target/arm/vec_internal.h b/target/arm/vec_internal.h index e3eb3e7a6b..dba481e001 100644 --- a/target/arm/vec_internal.h +++ b/target/arm/vec_internal.h @@ -20,6 +20,30 @@ #ifndef TARGET_ARM_VEC_INTERNALS_H #define TARGET_ARM_VEC_INTERNALS_H +/* + * Note that vector data is stored in host-endian 64-bit chunks, + * so addressing units smaller than that needs a host-endian fixup. + * + * The H<N> macros are used when indexing an array of elements of size N. + * + * The H1_<N> macros are used when performing byte arithmetic and then + * casting the final pointer to a type of size N. + */ +#ifdef HOST_WORDS_BIGENDIAN +#define H1(x) ((x) ^ 7) +#define H1_2(x) ((x) ^ 6) +#define H1_4(x) ((x) ^ 4) +#define H2(x) ((x) ^ 3) +#define H4(x) ((x) ^ 1) +#else +#define H1(x) (x) +#define H1_2(x) (x) +#define H1_4(x) (x) +#define H2(x) (x) +#define H4(x) (x) +#endif + + static inline void clear_tail(void *vd, uintptr_t opr_sz, uintptr_t max_sz) { uint64_t *d = vd + opr_sz; @@ -30,4 +54,147 @@ static inline void clear_tail(void *vd, uintptr_t opr_sz, uintptr_t max_sz) } } +static inline int32_t do_sqrshl_bhs(int32_t src, int32_t shift, int bits, + bool round, uint32_t *sat) +{ + if (shift <= -bits) { + /* Rounding the sign bit always produces 0. */ + if (round) { + return 0; + } + return src >> 31; + } else if (shift < 0) { + if (round) { + src >>= -shift - 1; + return (src >> 1) + (src & 1); + } + return src >> -shift; + } else if (shift < bits) { + int32_t val = src << shift; + if (bits == 32) { + if (!sat || val >> shift == src) { + return val; + } + } else { + int32_t extval = sextract32(val, 0, bits); + if (!sat || val == extval) { + return extval; + } + } + } else if (!sat || src == 0) { + return 0; + } + + *sat = 1; + return (1u << (bits - 1)) - (src >= 0); +} + +static inline uint32_t do_uqrshl_bhs(uint32_t src, int32_t shift, int bits, + bool round, uint32_t *sat) +{ + if (shift <= -(bits + round)) { + return 0; + } else if (shift < 0) { + if (round) { + src >>= -shift - 1; + return (src >> 1) + (src & 1); + } + return src >> -shift; + } else if (shift < bits) { + uint32_t val = src << shift; + if (bits == 32) { + if (!sat || val >> shift == src) { + return val; + } + } else { + uint32_t extval = extract32(val, 0, bits); + if (!sat || val == extval) { + return extval; + } + } + } else if (!sat || src == 0) { + return 0; + } + + *sat = 1; + return MAKE_64BIT_MASK(0, bits); +} + +static inline int32_t do_suqrshl_bhs(int32_t src, int32_t shift, int bits, + bool round, uint32_t *sat) +{ + if (sat && src < 0) { + *sat = 1; + return 0; + } + return do_uqrshl_bhs(src, shift, bits, round, sat); +} + +static inline int64_t do_sqrshl_d(int64_t src, int64_t shift, + bool round, uint32_t *sat) +{ + if (shift <= -64) { + /* Rounding the sign bit always produces 0. */ + if (round) { + return 0; + } + return src >> 63; + } else if (shift < 0) { + if (round) { + src >>= -shift - 1; + return (src >> 1) + (src & 1); + } + return src >> -shift; + } else if (shift < 64) { + int64_t val = src << shift; + if (!sat || val >> shift == src) { + return val; + } + } else if (!sat || src == 0) { + return 0; + } + + *sat = 1; + return src < 0 ? INT64_MIN : INT64_MAX; +} + +static inline uint64_t do_uqrshl_d(uint64_t src, int64_t shift, + bool round, uint32_t *sat) +{ + if (shift <= -(64 + round)) { + return 0; + } else if (shift < 0) { + if (round) { + src >>= -shift - 1; + return (src >> 1) + (src & 1); + } + return src >> -shift; + } else if (shift < 64) { + uint64_t val = src << shift; + if (!sat || val >> shift == src) { + return val; + } + } else if (!sat || src == 0) { + return 0; + } + + *sat = 1; + return UINT64_MAX; +} + +static inline int64_t do_suqrshl_d(int64_t src, int64_t shift, + bool round, uint32_t *sat) +{ + if (sat && src < 0) { + *sat = 1; + return 0; + } + return do_uqrshl_d(src, shift, round, sat); +} + +int8_t do_sqrdmlah_b(int8_t, int8_t, int8_t, bool, bool); +int16_t do_sqrdmlah_h(int16_t, int16_t, int16_t, bool, bool, uint32_t *); +int32_t do_sqrdmlah_s(int32_t, int32_t, int32_t, bool, bool, uint32_t *); +int64_t do_sqrdmlah_d(int64_t, int64_t, int64_t, bool, bool); + #endif /* TARGET_ARM_VEC_INTERNALS_H */ |