commit 8e3da4c716ad6251e93972bf84428569737a913f
author Richard Henderson <richard.henderson@linaro.org> Mon Jul 10 16:07:57 2023 +0100
committer Richard Henderson <richard.henderson@linaro.org> Fri Sep 15 13:56:59 2023 +0000
tree f9b55a78ec70c9cd8f82b8ecdd08a9f74edb1790
parent 07f348d77c35b6ff1f99075e20bffbf67e772d8b

target/arm: Use clmul_8* routines

Use generic routines for 8-bit carry-less multiply.
Remove our local version of pmull_h.

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

target/arm/tcg/mve_helper.c

diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index 403b345..96ddfb4 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)
 {
@@ -984,15 +985,12 @@
  * 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(vmullpbh, 8, uint64_t, clmul_8x4_even)
+DO_2OP(vmullpth, 8, uint64_t, clmul_8x4_odd)
 DO_2OP(vmullpbw, 8, uint64_t, DO_VMULLPBW)
 DO_2OP(vmullptw, 8, uint64_t, DO_VMULLPTW)