diff mbox series

[v2,5/5] x86_64: Add evex optimized bcmp implementation in bcmp-evex.S

Message ID 20210914063039.1126196-5-goldstein.w.n@gmail.com
State New
Headers show
Series [v2,1/5] x86_64: Add support for bcmp using sse2, sse4_1, avx2, and evex | expand

Commit Message

Noah Goldstein Sept. 14, 2021, 6:30 a.m. UTC
No bug. This commit adds new optimized bcmp implementation for evex.

The primary optimizations are 1) skipping the logic to find the
difference of the first mismatched byte and 2) not updating src/dst
addresses as the non-equals logic does not need to be reused by
different areas.

The entry alignment has been fixed at 64. In throughput sensitive
functions which bcmp can potentially be frontend loop performance is
important to opimized for. This is impossible/difficult to do/maintain
with only 16 byte fixed alignment.

test-memcmp, test-bcmp, and test-wmemcmp are all passing.
---
 sysdeps/x86_64/multiarch/bcmp-evex.S       | 305 ++++++++++++++++++++-
 sysdeps/x86_64/multiarch/ifunc-bcmp.h      |   3 +-
 sysdeps/x86_64/multiarch/ifunc-impl-list.c |   1 -
 3 files changed, 302 insertions(+), 7 deletions(-)
diff mbox series

Patch

diff --git a/sysdeps/x86_64/multiarch/bcmp-evex.S b/sysdeps/x86_64/multiarch/bcmp-evex.S
index ade52e8c68..1bfe824eb4 100644
--- a/sysdeps/x86_64/multiarch/bcmp-evex.S
+++ b/sysdeps/x86_64/multiarch/bcmp-evex.S
@@ -16,8 +16,305 @@ 
    License along with the GNU C Library; if not, see
    <https://www.gnu.org/licenses/>.  */
 
-#ifndef MEMCMP
-# define MEMCMP	__bcmp_evex
-#endif
+#if IS_IN (libc)
+
+/* bcmp is implemented as:
+   1. Use ymm vector compares when possible. The only case where
+      vector compares is not possible for when size < VEC_SIZE
+      and loading from either s1 or s2 would cause a page cross.
+   2. Use xmm vector compare when size >= 8 bytes.
+   3. Optimistically compare up to first 4 * VEC_SIZE one at a
+      to check for early mismatches. Only do this if its guranteed the
+      work is not wasted.
+   4. If size is 8 * VEC_SIZE or less, unroll the loop.
+   5. Compare 4 * VEC_SIZE at a time with the aligned first memory
+      area.
+   6. Use 2 vector compares when size is 2 * VEC_SIZE or less.
+   7. Use 4 vector compares when size is 4 * VEC_SIZE or less.
+   8. Use 8 vector compares when size is 8 * VEC_SIZE or less.  */
+
+# include <sysdep.h>
+
+# ifndef BCMP
+#  define BCMP	__bcmp_evex
+# endif
+
+# define VMOVU	vmovdqu64
+# define VPCMP	vpcmpub
+# define VPTEST	vptestmb
+
+# define VEC_SIZE	32
+# define PAGE_SIZE	4096
+
+# define YMM0		ymm16
+# define YMM1		ymm17
+# define YMM2		ymm18
+# define YMM3		ymm19
+# define YMM4		ymm20
+# define YMM5		ymm21
+# define YMM6		ymm22
+
+
+	.section .text.evex, "ax", @progbits
+ENTRY_P2ALIGN (BCMP, 6)
+# ifdef __ILP32__
+	/* Clear the upper 32 bits.  */
+	movl	%edx, %edx
+# endif
+	cmp	$VEC_SIZE, %RDX_LP
+	jb	L(less_vec)
+
+	/* From VEC to 2 * VEC.  No branch when size == VEC_SIZE.  */
+	VMOVU	(%rsi), %YMM1
+	/* Use compare not equals to directly check for mismatch.  */
+	VPCMP	$4, (%rdi), %YMM1, %k1
+	kmovd	%k1, %eax
+	testl	%eax, %eax
+	jnz	L(return_neq0)
+
+	cmpq	$(VEC_SIZE * 2), %rdx
+	jbe	L(last_1x_vec)
+
+	/* Check second VEC no matter what.  */
+	VMOVU	VEC_SIZE(%rsi), %YMM2
+	VPCMP	$4, VEC_SIZE(%rdi), %YMM2, %k1
+	kmovd	%k1, %eax
+	testl	%eax, %eax
+	jnz	L(return_neq0)
+
+	/* Less than 4 * VEC.  */
+	cmpq	$(VEC_SIZE * 4), %rdx
+	jbe	L(last_2x_vec)
+
+	/* Check third and fourth VEC no matter what.  */
+	VMOVU	(VEC_SIZE * 2)(%rsi), %YMM3
+	VPCMP	$4, (VEC_SIZE * 2)(%rdi), %YMM3, %k1
+	kmovd	%k1, %eax
+	testl	%eax, %eax
+	jnz	L(return_neq0)
+
+	VMOVU	(VEC_SIZE * 3)(%rsi), %YMM4
+	VPCMP	$4, (VEC_SIZE * 3)(%rdi), %YMM4, %k1
+	kmovd	%k1, %eax
+	testl	%eax, %eax
+	jnz	L(return_neq0)
+
+	/* Go to 4x VEC loop.  */
+	cmpq	$(VEC_SIZE * 8), %rdx
+	ja	L(more_8x_vec)
+
+	/* Handle remainder of size = 4 * VEC + 1 to 8 * VEC without any
+	   branches.  */
+
+	VMOVU	-(VEC_SIZE * 4)(%rsi, %rdx), %YMM1
+	VMOVU	-(VEC_SIZE * 3)(%rsi, %rdx), %YMM2
+	addq	%rdx, %rdi
+
+	/* Wait to load from s1 until addressed adjust due to unlamination.
+	 */
+
+	/* vpxor will be all 0s if s1 and s2 are equal. Otherwise it will
+	   have some 1s.  */
+	vpxorq	-(VEC_SIZE * 4)(%rdi), %YMM1, %YMM1
+	vpxorq	-(VEC_SIZE * 3)(%rdi), %YMM2, %YMM2
+
+	VMOVU	-(VEC_SIZE * 2)(%rsi, %rdx), %YMM3
+	vpxorq	-(VEC_SIZE * 2)(%rdi), %YMM3, %YMM3
+	/* Or together YMM1, YMM2, and YMM3 into YMM3.  */
+	vpternlogd $0xfe, %YMM1, %YMM2, %YMM3
 
-#include "memcmp-evex-movbe.S"
+	VMOVU	-(VEC_SIZE)(%rsi, %rdx), %YMM4
+	/* Ternary logic to xor (VEC_SIZE * 3)(%rdi) with YMM4 while oring
+	   with YMM3. Result is stored in YMM4.  */
+	vpternlogd $0xde, -(VEC_SIZE)(%rdi), %YMM3, %YMM4
+	/* Compare YMM4 with 0. If any 1s s1 and s2 don't match.  */
+	VPTEST	%YMM4, %YMM4, %k1
+	kmovd	%k1, %eax
+L(return_neq0):
+	ret
+
+	/* Fits in padding needed to .p2align 5 L(less_vec).  */
+L(last_1x_vec):
+	VMOVU	-(VEC_SIZE * 1)(%rsi, %rdx), %YMM1
+	VPCMP	$4, -(VEC_SIZE * 1)(%rdi, %rdx), %YMM1, %k1
+	kmovd	%k1, %eax
+	ret
+
+	/* NB: p2align 5 here will ensure the L(loop_4x_vec) is also 32 byte
+	   aligned.  */
+	.p2align 5
+L(less_vec):
+	/* Check if one or less char. This is necessary for size = 0 but is
+	   also faster for size = 1.  */
+	cmpl	$1, %edx
+	jbe	L(one_or_less)
+
+	/* Check if loading one VEC from either s1 or s2 could cause a page
+	   cross. This can have false positives but is by far the fastest
+	   method.  */
+	movl	%edi, %eax
+	orl	%esi, %eax
+	andl	$(PAGE_SIZE - 1), %eax
+	cmpl	$(PAGE_SIZE - VEC_SIZE), %eax
+	jg	L(page_cross_less_vec)
+
+	/* No page cross possible.  */
+	VMOVU	(%rsi), %YMM2
+	VPCMP	$4, (%rdi), %YMM2, %k1
+	kmovd	%k1, %eax
+	/* Result will be zero if s1 and s2 match. Otherwise first set bit
+	   will be first mismatch.  */
+	bzhil	%edx, %eax, %eax
+	ret
+
+	/* Relatively cold but placing close to L(less_vec) for 2 byte jump
+	   encoding.  */
+	.p2align 4
+L(one_or_less):
+	jb	L(zero)
+	movzbl	(%rsi), %ecx
+	movzbl	(%rdi), %eax
+	subl	%ecx, %eax
+	/* No ymm register was touched.  */
+	ret
+	/* Within the same 16 byte block is L(one_or_less).  */
+L(zero):
+	xorl	%eax, %eax
+	ret
+
+	.p2align 4
+L(last_2x_vec):
+	VMOVU	-(VEC_SIZE * 2)(%rsi, %rdx), %YMM1
+	vpxorq	-(VEC_SIZE * 2)(%rdi, %rdx), %YMM1, %YMM1
+	VMOVU	-(VEC_SIZE * 1)(%rsi, %rdx), %YMM2
+	vpternlogd $0xde, -(VEC_SIZE * 1)(%rdi, %rdx), %YMM1, %YMM2
+	VPTEST	%YMM2, %YMM2, %k1
+	kmovd	%k1, %eax
+	ret
+
+	.p2align 4
+L(more_8x_vec):
+	/* Set end of s1 in rdx.  */
+	leaq	-(VEC_SIZE * 4)(%rdi, %rdx), %rdx
+	/* rsi stores s2 - s1. This allows loop to only update one pointer.
+	 */
+	subq	%rdi, %rsi
+	/* Align s1 pointer.  */
+	andq	$-VEC_SIZE, %rdi
+	/* Adjust because first 4x vec where check already.  */
+	subq	$-(VEC_SIZE * 4), %rdi
+	.p2align 4
+L(loop_4x_vec):
+	VMOVU	(%rsi, %rdi), %YMM1
+	vpxorq	(%rdi), %YMM1, %YMM1
+
+	VMOVU	VEC_SIZE(%rsi, %rdi), %YMM2
+	vpxorq	VEC_SIZE(%rdi), %YMM2, %YMM2
+
+	VMOVU	(VEC_SIZE * 2)(%rsi, %rdi), %YMM3
+	vpxorq	(VEC_SIZE * 2)(%rdi), %YMM3, %YMM3
+	vpternlogd $0xfe, %YMM1, %YMM2, %YMM3
+
+	VMOVU	(VEC_SIZE * 3)(%rsi, %rdi), %YMM4
+	vpternlogd $0xde, (VEC_SIZE * 3)(%rdi), %YMM3, %YMM4
+	VPTEST	%YMM4, %YMM4, %k1
+	kmovd	%k1, %eax
+	testl	%eax, %eax
+	jnz	L(return_neq2)
+	subq	$-(VEC_SIZE * 4), %rdi
+	cmpq	%rdx, %rdi
+	jb	L(loop_4x_vec)
+
+	subq	%rdx, %rdi
+	VMOVU	(VEC_SIZE * 3)(%rsi, %rdx), %YMM4
+	vpxorq	(VEC_SIZE * 3)(%rdx), %YMM4, %YMM4
+	/* rdi has 4 * VEC_SIZE - remaining length.  */
+	cmpl	$(VEC_SIZE * 3), %edi
+	jae	L(8x_last_1x_vec)
+	/* Load regardless of branch.  */
+	VMOVU	(VEC_SIZE * 2)(%rsi, %rdx), %YMM3
+	/* Ternary logic to xor (VEC_SIZE * 2)(%rdx) with YMM3 while oring
+	   with YMM4. Result is stored in YMM4.  */
+	vpternlogd $0xf6, (VEC_SIZE * 2)(%rdx), %YMM3, %YMM4
+	cmpl	$(VEC_SIZE * 2), %edi
+	jae	L(8x_last_2x_vec)
+
+	VMOVU	VEC_SIZE(%rsi, %rdx), %YMM2
+	vpxorq	VEC_SIZE(%rdx), %YMM2, %YMM2
+
+	VMOVU	(%rsi, %rdx), %YMM1
+	vpxorq	(%rdx), %YMM1, %YMM1
+
+	vpternlogd $0xfe, %YMM1, %YMM2, %YMM4
+L(8x_last_1x_vec):
+L(8x_last_2x_vec):
+	VPTEST	%YMM4, %YMM4, %k1
+	kmovd	%k1, %eax
+L(return_neq2):
+	ret
+
+	/* Relatively cold case as page cross are unexpected.  */
+	.p2align 4
+L(page_cross_less_vec):
+	cmpl	$16, %edx
+	jae	L(between_16_31)
+	cmpl	$8, %edx
+	ja	L(between_9_15)
+	cmpl	$4, %edx
+	jb	L(between_2_3)
+	/* From 4 to 8 bytes.  No branch when size == 4.  */
+	movl	(%rdi), %eax
+	movl	(%rsi), %ecx
+	subl	%ecx, %eax
+	movl	-4(%rdi, %rdx), %ecx
+	movl	-4(%rsi, %rdx), %esi
+	subl	%esi, %ecx
+	orl	%ecx, %eax
+	ret
+
+	.p2align 4,, 8
+L(between_9_15):
+	/* Safe to use xmm[0, 15] as no vzeroupper is needed so RTM safe.
+	 */
+	vmovq	(%rdi), %xmm1
+	vmovq	(%rsi), %xmm2
+	vpcmpeqb %xmm1, %xmm2, %xmm3
+	vmovq	-8(%rdi, %rdx), %xmm1
+	vmovq	-8(%rsi, %rdx), %xmm2
+	vpcmpeqb %xmm1, %xmm2, %xmm2
+	vpand	%xmm2, %xmm3, %xmm3
+	vpmovmskb %xmm3, %eax
+	subl	$0xffff, %eax
+	/* No ymm register was touched.  */
+	ret
+
+	.p2align 4,, 8
+L(between_16_31):
+	/* From 16 to 31 bytes.  No branch when size == 16.  */
+
+	/* Safe to use xmm[0, 15] as no vzeroupper is needed so RTM safe.
+	 */
+	vmovdqu	(%rsi), %xmm1
+	vpcmpeqb (%rdi), %xmm1, %xmm1
+	vmovdqu	-16(%rsi, %rdx), %xmm2
+	vpcmpeqb -16(%rdi, %rdx), %xmm2, %xmm2
+	vpand	%xmm1, %xmm2, %xmm2
+	vpmovmskb %xmm2, %eax
+	subl	$0xffff, %eax
+	/* No ymm register was touched.  */
+	ret
+
+	.p2align 4,, 8
+L(between_2_3):
+	/* From 2 to 3 bytes.  No branch when size == 2.  */
+	movzwl	(%rdi), %eax
+	movzwl	(%rsi), %ecx
+	subl	%ecx, %eax
+	movzbl	-1(%rdi, %rdx), %edi
+	movzbl	-1(%rsi, %rdx), %esi
+	subl	%edi, %esi
+	orl	%esi, %eax
+	/* No ymm register was touched.  */
+	ret
+END (BCMP)
+#endif
diff --git a/sysdeps/x86_64/multiarch/ifunc-bcmp.h b/sysdeps/x86_64/multiarch/ifunc-bcmp.h
index f94516e5ee..51f251d0c9 100644
--- a/sysdeps/x86_64/multiarch/ifunc-bcmp.h
+++ b/sysdeps/x86_64/multiarch/ifunc-bcmp.h
@@ -35,8 +35,7 @@  IFUNC_SELECTOR (void)
       && CPU_FEATURES_ARCH_P (cpu_features, AVX_Fast_Unaligned_Load))
     {
       if (CPU_FEATURE_USABLE_P (cpu_features, AVX512VL)
-	  && CPU_FEATURE_USABLE_P (cpu_features, AVX512BW)
-	  && CPU_FEATURE_USABLE_P (cpu_features, MOVBE))
+	  && CPU_FEATURE_USABLE_P (cpu_features, AVX512BW))
 	return OPTIMIZE (evex);
 
       if (CPU_FEATURE_USABLE_P (cpu_features, RTM))
diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
index cda0316928..abbb4e407f 100644
--- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c
+++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
@@ -52,7 +52,6 @@  __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 	      IFUNC_IMPL_ADD (array, i, bcmp,
 			      (CPU_FEATURE_USABLE (AVX512VL)
 			       && CPU_FEATURE_USABLE (AVX512BW)
-                   && CPU_FEATURE_USABLE (MOVBE)
 			       && CPU_FEATURE_USABLE (BMI2)),
 			      __bcmp_evex)
 	      IFUNC_IMPL_ADD (array, i, bcmp, CPU_FEATURE_USABLE (SSE4_1),