target/arm: Use clmul_16* routines

Use generic routines for 16-bit carry-less multiply.
Remove our local version of pmull_w.

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

diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index 96ddfb4b3a30d39653e352027e464d6c39b300c7..c666a96ba17d41e5c6d39faf6dd19e33ccf5f9cb 100644 (file)
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -985,14 +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 VMULLPW_MASK 0x0000ffff0000ffffULL
-#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, 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)
+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,

diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index cd630ff905f31788a3b006fa27e99f052a19236a..5def86b5730c1f7bb82caad00825cfe492a32e88 100644 (file)
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -2029,19 +2029,6 @@ void HELPER(gvec_pmull_q)(void *vd, void *vn, void *vm, uint32_t desc)
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-uint64_t pmull_w(uint64_t op1, uint64_t op2)
-{
-    uint64_t result = 0;
-    int i;
-    for (i = 0; i < 16; ++i) {
-        uint64_t mask = (op1 & 0x0000000100000001ull) * 0xffffffff;
-        result ^= op2 & mask;
-        op1 >>= 1;
-        op2 <<= 1;
-    }
-    return result;
-}
-
 void HELPER(neon_pmull_h)(void *vd, void *vn, void *vm, uint32_t desc)
 {
     int hi = simd_data(desc);

diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h
index c4afba6d9f12c6e98b39d632ca9e367699c48840..3ca1b94ccf989e151ca308337111b63480432033 100644 (file)
--- a/target/arm/tcg/vec_internal.h
+++ b/target/arm/tcg/vec_internal.h
@@ -219,12 +219,6 @@ 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);
 
-/*
- * 16 x 16 -> 32 vector polynomial multiply where the inputs are
- * in the low 16 bits of each 32-bit element
- */
-uint64_t pmull_w(uint64_t op1, uint64_t op2);
-
 /**
  * bfdotadd:
  * @sum: addend