From d16c728bff5a92a254d7078d1766a4f3070acd66 Mon Sep 17 00:00:00 2001
From: Noah Goldstein <goldstein.w.n@gmail.com>
Date: Mon, 10 Jan 2022 15:35:39 -0600
Subject: [PATCH] x86: Optimize strcmp-evex.S

Optimization are primarily to the loop logic and how the page cross
logic interacts with the loop.

The page cross logic is at times more expensive for short strings near
the end of a page but not crossing the page. This is done to retest
the page cross conditions with a non-faulty check and to improve the
logic for entering the loop afterwards. This is only particular cases,
however, and is general made up for by more than 10x improvements on
the transition from the page cross -> loop case.

The non-page cross cases as well are nearly universally improved.

test-strcmp, test-strncmp, test-wcscmp, and test-wcsncmp all pass.

Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
(cherry picked from commit 8418eb3ff4b781d31c4ed5dc6c0bd7356bc45db9)
---
 sysdeps/x86_64/multiarch/strcmp-evex.S | 1712 +++++++++++++-----------
 1 file changed, 919 insertions(+), 793 deletions(-)

diff --git a/sysdeps/x86_64/multiarch/strcmp-evex.S b/sysdeps/x86_64/multiarch/strcmp-evex.S
index 6f5c4bf9..99d8409a 100644
--- a/sysdeps/x86_64/multiarch/strcmp-evex.S
+++ b/sysdeps/x86_64/multiarch/strcmp-evex.S
@@ -26,54 +26,69 @@
 
 # define PAGE_SIZE	4096
 
-/* VEC_SIZE = Number of bytes in a ymm register */
+	/* VEC_SIZE = Number of bytes in a ymm register.  */
 # define VEC_SIZE	32
+# define CHAR_PER_VEC	(VEC_SIZE	/	SIZE_OF_CHAR)
 
-/* Shift for dividing by (VEC_SIZE * 4).  */
-# define DIVIDE_BY_VEC_4_SHIFT	7
-# if (VEC_SIZE * 4) != (1 << DIVIDE_BY_VEC_4_SHIFT)
-#  error (VEC_SIZE * 4) != (1 << DIVIDE_BY_VEC_4_SHIFT)
-# endif
-
-# define VMOVU		vmovdqu64
-# define VMOVA		vmovdqa64
+# define VMOVU	vmovdqu64
+# define VMOVA	vmovdqa64
 
 # ifdef USE_AS_WCSCMP
-/* Compare packed dwords.  */
-#  define VPCMP		vpcmpd
+#  define TESTEQ	subl	$0xff,
+	/* Compare packed dwords.  */
+#  define VPCMP	vpcmpd
 #  define VPMINU	vpminud
 #  define VPTESTM	vptestmd
-#  define SHIFT_REG32	r8d
-#  define SHIFT_REG64	r8
-/* 1 dword char == 4 bytes.  */
+	/* 1 dword char == 4 bytes.  */
 #  define SIZE_OF_CHAR	4
 # else
-/* Compare packed bytes.  */
-#  define VPCMP		vpcmpb
+#  define TESTEQ	incl
+	/* Compare packed bytes.  */
+#  define VPCMP	vpcmpb
 #  define VPMINU	vpminub
 #  define VPTESTM	vptestmb
-#  define SHIFT_REG32	ecx
-#  define SHIFT_REG64	rcx
-/* 1 byte char == 1 byte.  */
+	/* 1 byte char == 1 byte.  */
 #  define SIZE_OF_CHAR	1
 # endif
 
+# ifdef USE_AS_STRNCMP
+#  define LOOP_REG	r9d
+#  define LOOP_REG64	r9
+
+#  define OFFSET_REG8	r9b
+#  define OFFSET_REG	r9d
+#  define OFFSET_REG64	r9
+# else
+#  define LOOP_REG	edx
+#  define LOOP_REG64	rdx
+
+#  define OFFSET_REG8	dl
+#  define OFFSET_REG	edx
+#  define OFFSET_REG64	rdx
+# endif
+
+# if defined USE_AS_STRNCMP || defined USE_AS_WCSCMP
+#  define VEC_OFFSET	0
+# else
+#  define VEC_OFFSET	(-VEC_SIZE)
+# endif
+
 # define XMMZERO	xmm16
-# define XMM0		xmm17
-# define XMM1		xmm18
+# define XMM0	xmm17
+# define XMM1	xmm18
 
 # define YMMZERO	ymm16
-# define YMM0		ymm17
-# define YMM1		ymm18
-# define YMM2		ymm19
-# define YMM3		ymm20
-# define YMM4		ymm21
-# define YMM5		ymm22
-# define YMM6		ymm23
-# define YMM7		ymm24
-# define YMM8		ymm25
-# define YMM9		ymm26
-# define YMM10		ymm27
+# define YMM0	ymm17
+# define YMM1	ymm18
+# define YMM2	ymm19
+# define YMM3	ymm20
+# define YMM4	ymm21
+# define YMM5	ymm22
+# define YMM6	ymm23
+# define YMM7	ymm24
+# define YMM8	ymm25
+# define YMM9	ymm26
+# define YMM10	ymm27
 
 /* Warning!
            wcscmp/wcsncmp have to use SIGNED comparison for elements.
@@ -96,985 +111,1096 @@
    the maximum offset is reached before a difference is found, zero is
    returned.  */
 
-	.section .text.evex,"ax",@progbits
-ENTRY (STRCMP)
+	.section .text.evex, "ax", @progbits
+ENTRY(STRCMP)
 # ifdef USE_AS_STRNCMP
-	/* Check for simple cases (0 or 1) in offset.  */
-	cmp	$1, %RDX_LP
-	je	L(char0)
-	jb	L(zero)
-#  ifdef USE_AS_WCSCMP
-#  ifndef __ILP32__
-	movq	%rdx, %rcx
-	/* Check if length could overflow when multiplied by
-	   sizeof(wchar_t). Checking top 8 bits will cover all potential
-	   overflow cases as well as redirect cases where its impossible to
-	   length to bound a valid memory region. In these cases just use
-	   'wcscmp'.  */
-	shrq	$56, %rcx
-	jnz	__wcscmp_evex
-#  endif
-	/* Convert units: from wide to byte char.  */
-	shl	$2, %RDX_LP
+#  ifdef __ILP32__
+	/* Clear the upper 32 bits.  */
+	movl	%edx, %rdx
 #  endif
-	/* Register %r11 tracks the maximum offset.  */
-	mov	%RDX_LP, %R11_LP
+	cmp	$1, %RDX_LP
+	/* Signed comparison intentional. We use this branch to also
+	   test cases where length >= 2^63. These very large sizes can be
+	   handled with strcmp as there is no way for that length to
+	   actually bound the buffer.  */
+	jle	L(one_or_less)
 # endif
 	movl	%edi, %eax
-	xorl	%edx, %edx
-	/* Make %XMMZERO (%YMMZERO) all zeros in this function.  */
-	vpxorq	%XMMZERO, %XMMZERO, %XMMZERO
 	orl	%esi, %eax
-	andl	$(PAGE_SIZE - 1), %eax
-	cmpl	$(PAGE_SIZE - (VEC_SIZE * 4)), %eax
-	jg	L(cross_page)
-	/* Start comparing 4 vectors.  */
+	/* Shift out the bits irrelivant to page boundary ([63:12]).  */
+	sall	$20, %eax
+	/* Check if s1 or s2 may cross a page in next 4x VEC loads.  */
+	cmpl	$((PAGE_SIZE -(VEC_SIZE * 4)) << 20), %eax
+	ja	L(page_cross)
+
+L(no_page_cross):
+	/* Safe to compare 4x vectors.  */
 	VMOVU	(%rdi), %YMM0
-
-	/* Each bit set in K2 represents a non-null CHAR in YMM0.  */
 	VPTESTM	%YMM0, %YMM0, %k2
-
 	/* Each bit cleared in K1 represents a mismatch or a null CHAR
 	   in YMM0 and 32 bytes at (%rsi).  */
 	VPCMP	$0, (%rsi), %YMM0, %k1{%k2}
-
 	kmovd	%k1, %ecx
-# ifdef USE_AS_WCSCMP
-	subl	$0xff, %ecx
-# else
-	incl	%ecx
-# endif
-	je	L(next_3_vectors)
-	tzcntl	%ecx, %edx
-# ifdef USE_AS_WCSCMP
-	/* NB: Multiply wchar_t count by 4 to get the number of bytes.  */
-	sall	$2, %edx
-# endif
 # ifdef USE_AS_STRNCMP
-	/* Return 0 if the mismatched index (%rdx) is after the maximum
-	   offset (%r11).   */
-	cmpq	%r11, %rdx
-	jae	L(zero)
+	cmpq	$CHAR_PER_VEC, %rdx
+	jbe	L(vec_0_test_len)
 # endif
+
+	/* TESTEQ is `incl` for strcmp/strncmp and `subl $0xff` for
+	   wcscmp/wcsncmp.  */
+
+	/* All 1s represents all equals. TESTEQ will overflow to zero in
+	   all equals case. Otherwise 1s will carry until position of first
+	   mismatch.  */
+	TESTEQ	%ecx
+	jz	L(more_3x_vec)
+
+	.p2align 4,, 4
+L(return_vec_0):
+	tzcntl	%ecx, %ecx
 # ifdef USE_AS_WCSCMP
+	movl	(%rdi, %rcx, SIZE_OF_CHAR), %edx
 	xorl	%eax, %eax
-	movl	(%rdi, %rdx), %ecx
-	cmpl	(%rsi, %rdx), %ecx
-	je	L(return)
-L(wcscmp_return):
+	cmpl	(%rsi, %rcx, SIZE_OF_CHAR), %edx
+	je	L(ret0)
 	setl	%al
 	negl	%eax
 	orl	$1, %eax
-L(return):
 # else
-	movzbl	(%rdi, %rdx), %eax
-	movzbl	(%rsi, %rdx), %edx
-	subl	%edx, %eax
+	movzbl	(%rdi, %rcx), %eax
+	movzbl	(%rsi, %rcx), %ecx
+	subl	%ecx, %eax
 # endif
+L(ret0):
 	ret
 
-L(return_vec_size):
-	tzcntl	%ecx, %edx
-# ifdef USE_AS_WCSCMP
-	/* NB: Multiply wchar_t count by 4 to get the number of bytes.  */
-	sall	$2, %edx
-# endif
 # ifdef USE_AS_STRNCMP
-	/* Return 0 if the mismatched index (%rdx + VEC_SIZE) is after
-	   the maximum offset (%r11).  */
-	addq	$VEC_SIZE, %rdx
-	cmpq	%r11, %rdx
-	jae	L(zero)
-#  ifdef USE_AS_WCSCMP
+	.p2align 4,, 4
+L(vec_0_test_len):
+	notl	%ecx
+	bzhil	%edx, %ecx, %eax
+	jnz	L(return_vec_0)
+	/* Align if will cross fetch block.  */
+	.p2align 4,, 2
+L(ret_zero):
 	xorl	%eax, %eax
-	movl	(%rdi, %rdx), %ecx
-	cmpl	(%rsi, %rdx), %ecx
-	jne	L(wcscmp_return)
-#  else
-	movzbl	(%rdi, %rdx), %eax
-	movzbl	(%rsi, %rdx), %edx
-	subl	%edx, %eax
-#  endif
-# else
+	ret
+
+	.p2align 4,, 5
+L(one_or_less):
+	jb	L(ret_zero)
 #  ifdef USE_AS_WCSCMP
+	/* 'nbe' covers the case where length is negative (large
+	   unsigned).  */
+	jnbe	__wcscmp_evex
+	movl	(%rdi), %edx
 	xorl	%eax, %eax
-	movl	VEC_SIZE(%rdi, %rdx), %ecx
-	cmpl	VEC_SIZE(%rsi, %rdx), %ecx
-	jne	L(wcscmp_return)
+	cmpl	(%rsi), %edx
+	je	L(ret1)
+	setl	%al
+	negl	%eax
+	orl	$1, %eax
 #  else
-	movzbl	VEC_SIZE(%rdi, %rdx), %eax
-	movzbl	VEC_SIZE(%rsi, %rdx), %edx
-	subl	%edx, %eax
+	/* 'nbe' covers the case where length is negative (large
+	   unsigned).  */
+	jnbe	__strcmp_evex
+	movzbl	(%rdi), %eax
+	movzbl	(%rsi), %ecx
+	subl	%ecx, %eax
 #  endif
-# endif
+L(ret1):
 	ret
+# endif
 
-L(return_2_vec_size):
-	tzcntl	%ecx, %edx
+	.p2align 4,, 10
+L(return_vec_1):
+	tzcntl	%ecx, %ecx
+# ifdef USE_AS_STRNCMP
+	/* rdx must be > CHAR_PER_VEC so its safe to subtract without
+	   worrying about underflow.  */
+	addq	$-CHAR_PER_VEC, %rdx
+	cmpq	%rcx, %rdx
+	jbe	L(ret_zero)
+# endif
 # ifdef USE_AS_WCSCMP
-	/* NB: Multiply wchar_t count by 4 to get the number of bytes.  */
-	sall	$2, %edx
+	movl	VEC_SIZE(%rdi, %rcx, SIZE_OF_CHAR), %edx
+	xorl	%eax, %eax
+	cmpl	VEC_SIZE(%rsi, %rcx, SIZE_OF_CHAR), %edx
+	je	L(ret2)
+	setl	%al
+	negl	%eax
+	orl	$1, %eax
+# else
+	movzbl	VEC_SIZE(%rdi, %rcx), %eax
+	movzbl	VEC_SIZE(%rsi, %rcx), %ecx
+	subl	%ecx, %eax
 # endif
+L(ret2):
+	ret
+
+	.p2align 4,, 10
 # ifdef USE_AS_STRNCMP
-	/* Return 0 if the mismatched index (%rdx + 2 * VEC_SIZE) is
-	   after the maximum offset (%r11).  */
-	addq	$(VEC_SIZE * 2), %rdx
-	cmpq	%r11, %rdx
-	jae	L(zero)
-#  ifdef USE_AS_WCSCMP
-	xorl	%eax, %eax
-	movl	(%rdi, %rdx), %ecx
-	cmpl	(%rsi, %rdx), %ecx
-	jne	L(wcscmp_return)
+L(return_vec_3):
+#  if CHAR_PER_VEC <= 16
+	sall	$CHAR_PER_VEC, %ecx
 #  else
-	movzbl	(%rdi, %rdx), %eax
-	movzbl	(%rsi, %rdx), %edx
-	subl	%edx, %eax
+	salq	$CHAR_PER_VEC, %rcx
 #  endif
+# endif
+L(return_vec_2):
+# if (CHAR_PER_VEC <= 16) || !(defined USE_AS_STRNCMP)
+	tzcntl	%ecx, %ecx
 # else
-#  ifdef USE_AS_WCSCMP
-	xorl	%eax, %eax
-	movl	(VEC_SIZE * 2)(%rdi, %rdx), %ecx
-	cmpl	(VEC_SIZE * 2)(%rsi, %rdx), %ecx
-	jne	L(wcscmp_return)
-#  else
-	movzbl	(VEC_SIZE * 2)(%rdi, %rdx), %eax
-	movzbl	(VEC_SIZE * 2)(%rsi, %rdx), %edx
-	subl	%edx, %eax
-#  endif
+	tzcntq	%rcx, %rcx
 # endif
-	ret
 
-L(return_3_vec_size):
-	tzcntl	%ecx, %edx
-# ifdef USE_AS_WCSCMP
-	/* NB: Multiply wchar_t count by 4 to get the number of bytes.  */
-	sall	$2, %edx
-# endif
 # ifdef USE_AS_STRNCMP
-	/* Return 0 if the mismatched index (%rdx + 3 * VEC_SIZE) is
-	   after the maximum offset (%r11).  */
-	addq	$(VEC_SIZE * 3), %rdx
-	cmpq	%r11, %rdx
-	jae	L(zero)
-#  ifdef USE_AS_WCSCMP
+	cmpq	%rcx, %rdx
+	jbe	L(ret_zero)
+# endif
+
+# ifdef USE_AS_WCSCMP
+	movl	(VEC_SIZE * 2)(%rdi, %rcx, SIZE_OF_CHAR), %edx
 	xorl	%eax, %eax
-	movl	(%rdi, %rdx), %ecx
-	cmpl	(%rsi, %rdx), %ecx
-	jne	L(wcscmp_return)
-#  else
-	movzbl	(%rdi, %rdx), %eax
-	movzbl	(%rsi, %rdx), %edx
-	subl	%edx, %eax
-#  endif
+	cmpl	(VEC_SIZE * 2)(%rsi, %rcx, SIZE_OF_CHAR), %edx
+	je	L(ret3)
+	setl	%al
+	negl	%eax
+	orl	$1, %eax
 # else
+	movzbl	(VEC_SIZE * 2)(%rdi, %rcx), %eax
+	movzbl	(VEC_SIZE * 2)(%rsi, %rcx), %ecx
+	subl	%ecx, %eax
+# endif
+L(ret3):
+	ret
+
+# ifndef USE_AS_STRNCMP
+	.p2align 4,, 10
+L(return_vec_3):
+	tzcntl	%ecx, %ecx
 #  ifdef USE_AS_WCSCMP
+	movl	(VEC_SIZE * 3)(%rdi, %rcx, SIZE_OF_CHAR), %edx
 	xorl	%eax, %eax
-	movl	(VEC_SIZE * 3)(%rdi, %rdx), %ecx
-	cmpl	(VEC_SIZE * 3)(%rsi, %rdx), %ecx
-	jne	L(wcscmp_return)
+	cmpl	(VEC_SIZE * 3)(%rsi, %rcx, SIZE_OF_CHAR), %edx
+	je	L(ret4)
+	setl	%al
+	negl	%eax
+	orl	$1, %eax
 #  else
-	movzbl	(VEC_SIZE * 3)(%rdi, %rdx), %eax
-	movzbl	(VEC_SIZE * 3)(%rsi, %rdx), %edx
-	subl	%edx, %eax
+	movzbl	(VEC_SIZE * 3)(%rdi, %rcx), %eax
+	movzbl	(VEC_SIZE * 3)(%rsi, %rcx), %ecx
+	subl	%ecx, %eax
 #  endif
-# endif
+L(ret4):
 	ret
+# endif
 
-	.p2align 4
-L(next_3_vectors):
-	VMOVU	VEC_SIZE(%rdi), %YMM0
-	/* Each bit set in K2 represents a non-null CHAR in YMM0.  */
+	/* 32 byte align here ensures the main loop is ideally aligned
+	   for DSB.  */
+	.p2align 5
+L(more_3x_vec):
+	/* Safe to compare 4x vectors.  */
+	VMOVU	(VEC_SIZE)(%rdi), %YMM0
 	VPTESTM	%YMM0, %YMM0, %k2
-	/* Each bit cleared in K1 represents a mismatch or a null CHAR
-	   in YMM0 and 32 bytes at VEC_SIZE(%rsi).  */
-	VPCMP	$0, VEC_SIZE(%rsi), %YMM0, %k1{%k2}
+	VPCMP	$0, (VEC_SIZE)(%rsi), %YMM0, %k1{%k2}
 	kmovd	%k1, %ecx
-# ifdef USE_AS_WCSCMP
-	subl	$0xff, %ecx
-# else
-	incl	%ecx
+	TESTEQ	%ecx
+	jnz	L(return_vec_1)
+
+# ifdef USE_AS_STRNCMP
+	subq	$(CHAR_PER_VEC * 2), %rdx
+	jbe	L(ret_zero)
 # endif
-	jne	L(return_vec_size)
 
 	VMOVU	(VEC_SIZE * 2)(%rdi), %YMM0
-	/* Each bit set in K2 represents a non-null CHAR in YMM0.  */
 	VPTESTM	%YMM0, %YMM0, %k2
-	/* Each bit cleared in K1 represents a mismatch or a null CHAR
-	   in YMM0 and 32 bytes at (VEC_SIZE * 2)(%rsi).  */
 	VPCMP	$0, (VEC_SIZE * 2)(%rsi), %YMM0, %k1{%k2}
 	kmovd	%k1, %ecx
-# ifdef USE_AS_WCSCMP
-	subl	$0xff, %ecx
-# else
-	incl	%ecx
-# endif
-	jne	L(return_2_vec_size)
+	TESTEQ	%ecx
+	jnz	L(return_vec_2)
 
 	VMOVU	(VEC_SIZE * 3)(%rdi), %YMM0
-	/* Each bit set in K2 represents a non-null CHAR in YMM0.  */
 	VPTESTM	%YMM0, %YMM0, %k2
-	/* Each bit cleared in K1 represents a mismatch or a null CHAR
-	   in YMM0 and 32 bytes at (VEC_SIZE * 2)(%rsi).  */
 	VPCMP	$0, (VEC_SIZE * 3)(%rsi), %YMM0, %k1{%k2}
 	kmovd	%k1, %ecx
+	TESTEQ	%ecx
+	jnz	L(return_vec_3)
+
+# ifdef USE_AS_STRNCMP
+	cmpq	$(CHAR_PER_VEC * 2), %rdx
+	jbe	L(ret_zero)
+# endif
+
+
 # ifdef USE_AS_WCSCMP
-	subl	$0xff, %ecx
+	/* any non-zero positive value that doesn't inference with 0x1.
+	 */
+	movl	$2, %r8d
+
 # else
-	incl	%ecx
+	xorl	%r8d, %r8d
 # endif
-	jne	L(return_3_vec_size)
-L(main_loop_header):
-	leaq	(VEC_SIZE * 4)(%rdi), %rdx
-	movl	$PAGE_SIZE, %ecx
-	/* Align load via RAX.  */
-	andq	$-(VEC_SIZE * 4), %rdx
-	subq	%rdi, %rdx
-	leaq	(%rdi, %rdx), %rax
+
+	/* The prepare labels are various entry points from the page
+	   cross logic.  */
+L(prepare_loop):
+
 # ifdef USE_AS_STRNCMP
-	/* Starting from this point, the maximum offset, or simply the
-	   'offset', DECREASES by the same amount when base pointers are
-	   moved forward.  Return 0 when:
-	     1) On match: offset <= the matched vector index.
-	     2) On mistmach, offset is before the mistmatched index.
-	 */
-	subq	%rdx, %r11
-	jbe	L(zero)
+#  ifdef USE_AS_WCSCMP
+L(prepare_loop_no_len):
+	movl	%edi, %ecx
+	andl	$(VEC_SIZE * 4 - 1), %ecx
+	shrl	$2, %ecx
+	leaq	(CHAR_PER_VEC * 2)(%rdx, %rcx), %rdx
+#  else
+	/* Store N + (VEC_SIZE * 4) and place check at the begining of
+	   the loop.  */
+	leaq	(VEC_SIZE * 2)(%rdi, %rdx), %rdx
+L(prepare_loop_no_len):
+#  endif
+# else
+L(prepare_loop_no_len):
 # endif
-	addq	%rsi, %rdx
-	movq	%rdx, %rsi
-	andl	$(PAGE_SIZE - 1), %esi
-	/* Number of bytes before page crossing.  */
-	subq	%rsi, %rcx
-	/* Number of VEC_SIZE * 4 blocks before page crossing.  */
-	shrq	$DIVIDE_BY_VEC_4_SHIFT, %rcx
-	/* ESI: Number of VEC_SIZE * 4 blocks before page crossing.   */
-	movl	%ecx, %esi
-	jmp	L(loop_start)
 
+	/* Align s1 and adjust s2 accordingly.  */
+	subq	%rdi, %rsi
+	andq	$-(VEC_SIZE * 4), %rdi
+L(prepare_loop_readj):
+	addq	%rdi, %rsi
+# if (defined USE_AS_STRNCMP) && !(defined USE_AS_WCSCMP)
+	subq	%rdi, %rdx
+# endif
+
+L(prepare_loop_aligned):
+	/* eax stores distance from rsi to next page cross. These cases
+	   need to be handled specially as the 4x loop could potentially
+	   read memory past the length of s1 or s2 and across a page
+	   boundary.  */
+	movl	$-(VEC_SIZE * 4), %eax
+	subl	%esi, %eax
+	andl	$(PAGE_SIZE - 1), %eax
+
+	vpxorq	%YMMZERO, %YMMZERO, %YMMZERO
+
+	/* Loop 4x comparisons at a time.  */
 	.p2align 4
 L(loop):
+
+	/* End condition for strncmp.  */
 # ifdef USE_AS_STRNCMP
-	/* Base pointers are moved forward by 4 * VEC_SIZE.  Decrease
-	   the maximum offset (%r11) by the same amount.  */
-	subq	$(VEC_SIZE * 4), %r11
-	jbe	L(zero)
+	subq	$(CHAR_PER_VEC * 4), %rdx
+	jbe	L(ret_zero)
 # endif
-	addq	$(VEC_SIZE * 4), %rax
-	addq	$(VEC_SIZE * 4), %rdx
-L(loop_start):
-	testl	%esi, %esi
-	leal	-1(%esi), %esi
-	je	L(loop_cross_page)
-L(back_to_loop):
-	/* Main loop, comparing 4 vectors are a time.  */
-	VMOVA	(%rax), %YMM0
-	VMOVA	VEC_SIZE(%rax), %YMM2
-	VMOVA	(VEC_SIZE * 2)(%rax), %YMM4
-	VMOVA	(VEC_SIZE * 3)(%rax), %YMM6
+
+	subq	$-(VEC_SIZE * 4), %rdi
+	subq	$-(VEC_SIZE * 4), %rsi
+
+	/* Check if rsi loads will cross a page boundary.  */
+	addl	$-(VEC_SIZE * 4), %eax
+	jnb	L(page_cross_during_loop)
+
+	/* Loop entry after handling page cross during loop.  */
+L(loop_skip_page_cross_check):
+	VMOVA	(VEC_SIZE * 0)(%rdi), %YMM0
+	VMOVA	(VEC_SIZE * 1)(%rdi), %YMM2
+	VMOVA	(VEC_SIZE * 2)(%rdi), %YMM4
+	VMOVA	(VEC_SIZE * 3)(%rdi), %YMM6
 
 	VPMINU	%YMM0, %YMM2, %YMM8
 	VPMINU	%YMM4, %YMM6, %YMM9
 
-	/* A zero CHAR in YMM8 means that there is a null CHAR.  */
-	VPMINU	%YMM8, %YMM9, %YMM8
+	/* A zero CHAR in YMM9 means that there is a null CHAR.  */
+	VPMINU	%YMM8, %YMM9, %YMM9
 
 	/* Each bit set in K1 represents a non-null CHAR in YMM8.  */
-	VPTESTM	%YMM8, %YMM8, %k1
+	VPTESTM	%YMM9, %YMM9, %k1
 
-	/* (YMM ^ YMM): A non-zero CHAR represents a mismatch.  */
-	vpxorq	(%rdx), %YMM0, %YMM1
-	vpxorq	VEC_SIZE(%rdx), %YMM2, %YMM3
-	vpxorq	(VEC_SIZE * 2)(%rdx), %YMM4, %YMM5
-	vpxorq	(VEC_SIZE * 3)(%rdx), %YMM6, %YMM7
+	vpxorq	(VEC_SIZE * 0)(%rsi), %YMM0, %YMM1
+	vpxorq	(VEC_SIZE * 1)(%rsi), %YMM2, %YMM3
+	vpxorq	(VEC_SIZE * 2)(%rsi), %YMM4, %YMM5
+	/* Ternary logic to xor (VEC_SIZE * 3)(%rsi) with YMM6 while
+	   oring with YMM1. Result is stored in YMM6.  */
+	vpternlogd $0xde, (VEC_SIZE * 3)(%rsi), %YMM1, %YMM6
 
-	vporq	%YMM1, %YMM3, %YMM9
-	vporq	%YMM5, %YMM7, %YMM10
+	/* Or together YMM3, YMM5, and YMM6.  */
+	vpternlogd $0xfe, %YMM3, %YMM5, %YMM6
 
-	/* A non-zero CHAR in YMM9 represents a mismatch.  */
-	vporq	%YMM9, %YMM10, %YMM9
 
-	/* Each bit cleared in K0 represents a mismatch or a null CHAR.  */
-	VPCMP	$0, %YMMZERO, %YMM9, %k0{%k1}
-	kmovd   %k0, %ecx
-# ifdef USE_AS_WCSCMP
-	subl	$0xff, %ecx
-# else
-	incl	%ecx
-# endif
-	je	 L(loop)
+	/* A non-zero CHAR in YMM6 represents a mismatch.  */
+	VPCMP	$0, %YMMZERO, %YMM6, %k0{%k1}
+	kmovd	%k0, %LOOP_REG
 
-	/* Each bit set in K1 represents a non-null CHAR in YMM0.  */
+	TESTEQ	%LOOP_REG
+	jz	L(loop)
+
+
+	/* Find which VEC has the mismatch of end of string.  */
 	VPTESTM	%YMM0, %YMM0, %k1
-	/* Each bit cleared in K0 represents a mismatch or a null CHAR
-	   in YMM0 and (%rdx).  */
 	VPCMP	$0, %YMMZERO, %YMM1, %k0{%k1}
 	kmovd	%k0, %ecx
-# ifdef USE_AS_WCSCMP
-	subl	$0xff, %ecx
-# else
-	incl	%ecx
-# endif
-	je	L(test_vec)
-	tzcntl	%ecx, %ecx
-# ifdef USE_AS_WCSCMP
-	/* NB: Multiply wchar_t count by 4 to get the number of bytes.  */
-	sall	$2, %ecx
-# endif
-# ifdef USE_AS_STRNCMP
-	cmpq	%rcx, %r11
-	jbe	L(zero)
-#  ifdef USE_AS_WCSCMP
-	movq	%rax, %rsi
-	xorl	%eax, %eax
-	movl	(%rsi, %rcx), %edi
-	cmpl	(%rdx, %rcx), %edi
-	jne	L(wcscmp_return)
-#  else
-	movzbl	(%rax, %rcx), %eax
-	movzbl	(%rdx, %rcx), %edx
-	subl	%edx, %eax
-#  endif
-# else
-#  ifdef USE_AS_WCSCMP
-	movq	%rax, %rsi
-	xorl	%eax, %eax
-	movl	(%rsi, %rcx), %edi
-	cmpl	(%rdx, %rcx), %edi
-	jne	L(wcscmp_return)
-#  else
-	movzbl	(%rax, %rcx), %eax
-	movzbl	(%rdx, %rcx), %edx
-	subl	%edx, %eax
-#  endif
-# endif
-	ret
+	TESTEQ	%ecx
+	jnz	L(return_vec_0_end)
 
-	.p2align 4
-L(test_vec):
-# ifdef USE_AS_STRNCMP
-	/* The first vector matched.  Return 0 if the maximum offset
-	   (%r11) <= VEC_SIZE.  */
-	cmpq	$VEC_SIZE, %r11
-	jbe	L(zero)
-# endif
-	/* Each bit set in K1 represents a non-null CHAR in YMM2.  */
 	VPTESTM	%YMM2, %YMM2, %k1
-	/* Each bit cleared in K0 represents a mismatch or a null CHAR
-	   in YMM2 and VEC_SIZE(%rdx).  */
 	VPCMP	$0, %YMMZERO, %YMM3, %k0{%k1}
 	kmovd	%k0, %ecx
-# ifdef USE_AS_WCSCMP
-	subl	$0xff, %ecx
-# else
-	incl	%ecx
-# endif
-	je	L(test_2_vec)
-	tzcntl	%ecx, %edi
-# ifdef USE_AS_WCSCMP
-	/* NB: Multiply wchar_t count by 4 to get the number of bytes.  */
-	sall	$2, %edi
-# endif
-# ifdef USE_AS_STRNCMP
-	addq	$VEC_SIZE, %rdi
-	cmpq	%rdi, %r11
-	jbe	L(zero)
-#  ifdef USE_AS_WCSCMP
-	movq	%rax, %rsi
-	xorl	%eax, %eax
-	movl	(%rsi, %rdi), %ecx
-	cmpl	(%rdx, %rdi), %ecx
-	jne	L(wcscmp_return)
-#  else
-	movzbl	(%rax, %rdi), %eax
-	movzbl	(%rdx, %rdi), %edx
-	subl	%edx, %eax
-#  endif
-# else
-#  ifdef USE_AS_WCSCMP
-	movq	%rax, %rsi
-	xorl	%eax, %eax
-	movl	VEC_SIZE(%rsi, %rdi), %ecx
-	cmpl	VEC_SIZE(%rdx, %rdi), %ecx
-	jne	L(wcscmp_return)
-#  else
-	movzbl	VEC_SIZE(%rax, %rdi), %eax
-	movzbl	VEC_SIZE(%rdx, %rdi), %edx
-	subl	%edx, %eax
-#  endif
-# endif
-	ret
+	TESTEQ	%ecx
+	jnz	L(return_vec_1_end)
 
-	.p2align 4
-L(test_2_vec):
+
+	/* Handle VEC 2 and 3 without branches.  */
+L(return_vec_2_3_end):
 # ifdef USE_AS_STRNCMP
-	/* The first 2 vectors matched.  Return 0 if the maximum offset
-	   (%r11) <= 2 * VEC_SIZE.  */
-	cmpq	$(VEC_SIZE * 2), %r11
-	jbe	L(zero)
+	subq	$(CHAR_PER_VEC * 2), %rdx
+	jbe	L(ret_zero_end)
 # endif
-	/* Each bit set in K1 represents a non-null CHAR in YMM4.  */
+
 	VPTESTM	%YMM4, %YMM4, %k1
-	/* Each bit cleared in K0 represents a mismatch or a null CHAR
-	   in YMM4 and (VEC_SIZE * 2)(%rdx).  */
 	VPCMP	$0, %YMMZERO, %YMM5, %k0{%k1}
 	kmovd	%k0, %ecx
-# ifdef USE_AS_WCSCMP
-	subl	$0xff, %ecx
+	TESTEQ	%ecx
+# if CHAR_PER_VEC <= 16
+	sall	$CHAR_PER_VEC, %LOOP_REG
+	orl	%ecx, %LOOP_REG
 # else
-	incl	%ecx
+	salq	$CHAR_PER_VEC, %LOOP_REG64
+	orq	%rcx, %LOOP_REG64
+# endif
+L(return_vec_3_end):
+	/* LOOP_REG contains matches for null/mismatch from the loop. If
+	   VEC 0,1,and 2 all have no null and no mismatches then mismatch
+	   must entirely be from VEC 3 which is fully represented by
+	   LOOP_REG.  */
+# if CHAR_PER_VEC <= 16
+	tzcntl	%LOOP_REG, %LOOP_REG
+# else
+	tzcntq	%LOOP_REG64, %LOOP_REG64
+# endif
+# ifdef USE_AS_STRNCMP
+	cmpq	%LOOP_REG64, %rdx
+	jbe	L(ret_zero_end)
 # endif
-	je	L(test_3_vec)
-	tzcntl	%ecx, %edi
+
 # ifdef USE_AS_WCSCMP
-	/* NB: Multiply wchar_t count by 4 to get the number of bytes.  */
-	sall	$2, %edi
+	movl	(VEC_SIZE * 2)(%rdi, %LOOP_REG64, SIZE_OF_CHAR), %ecx
+	xorl	%eax, %eax
+	cmpl	(VEC_SIZE * 2)(%rsi, %LOOP_REG64, SIZE_OF_CHAR), %ecx
+	je	L(ret5)
+	setl	%al
+	negl	%eax
+	xorl	%r8d, %eax
+# else
+	movzbl	(VEC_SIZE * 2)(%rdi, %LOOP_REG64), %eax
+	movzbl	(VEC_SIZE * 2)(%rsi, %LOOP_REG64), %ecx
+	subl	%ecx, %eax
+	xorl	%r8d, %eax
+	subl	%r8d, %eax
 # endif
+L(ret5):
+	ret
+
 # ifdef USE_AS_STRNCMP
-	addq	$(VEC_SIZE * 2), %rdi
-	cmpq	%rdi, %r11
-	jbe	L(zero)
-#  ifdef USE_AS_WCSCMP
-	movq	%rax, %rsi
+	.p2align 4,, 2
+L(ret_zero_end):
 	xorl	%eax, %eax
-	movl	(%rsi, %rdi), %ecx
-	cmpl	(%rdx, %rdi), %ecx
-	jne	L(wcscmp_return)
+	ret
+# endif
+
+
+	/* The L(return_vec_N_end) differ from L(return_vec_N) in that
+	   they use the value of `r8` to negate the return value. This is
+	   because the page cross logic can swap `rdi` and `rsi`.  */
+	.p2align 4,, 10
+# ifdef USE_AS_STRNCMP
+L(return_vec_1_end):
+#  if CHAR_PER_VEC <= 16
+	sall	$CHAR_PER_VEC, %ecx
 #  else
-	movzbl	(%rax, %rdi), %eax
-	movzbl	(%rdx, %rdi), %edx
-	subl	%edx, %eax
+	salq	$CHAR_PER_VEC, %rcx
 #  endif
+# endif
+L(return_vec_0_end):
+# if (CHAR_PER_VEC <= 16) || !(defined USE_AS_STRNCMP)
+	tzcntl	%ecx, %ecx
 # else
-#  ifdef USE_AS_WCSCMP
-	movq	%rax, %rsi
-	xorl	%eax, %eax
-	movl	(VEC_SIZE * 2)(%rsi, %rdi), %ecx
-	cmpl	(VEC_SIZE * 2)(%rdx, %rdi), %ecx
-	jne	L(wcscmp_return)
-#  else
-	movzbl	(VEC_SIZE * 2)(%rax, %rdi), %eax
-	movzbl	(VEC_SIZE * 2)(%rdx, %rdi), %edx
-	subl	%edx, %eax
-#  endif
+	tzcntq	%rcx, %rcx
 # endif
-	ret
 
-	.p2align 4
-L(test_3_vec):
 # ifdef USE_AS_STRNCMP
-	/* The first 3 vectors matched.  Return 0 if the maximum offset
-	   (%r11) <= 3 * VEC_SIZE.  */
-	cmpq	$(VEC_SIZE * 3), %r11
-	jbe	L(zero)
+	cmpq	%rcx, %rdx
+	jbe	L(ret_zero_end)
 # endif
-	/* Each bit set in K1 represents a non-null CHAR in YMM6.  */
-	VPTESTM	%YMM6, %YMM6, %k1
-	/* Each bit cleared in K0 represents a mismatch or a null CHAR
-	   in YMM6 and (VEC_SIZE * 3)(%rdx).  */
-	VPCMP	$0, %YMMZERO, %YMM7, %k0{%k1}
-	kmovd	%k0, %ecx
+
 # ifdef USE_AS_WCSCMP
-	subl	$0xff, %ecx
+	movl	(%rdi, %rcx, SIZE_OF_CHAR), %edx
+	xorl	%eax, %eax
+	cmpl	(%rsi, %rcx, SIZE_OF_CHAR), %edx
+	je	L(ret6)
+	setl	%al
+	negl	%eax
+	/* This is the non-zero case for `eax` so just xorl with `r8d`
+	   flip is `rdi` and `rsi` where swapped.  */
+	xorl	%r8d, %eax
 # else
-	incl	%ecx
+	movzbl	(%rdi, %rcx), %eax
+	movzbl	(%rsi, %rcx), %ecx
+	subl	%ecx, %eax
+	/* Flip `eax` if `rdi` and `rsi` where swapped in page cross
+	   logic. Subtract `r8d` after xor for zero case.  */
+	xorl	%r8d, %eax
+	subl	%r8d, %eax
 # endif
+L(ret6):
+	ret
+
+# ifndef USE_AS_STRNCMP
+	.p2align 4,, 10
+L(return_vec_1_end):
 	tzcntl	%ecx, %ecx
-# ifdef USE_AS_WCSCMP
-	/* NB: Multiply wchar_t count by 4 to get the number of bytes.  */
-	sall	$2, %ecx
-# endif
-# ifdef USE_AS_STRNCMP
-	addq	$(VEC_SIZE * 3), %rcx
-	cmpq	%rcx, %r11
-	jbe	L(zero)
 #  ifdef USE_AS_WCSCMP
-	movq	%rax, %rsi
+	movl	VEC_SIZE(%rdi, %rcx, SIZE_OF_CHAR), %edx
 	xorl	%eax, %eax
-	movl	(%rsi, %rcx), %esi
-	cmpl	(%rdx, %rcx), %esi
-	jne	L(wcscmp_return)
-#  else
-	movzbl	(%rax, %rcx), %eax
-	movzbl	(%rdx, %rcx), %edx
-	subl	%edx, %eax
-#  endif
-# else
-#  ifdef USE_AS_WCSCMP
-	movq	%rax, %rsi
-	xorl	%eax, %eax
-	movl	(VEC_SIZE * 3)(%rsi, %rcx), %esi
-	cmpl	(VEC_SIZE * 3)(%rdx, %rcx), %esi
-	jne	L(wcscmp_return)
+	cmpl	VEC_SIZE(%rsi, %rcx, SIZE_OF_CHAR), %edx
+	je	L(ret7)
+	setl	%al
+	negl	%eax
+	xorl	%r8d, %eax
 #  else
-	movzbl	(VEC_SIZE * 3)(%rax, %rcx), %eax
-	movzbl	(VEC_SIZE * 3)(%rdx, %rcx), %edx
-	subl	%edx, %eax
+	movzbl	VEC_SIZE(%rdi, %rcx), %eax
+	movzbl	VEC_SIZE(%rsi, %rcx), %ecx
+	subl	%ecx, %eax
+	xorl	%r8d, %eax
+	subl	%r8d, %eax
 #  endif
-# endif
+L(ret7):
 	ret
-
-	.p2align 4
-L(loop_cross_page):
-	xorl	%r10d, %r10d
-	movq	%rdx, %rcx
-	/* Align load via RDX.  We load the extra ECX bytes which should
-	   be ignored.  */
-	andl	$((VEC_SIZE * 4) - 1), %ecx
-	/* R10 is -RCX.  */
-	subq	%rcx, %r10
-
-	/* This works only if VEC_SIZE * 2 == 64. */
-# if (VEC_SIZE * 2) != 64
-#  error (VEC_SIZE * 2) != 64
 # endif
 
-	/* Check if the first VEC_SIZE * 2 bytes should be ignored.  */
-	cmpl	$(VEC_SIZE * 2), %ecx
-	jge	L(loop_cross_page_2_vec)
 
-	VMOVU	(%rax, %r10), %YMM2
-	VMOVU	VEC_SIZE(%rax, %r10), %YMM3
+	/* Page cross in rsi in next 4x VEC.  */
 
-	/* Each bit set in K2 represents a non-null CHAR in YMM2.  */
-	VPTESTM	%YMM2, %YMM2, %k2
-	/* Each bit cleared in K1 represents a mismatch or a null CHAR
-	   in YMM2 and 32 bytes at (%rdx, %r10).  */
-	VPCMP	$0, (%rdx, %r10), %YMM2, %k1{%k2}
-	kmovd	%k1, %r9d
-	/* Don't use subl since it is the lower 16/32 bits of RDI
-	   below.  */
-	notl	%r9d
-# ifdef USE_AS_WCSCMP
-	/* Only last 8 bits are valid.  */
-	andl	$0xff, %r9d
-# endif
+	/* TODO: Improve logic here.  */
+	.p2align 4,, 10
+L(page_cross_during_loop):
+	/* eax contains [distance_from_page - (VEC_SIZE * 4)].  */
 
-	/* Each bit set in K4 represents a non-null CHAR in YMM3.  */
-	VPTESTM	%YMM3, %YMM3, %k4
-	/* Each bit cleared in K3 represents a mismatch or a null CHAR
-	   in YMM3 and 32 bytes at VEC_SIZE(%rdx, %r10).  */
-	VPCMP	$0, VEC_SIZE(%rdx, %r10), %YMM3, %k3{%k4}
-	kmovd	%k3, %edi
-    /* Must use notl %edi here as lower bits are for CHAR
-	   comparisons potentially out of range thus can be 0 without
-	   indicating mismatch.  */
-	notl	%edi
-# ifdef USE_AS_WCSCMP
-	/* Don't use subl since it is the upper 8 bits of EDI below.  */
-	andl	$0xff, %edi
-# endif
+	/* Optimistically rsi and rdi and both aligned in which case we
+	   don't need any logic here.  */
+	cmpl	$-(VEC_SIZE * 4), %eax
+	/* Don't adjust eax before jumping back to loop and we will
+	   never hit page cross case again.  */
+	je	L(loop_skip_page_cross_check)
 
-# ifdef USE_AS_WCSCMP
-	/* NB: Each bit in EDI/R9D represents 4-byte element.  */
-	sall	$8, %edi
-	/* NB: Divide shift count by 4 since each bit in K1 represent 4
-	   bytes.  */
-	movl	%ecx, %SHIFT_REG32
-	sarl	$2, %SHIFT_REG32
-
-	/* Each bit in EDI represents a null CHAR or a mismatch.  */
-	orl	%r9d, %edi
-# else
-	salq	$32, %rdi
+	/* Check if we can safely load a VEC.  */
+	cmpl	$-(VEC_SIZE * 3), %eax
+	jle	L(less_1x_vec_till_page_cross)
 
-	/* Each bit in RDI represents a null CHAR or a mismatch.  */
-	orq	%r9, %rdi
-# endif
+	VMOVA	(%rdi), %YMM0
+	VPTESTM	%YMM0, %YMM0, %k2
+	VPCMP	$0, (%rsi), %YMM0, %k1{%k2}
+	kmovd	%k1, %ecx
+	TESTEQ	%ecx
+	jnz	L(return_vec_0_end)
+
+	/* if distance >= 2x VEC then eax > -(VEC_SIZE * 2).  */
+	cmpl	$-(VEC_SIZE * 2), %eax
+	jg	L(more_2x_vec_till_page_cross)
+
+	.p2align 4,, 4
+L(less_1x_vec_till_page_cross):
+	subl	$-(VEC_SIZE * 4), %eax
+	/* Guranteed safe to read from rdi - VEC_SIZE here. The only
+	   concerning case is first iteration if incoming s1 was near start
+	   of a page and s2 near end. If s1 was near the start of the page
+	   we already aligned up to nearest VEC_SIZE * 4 so gurnateed safe
+	   to read back -VEC_SIZE. If rdi is truly at the start of a page
+	   here, it means the previous page (rdi - VEC_SIZE) has already
+	   been loaded earlier so must be valid.  */
+	VMOVU	-VEC_SIZE(%rdi, %rax), %YMM0
+	VPTESTM	%YMM0, %YMM0, %k2
+	VPCMP	$0, -VEC_SIZE(%rsi, %rax), %YMM0, %k1{%k2}
+
+	/* Mask of potentially valid bits. The lower bits can be out of
+	   range comparisons (but safe regarding page crosses).  */
 
-	/* Since ECX < VEC_SIZE * 2, simply skip the first ECX bytes.  */
-	shrxq	%SHIFT_REG64, %rdi, %rdi
-	testq	%rdi, %rdi
-	je	L(loop_cross_page_2_vec)
-	tzcntq	%rdi, %rcx
 # ifdef USE_AS_WCSCMP
-	/* NB: Multiply wchar_t count by 4 to get the number of bytes.  */
-	sall	$2, %ecx
+	movl	$-1, %r10d
+	movl	%esi, %ecx
+	andl	$(VEC_SIZE - 1), %ecx
+	shrl	$2, %ecx
+	shlxl	%ecx, %r10d, %ecx
+	movzbl	%cl, %r10d
+# else
+	movl	$-1, %ecx
+	shlxl	%esi, %ecx, %r10d
 # endif
+
+	kmovd	%k1, %ecx
+	notl	%ecx
+
+
 # ifdef USE_AS_STRNCMP
-	cmpq	%rcx, %r11
-	jbe	L(zero)
 #  ifdef USE_AS_WCSCMP
-	movq	%rax, %rsi
-	xorl	%eax, %eax
-	movl	(%rsi, %rcx), %edi
-	cmpl	(%rdx, %rcx), %edi
-	jne	L(wcscmp_return)
+	movl	%eax, %r11d
+	shrl	$2, %r11d
+	cmpq	%r11, %rdx
 #  else
-	movzbl	(%rax, %rcx), %eax
-	movzbl	(%rdx, %rcx), %edx
-	subl	%edx, %eax
+	cmpq	%rax, %rdx
 #  endif
+	jbe	L(return_page_cross_end_check)
+# endif
+	movl	%eax, %OFFSET_REG
+
+	/* Readjust eax before potentially returning to the loop.  */
+	addl	$(PAGE_SIZE - VEC_SIZE * 4), %eax
+
+	andl	%r10d, %ecx
+	jz	L(loop_skip_page_cross_check)
+
+	.p2align 4,, 3
+L(return_page_cross_end):
+	tzcntl	%ecx, %ecx
+
+# if (defined USE_AS_STRNCMP) || (defined USE_AS_WCSCMP)
+	leal	-VEC_SIZE(%OFFSET_REG64, %rcx, SIZE_OF_CHAR), %ecx
+L(return_page_cross_cmp_mem):
 # else
-#  ifdef USE_AS_WCSCMP
-	movq	%rax, %rsi
+	addl	%OFFSET_REG, %ecx
+# endif
+# ifdef USE_AS_WCSCMP
+	movl	VEC_OFFSET(%rdi, %rcx), %edx
 	xorl	%eax, %eax
-	movl	(%rsi, %rcx), %edi
-	cmpl	(%rdx, %rcx), %edi
-	jne	L(wcscmp_return)
-#  else
-	movzbl	(%rax, %rcx), %eax
-	movzbl	(%rdx, %rcx), %edx
-	subl	%edx, %eax
-#  endif
+	cmpl	VEC_OFFSET(%rsi, %rcx), %edx
+	je	L(ret8)
+	setl	%al
+	negl	%eax
+	xorl	%r8d, %eax
+# else
+	movzbl	VEC_OFFSET(%rdi, %rcx), %eax
+	movzbl	VEC_OFFSET(%rsi, %rcx), %ecx
+	subl	%ecx, %eax
+	xorl	%r8d, %eax
+	subl	%r8d, %eax
 # endif
+L(ret8):
 	ret
 
-	.p2align 4
-L(loop_cross_page_2_vec):
-	/* The first VEC_SIZE * 2 bytes match or are ignored.  */
-	VMOVU	(VEC_SIZE * 2)(%rax, %r10), %YMM0
-	VMOVU	(VEC_SIZE * 3)(%rax, %r10), %YMM1
+# ifdef USE_AS_STRNCMP
+	.p2align 4,, 10
+L(return_page_cross_end_check):
+	tzcntl	%ecx, %ecx
+	leal	-VEC_SIZE(%rax, %rcx, SIZE_OF_CHAR), %ecx
+#  ifdef USE_AS_WCSCMP
+	sall	$2, %edx
+#  endif
+	cmpl	%ecx, %edx
+	ja	L(return_page_cross_cmp_mem)
+	xorl	%eax, %eax
+	ret
+# endif
+
 
+	.p2align 4,, 10
+L(more_2x_vec_till_page_cross):
+	/* If more 2x vec till cross we will complete a full loop
+	   iteration here.  */
+
+	VMOVA	VEC_SIZE(%rdi), %YMM0
 	VPTESTM	%YMM0, %YMM0, %k2
-	/* Each bit cleared in K1 represents a mismatch or a null CHAR
-	   in YMM0 and 32 bytes at (VEC_SIZE * 2)(%rdx, %r10).  */
-	VPCMP	$0, (VEC_SIZE * 2)(%rdx, %r10), %YMM0, %k1{%k2}
-	kmovd	%k1, %r9d
-	/* Don't use subl since it is the lower 16/32 bits of RDI
-	   below.  */
-	notl	%r9d
-# ifdef USE_AS_WCSCMP
-	/* Only last 8 bits are valid.  */
-	andl	$0xff, %r9d
-# endif
+	VPCMP	$0, VEC_SIZE(%rsi), %YMM0, %k1{%k2}
+	kmovd	%k1, %ecx
+	TESTEQ	%ecx
+	jnz	L(return_vec_1_end)
 
-	VPTESTM	%YMM1, %YMM1, %k4
-	/* Each bit cleared in K3 represents a mismatch or a null CHAR
-	   in YMM1 and 32 bytes at (VEC_SIZE * 3)(%rdx, %r10).  */
-	VPCMP	$0, (VEC_SIZE * 3)(%rdx, %r10), %YMM1, %k3{%k4}
-	kmovd	%k3, %edi
-	/* Must use notl %edi here as lower bits are for CHAR
-	   comparisons potentially out of range thus can be 0 without
-	   indicating mismatch.  */
-	notl	%edi
-# ifdef USE_AS_WCSCMP
-	/* Don't use subl since it is the upper 8 bits of EDI below.  */
-	andl	$0xff, %edi
+# ifdef USE_AS_STRNCMP
+	cmpq	$(CHAR_PER_VEC * 2), %rdx
+	jbe	L(ret_zero_in_loop_page_cross)
 # endif
 
-# ifdef USE_AS_WCSCMP
-	/* NB: Each bit in EDI/R9D represents 4-byte element.  */
-	sall	$8, %edi
+	subl	$-(VEC_SIZE * 4), %eax
 
-	/* Each bit in EDI represents a null CHAR or a mismatch.  */
-	orl	%r9d, %edi
-# else
-	salq	$32, %rdi
+	/* Safe to include comparisons from lower bytes.  */
+	VMOVU	-(VEC_SIZE * 2)(%rdi, %rax), %YMM0
+	VPTESTM	%YMM0, %YMM0, %k2
+	VPCMP	$0, -(VEC_SIZE * 2)(%rsi, %rax), %YMM0, %k1{%k2}
+	kmovd	%k1, %ecx
+	TESTEQ	%ecx
+	jnz	L(return_vec_page_cross_0)
+
+	VMOVU	-(VEC_SIZE * 1)(%rdi, %rax), %YMM0
+	VPTESTM	%YMM0, %YMM0, %k2
+	VPCMP	$0, -(VEC_SIZE * 1)(%rsi, %rax), %YMM0, %k1{%k2}
+	kmovd	%k1, %ecx
+	TESTEQ	%ecx
+	jnz	L(return_vec_page_cross_1)
 
-	/* Each bit in RDI represents a null CHAR or a mismatch.  */
-	orq	%r9, %rdi
+# ifdef USE_AS_STRNCMP
+	/* Must check length here as length might proclude reading next
+	   page.  */
+#  ifdef USE_AS_WCSCMP
+	movl	%eax, %r11d
+	shrl	$2, %r11d
+	cmpq	%r11, %rdx
+#  else
+	cmpq	%rax, %rdx
+#  endif
+	jbe	L(ret_zero_in_loop_page_cross)
 # endif
 
-	xorl	%r8d, %r8d
-	/* If ECX > VEC_SIZE * 2, skip ECX - (VEC_SIZE * 2) bytes.  */
-	subl	$(VEC_SIZE * 2), %ecx
-	jle	1f
-	/* R8 has number of bytes skipped.  */
-	movl	%ecx, %r8d
-# ifdef USE_AS_WCSCMP
-	/* NB: Divide shift count by 4 since each bit in RDI represent 4
-	   bytes.  */
-	sarl	$2, %ecx
-	/* Skip ECX bytes.  */
-	shrl	%cl, %edi
+	/* Finish the loop.  */
+	VMOVA	(VEC_SIZE * 2)(%rdi), %YMM4
+	VMOVA	(VEC_SIZE * 3)(%rdi), %YMM6
+	VPMINU	%YMM4, %YMM6, %YMM9
+	VPTESTM	%YMM9, %YMM9, %k1
+
+	vpxorq	(VEC_SIZE * 2)(%rsi), %YMM4, %YMM5
+	/* YMM6 = YMM5 | ((VEC_SIZE * 3)(%rsi) ^ YMM6).  */
+	vpternlogd $0xde, (VEC_SIZE * 3)(%rsi), %YMM5, %YMM6
+
+	VPCMP	$0, %YMMZERO, %YMM6, %k0{%k1}
+	kmovd	%k0, %LOOP_REG
+	TESTEQ	%LOOP_REG
+	jnz	L(return_vec_2_3_end)
+
+	/* Best for code size to include ucond-jmp here. Would be faster
+	   if this case is hot to duplicate the L(return_vec_2_3_end) code
+	   as fall-through and have jump back to loop on mismatch
+	   comparison.  */
+	subq	$-(VEC_SIZE * 4), %rdi
+	subq	$-(VEC_SIZE * 4), %rsi
+	addl	$(PAGE_SIZE - VEC_SIZE * 8), %eax
+# ifdef USE_AS_STRNCMP
+	subq	$(CHAR_PER_VEC * 4), %rdx
+	ja	L(loop_skip_page_cross_check)
+L(ret_zero_in_loop_page_cross):
+	xorl	%eax, %eax
+	ret
 # else
-	/* Skip ECX bytes.  */
-	shrq	%cl, %rdi
+	jmp	L(loop_skip_page_cross_check)
 # endif
-1:
-	/* Before jumping back to the loop, set ESI to the number of
-	   VEC_SIZE * 4 blocks before page crossing.  */
-	movl	$(PAGE_SIZE / (VEC_SIZE * 4) - 1), %esi
 
-	testq	%rdi, %rdi
-# ifdef USE_AS_STRNCMP
-	/* At this point, if %rdi value is 0, it already tested
-	   VEC_SIZE*4+%r10 byte starting from %rax. This label
-	   checks whether strncmp maximum offset reached or not.  */
-	je	L(string_nbyte_offset_check)
+
+	.p2align 4,, 10
+L(return_vec_page_cross_0):
+	addl	$-VEC_SIZE, %eax
+L(return_vec_page_cross_1):
+	tzcntl	%ecx, %ecx
+# if defined USE_AS_STRNCMP || defined USE_AS_WCSCMP
+	leal	-VEC_SIZE(%rax, %rcx, SIZE_OF_CHAR), %ecx
+#  ifdef USE_AS_STRNCMP
+#   ifdef USE_AS_WCSCMP
+	/* Must divide ecx instead of multiply rdx due to overflow.  */
+	movl	%ecx, %eax
+	shrl	$2, %eax
+	cmpq	%rax, %rdx
+#   else
+	cmpq	%rcx, %rdx
+#   endif
+	jbe	L(ret_zero_in_loop_page_cross)
+#  endif
 # else
-	je	L(back_to_loop)
+	addl	%eax, %ecx
 # endif
-	tzcntq	%rdi, %rcx
+
 # ifdef USE_AS_WCSCMP
-	/* NB: Multiply wchar_t count by 4 to get the number of bytes.  */
-	sall	$2, %ecx
-# endif
-	addq	%r10, %rcx
-	/* Adjust for number of bytes skipped.  */
-	addq	%r8, %rcx
-# ifdef USE_AS_STRNCMP
-	addq	$(VEC_SIZE * 2), %rcx
-	subq	%rcx, %r11
-	jbe	L(zero)
-#  ifdef USE_AS_WCSCMP
-	movq	%rax, %rsi
+	movl	VEC_OFFSET(%rdi, %rcx), %edx
 	xorl	%eax, %eax
-	movl	(%rsi, %rcx), %edi
-	cmpl	(%rdx, %rcx), %edi
-	jne	L(wcscmp_return)
-#  else
-	movzbl	(%rax, %rcx), %eax
-	movzbl	(%rdx, %rcx), %edx
-	subl	%edx, %eax
-#  endif
+	cmpl	VEC_OFFSET(%rsi, %rcx), %edx
+	je	L(ret9)
+	setl	%al
+	negl	%eax
+	xorl	%r8d, %eax
 # else
-#  ifdef USE_AS_WCSCMP
-	movq	%rax, %rsi
-	xorl	%eax, %eax
-	movl	(VEC_SIZE * 2)(%rsi, %rcx), %edi
-	cmpl	(VEC_SIZE * 2)(%rdx, %rcx), %edi
-	jne	L(wcscmp_return)
-#  else
-	movzbl	(VEC_SIZE * 2)(%rax, %rcx), %eax
-	movzbl	(VEC_SIZE * 2)(%rdx, %rcx), %edx
-	subl	%edx, %eax
-#  endif
+	movzbl	VEC_OFFSET(%rdi, %rcx), %eax
+	movzbl	VEC_OFFSET(%rsi, %rcx), %ecx
+	subl	%ecx, %eax
+	xorl	%r8d, %eax
+	subl	%r8d, %eax
 # endif
+L(ret9):
 	ret
 
-# ifdef USE_AS_STRNCMP
-L(string_nbyte_offset_check):
-	leaq	(VEC_SIZE * 4)(%r10), %r10
-	cmpq	%r10, %r11
-	jbe	L(zero)
-	jmp	L(back_to_loop)
+
+	.p2align 4,, 10
+L(page_cross):
+# ifndef USE_AS_STRNCMP
+	/* If both are VEC aligned we don't need any special logic here.
+	   Only valid for strcmp where stop condition is guranteed to be
+	   reachable by just reading memory.  */
+	testl	$((VEC_SIZE - 1) << 20), %eax
+	jz	L(no_page_cross)
 # endif
 
-	.p2align 4
-L(cross_page_loop):
-	/* Check one byte/dword at a time.  */
+	movl	%edi, %eax
+	movl	%esi, %ecx
+	andl	$(PAGE_SIZE - 1), %eax
+	andl	$(PAGE_SIZE - 1), %ecx
+
+	xorl	%OFFSET_REG, %OFFSET_REG
+
+	/* Check which is closer to page cross, s1 or s2.  */
+	cmpl	%eax, %ecx
+	jg	L(page_cross_s2)
+
+	/* The previous page cross check has false positives. Check for
+	   true positive as page cross logic is very expensive.  */
+	subl	$(PAGE_SIZE - VEC_SIZE * 4), %eax
+	jbe	L(no_page_cross)
+
+
+	/* Set r8 to not interfere with normal return value (rdi and rsi
+	   did not swap).  */
 # ifdef USE_AS_WCSCMP
-	cmpl	%ecx, %eax
+	/* any non-zero positive value that doesn't inference with 0x1.
+	 */
+	movl	$2, %r8d
 # else
-	subl	%ecx, %eax
+	xorl	%r8d, %r8d
 # endif
-	jne	L(different)
-	addl	$SIZE_OF_CHAR, %edx
-	cmpl	$(VEC_SIZE * 4), %edx
-	je	L(main_loop_header)
+
+	/* Check if less than 1x VEC till page cross.  */
+	subl	$(VEC_SIZE * 3), %eax
+	jg	L(less_1x_vec_till_page)
+
+
+	/* If more than 1x VEC till page cross, loop throuh safely
+	   loadable memory until within 1x VEC of page cross.  */
+	.p2align 4,, 8
+L(page_cross_loop):
+	VMOVU	(%rdi, %OFFSET_REG64, SIZE_OF_CHAR), %YMM0
+	VPTESTM	%YMM0, %YMM0, %k2
+	VPCMP	$0, (%rsi, %OFFSET_REG64, SIZE_OF_CHAR), %YMM0, %k1{%k2}
+	kmovd	%k1, %ecx
+	TESTEQ	%ecx
+	jnz	L(check_ret_vec_page_cross)
+	addl	$CHAR_PER_VEC, %OFFSET_REG
 # ifdef USE_AS_STRNCMP
-	cmpq	%r11, %rdx
-	jae	L(zero)
+	cmpq	%OFFSET_REG64, %rdx
+	jbe	L(ret_zero_page_cross)
 # endif
+	addl	$VEC_SIZE, %eax
+	jl	L(page_cross_loop)
+
 # ifdef USE_AS_WCSCMP
-	movl	(%rdi, %rdx), %eax
-	movl	(%rsi, %rdx), %ecx
-# else
-	movzbl	(%rdi, %rdx), %eax
-	movzbl	(%rsi, %rdx), %ecx
+	shrl	$2, %eax
 # endif
-	/* Check null CHAR.  */
-	testl	%eax, %eax
-	jne	L(cross_page_loop)
-	/* Since %eax == 0, subtract is OK for both SIGNED and UNSIGNED
-	   comparisons.  */
-	subl	%ecx, %eax
-# ifndef USE_AS_WCSCMP
-L(different):
+
+
+	subl	%eax, %OFFSET_REG
+	/* OFFSET_REG has distance to page cross - VEC_SIZE. Guranteed
+	   to not cross page so is safe to load. Since we have already
+	   loaded at least 1 VEC from rsi it is also guranteed to be safe.
+	 */
+	VMOVU	(%rdi, %OFFSET_REG64, SIZE_OF_CHAR), %YMM0
+	VPTESTM	%YMM0, %YMM0, %k2
+	VPCMP	$0, (%rsi, %OFFSET_REG64, SIZE_OF_CHAR), %YMM0, %k1{%k2}
+
+	kmovd	%k1, %ecx
+# ifdef USE_AS_STRNCMP
+	leal	CHAR_PER_VEC(%OFFSET_REG64), %eax
+	cmpq	%rax, %rdx
+	jbe	L(check_ret_vec_page_cross2)
+#  ifdef USE_AS_WCSCMP
+	addq	$-(CHAR_PER_VEC * 2), %rdx
+#  else
+	addq	%rdi, %rdx
+#  endif
 # endif
-	ret
+	TESTEQ	%ecx
+	jz	L(prepare_loop_no_len)
 
+	.p2align 4,, 4
+L(ret_vec_page_cross):
+# ifndef USE_AS_STRNCMP
+L(check_ret_vec_page_cross):
+# endif
+	tzcntl	%ecx, %ecx
+	addl	%OFFSET_REG, %ecx
+L(ret_vec_page_cross_cont):
 # ifdef USE_AS_WCSCMP
-	.p2align 4
-L(different):
-	/* Use movl to avoid modifying EFLAGS.  */
-	movl	$0, %eax
+	movl	(%rdi, %rcx, SIZE_OF_CHAR), %edx
+	xorl	%eax, %eax
+	cmpl	(%rsi, %rcx, SIZE_OF_CHAR), %edx
+	je	L(ret12)
 	setl	%al
 	negl	%eax
-	orl	$1, %eax
-	ret
+	xorl	%r8d, %eax
+# else
+	movzbl	(%rdi, %rcx, SIZE_OF_CHAR), %eax
+	movzbl	(%rsi, %rcx, SIZE_OF_CHAR), %ecx
+	subl	%ecx, %eax
+	xorl	%r8d, %eax
+	subl	%r8d, %eax
 # endif
+L(ret12):
+	ret
+
 
 # ifdef USE_AS_STRNCMP
-	.p2align 4
-L(zero):
+	.p2align 4,, 10
+L(check_ret_vec_page_cross2):
+	TESTEQ	%ecx
+L(check_ret_vec_page_cross):
+	tzcntl	%ecx, %ecx
+	addl	%OFFSET_REG, %ecx
+	cmpq	%rcx, %rdx
+	ja	L(ret_vec_page_cross_cont)
+	.p2align 4,, 2
+L(ret_zero_page_cross):
 	xorl	%eax, %eax
 	ret
+# endif
 
-	.p2align 4
-L(char0):
-#  ifdef USE_AS_WCSCMP
-	xorl	%eax, %eax
-	movl	(%rdi), %ecx
-	cmpl	(%rsi), %ecx
-	jne	L(wcscmp_return)
-#  else
-	movzbl	(%rsi), %ecx
-	movzbl	(%rdi), %eax
-	subl	%ecx, %eax
-#  endif
-	ret
+	.p2align 4,, 4
+L(page_cross_s2):
+	/* Ensure this is a true page cross.  */
+	subl	$(PAGE_SIZE - VEC_SIZE * 4), %ecx
+	jbe	L(no_page_cross)
+
+
+	movl	%ecx, %eax
+	movq	%rdi, %rcx
+	movq	%rsi, %rdi
+	movq	%rcx, %rsi
+
+	/* set r8 to negate return value as rdi and rsi swapped.  */
+# ifdef USE_AS_WCSCMP
+	movl	$-4, %r8d
+# else
+	movl	$-1, %r8d
 # endif
+	xorl	%OFFSET_REG, %OFFSET_REG
 
-	.p2align 4
-L(last_vector):
-	addq	%rdx, %rdi
-	addq	%rdx, %rsi
-# ifdef USE_AS_STRNCMP
-	subq	%rdx, %r11
+	/* Check if more than 1x VEC till page cross.  */
+	subl	$(VEC_SIZE * 3), %eax
+	jle	L(page_cross_loop)
+
+	.p2align 4,, 6
+L(less_1x_vec_till_page):
+# ifdef USE_AS_WCSCMP
+	shrl	$2, %eax
 # endif
-	tzcntl	%ecx, %edx
+	/* Find largest load size we can use.  */
+	cmpl	$(16 / SIZE_OF_CHAR), %eax
+	ja	L(less_16_till_page)
+
+	/* Use 16 byte comparison.  */
+	vmovdqu	(%rdi), %xmm0
+	VPTESTM	%xmm0, %xmm0, %k2
+	VPCMP	$0, (%rsi), %xmm0, %k1{%k2}
+	kmovd	%k1, %ecx
 # ifdef USE_AS_WCSCMP
-	/* NB: Multiply wchar_t count by 4 to get the number of bytes.  */
-	sall	$2, %edx
+	subl	$0xf, %ecx
+# else
+	incw	%cx
 # endif
+	jnz	L(check_ret_vec_page_cross)
+	movl	$(16 / SIZE_OF_CHAR), %OFFSET_REG
 # ifdef USE_AS_STRNCMP
-	cmpq	%r11, %rdx
-	jae	L(zero)
+	cmpq	%OFFSET_REG64, %rdx
+	jbe	L(ret_zero_page_cross_slow_case0)
+	subl	%eax, %OFFSET_REG
+# else
+	/* Explicit check for 16 byte alignment.  */
+	subl	%eax, %OFFSET_REG
+	jz	L(prepare_loop)
 # endif
+	vmovdqu	(%rdi, %OFFSET_REG64, SIZE_OF_CHAR), %xmm0
+	VPTESTM	%xmm0, %xmm0, %k2
+	VPCMP	$0, (%rsi, %OFFSET_REG64, SIZE_OF_CHAR), %xmm0, %k1{%k2}
+	kmovd	%k1, %ecx
 # ifdef USE_AS_WCSCMP
-	xorl	%eax, %eax
-	movl	(%rdi, %rdx), %ecx
-	cmpl	(%rsi, %rdx), %ecx
-	jne	L(wcscmp_return)
+	subl	$0xf, %ecx
 # else
-	movzbl	(%rdi, %rdx), %eax
-	movzbl	(%rsi, %rdx), %edx
-	subl	%edx, %eax
+	incw	%cx
 # endif
+	jnz	L(check_ret_vec_page_cross)
+# ifdef USE_AS_STRNCMP
+	addl	$(16 / SIZE_OF_CHAR), %OFFSET_REG
+	subq	%OFFSET_REG64, %rdx
+	jbe	L(ret_zero_page_cross_slow_case0)
+	subq	$-(CHAR_PER_VEC * 4), %rdx
+
+	leaq	-(VEC_SIZE * 4)(%rdi, %OFFSET_REG64, SIZE_OF_CHAR), %rdi
+	leaq	-(VEC_SIZE * 4)(%rsi, %OFFSET_REG64, SIZE_OF_CHAR), %rsi
+# else
+	leaq	(16 - VEC_SIZE * 4)(%rdi, %OFFSET_REG64, SIZE_OF_CHAR), %rdi
+	leaq	(16 - VEC_SIZE * 4)(%rsi, %OFFSET_REG64, SIZE_OF_CHAR), %rsi
+# endif
+	jmp	L(prepare_loop_aligned)
+
+# ifdef USE_AS_STRNCMP
+	.p2align 4,, 2
+L(ret_zero_page_cross_slow_case0):
+	xorl	%eax, %eax
 	ret
+# endif
 
-	/* Comparing on page boundary region requires special treatment:
-	   It must done one vector at the time, starting with the wider
-	   ymm vector if possible, if not, with xmm. If fetching 16 bytes
-	   (xmm) still passes the boundary, byte comparison must be done.
-	 */
-	.p2align 4
-L(cross_page):
-	/* Try one ymm vector at a time.  */
-	cmpl	$(PAGE_SIZE - VEC_SIZE), %eax
-	jg	L(cross_page_1_vector)
-L(loop_1_vector):
-	VMOVU	(%rdi, %rdx), %YMM0
 
-	VPTESTM	%YMM0, %YMM0, %k2
-	/* Each bit cleared in K1 represents a mismatch or a null CHAR
-	   in YMM0 and 32 bytes at (%rsi, %rdx).  */
-	VPCMP	$0, (%rsi, %rdx), %YMM0, %k1{%k2}
+	.p2align 4,, 10
+L(less_16_till_page):
+	cmpl	$(24 / SIZE_OF_CHAR), %eax
+	ja	L(less_8_till_page)
+
+	/* Use 8 byte comparison.  */
+	vmovq	(%rdi), %xmm0
+	vmovq	(%rsi), %xmm1
+	VPTESTM	%xmm0, %xmm0, %k2
+	VPCMP	$0, %xmm1, %xmm0, %k1{%k2}
 	kmovd	%k1, %ecx
 # ifdef USE_AS_WCSCMP
-	subl	$0xff, %ecx
+	subl	$0x3, %ecx
 # else
-	incl	%ecx
+	incb	%cl
 # endif
-	jne	L(last_vector)
+	jnz	L(check_ret_vec_page_cross)
 
-	addl	$VEC_SIZE, %edx
 
-	addl	$VEC_SIZE, %eax
 # ifdef USE_AS_STRNCMP
-	/* Return 0 if the current offset (%rdx) >= the maximum offset
-	   (%r11).  */
-	cmpq	%r11, %rdx
-	jae	L(zero)
+	cmpq	$(8 / SIZE_OF_CHAR), %rdx
+	jbe	L(ret_zero_page_cross_slow_case0)
 # endif
-	cmpl	$(PAGE_SIZE - VEC_SIZE), %eax
-	jle	L(loop_1_vector)
-L(cross_page_1_vector):
-	/* Less than 32 bytes to check, try one xmm vector.  */
-	cmpl	$(PAGE_SIZE - 16), %eax
-	jg	L(cross_page_1_xmm)
-	VMOVU	(%rdi, %rdx), %XMM0
+	movl	$(24 / SIZE_OF_CHAR), %OFFSET_REG
+	subl	%eax, %OFFSET_REG
 
-	VPTESTM	%YMM0, %YMM0, %k2
-	/* Each bit cleared in K1 represents a mismatch or a null CHAR
-	   in XMM0 and 16 bytes at (%rsi, %rdx).  */
-	VPCMP	$0, (%rsi, %rdx), %XMM0, %k1{%k2}
+	vmovq	(%rdi, %OFFSET_REG64, SIZE_OF_CHAR), %xmm0
+	vmovq	(%rsi, %OFFSET_REG64, SIZE_OF_CHAR), %xmm1
+	VPTESTM	%xmm0, %xmm0, %k2
+	VPCMP	$0, %xmm1, %xmm0, %k1{%k2}
 	kmovd	%k1, %ecx
 # ifdef USE_AS_WCSCMP
-	subl	$0xf, %ecx
+	subl	$0x3, %ecx
 # else
-	subl	$0xffff, %ecx
+	incb	%cl
 # endif
-	jne	L(last_vector)
+	jnz	L(check_ret_vec_page_cross)
+
 
-	addl	$16, %edx
-# ifndef USE_AS_WCSCMP
-	addl	$16, %eax
-# endif
 # ifdef USE_AS_STRNCMP
-	/* Return 0 if the current offset (%rdx) >= the maximum offset
-	   (%r11).  */
-	cmpq	%r11, %rdx
-	jae	L(zero)
+	addl	$(8 / SIZE_OF_CHAR), %OFFSET_REG
+	subq	%OFFSET_REG64, %rdx
+	jbe	L(ret_zero_page_cross_slow_case0)
+	subq	$-(CHAR_PER_VEC * 4), %rdx
+
+	leaq	-(VEC_SIZE * 4)(%rdi, %OFFSET_REG64, SIZE_OF_CHAR), %rdi
+	leaq	-(VEC_SIZE * 4)(%rsi, %OFFSET_REG64, SIZE_OF_CHAR), %rsi
+# else
+	leaq	(8 - VEC_SIZE * 4)(%rdi, %OFFSET_REG64, SIZE_OF_CHAR), %rdi
+	leaq	(8 - VEC_SIZE * 4)(%rsi, %OFFSET_REG64, SIZE_OF_CHAR), %rsi
 # endif
+	jmp	L(prepare_loop_aligned)
 
-L(cross_page_1_xmm):
-# ifndef USE_AS_WCSCMP
-	/* Less than 16 bytes to check, try 8 byte vector.  NB: No need
-	   for wcscmp nor wcsncmp since wide char is 4 bytes.   */
-	cmpl	$(PAGE_SIZE - 8), %eax
-	jg	L(cross_page_8bytes)
-	vmovq	(%rdi, %rdx), %XMM0
-	vmovq	(%rsi, %rdx), %XMM1
 
-	VPTESTM	%YMM0, %YMM0, %k2
-	/* Each bit cleared in K1 represents a mismatch or a null CHAR
-	   in XMM0 and XMM1.  */
-	VPCMP	$0, %XMM1, %XMM0, %k1{%k2}
-	kmovb	%k1, %ecx
+
+
+	.p2align 4,, 10
+L(less_8_till_page):
 # ifdef USE_AS_WCSCMP
-	subl	$0x3, %ecx
+	/* If using wchar then this is the only check before we reach
+	   the page boundary.  */
+	movl	(%rdi), %eax
+	movl	(%rsi), %ecx
+	cmpl	%ecx, %eax
+	jnz	L(ret_less_8_wcs)
+#  ifdef USE_AS_STRNCMP
+	addq	$-(CHAR_PER_VEC * 2), %rdx
+	/* We already checked for len <= 1 so cannot hit that case here.
+	 */
+#  endif
+	testl	%eax, %eax
+	jnz	L(prepare_loop)
+	ret
+
+	.p2align 4,, 8
+L(ret_less_8_wcs):
+	setl	%OFFSET_REG8
+	negl	%OFFSET_REG
+	movl	%OFFSET_REG, %eax
+	xorl	%r8d, %eax
+	ret
+
 # else
-	subl	$0xff, %ecx
-# endif
-	jne	L(last_vector)
+	cmpl	$28, %eax
+	ja	L(less_4_till_page)
+
+	vmovd	(%rdi), %xmm0
+	vmovd	(%rsi), %xmm1
+	VPTESTM	%xmm0, %xmm0, %k2
+	VPCMP	$0, %xmm1, %xmm0, %k1{%k2}
+	kmovd	%k1, %ecx
+	subl	$0xf, %ecx
+	jnz	L(check_ret_vec_page_cross)
 
-	addl	$8, %edx
-	addl	$8, %eax
 #  ifdef USE_AS_STRNCMP
-	/* Return 0 if the current offset (%rdx) >= the maximum offset
-	   (%r11).  */
-	cmpq	%r11, %rdx
-	jae	L(zero)
+	cmpq	$4, %rdx
+	jbe	L(ret_zero_page_cross_slow_case1)
 #  endif
+	movl	$(28 / SIZE_OF_CHAR), %OFFSET_REG
+	subl	%eax, %OFFSET_REG
 
-L(cross_page_8bytes):
-	/* Less than 8 bytes to check, try 4 byte vector.  */
-	cmpl	$(PAGE_SIZE - 4), %eax
-	jg	L(cross_page_4bytes)
-	vmovd	(%rdi, %rdx), %XMM0
-	vmovd	(%rsi, %rdx), %XMM1
-
-	VPTESTM	%YMM0, %YMM0, %k2
-	/* Each bit cleared in K1 represents a mismatch or a null CHAR
-	   in XMM0 and XMM1.  */
-	VPCMP	$0, %XMM1, %XMM0, %k1{%k2}
+	vmovd	(%rdi, %OFFSET_REG64, SIZE_OF_CHAR), %xmm0
+	vmovd	(%rsi, %OFFSET_REG64, SIZE_OF_CHAR), %xmm1
+	VPTESTM	%xmm0, %xmm0, %k2
+	VPCMP	$0, %xmm1, %xmm0, %k1{%k2}
 	kmovd	%k1, %ecx
-# ifdef USE_AS_WCSCMP
-	subl	$0x1, %ecx
-# else
 	subl	$0xf, %ecx
-# endif
-	jne	L(last_vector)
+	jnz	L(check_ret_vec_page_cross)
+#  ifdef USE_AS_STRNCMP
+	addl	$(4 / SIZE_OF_CHAR), %OFFSET_REG
+	subq	%OFFSET_REG64, %rdx
+	jbe	L(ret_zero_page_cross_slow_case1)
+	subq	$-(CHAR_PER_VEC * 4), %rdx
+
+	leaq	-(VEC_SIZE * 4)(%rdi, %OFFSET_REG64, SIZE_OF_CHAR), %rdi
+	leaq	-(VEC_SIZE * 4)(%rsi, %OFFSET_REG64, SIZE_OF_CHAR), %rsi
+#  else
+	leaq	(4 - VEC_SIZE * 4)(%rdi, %OFFSET_REG64, SIZE_OF_CHAR), %rdi
+	leaq	(4 - VEC_SIZE * 4)(%rsi, %OFFSET_REG64, SIZE_OF_CHAR), %rsi
+#  endif
+	jmp	L(prepare_loop_aligned)
+
 
-	addl	$4, %edx
 #  ifdef USE_AS_STRNCMP
-	/* Return 0 if the current offset (%rdx) >= the maximum offset
-	   (%r11).  */
-	cmpq	%r11, %rdx
-	jae	L(zero)
+	.p2align 4,, 2
+L(ret_zero_page_cross_slow_case1):
+	xorl	%eax, %eax
+	ret
 #  endif
 
-L(cross_page_4bytes):
-# endif
-	/* Less than 4 bytes to check, try one byte/dword at a time.  */
-# ifdef USE_AS_STRNCMP
-	cmpq	%r11, %rdx
-	jae	L(zero)
-# endif
-# ifdef USE_AS_WCSCMP
-	movl	(%rdi, %rdx), %eax
-	movl	(%rsi, %rdx), %ecx
-# else
-	movzbl	(%rdi, %rdx), %eax
-	movzbl	(%rsi, %rdx), %ecx
-# endif
-	testl	%eax, %eax
-	jne	L(cross_page_loop)
+	.p2align 4,, 10
+L(less_4_till_page):
+	subq	%rdi, %rsi
+	/* Extremely slow byte comparison loop.  */
+L(less_4_loop):
+	movzbl	(%rdi), %eax
+	movzbl	(%rsi, %rdi), %ecx
 	subl	%ecx, %eax
+	jnz	L(ret_less_4_loop)
+	testl	%ecx, %ecx
+	jz	L(ret_zero_4_loop)
+#  ifdef USE_AS_STRNCMP
+	decq	%rdx
+	jz	L(ret_zero_4_loop)
+#  endif
+	incq	%rdi
+	/* end condition is reach page boundary (rdi is aligned).  */
+	testl	$31, %edi
+	jnz	L(less_4_loop)
+	leaq	-(VEC_SIZE * 4)(%rdi, %rsi), %rsi
+	addq	$-(VEC_SIZE * 4), %rdi
+#  ifdef USE_AS_STRNCMP
+	subq	$-(CHAR_PER_VEC * 4), %rdx
+#  endif
+	jmp	L(prepare_loop_aligned)
+
+L(ret_zero_4_loop):
+	xorl	%eax, %eax
+	ret
+L(ret_less_4_loop):
+	xorl	%r8d, %eax
+	subl	%r8d, %eax
 	ret
-END (STRCMP)
+# endif
+END(STRCMP)
 #endif
-- 
GitLab