[PATCH v1 8/8] x86: Shrink code size of memchr-evex.S

[Noah Goldstein <goldstein.w.n@gmail.com>]

This is not meant as a performance optimization. The previous code was
far to liberal in aligning targets and wasted code size unnecissarily.

The total code size saving is: 32 bytes

There are no non-negligible changes in the benchmarks.
Geometric Mean of all benchmarks New / Old: 1.000

Full xcheck passes on x86_64.
---
 sysdeps/x86_64/multiarch/memchr-evex.S | 32 ++++++++++++++------------
 1 file changed, 17 insertions(+), 15 deletions(-)

diff --git a/sysdeps/x86_64/multiarch/memchr-evex.S b/sysdeps/x86_64/multiarch/memchr-evex.S
index cfaf02907d..ac705d66cb 100644
--- a/sysdeps/x86_64/multiarch/memchr-evex.S
+++ b/sysdeps/x86_64/multiarch/memchr-evex.S
@@ -88,7 +88,7 @@
 # define PAGE_SIZE 4096
 
 	.section SECTION(.text),"ax",@progbits
-ENTRY (MEMCHR)
+ENTRY_P2ALIGN (MEMCHR, 6)
 # ifndef USE_AS_RAWMEMCHR
 	/* Check for zero length.  */
 	test	%RDX_LP, %RDX_LP
@@ -131,22 +131,24 @@ L(zero):
 	xorl	%eax, %eax
 	ret
 
-	.p2align 5
+	.p2align 4
 L(first_vec_x0):
-	/* Check if first match was before length.  */
-	tzcntl	%eax, %eax
-	xorl	%ecx, %ecx
-	cmpl	%eax, %edx
-	leaq	(%rdi, %rax, CHAR_SIZE), %rax
-	cmovle	%rcx, %rax
+	/* Check if first match was before length. NB: tzcnt has false data-
+	   dependency on destination. eax already had a data-dependency on esi
+	   so this should have no affect here.  */
+	tzcntl	%eax, %esi
+#  ifdef USE_AS_WMEMCHR
+	leaq	(%rdi, %rsi, CHAR_SIZE), %rdi
+#  else
+	addq	%rsi, %rdi
+#  endif
+	xorl	%eax, %eax
+	cmpl	%esi, %edx
+	cmovg	%rdi, %rax
 	ret
-# else
-	/* NB: first_vec_x0 is 17 bytes which will leave
-	   cross_page_boundary (which is relatively cold) close enough
-	   to ideal alignment. So only realign L(cross_page_boundary) if
-	   rawmemchr.  */
-	.p2align 4
 # endif
+
+	.p2align 4
 L(cross_page_boundary):
 	/* Save pointer before aligning as its original value is
 	   necessary for computer return address if byte is found or
@@ -562,6 +564,6 @@ L(last_vec_x3):
 	leaq	(VEC_SIZE * 3)(%rdi, %rax, CHAR_SIZE), %rax
 	ret
 # endif
-
+	/* 7 bytes from next cache line.  */
 END (MEMCHR)
 #endif
-- 
2.34.1