target/arm: Convert PMUL.8 to gvec

The gvec form will be needed for implementing SVE2.

Extend the implementation to operate on uint64_t instead of uint32_t.
Use a counted inner loop instead of terminating when op1 goes to zero,
looking toward the required implementation for ARMv8.4-DIT.

Tested-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200216214232.4230-3-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 0 insertions, 22 deletions

diff --git a/target/arm/neon_helper.c b/target/arm/neon_helper.c
index c581ffb7d3..9e7a9a1ac5 100644
--- a/target/arm/neon_helper.c
+++ b/target/arm/neon_helper.c
@@ -1131,28 +1131,6 @@ NEON_VOP(mul_u16, neon_u16, 2)
 
 /* Polynomial multiplication is like integer multiplication except the
    partial products are XORed, not added.  */
-uint32_t HELPER(neon_mul_p8)(uint32_t op1, uint32_t op2)
-{
-    uint32_t mask;
-    uint32_t result;
-    result = 0;
-    while (op1) {
-        mask = 0;
-        if (op1 & 1)
-            mask |= 0xff;
-        if (op1 & (1 << 8))
-            mask |= (0xff << 8);
-        if (op1 & (1 << 16))
-            mask |= (0xff << 16);
-        if (op1 & (1 << 24))
-            mask |= (0xff << 24);
-        result ^= op2 & mask;
-        op1 = (op1 >> 1) & 0x7f7f7f7f;
-        op2 = (op2 << 1) & 0xfefefefe;
-    }
-    return result;
-}
-
 uint64_t HELPER(neon_mull_p8)(uint32_t op1, uint32_t op2)
 {
     uint64_t result = 0;