glibc/SOURCES/glibc-upstream-2.34-178.patch
2022-11-15 11:09:11 +00:00

691 lines
20 KiB
Diff

commit f35ad30da4880a1574996df0674986ecf82fa7ae
Author: H.J. Lu <hjl.tools@gmail.com>
Date: Fri Oct 29 12:40:20 2021 -0700
x86-64: Improve EVEX strcmp with masked load
In strcmp-evex.S, to compare 2 32-byte strings, replace
VMOVU (%rdi, %rdx), %YMM0
VMOVU (%rsi, %rdx), %YMM1
/* Each bit in K0 represents a mismatch in YMM0 and YMM1. */
VPCMP $4, %YMM0, %YMM1, %k0
VPCMP $0, %YMMZERO, %YMM0, %k1
VPCMP $0, %YMMZERO, %YMM1, %k2
/* Each bit in K1 represents a NULL in YMM0 or YMM1. */
kord %k1, %k2, %k1
/* Each bit in K1 represents a NULL or a mismatch. */
kord %k0, %k1, %k1
kmovd %k1, %ecx
testl %ecx, %ecx
jne L(last_vector)
with
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}
kmovd %k1, %ecx
incl %ecx
jne L(last_vector)
It makes EVEX strcmp faster than AVX2 strcmp by up to 40% on Tiger Lake
and Ice Lake.
Co-Authored-By: Noah Goldstein <goldstein.w.n@gmail.com>
(cherry picked from commit c46e9afb2df5fc9e39ff4d13777e4b4c26e04e55)
diff --git a/sysdeps/x86_64/multiarch/strcmp-evex.S b/sysdeps/x86_64/multiarch/strcmp-evex.S
index d5aa6daa46c7ed25..82f12ac89bcae20b 100644
--- a/sysdeps/x86_64/multiarch/strcmp-evex.S
+++ b/sysdeps/x86_64/multiarch/strcmp-evex.S
@@ -41,6 +41,8 @@
# ifdef USE_AS_WCSCMP
/* 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. */
@@ -48,6 +50,8 @@
# else
/* 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. */
@@ -67,6 +71,9 @@
# 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.
@@ -76,7 +83,7 @@
/* The main idea of the string comparison (byte or dword) using 256-bit
EVEX instructions consists of comparing (VPCMP) two ymm vectors. The
latter can be on either packed bytes or dwords depending on
- USE_AS_WCSCMP. In order to check the null char, algorithm keeps the
+ USE_AS_WCSCMP. In order to check the null CHAR, algorithm keeps the
matched bytes/dwords, requiring 5 EVEX instructions (3 VPCMP and 2
KORD). In general, the costs of comparing VEC_SIZE bytes (32-bytes)
are 3 VPCMP and 2 KORD instructions, together with VMOVU and ktestd
@@ -123,27 +130,21 @@ ENTRY (STRCMP)
jg L(cross_page)
/* Start comparing 4 vectors. */
VMOVU (%rdi), %YMM0
- VMOVU (%rsi), %YMM1
- /* Each bit in K0 represents a mismatch in YMM0 and YMM1. */
- VPCMP $4, %YMM0, %YMM1, %k0
+ /* Each bit set in K2 represents a non-null CHAR in YMM0. */
+ VPTESTM %YMM0, %YMM0, %k2
- /* Check for NULL in YMM0. */
- VPCMP $0, %YMMZERO, %YMM0, %k1
- /* Check for NULL in YMM1. */
- VPCMP $0, %YMMZERO, %YMM1, %k2
- /* Each bit in K1 represents a NULL in YMM0 or YMM1. */
- kord %k1, %k2, %k1
+ /* 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}
- /* Each bit in K1 represents:
- 1. A mismatch in YMM0 and YMM1. Or
- 2. A NULL in YMM0 or YMM1.
- */
- kord %k0, %k1, %k1
-
- ktestd %k1, %k1
- je L(next_3_vectors)
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. */
@@ -172,9 +173,7 @@ L(return):
# endif
ret
- .p2align 4
L(return_vec_size):
- kmovd %k1, %ecx
tzcntl %ecx, %edx
# ifdef USE_AS_WCSCMP
/* NB: Multiply wchar_t count by 4 to get the number of bytes. */
@@ -210,9 +209,7 @@ L(return_vec_size):
# endif
ret
- .p2align 4
L(return_2_vec_size):
- kmovd %k1, %ecx
tzcntl %ecx, %edx
# ifdef USE_AS_WCSCMP
/* NB: Multiply wchar_t count by 4 to get the number of bytes. */
@@ -248,9 +245,7 @@ L(return_2_vec_size):
# endif
ret
- .p2align 4
L(return_3_vec_size):
- kmovd %k1, %ecx
tzcntl %ecx, %edx
# ifdef USE_AS_WCSCMP
/* NB: Multiply wchar_t count by 4 to get the number of bytes. */
@@ -289,43 +284,45 @@ L(return_3_vec_size):
.p2align 4
L(next_3_vectors):
VMOVU VEC_SIZE(%rdi), %YMM0
- VMOVU VEC_SIZE(%rsi), %YMM1
- /* Each bit in K0 represents a mismatch in YMM0 and YMM1. */
- VPCMP $4, %YMM0, %YMM1, %k0
- VPCMP $0, %YMMZERO, %YMM0, %k1
- VPCMP $0, %YMMZERO, %YMM1, %k2
- /* Each bit in K1 represents a NULL in YMM0 or YMM1. */
- kord %k1, %k2, %k1
- /* Each bit in K1 represents a NULL or a mismatch. */
- kord %k0, %k1, %k1
- ktestd %k1, %k1
+ /* 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(%rsi). */
+ VPCMP $0, VEC_SIZE(%rsi), %YMM0, %k1{%k2}
+ kmovd %k1, %ecx
+# ifdef USE_AS_WCSCMP
+ subl $0xff, %ecx
+# else
+ incl %ecx
+# endif
jne L(return_vec_size)
- VMOVU (VEC_SIZE * 2)(%rdi), %YMM2
- VMOVU (VEC_SIZE * 3)(%rdi), %YMM3
- VMOVU (VEC_SIZE * 2)(%rsi), %YMM4
- VMOVU (VEC_SIZE * 3)(%rsi), %YMM5
-
- /* Each bit in K0 represents a mismatch in YMM2 and YMM4. */
- VPCMP $4, %YMM2, %YMM4, %k0
- VPCMP $0, %YMMZERO, %YMM2, %k1
- VPCMP $0, %YMMZERO, %YMM4, %k2
- /* Each bit in K1 represents a NULL in YMM2 or YMM4. */
- kord %k1, %k2, %k1
- /* Each bit in K1 represents a NULL or a mismatch. */
- kord %k0, %k1, %k1
- ktestd %k1, %k1
+ 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)
- /* Each bit in K0 represents a mismatch in YMM3 and YMM5. */
- VPCMP $4, %YMM3, %YMM5, %k0
- VPCMP $0, %YMMZERO, %YMM3, %k1
- VPCMP $0, %YMMZERO, %YMM5, %k2
- /* Each bit in K1 represents a NULL in YMM3 or YMM5. */
- kord %k1, %k2, %k1
- /* Each bit in K1 represents a NULL or a mismatch. */
- kord %k0, %k1, %k1
- ktestd %k1, %k1
+ 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
+# ifdef USE_AS_WCSCMP
+ subl $0xff, %ecx
+# else
+ incl %ecx
+# endif
jne L(return_3_vec_size)
L(main_loop_header):
leaq (VEC_SIZE * 4)(%rdi), %rdx
@@ -375,56 +372,51 @@ L(back_to_loop):
VMOVA VEC_SIZE(%rax), %YMM2
VMOVA (VEC_SIZE * 2)(%rax), %YMM4
VMOVA (VEC_SIZE * 3)(%rax), %YMM6
- VMOVU (%rdx), %YMM1
- VMOVU VEC_SIZE(%rdx), %YMM3
- VMOVU (VEC_SIZE * 2)(%rdx), %YMM5
- VMOVU (VEC_SIZE * 3)(%rdx), %YMM7
-
- VPCMP $4, %YMM0, %YMM1, %k0
- VPCMP $0, %YMMZERO, %YMM0, %k1
- VPCMP $0, %YMMZERO, %YMM1, %k2
- kord %k1, %k2, %k1
- /* Each bit in K4 represents a NULL or a mismatch in YMM0 and
- YMM1. */
- kord %k0, %k1, %k4
-
- VPCMP $4, %YMM2, %YMM3, %k0
- VPCMP $0, %YMMZERO, %YMM2, %k1
- VPCMP $0, %YMMZERO, %YMM3, %k2
- kord %k1, %k2, %k1
- /* Each bit in K5 represents a NULL or a mismatch in YMM2 and
- YMM3. */
- kord %k0, %k1, %k5
-
- VPCMP $4, %YMM4, %YMM5, %k0
- VPCMP $0, %YMMZERO, %YMM4, %k1
- VPCMP $0, %YMMZERO, %YMM5, %k2
- kord %k1, %k2, %k1
- /* Each bit in K6 represents a NULL or a mismatch in YMM4 and
- YMM5. */
- kord %k0, %k1, %k6
-
- VPCMP $4, %YMM6, %YMM7, %k0
- VPCMP $0, %YMMZERO, %YMM6, %k1
- VPCMP $0, %YMMZERO, %YMM7, %k2
- kord %k1, %k2, %k1
- /* Each bit in K7 represents a NULL or a mismatch in YMM6 and
- YMM7. */
- kord %k0, %k1, %k7
-
- kord %k4, %k5, %k0
- kord %k6, %k7, %k1
-
- /* Test each mask (32 bits) individually because for VEC_SIZE
- == 32 is not possible to OR the four masks and keep all bits
- in a 64-bit integer register, differing from SSE2 strcmp
- where ORing is possible. */
- kortestd %k0, %k1
- je L(loop)
- ktestd %k4, %k4
+
+ VPMINU %YMM0, %YMM2, %YMM8
+ VPMINU %YMM4, %YMM6, %YMM9
+
+ /* A zero CHAR in YMM8 means that there is a null CHAR. */
+ VPMINU %YMM8, %YMM9, %YMM8
+
+ /* Each bit set in K1 represents a non-null CHAR in YMM8. */
+ VPTESTM %YMM8, %YMM8, %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
+
+ vporq %YMM1, %YMM3, %YMM9
+ vporq %YMM5, %YMM7, %YMM10
+
+ /* 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)
+
+ /* Each bit set in K1 represents a non-null CHAR in YMM0. */
+ 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)
- kmovd %k4, %edi
- tzcntl %edi, %ecx
+ tzcntl %ecx, %ecx
# ifdef USE_AS_WCSCMP
/* NB: Multiply wchar_t count by 4 to get the number of bytes. */
sall $2, %ecx
@@ -466,9 +458,18 @@ L(test_vec):
cmpq $VEC_SIZE, %r11
jbe L(zero)
# endif
- ktestd %k5, %k5
+ /* 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)
- kmovd %k5, %ecx
tzcntl %ecx, %edi
# ifdef USE_AS_WCSCMP
/* NB: Multiply wchar_t count by 4 to get the number of bytes. */
@@ -512,9 +513,18 @@ L(test_2_vec):
cmpq $(VEC_SIZE * 2), %r11
jbe L(zero)
# endif
- ktestd %k6, %k6
+ /* 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
+# else
+ incl %ecx
+# endif
je L(test_3_vec)
- kmovd %k6, %ecx
tzcntl %ecx, %edi
# ifdef USE_AS_WCSCMP
/* NB: Multiply wchar_t count by 4 to get the number of bytes. */
@@ -558,8 +568,18 @@ L(test_3_vec):
cmpq $(VEC_SIZE * 3), %r11
jbe L(zero)
# endif
- kmovd %k7, %esi
- tzcntl %esi, %ecx
+ /* 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
+# else
+ incl %ecx
+# endif
+ tzcntl %ecx, %ecx
# ifdef USE_AS_WCSCMP
/* NB: Multiply wchar_t count by 4 to get the number of bytes. */
sall $2, %ecx
@@ -615,39 +635,51 @@ L(loop_cross_page):
VMOVU (%rax, %r10), %YMM2
VMOVU VEC_SIZE(%rax, %r10), %YMM3
- VMOVU (%rdx, %r10), %YMM4
- VMOVU VEC_SIZE(%rdx, %r10), %YMM5
-
- VPCMP $4, %YMM4, %YMM2, %k0
- VPCMP $0, %YMMZERO, %YMM2, %k1
- VPCMP $0, %YMMZERO, %YMM4, %k2
- kord %k1, %k2, %k1
- /* Each bit in K1 represents a NULL or a mismatch in YMM2 and
- YMM4. */
- kord %k0, %k1, %k1
-
- VPCMP $4, %YMM5, %YMM3, %k3
- VPCMP $0, %YMMZERO, %YMM3, %k4
- VPCMP $0, %YMMZERO, %YMM5, %k5
- kord %k4, %k5, %k4
- /* Each bit in K3 represents a NULL or a mismatch in YMM3 and
- YMM5. */
- kord %k3, %k4, %k3
+
+ /* 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
+
+ /* 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
+# ifdef USE_AS_WCSCMP
+ /* Don't use subl since it is the upper 8 bits of EDI below. */
+ notl %edi
+ andl $0xff, %edi
+# else
+ incl %edi
+# endif
# ifdef USE_AS_WCSCMP
- /* NB: Each bit in K1/K3 represents 4-byte element. */
- kshiftlw $8, %k3, %k2
+ /* 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
- kshiftlq $32, %k3, %k2
-# endif
+ salq $32, %rdi
- /* Each bit in K1 represents a NULL or a mismatch. */
- korq %k1, %k2, %k1
- kmovq %k1, %rdi
+ /* Each bit in RDI represents a null CHAR or a mismatch. */
+ orq %r9, %rdi
+# endif
/* Since ECX < VEC_SIZE * 2, simply skip the first ECX bytes. */
shrxq %SHIFT_REG64, %rdi, %rdi
@@ -692,35 +724,45 @@ 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
- VMOVU (VEC_SIZE * 2)(%rdx, %r10), %YMM2
- VMOVU (VEC_SIZE * 3)(%rdx, %r10), %YMM3
-
- VPCMP $4, %YMM0, %YMM2, %k0
- VPCMP $0, %YMMZERO, %YMM0, %k1
- VPCMP $0, %YMMZERO, %YMM2, %k2
- kord %k1, %k2, %k1
- /* Each bit in K1 represents a NULL or a mismatch in YMM0 and
- YMM2. */
- kord %k0, %k1, %k1
-
- VPCMP $4, %YMM1, %YMM3, %k3
- VPCMP $0, %YMMZERO, %YMM1, %k4
- VPCMP $0, %YMMZERO, %YMM3, %k5
- kord %k4, %k5, %k4
- /* Each bit in K3 represents a NULL or a mismatch in YMM1 and
- YMM3. */
- kord %k3, %k4, %k3
+ 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
- /* NB: Each bit in K1/K3 represents 4-byte element. */
- kshiftlw $8, %k3, %k2
+ /* Only last 8 bits are valid. */
+ andl $0xff, %r9d
+# endif
+
+ 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
+# ifdef USE_AS_WCSCMP
+ /* Don't use subl since it is the upper 8 bits of EDI below. */
+ notl %edi
+ andl $0xff, %edi
# else
- kshiftlq $32, %k3, %k2
+ incl %edi
# endif
- /* Each bit in K1 represents a NULL or a mismatch. */
- korq %k1, %k2, %k1
- kmovq %k1, %rdi
+# ifdef USE_AS_WCSCMP
+ /* NB: Each bit in EDI/R9D represents 4-byte element. */
+ sall $8, %edi
+
+ /* Each bit in EDI represents a null CHAR or a mismatch. */
+ orl %r9d, %edi
+# else
+ salq $32, %rdi
+
+ /* Each bit in RDI represents a null CHAR or a mismatch. */
+ orq %r9, %rdi
+# endif
xorl %r8d, %r8d
/* If ECX > VEC_SIZE * 2, skip ECX - (VEC_SIZE * 2) bytes. */
@@ -729,12 +771,15 @@ L(loop_cross_page_2_vec):
/* R8 has number of bytes skipped. */
movl %ecx, %r8d
# ifdef USE_AS_WCSCMP
- /* NB: Divide shift count by 4 since each bit in K1 represent 4
+ /* NB: Divide shift count by 4 since each bit in RDI represent 4
bytes. */
sarl $2, %ecx
-# endif
+ /* Skip ECX bytes. */
+ shrl %cl, %edi
+# else
/* Skip ECX bytes. */
shrq %cl, %rdi
+# endif
1:
/* Before jumping back to the loop, set ESI to the number of
VEC_SIZE * 4 blocks before page crossing. */
@@ -818,7 +863,7 @@ L(cross_page_loop):
movzbl (%rdi, %rdx), %eax
movzbl (%rsi, %rdx), %ecx
# endif
- /* Check null char. */
+ /* Check null CHAR. */
testl %eax, %eax
jne L(cross_page_loop)
/* Since %eax == 0, subtract is OK for both SIGNED and UNSIGNED
@@ -901,18 +946,17 @@ L(cross_page):
jg L(cross_page_1_vector)
L(loop_1_vector):
VMOVU (%rdi, %rdx), %YMM0
- VMOVU (%rsi, %rdx), %YMM1
-
- /* Each bit in K0 represents a mismatch in YMM0 and YMM1. */
- VPCMP $4, %YMM0, %YMM1, %k0
- VPCMP $0, %YMMZERO, %YMM0, %k1
- VPCMP $0, %YMMZERO, %YMM1, %k2
- /* Each bit in K1 represents a NULL in YMM0 or YMM1. */
- kord %k1, %k2, %k1
- /* Each bit in K1 represents a NULL or a mismatch. */
- kord %k0, %k1, %k1
+
+ 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}
kmovd %k1, %ecx
- testl %ecx, %ecx
+# ifdef USE_AS_WCSCMP
+ subl $0xff, %ecx
+# else
+ incl %ecx
+# endif
jne L(last_vector)
addl $VEC_SIZE, %edx
@@ -931,18 +975,17 @@ L(cross_page_1_vector):
cmpl $(PAGE_SIZE - 16), %eax
jg L(cross_page_1_xmm)
VMOVU (%rdi, %rdx), %XMM0
- VMOVU (%rsi, %rdx), %XMM1
-
- /* Each bit in K0 represents a mismatch in XMM0 and XMM1. */
- VPCMP $4, %XMM0, %XMM1, %k0
- VPCMP $0, %XMMZERO, %XMM0, %k1
- VPCMP $0, %XMMZERO, %XMM1, %k2
- /* Each bit in K1 represents a NULL in XMM0 or XMM1. */
- korw %k1, %k2, %k1
- /* Each bit in K1 represents a NULL or a mismatch. */
- korw %k0, %k1, %k1
- kmovw %k1, %ecx
- testl %ecx, %ecx
+
+ 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}
+ kmovd %k1, %ecx
+# ifdef USE_AS_WCSCMP
+ subl $0xf, %ecx
+# else
+ subl $0xffff, %ecx
+# endif
jne L(last_vector)
addl $16, %edx
@@ -965,25 +1008,16 @@ L(cross_page_1_xmm):
vmovq (%rdi, %rdx), %XMM0
vmovq (%rsi, %rdx), %XMM1
- /* Each bit in K0 represents a mismatch in XMM0 and XMM1. */
- VPCMP $4, %XMM0, %XMM1, %k0
- VPCMP $0, %XMMZERO, %XMM0, %k1
- VPCMP $0, %XMMZERO, %XMM1, %k2
- /* Each bit in K1 represents a NULL in XMM0 or XMM1. */
- kord %k1, %k2, %k1
- /* Each bit in K1 represents a NULL or a mismatch. */
- kord %k0, %k1, %k1
- kmovd %k1, %ecx
-
+ 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
# ifdef USE_AS_WCSCMP
- /* Only last 2 bits are valid. */
- andl $0x3, %ecx
+ subl $0x3, %ecx
# else
- /* Only last 8 bits are valid. */
- andl $0xff, %ecx
+ subl $0xff, %ecx
# endif
-
- testl %ecx, %ecx
jne L(last_vector)
addl $8, %edx
@@ -1002,25 +1036,16 @@ L(cross_page_8bytes):
vmovd (%rdi, %rdx), %XMM0
vmovd (%rsi, %rdx), %XMM1
- /* Each bit in K0 represents a mismatch in XMM0 and XMM1. */
- VPCMP $4, %XMM0, %XMM1, %k0
- VPCMP $0, %XMMZERO, %XMM0, %k1
- VPCMP $0, %XMMZERO, %XMM1, %k2
- /* Each bit in K1 represents a NULL in XMM0 or XMM1. */
- kord %k1, %k2, %k1
- /* Each bit in K1 represents a NULL or a mismatch. */
- kord %k0, %k1, %k1
+ 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}
kmovd %k1, %ecx
-
# ifdef USE_AS_WCSCMP
- /* Only the last bit is valid. */
- andl $0x1, %ecx
+ subl $0x1, %ecx
# else
- /* Only last 4 bits are valid. */
- andl $0xf, %ecx
+ subl $0xf, %ecx
# endif
-
- testl %ecx, %ecx
jne L(last_vector)
addl $4, %edx