diff options
Diffstat (limited to 'target/arm/tcg/mve_helper.c')
| -rw-r--r-- | target/arm/tcg/mve_helper.c | 16 |
1 files changed, 5 insertions, 11 deletions
diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index 403b345ea3..c666a96ba1 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -26,6 +26,7 @@ #include "exec/exec-all.h" #include "tcg/tcg.h" #include "fpu/softfloat.h" +#include "crypto/clmul.h" static uint16_t mve_eci_mask(CPUARMState *env) { @@ -984,17 +985,10 @@ DO_2OP_L(vmulltuw, 1, 4, uint32_t, 8, uint64_t, DO_MUL) * Polynomial multiply. We can always do this generating 64 bits * of the result at a time, so we don't need to use DO_2OP_L. */ -#define VMULLPH_MASK 0x00ff00ff00ff00ffULL -#define VMULLPW_MASK 0x0000ffff0000ffffULL -#define DO_VMULLPBH(N, M) pmull_h((N) & VMULLPH_MASK, (M) & VMULLPH_MASK) -#define DO_VMULLPTH(N, M) DO_VMULLPBH((N) >> 8, (M) >> 8) -#define DO_VMULLPBW(N, M) pmull_w((N) & VMULLPW_MASK, (M) & VMULLPW_MASK) -#define DO_VMULLPTW(N, M) DO_VMULLPBW((N) >> 16, (M) >> 16) - -DO_2OP(vmullpbh, 8, uint64_t, DO_VMULLPBH) -DO_2OP(vmullpth, 8, uint64_t, DO_VMULLPTH) -DO_2OP(vmullpbw, 8, uint64_t, DO_VMULLPBW) -DO_2OP(vmullptw, 8, uint64_t, DO_VMULLPTW) +DO_2OP(vmullpbh, 8, uint64_t, clmul_8x4_even) +DO_2OP(vmullpth, 8, uint64_t, clmul_8x4_odd) +DO_2OP(vmullpbw, 8, uint64_t, clmul_16x2_even) +DO_2OP(vmullptw, 8, uint64_t, clmul_16x2_odd) /* * Because the computation type is at least twice as large as required, |