x86: Replace sse2 instructions with avx in memcmp-evex-movbe.S

This commit replaces two usages of SSE2 'movups' with AVX 'vmovdqu'.

it could potentially be dangerous to use SSE2 if this function is ever
called without using 'vzeroupper' beforehand. While compilers appear
to use 'vzeroupper' before function calls if AVX2 has been used, using
SSE2 here is more brittle. Since it is not absolutely necessary it
should be avoided.

It costs 2-extra bytes but the extra bytes should only eat into
alignment padding.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>

diff --git a/sysdeps/x86_64/multiarch/memcmp-evex-movbe.S b/sysdeps/x86_64/multiarch/memcmp-evex-movbe.S
index 2761b54f2e7dea9f080ae173b7976c4650b6bc2c..640f6757fac8a356c726f1d9978ad074126edd62 100644 (file)
--- a/sysdeps/x86_64/multiarch/memcmp-evex-movbe.S
+++ b/sysdeps/x86_64/multiarch/memcmp-evex-movbe.S
@@ -561,13 +561,13 @@ L(between_16_31):
        /* From 16 to 31 bytes.  No branch when size == 16.  */
 
        /* Use movups to save code size.  */
-       movups  (%rsi), %xmm2
+       vmovdqu (%rsi), %xmm2
        VPCMP   $4, (%rdi), %xmm2, %k1
        kmovd   %k1, %eax
        testl   %eax, %eax
        jnz     L(return_vec_0_lv)
        /* Use overlapping loads to avoid branches.  */
-       movups  -16(%rsi, %rdx, CHAR_SIZE), %xmm2
+       vmovdqu -16(%rsi, %rdx, CHAR_SIZE), %xmm2
        VPCMP   $4, -16(%rdi, %rdx, CHAR_SIZE), %xmm2, %k1
        addl    $(CHAR_PER_VEC - (16 / CHAR_SIZE)), %edx
        kmovd   %k1, %eax