diff options
Diffstat (limited to 'target/arm/tcg/sve_helper.c')
| -rw-r--r-- | target/arm/tcg/sve_helper.c | 294 |
1 files changed, 196 insertions, 98 deletions
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c index 43b872c7fd..c442fcb540 100644 --- a/target/arm/tcg/sve_helper.c +++ b/target/arm/tcg/sve_helper.c @@ -4484,33 +4484,35 @@ static TYPE FUNC##_reduce(TYPE *data, float_status *status, uintptr_t n) \ } \ } \ uint64_t helper_sve_##NAME##v_##SUF(void *vn, void *vg, \ - float_status *s, uint32_t desc) \ + float_status *status, uint32_t desc) \ { \ uintptr_t i, oprsz = simd_oprsz(desc), maxsz = simd_data(desc); \ TYPE data[sizeof(ARMVectorReg) / sizeof(TYPE)]; \ + TYPE ident = IDENT; \ for (i = 0; i < oprsz; ) { \ uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ do { \ TYPE nn = *(TYPE *)(vn + H(i)); \ - *(TYPE *)((void *)data + i) = (pg & 1 ? nn : IDENT); \ + *(TYPE *)((void *)data + i) = (pg & 1 ? nn : ident); \ i += sizeof(TYPE), pg >>= sizeof(TYPE); \ } while (i & 15); \ } \ for (; i < maxsz; i += sizeof(TYPE)) { \ - *(TYPE *)((void *)data + i) = IDENT; \ + *(TYPE *)((void *)data + i) = ident; \ } \ - return FUNC##_reduce(data, s, maxsz / sizeof(TYPE)); \ + return FUNC##_reduce(data, status, maxsz / sizeof(TYPE)); \ } \ void helper_sve2p1_##NAME##qv_##SUF(void *vd, void *vn, void *vg, \ float_status *status, uint32_t desc) \ { \ unsigned oprsz = simd_oprsz(desc), segments = oprsz / 16; \ + TYPE ident = IDENT; \ for (unsigned e = 0; e < 16; e += sizeof(TYPE)) { \ TYPE data[ARM_MAX_VQ]; \ for (unsigned s = 0; s < segments; s++) { \ uint16_t pg = *(uint16_t *)(vg + H1_2(s * 2)); \ - TYPE nn = *(TYPE *)(vn + H(s * 16 + H(e))); \ - data[s] = (pg >> e) & 1 ? nn : IDENT; \ + TYPE nn = *(TYPE *)(vn + (s * 16 + H(e))); \ + data[s] = (pg >> e) & 1 ? nn : ident; \ } \ *(TYPE *)(vd + H(e)) = FUNC##_reduce(data, status, segments); \ } \ @@ -4521,14 +4523,17 @@ DO_REDUCE(fadd,h, float16, H1_2, float16_add, float16_zero) DO_REDUCE(fadd,s, float32, H1_4, float32_add, float32_zero) DO_REDUCE(fadd,d, float64, H1_8, float64_add, float64_zero) -/* Identity is floatN_default_nan, without the function call. */ -DO_REDUCE(fminnm,h, float16, H1_2, float16_minnum, 0x7E00) -DO_REDUCE(fminnm,s, float32, H1_4, float32_minnum, 0x7FC00000) -DO_REDUCE(fminnm,d, float64, H1_8, float64_minnum, 0x7FF8000000000000ULL) +/* + * We can't avoid the function call for the default NaN value, because + * it changes when FPCR.AH is set. + */ +DO_REDUCE(fminnm,h, float16, H1_2, float16_minnum, float16_default_nan(status)) +DO_REDUCE(fminnm,s, float32, H1_4, float32_minnum, float32_default_nan(status)) +DO_REDUCE(fminnm,d, float64, H1_8, float64_minnum, float64_default_nan(status)) -DO_REDUCE(fmaxnm,h, float16, H1_2, float16_maxnum, 0x7E00) -DO_REDUCE(fmaxnm,s, float32, H1_4, float32_maxnum, 0x7FC00000) -DO_REDUCE(fmaxnm,d, float64, H1_8, float64_maxnum, 0x7FF8000000000000ULL) +DO_REDUCE(fmaxnm,h, float16, H1_2, float16_maxnum, float16_default_nan(status)) +DO_REDUCE(fmaxnm,s, float32, H1_4, float32_maxnum, float32_default_nan(status)) +DO_REDUCE(fmaxnm,d, float64, H1_8, float64_maxnum, float64_default_nan(status)) DO_REDUCE(fmin,h, float16, H1_2, float16_min, float16_infinity) DO_REDUCE(fmin,s, float32, H1_4, float32_min, float32_infinity) @@ -4629,14 +4634,17 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, \ } while (i != 0); \ } +DO_ZPZZ_FP(sve_fadd_b16, uint16_t, H1_2, bfloat16_add) DO_ZPZZ_FP(sve_fadd_h, uint16_t, H1_2, float16_add) DO_ZPZZ_FP(sve_fadd_s, uint32_t, H1_4, float32_add) DO_ZPZZ_FP(sve_fadd_d, uint64_t, H1_8, float64_add) +DO_ZPZZ_FP(sve_fsub_b16, uint16_t, H1_2, bfloat16_sub) DO_ZPZZ_FP(sve_fsub_h, uint16_t, H1_2, float16_sub) DO_ZPZZ_FP(sve_fsub_s, uint32_t, H1_4, float32_sub) DO_ZPZZ_FP(sve_fsub_d, uint64_t, H1_8, float64_sub) +DO_ZPZZ_FP(sve_fmul_b16, uint16_t, H1_2, bfloat16_mul) DO_ZPZZ_FP(sve_fmul_h, uint16_t, H1_2, float16_mul) DO_ZPZZ_FP(sve_fmul_s, uint32_t, H1_4, float32_mul) DO_ZPZZ_FP(sve_fmul_d, uint64_t, H1_8, float64_mul) @@ -4645,26 +4653,32 @@ DO_ZPZZ_FP(sve_fdiv_h, uint16_t, H1_2, float16_div) DO_ZPZZ_FP(sve_fdiv_s, uint32_t, H1_4, float32_div) DO_ZPZZ_FP(sve_fdiv_d, uint64_t, H1_8, float64_div) +DO_ZPZZ_FP(sve_fmin_b16, uint16_t, H1_2, bfloat16_min) DO_ZPZZ_FP(sve_fmin_h, uint16_t, H1_2, float16_min) DO_ZPZZ_FP(sve_fmin_s, uint32_t, H1_4, float32_min) DO_ZPZZ_FP(sve_fmin_d, uint64_t, H1_8, float64_min) +DO_ZPZZ_FP(sve_fmax_b16, uint16_t, H1_2, bfloat16_max) DO_ZPZZ_FP(sve_fmax_h, uint16_t, H1_2, float16_max) DO_ZPZZ_FP(sve_fmax_s, uint32_t, H1_4, float32_max) DO_ZPZZ_FP(sve_fmax_d, uint64_t, H1_8, float64_max) +DO_ZPZZ_FP(sve_ah_fmin_b16, uint16_t, H1_2, helper_sme2_ah_fmin_b16) DO_ZPZZ_FP(sve_ah_fmin_h, uint16_t, H1_2, helper_vfp_ah_minh) DO_ZPZZ_FP(sve_ah_fmin_s, uint32_t, H1_4, helper_vfp_ah_mins) DO_ZPZZ_FP(sve_ah_fmin_d, uint64_t, H1_8, helper_vfp_ah_mind) +DO_ZPZZ_FP(sve_ah_fmax_b16, uint16_t, H1_2, helper_sme2_ah_fmax_b16) DO_ZPZZ_FP(sve_ah_fmax_h, uint16_t, H1_2, helper_vfp_ah_maxh) DO_ZPZZ_FP(sve_ah_fmax_s, uint32_t, H1_4, helper_vfp_ah_maxs) DO_ZPZZ_FP(sve_ah_fmax_d, uint64_t, H1_8, helper_vfp_ah_maxd) +DO_ZPZZ_FP(sve_fminnum_b16, uint16_t, H1_2, bfloat16_minnum) DO_ZPZZ_FP(sve_fminnum_h, uint16_t, H1_2, float16_minnum) DO_ZPZZ_FP(sve_fminnum_s, uint32_t, H1_4, float32_minnum) DO_ZPZZ_FP(sve_fminnum_d, uint64_t, H1_8, float64_minnum) +DO_ZPZZ_FP(sve_fmaxnum_b16, uint16_t, H1_2, bfloat16_maxnum) DO_ZPZZ_FP(sve_fmaxnum_h, uint16_t, H1_2, float16_maxnum) DO_ZPZZ_FP(sve_fmaxnum_s, uint32_t, H1_4, float32_maxnum) DO_ZPZZ_FP(sve_fmaxnum_d, uint64_t, H1_8, float64_maxnum) @@ -5090,6 +5104,75 @@ DO_ZPZ_FP(flogb_d, float64, H1_8, do_float64_logb_as_int) #undef DO_ZPZ_FP +static void do_fmla_zpzzz_b16(void *vd, void *vn, void *vm, void *va, void *vg, + float_status *status, uint32_t desc, + uint16_t neg1, uint16_t neg3, int flags) +{ + intptr_t i = simd_oprsz(desc); + uint64_t *g = vg; + + do { + uint64_t pg = g[(i - 1) >> 6]; + do { + i -= 2; + if (likely((pg >> (i & 63)) & 1)) { + float16 e1, e2, e3, r; + + e1 = *(uint16_t *)(vn + H1_2(i)) ^ neg1; + e2 = *(uint16_t *)(vm + H1_2(i)); + e3 = *(uint16_t *)(va + H1_2(i)) ^ neg3; + r = bfloat16_muladd(e1, e2, e3, flags, status); + *(uint16_t *)(vd + H1_2(i)) = r; + } + } while (i & 63); + } while (i != 0); +} + +void HELPER(sve_fmla_zpzzz_b16)(void *vd, void *vn, void *vm, void *va, + void *vg, float_status *status, uint32_t desc) +{ + do_fmla_zpzzz_b16(vd, vn, vm, va, vg, status, desc, 0, 0, 0); +} + +void HELPER(sve_fmls_zpzzz_b16)(void *vd, void *vn, void *vm, void *va, + void *vg, float_status *status, uint32_t desc) +{ + do_fmla_zpzzz_b16(vd, vn, vm, va, vg, status, desc, 0x8000, 0, 0); +} + +void HELPER(sve_fnmla_zpzzz_b16)(void *vd, void *vn, void *vm, void *va, + void *vg, float_status *status, uint32_t desc) +{ + do_fmla_zpzzz_b16(vd, vn, vm, va, vg, status, desc, 0x8000, 0x8000, 0); +} + +void HELPER(sve_fnmls_zpzzz_b16)(void *vd, void *vn, void *vm, void *va, + void *vg, float_status *status, uint32_t desc) +{ + do_fmla_zpzzz_b16(vd, vn, vm, va, vg, status, desc, 0, 0x8000, 0); +} + +void HELPER(sve_ah_fmls_zpzzz_b16)(void *vd, void *vn, void *vm, void *va, + void *vg, float_status *status, uint32_t desc) +{ + do_fmla_zpzzz_b16(vd, vn, vm, va, vg, status, desc, 0, 0, + float_muladd_negate_product); +} + +void HELPER(sve_ah_fnmla_zpzzz_b16)(void *vd, void *vn, void *vm, void *va, + void *vg, float_status *status, uint32_t desc) +{ + do_fmla_zpzzz_b16(vd, vn, vm, va, vg, status, desc, 0, 0, + float_muladd_negate_product | float_muladd_negate_c); +} + +void HELPER(sve_ah_fnmls_zpzzz_b16)(void *vd, void *vn, void *vm, void *va, + void *vg, float_status *status, uint32_t desc) +{ + do_fmla_zpzzz_b16(vd, vn, vm, va, vg, status, desc, 0, 0, + float_muladd_negate_c); +} + static void do_fmla_zpzzz_h(void *vd, void *vn, void *vm, void *va, void *vg, float_status *status, uint32_t desc, uint16_t neg1, uint16_t neg3, int flags) @@ -6279,17 +6362,14 @@ void sve_ldN_r(CPUARMState *env, uint64_t *vg, const target_ulong addr, static inline QEMU_ALWAYS_INLINE void sve_ldN_r_mte(CPUARMState *env, uint64_t *vg, target_ulong addr, - uint32_t desc, const uintptr_t ra, + uint64_t desc, const uintptr_t ra, const int esz, const int msz, const int N, sve_ldst1_host_fn *host_fn, sve_ldst1_tlb_fn *tlb_fn) { - uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + uint32_t mtedesc = desc >> 32; int bit55 = extract64(addr, 55, 1); - /* Remove mtedesc from the normal sve descriptor. */ - desc = extract32(desc, 0, SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); - /* Perform gross MTE suppression early. */ if (!tbi_check(mtedesc, bit55) || tcma_check(mtedesc, bit55, allocation_tag_from_addr(addr))) { @@ -6301,13 +6381,13 @@ void sve_ldN_r_mte(CPUARMState *env, uint64_t *vg, target_ulong addr, #define DO_LD1_1(NAME, ESZ) \ void HELPER(sve_##NAME##_r)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldN_r(env, vg, addr, desc, GETPC(), ESZ, MO_8, 1, 0, \ sve_##NAME##_host, sve_##NAME##_tlb); \ } \ void HELPER(sve_##NAME##_r_mte)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldN_r_mte(env, vg, addr, desc, GETPC(), ESZ, MO_8, 1, \ sve_##NAME##_host, sve_##NAME##_tlb); \ @@ -6315,25 +6395,25 @@ void HELPER(sve_##NAME##_r_mte)(CPUARMState *env, void *vg, \ #define DO_LD1_2(NAME, ESZ, MSZ) \ void HELPER(sve_##NAME##_le_r)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldN_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, 1, 0, \ sve_##NAME##_le_host, sve_##NAME##_le_tlb); \ } \ void HELPER(sve_##NAME##_be_r)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldN_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, 1, 0, \ sve_##NAME##_be_host, sve_##NAME##_be_tlb); \ } \ void HELPER(sve_##NAME##_le_r_mte)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldN_r_mte(env, vg, addr, desc, GETPC(), ESZ, MSZ, 1, \ sve_##NAME##_le_host, sve_##NAME##_le_tlb); \ } \ void HELPER(sve_##NAME##_be_r_mte)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldN_r_mte(env, vg, addr, desc, GETPC(), ESZ, MSZ, 1, \ sve_##NAME##_be_host, sve_##NAME##_be_tlb); \ @@ -6359,21 +6439,21 @@ DO_LD1_2(ld1sds, MO_64, MO_32) DO_LD1_2(ld1dd, MO_64, MO_64) -DO_LD1_2(ld1squ, MO_32, MO_128) -DO_LD1_2(ld1dqu, MO_64, MO_128) +DO_LD1_2(ld1squ, MO_128, MO_32) +DO_LD1_2(ld1dqu, MO_128, MO_64) #undef DO_LD1_1 #undef DO_LD1_2 #define DO_LDN_1(N) \ void HELPER(sve_ld##N##bb_r)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldN_r(env, vg, addr, desc, GETPC(), MO_8, MO_8, N, 0, \ sve_ld1bb_host, sve_ld1bb_tlb); \ } \ void HELPER(sve_ld##N##bb_r_mte)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldN_r_mte(env, vg, addr, desc, GETPC(), MO_8, MO_8, N, \ sve_ld1bb_host, sve_ld1bb_tlb); \ @@ -6381,25 +6461,25 @@ void HELPER(sve_ld##N##bb_r_mte)(CPUARMState *env, void *vg, \ #define DO_LDN_2(N, SUFF, ESZ) \ void HELPER(sve_ld##N##SUFF##_le_r)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldN_r(env, vg, addr, desc, GETPC(), ESZ, ESZ, N, 0, \ sve_ld1##SUFF##_le_host, sve_ld1##SUFF##_le_tlb); \ } \ void HELPER(sve_ld##N##SUFF##_be_r)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldN_r(env, vg, addr, desc, GETPC(), ESZ, ESZ, N, 0, \ sve_ld1##SUFF##_be_host, sve_ld1##SUFF##_be_tlb); \ } \ void HELPER(sve_ld##N##SUFF##_le_r_mte)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldN_r_mte(env, vg, addr, desc, GETPC(), ESZ, ESZ, N, \ sve_ld1##SUFF##_le_host, sve_ld1##SUFF##_le_tlb); \ } \ void HELPER(sve_ld##N##SUFF##_be_r_mte)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldN_r_mte(env, vg, addr, desc, GETPC(), ESZ, ESZ, N, \ sve_ld1##SUFF##_be_host, sve_ld1##SUFF##_be_tlb); \ @@ -6644,17 +6724,14 @@ void sve_ldnfff1_r(CPUARMState *env, void *vg, const target_ulong addr, static inline QEMU_ALWAYS_INLINE void sve_ldnfff1_r_mte(CPUARMState *env, void *vg, target_ulong addr, - uint32_t desc, const uintptr_t retaddr, + uint64_t desc, const uintptr_t retaddr, const int esz, const int msz, const SVEContFault fault, sve_ldst1_host_fn *host_fn, sve_ldst1_tlb_fn *tlb_fn) { - uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + uint32_t mtedesc = desc >> 32; int bit55 = extract64(addr, 55, 1); - /* Remove mtedesc from the normal sve descriptor. */ - desc = extract32(desc, 0, SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); - /* Perform gross MTE suppression early. */ if (!tbi_check(mtedesc, bit55) || tcma_check(mtedesc, bit55, allocation_tag_from_addr(addr))) { @@ -6667,25 +6744,25 @@ void sve_ldnfff1_r_mte(CPUARMState *env, void *vg, target_ulong addr, #define DO_LDFF1_LDNF1_1(PART, ESZ) \ void HELPER(sve_ldff1##PART##_r)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldnfff1_r(env, vg, addr, desc, GETPC(), 0, ESZ, MO_8, FAULT_FIRST, \ sve_ld1##PART##_host, sve_ld1##PART##_tlb); \ } \ void HELPER(sve_ldnf1##PART##_r)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldnfff1_r(env, vg, addr, desc, GETPC(), 0, ESZ, MO_8, FAULT_NO, \ sve_ld1##PART##_host, sve_ld1##PART##_tlb); \ } \ void HELPER(sve_ldff1##PART##_r_mte)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldnfff1_r_mte(env, vg, addr, desc, GETPC(), ESZ, MO_8, FAULT_FIRST, \ sve_ld1##PART##_host, sve_ld1##PART##_tlb); \ } \ void HELPER(sve_ldnf1##PART##_r_mte)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldnfff1_r_mte(env, vg, addr, desc, GETPC(), ESZ, MO_8, FAULT_NO, \ sve_ld1##PART##_host, sve_ld1##PART##_tlb); \ @@ -6693,49 +6770,49 @@ void HELPER(sve_ldnf1##PART##_r_mte)(CPUARMState *env, void *vg, \ #define DO_LDFF1_LDNF1_2(PART, ESZ, MSZ) \ void HELPER(sve_ldff1##PART##_le_r)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldnfff1_r(env, vg, addr, desc, GETPC(), 0, ESZ, MSZ, FAULT_FIRST, \ sve_ld1##PART##_le_host, sve_ld1##PART##_le_tlb); \ } \ void HELPER(sve_ldnf1##PART##_le_r)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldnfff1_r(env, vg, addr, desc, GETPC(), 0, ESZ, MSZ, FAULT_NO, \ sve_ld1##PART##_le_host, sve_ld1##PART##_le_tlb); \ } \ void HELPER(sve_ldff1##PART##_be_r)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldnfff1_r(env, vg, addr, desc, GETPC(), 0, ESZ, MSZ, FAULT_FIRST, \ sve_ld1##PART##_be_host, sve_ld1##PART##_be_tlb); \ } \ void HELPER(sve_ldnf1##PART##_be_r)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldnfff1_r(env, vg, addr, desc, GETPC(), 0, ESZ, MSZ, FAULT_NO, \ sve_ld1##PART##_be_host, sve_ld1##PART##_be_tlb); \ } \ void HELPER(sve_ldff1##PART##_le_r_mte)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldnfff1_r_mte(env, vg, addr, desc, GETPC(), ESZ, MSZ, FAULT_FIRST, \ sve_ld1##PART##_le_host, sve_ld1##PART##_le_tlb); \ } \ void HELPER(sve_ldnf1##PART##_le_r_mte)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldnfff1_r_mte(env, vg, addr, desc, GETPC(), ESZ, MSZ, FAULT_NO, \ sve_ld1##PART##_le_host, sve_ld1##PART##_le_tlb); \ } \ void HELPER(sve_ldff1##PART##_be_r_mte)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldnfff1_r_mte(env, vg, addr, desc, GETPC(), ESZ, MSZ, FAULT_FIRST, \ sve_ld1##PART##_be_host, sve_ld1##PART##_be_tlb); \ } \ void HELPER(sve_ldnf1##PART##_be_r_mte)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_ldnfff1_r_mte(env, vg, addr, desc, GETPC(), ESZ, MSZ, FAULT_NO, \ sve_ld1##PART##_be_host, sve_ld1##PART##_be_tlb); \ @@ -6902,17 +6979,14 @@ void sve_stN_r(CPUARMState *env, uint64_t *vg, target_ulong addr, static inline QEMU_ALWAYS_INLINE void sve_stN_r_mte(CPUARMState *env, uint64_t *vg, target_ulong addr, - uint32_t desc, const uintptr_t ra, + uint64_t desc, const uintptr_t ra, const int esz, const int msz, const int N, sve_ldst1_host_fn *host_fn, sve_ldst1_tlb_fn *tlb_fn) { - uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + uint32_t mtedesc = desc >> 32; int bit55 = extract64(addr, 55, 1); - /* Remove mtedesc from the normal sve descriptor. */ - desc = extract32(desc, 0, SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); - /* Perform gross MTE suppression early. */ if (!tbi_check(mtedesc, bit55) || tcma_check(mtedesc, bit55, allocation_tag_from_addr(addr))) { @@ -6924,13 +6998,13 @@ void sve_stN_r_mte(CPUARMState *env, uint64_t *vg, target_ulong addr, #define DO_STN_1(N, NAME, ESZ) \ void HELPER(sve_st##N##NAME##_r)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_stN_r(env, vg, addr, desc, GETPC(), ESZ, MO_8, N, 0, \ sve_st1##NAME##_host, sve_st1##NAME##_tlb); \ } \ void HELPER(sve_st##N##NAME##_r_mte)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_stN_r_mte(env, vg, addr, desc, GETPC(), ESZ, MO_8, N, \ sve_st1##NAME##_host, sve_st1##NAME##_tlb); \ @@ -6938,25 +7012,25 @@ void HELPER(sve_st##N##NAME##_r_mte)(CPUARMState *env, void *vg, \ #define DO_STN_2(N, NAME, ESZ, MSZ) \ void HELPER(sve_st##N##NAME##_le_r)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_stN_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, N, 0, \ sve_st1##NAME##_le_host, sve_st1##NAME##_le_tlb); \ } \ void HELPER(sve_st##N##NAME##_be_r)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_stN_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, N, 0, \ sve_st1##NAME##_be_host, sve_st1##NAME##_be_tlb); \ } \ void HELPER(sve_st##N##NAME##_le_r_mte)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_stN_r_mte(env, vg, addr, desc, GETPC(), ESZ, MSZ, N, \ sve_st1##NAME##_le_host, sve_st1##NAME##_le_tlb); \ } \ void HELPER(sve_st##N##NAME##_be_r_mte)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint64_t desc) \ { \ sve_stN_r_mte(env, vg, addr, desc, GETPC(), ESZ, MSZ, N, \ sve_st1##NAME##_be_host, sve_st1##NAME##_be_tlb); \ @@ -7100,14 +7174,12 @@ void sve_ld1_z(CPUARMState *env, void *vd, uint64_t *vg, void *vm, static inline QEMU_ALWAYS_INLINE void sve_ld1_z_mte(CPUARMState *env, void *vd, uint64_t *vg, void *vm, - target_ulong base, uint32_t desc, uintptr_t retaddr, + target_ulong base, uint64_t desc, uintptr_t retaddr, int esize, int msize, zreg_off_fn *off_fn, sve_ldst1_host_fn *host_fn, sve_ldst1_tlb_fn *tlb_fn) { - uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); - /* Remove mtedesc from the normal sve descriptor. */ - desc = extract32(desc, 0, SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + uint32_t mtedesc = desc >> 32; /* * ??? TODO: For the 32-bit offset extractions, base + ofs cannot @@ -7121,13 +7193,13 @@ void sve_ld1_z_mte(CPUARMState *env, void *vd, uint64_t *vg, void *vm, #define DO_LD1_ZPZ_S(MEM, OFS, MSZ) \ void HELPER(sve_ld##MEM##_##OFS)(CPUARMState *env, void *vd, void *vg, \ - void *vm, target_ulong base, uint32_t desc) \ + void *vm, target_ulong base, uint64_t desc) \ { \ sve_ld1_z(env, vd, vg, vm, base, desc, GETPC(), 0, 4, 1 << MSZ, \ off_##OFS##_s, sve_ld1##MEM##_host, sve_ld1##MEM##_tlb); \ } \ void HELPER(sve_ld##MEM##_##OFS##_mte)(CPUARMState *env, void *vd, void *vg, \ - void *vm, target_ulong base, uint32_t desc) \ + void *vm, target_ulong base, uint64_t desc) \ { \ sve_ld1_z_mte(env, vd, vg, vm, base, desc, GETPC(), 4, 1 << MSZ, \ off_##OFS##_s, sve_ld1##MEM##_host, sve_ld1##MEM##_tlb); \ @@ -7135,18 +7207,32 @@ void HELPER(sve_ld##MEM##_##OFS##_mte)(CPUARMState *env, void *vd, void *vg, \ #define DO_LD1_ZPZ_D(MEM, OFS, MSZ) \ void HELPER(sve_ld##MEM##_##OFS)(CPUARMState *env, void *vd, void *vg, \ - void *vm, target_ulong base, uint32_t desc) \ + void *vm, target_ulong base, uint64_t desc) \ { \ sve_ld1_z(env, vd, vg, vm, base, desc, GETPC(), 0, 8, 1 << MSZ, \ off_##OFS##_d, sve_ld1##MEM##_host, sve_ld1##MEM##_tlb); \ } \ void HELPER(sve_ld##MEM##_##OFS##_mte)(CPUARMState *env, void *vd, void *vg, \ - void *vm, target_ulong base, uint32_t desc) \ + void *vm, target_ulong base, uint64_t desc) \ { \ sve_ld1_z_mte(env, vd, vg, vm, base, desc, GETPC(), 8, 1 << MSZ, \ off_##OFS##_d, sve_ld1##MEM##_host, sve_ld1##MEM##_tlb); \ } +#define DO_LD1_ZPZ_Q(MEM, OFS, MSZ) \ +void HELPER(sve_ld##MEM##_##OFS)(CPUARMState *env, void *vd, void *vg, \ + void *vm, target_ulong base, uint64_t desc) \ +{ \ + sve_ld1_z(env, vd, vg, vm, base, desc, GETPC(), 0, 16, 1 << MSZ, \ + off_##OFS##_d, sve_ld1##MEM##_host, sve_ld1##MEM##_tlb); \ +} \ +void HELPER(sve_ld##MEM##_##OFS##_mte)(CPUARMState *env, void *vd, void *vg, \ + void *vm, target_ulong base, uint64_t desc) \ +{ \ + sve_ld1_z_mte(env, vd, vg, vm, base, desc, GETPC(), 16, 1 << MSZ, \ + off_##OFS##_d, sve_ld1##MEM##_host, sve_ld1##MEM##_tlb); \ +} + DO_LD1_ZPZ_S(bsu, zsu, MO_8) DO_LD1_ZPZ_S(bsu, zss, MO_8) DO_LD1_ZPZ_D(bdu, zsu, MO_8) @@ -7211,8 +7297,8 @@ DO_LD1_ZPZ_D(dd_be, zsu, MO_64) DO_LD1_ZPZ_D(dd_be, zss, MO_64) DO_LD1_ZPZ_D(dd_be, zd, MO_64) -DO_LD1_ZPZ_D(qq_le, zd, MO_128) -DO_LD1_ZPZ_D(qq_be, zd, MO_128) +DO_LD1_ZPZ_Q(qq_le, zd, MO_128) +DO_LD1_ZPZ_Q(qq_be, zd, MO_128) #undef DO_LD1_ZPZ_S #undef DO_LD1_ZPZ_D @@ -7312,15 +7398,13 @@ void sve_ldff1_z(CPUARMState *env, void *vd, uint64_t *vg, void *vm, static inline QEMU_ALWAYS_INLINE void sve_ldff1_z_mte(CPUARMState *env, void *vd, uint64_t *vg, void *vm, - target_ulong base, uint32_t desc, uintptr_t retaddr, + target_ulong base, uint64_t desc, uintptr_t retaddr, const int esz, const int msz, zreg_off_fn *off_fn, sve_ldst1_host_fn *host_fn, sve_ldst1_tlb_fn *tlb_fn) { - uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); - /* Remove mtedesc from the normal sve descriptor. */ - desc = extract32(desc, 0, SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + uint32_t mtedesc = desc >> 32; /* * ??? TODO: For the 32-bit offset extractions, base + ofs cannot @@ -7335,14 +7419,14 @@ void sve_ldff1_z_mte(CPUARMState *env, void *vd, uint64_t *vg, void *vm, #define DO_LDFF1_ZPZ_S(MEM, OFS, MSZ) \ void HELPER(sve_ldff##MEM##_##OFS) \ (CPUARMState *env, void *vd, void *vg, \ - void *vm, target_ulong base, uint32_t desc) \ + void *vm, target_ulong base, uint64_t desc) \ { \ sve_ldff1_z(env, vd, vg, vm, base, desc, GETPC(), 0, MO_32, MSZ, \ off_##OFS##_s, sve_ld1##MEM##_host, sve_ld1##MEM##_tlb); \ } \ void HELPER(sve_ldff##MEM##_##OFS##_mte) \ (CPUARMState *env, void *vd, void *vg, \ - void *vm, target_ulong base, uint32_t desc) \ + void *vm, target_ulong base, uint64_t desc) \ { \ sve_ldff1_z_mte(env, vd, vg, vm, base, desc, GETPC(), MO_32, MSZ, \ off_##OFS##_s, sve_ld1##MEM##_host, sve_ld1##MEM##_tlb); \ @@ -7351,14 +7435,14 @@ void HELPER(sve_ldff##MEM##_##OFS##_mte) \ #define DO_LDFF1_ZPZ_D(MEM, OFS, MSZ) \ void HELPER(sve_ldff##MEM##_##OFS) \ (CPUARMState *env, void *vd, void *vg, \ - void *vm, target_ulong base, uint32_t desc) \ + void *vm, target_ulong base, uint64_t desc) \ { \ sve_ldff1_z(env, vd, vg, vm, base, desc, GETPC(), 0, MO_64, MSZ, \ off_##OFS##_d, sve_ld1##MEM##_host, sve_ld1##MEM##_tlb); \ } \ void HELPER(sve_ldff##MEM##_##OFS##_mte) \ (CPUARMState *env, void *vd, void *vg, \ - void *vm, target_ulong base, uint32_t desc) \ + void *vm, target_ulong base, uint64_t desc) \ { \ sve_ldff1_z_mte(env, vd, vg, vm, base, desc, GETPC(), MO_64, MSZ, \ off_##OFS##_d, sve_ld1##MEM##_host, sve_ld1##MEM##_tlb); \ @@ -7517,14 +7601,12 @@ void sve_st1_z(CPUARMState *env, void *vd, uint64_t *vg, void *vm, static inline QEMU_ALWAYS_INLINE void sve_st1_z_mte(CPUARMState *env, void *vd, uint64_t *vg, void *vm, - target_ulong base, uint32_t desc, uintptr_t retaddr, + target_ulong base, uint64_t desc, uintptr_t retaddr, int esize, int msize, zreg_off_fn *off_fn, sve_ldst1_host_fn *host_fn, sve_ldst1_tlb_fn *tlb_fn) { - uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); - /* Remove mtedesc from the normal sve descriptor. */ - desc = extract32(desc, 0, SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + uint32_t mtedesc = desc >> 32; /* * ??? TODO: For the 32-bit offset extractions, base + ofs cannot @@ -7538,13 +7620,13 @@ void sve_st1_z_mte(CPUARMState *env, void *vd, uint64_t *vg, void *vm, #define DO_ST1_ZPZ_S(MEM, OFS, MSZ) \ void HELPER(sve_st##MEM##_##OFS)(CPUARMState *env, void *vd, void *vg, \ - void *vm, target_ulong base, uint32_t desc) \ + void *vm, target_ulong base, uint64_t desc) \ { \ sve_st1_z(env, vd, vg, vm, base, desc, GETPC(), 0, 4, 1 << MSZ, \ off_##OFS##_s, sve_st1##MEM##_host, sve_st1##MEM##_tlb); \ } \ void HELPER(sve_st##MEM##_##OFS##_mte)(CPUARMState *env, void *vd, void *vg, \ - void *vm, target_ulong base, uint32_t desc) \ + void *vm, target_ulong base, uint64_t desc) \ { \ sve_st1_z_mte(env, vd, vg, vm, base, desc, GETPC(), 4, 1 << MSZ, \ off_##OFS##_s, sve_st1##MEM##_host, sve_st1##MEM##_tlb); \ @@ -7552,18 +7634,32 @@ void HELPER(sve_st##MEM##_##OFS##_mte)(CPUARMState *env, void *vd, void *vg, \ #define DO_ST1_ZPZ_D(MEM, OFS, MSZ) \ void HELPER(sve_st##MEM##_##OFS)(CPUARMState *env, void *vd, void *vg, \ - void *vm, target_ulong base, uint32_t desc) \ + void *vm, target_ulong base, uint64_t desc) \ { \ sve_st1_z(env, vd, vg, vm, base, desc, GETPC(), 0, 8, 1 << MSZ, \ off_##OFS##_d, sve_st1##MEM##_host, sve_st1##MEM##_tlb); \ } \ void HELPER(sve_st##MEM##_##OFS##_mte)(CPUARMState *env, void *vd, void *vg, \ - void *vm, target_ulong base, uint32_t desc) \ + void *vm, target_ulong base, uint64_t desc) \ { \ sve_st1_z_mte(env, vd, vg, vm, base, desc, GETPC(), 8, 1 << MSZ, \ off_##OFS##_d, sve_st1##MEM##_host, sve_st1##MEM##_tlb); \ } +#define DO_ST1_ZPZ_Q(MEM, OFS, MSZ) \ +void HELPER(sve_st##MEM##_##OFS)(CPUARMState *env, void *vd, void *vg, \ + void *vm, target_ulong base, uint64_t desc) \ +{ \ + sve_st1_z(env, vd, vg, vm, base, desc, GETPC(), 0, 16, 1 << MSZ, \ + off_##OFS##_d, sve_st1##MEM##_host, sve_st1##MEM##_tlb); \ +} \ +void HELPER(sve_st##MEM##_##OFS##_mte)(CPUARMState *env, void *vd, void *vg, \ + void *vm, target_ulong base, uint64_t desc) \ +{ \ + sve_st1_z_mte(env, vd, vg, vm, base, desc, GETPC(), 16, 1 << MSZ, \ + off_##OFS##_d, sve_st1##MEM##_host, sve_st1##MEM##_tlb); \ +} + DO_ST1_ZPZ_S(bs, zsu, MO_8) DO_ST1_ZPZ_S(hs_le, zsu, MO_16) DO_ST1_ZPZ_S(hs_be, zsu, MO_16) @@ -7600,8 +7696,8 @@ DO_ST1_ZPZ_D(sd_be, zd, MO_32) DO_ST1_ZPZ_D(dd_le, zd, MO_64) DO_ST1_ZPZ_D(dd_be, zd, MO_64) -DO_ST1_ZPZ_D(qq_le, zd, MO_128) -DO_ST1_ZPZ_D(qq_be, zd, MO_128) +DO_ST1_ZPZ_Q(qq_le, zd, MO_128) +DO_ST1_ZPZ_Q(qq_be, zd, MO_128) #undef DO_ST1_ZPZ_S #undef DO_ST1_ZPZ_D @@ -7770,14 +7866,15 @@ static void sve2p1_cont_ldst_mte_check(SVEContLdSt *info, CPUARMState *env, static inline QEMU_ALWAYS_INLINE void sve2p1_ld1_c(CPUARMState *env, ARMVectorReg *zd, const vaddr addr, - uint32_t png, uint32_t desc, + uint32_t png, uint64_t desc64, const uintptr_t ra, const MemOp esz, sve_ldst1_host_fn *host_fn, sve_ldst1_tlb_fn *tlb_fn) { + uint32_t mtedesc = desc64 >> 32; + uint32_t desc = desc64; const unsigned N = (desc >> SIMD_DATA_SHIFT) & 1 ? 4 : 2; const unsigned rstride = 1 << ((desc >> (SIMD_DATA_SHIFT + 1)) % 4); - uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); const intptr_t reg_max = simd_oprsz(desc); const unsigned esize = 1 << esz; intptr_t count_off, count_last; @@ -7912,7 +8009,7 @@ void sve2p1_ld1_c(CPUARMState *env, ARMVectorReg *zd, const vaddr addr, } void HELPER(sve2p1_ld1bb_c)(CPUARMState *env, void *vd, target_ulong addr, - uint32_t png, uint32_t desc) + uint32_t png, uint64_t desc) { sve2p1_ld1_c(env, vd, addr, png, desc, GETPC(), MO_8, sve_ld1bb_host, sve_ld1bb_tlb); @@ -7921,14 +8018,14 @@ void HELPER(sve2p1_ld1bb_c)(CPUARMState *env, void *vd, target_ulong addr, #define DO_LD1_2(NAME, ESZ) \ void HELPER(sve2p1_##NAME##_le_c)(CPUARMState *env, void *vd, \ target_ulong addr, uint32_t png, \ - uint32_t desc) \ + uint64_t desc) \ { \ sve2p1_ld1_c(env, vd, addr, png, desc, GETPC(), ESZ, \ sve_##NAME##_le_host, sve_##NAME##_le_tlb); \ } \ void HELPER(sve2p1_##NAME##_be_c)(CPUARMState *env, void *vd, \ target_ulong addr, uint32_t png, \ - uint32_t desc) \ + uint64_t desc) \ { \ sve2p1_ld1_c(env, vd, addr, png, desc, GETPC(), ESZ, \ sve_##NAME##_be_host, sve_##NAME##_be_tlb); \ @@ -7942,14 +8039,15 @@ DO_LD1_2(ld1dd, MO_64) static inline QEMU_ALWAYS_INLINE void sve2p1_st1_c(CPUARMState *env, ARMVectorReg *zd, const vaddr addr, - uint32_t png, uint32_t desc, + uint32_t png, uint64_t desc64, const uintptr_t ra, const int esz, sve_ldst1_host_fn *host_fn, sve_ldst1_tlb_fn *tlb_fn) { + uint32_t mtedesc = desc64 >> 32; + uint32_t desc = desc64; const unsigned N = (desc >> SIMD_DATA_SHIFT) & 1 ? 4 : 2; const unsigned rstride = 1 << ((desc >> (SIMD_DATA_SHIFT + 1)) % 4); - uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); const intptr_t reg_max = simd_oprsz(desc); const unsigned esize = 1 << esz; intptr_t count_off, count_last; @@ -8071,7 +8169,7 @@ void sve2p1_st1_c(CPUARMState *env, ARMVectorReg *zd, const vaddr addr, } void HELPER(sve2p1_st1bb_c)(CPUARMState *env, void *vd, target_ulong addr, - uint32_t png, uint32_t desc) + uint32_t png, uint64_t desc) { sve2p1_st1_c(env, vd, addr, png, desc, GETPC(), MO_8, sve_st1bb_host, sve_st1bb_tlb); @@ -8080,14 +8178,14 @@ void HELPER(sve2p1_st1bb_c)(CPUARMState *env, void *vd, target_ulong addr, #define DO_ST1_2(NAME, ESZ) \ void HELPER(sve2p1_##NAME##_le_c)(CPUARMState *env, void *vd, \ target_ulong addr, uint32_t png, \ - uint32_t desc) \ + uint64_t desc) \ { \ sve2p1_st1_c(env, vd, addr, png, desc, GETPC(), ESZ, \ sve_##NAME##_le_host, sve_##NAME##_le_tlb); \ } \ void HELPER(sve2p1_##NAME##_be_c)(CPUARMState *env, void *vd, \ target_ulong addr, uint32_t png, \ - uint32_t desc) \ + uint64_t desc) \ { \ sve2p1_st1_c(env, vd, addr, png, desc, GETPC(), ESZ, \ sve_##NAME##_be_host, sve_##NAME##_be_tlb); \ |