about summary refs log tree commit diff
path: root/sysdeps/x86_64/multiarch
diff options
context:
space:
mode:
authorH.J. Lu <hjl.tools@gmail.com>2017-04-18 14:01:45 -0700
committerH.J. Lu <hjl.tools@gmail.com>2017-04-18 14:01:45 -0700
commit4cb334c4d6249686653137ec273d081371b3672d (patch)
tree0ddce19851595aeccad1caf222c91014f7817de2 /sysdeps/x86_64/multiarch
parent1c53cb49de6d82d9469ccbd5aa0c55924502bd8b (diff)
downloadglibc-4cb334c4d6249686653137ec273d081371b3672d.tar.gz
glibc-4cb334c4d6249686653137ec273d081371b3672d.tar.xz
glibc-4cb334c4d6249686653137ec273d081371b3672d.zip
x86: Use AVX2 memcpy/memset on Skylake server [BZ #21396]
On Skylake server, AVX512 load/store instructions in memcpy/memset may
lead to lower CPU turbo frequency in certain situations.  Use of AVX2
in memcpy/memset has been observed to have improved overall performance
in many workloads due to the higher frequency.

Since AVX512ER is unique to Xeon Phi, this patch sets Prefer_No_AVX512
if AVX512ER isn't available so that AVX2 versions of memcpy/memset are
used on Skylake server.

	[BZ #21396]
	* sysdeps/x86/cpu-features.c (init_cpu_features): Set
	Prefer_No_AVX512 if AVX512ER isn't available.
	* sysdeps/x86/cpu-features.h (bit_arch_Prefer_No_AVX512): New.
	(index_arch_Prefer_No_AVX512): Likewise.
	* sysdeps/x86_64/multiarch/memcpy.S (__new_memcpy): Don't use
	AVX512 version if Prefer_No_AVX512 is set.
	* sysdeps/x86_64/multiarch/memcpy_chk.S (__memcpy_chk):
	Likewise.
	* sysdeps/x86_64/multiarch/memmove.S (__libc_memmove): Likewise.
	* sysdeps/x86_64/multiarch/memmove_chk.S (__memmove_chk):
	Likewise.
	* sysdeps/x86_64/multiarch/mempcpy.S (__mempcpy): Likewise.
	* sysdeps/x86_64/multiarch/mempcpy_chk.S (__mempcpy_chk):
	Likewise.
	* sysdeps/x86_64/multiarch/memset.S (memset): Likewise.
	* sysdeps/x86_64/multiarch/memset_chk.S (__memset_chk):
	Likewise.
Diffstat (limited to 'sysdeps/x86_64/multiarch')
-rw-r--r--sysdeps/x86_64/multiarch/memcpy.S2
-rw-r--r--sysdeps/x86_64/multiarch/memcpy_chk.S2
-rw-r--r--sysdeps/x86_64/multiarch/memmove.S2
-rw-r--r--sysdeps/x86_64/multiarch/memmove_chk.S2
-rw-r--r--sysdeps/x86_64/multiarch/mempcpy.S2
-rw-r--r--sysdeps/x86_64/multiarch/mempcpy_chk.S2
-rw-r--r--sysdeps/x86_64/multiarch/memset.S2
-rw-r--r--sysdeps/x86_64/multiarch/memset_chk.S2
8 files changed, 16 insertions, 0 deletions
diff --git a/sysdeps/x86_64/multiarch/memcpy.S b/sysdeps/x86_64/multiarch/memcpy.S
index 1f83ee3e84..af2770397c 100644
--- a/sysdeps/x86_64/multiarch/memcpy.S
+++ b/sysdeps/x86_64/multiarch/memcpy.S
@@ -32,6 +32,8 @@ ENTRY(__new_memcpy)
 	lea	__memcpy_erms(%rip), %RAX_LP
 	HAS_ARCH_FEATURE (Prefer_ERMS)
 	jnz	2f
+	HAS_ARCH_FEATURE (Prefer_No_AVX512)
+	jnz	1f
 	HAS_ARCH_FEATURE (AVX512F_Usable)
 	jz	1f
 	lea	__memcpy_avx512_no_vzeroupper(%rip), %RAX_LP
diff --git a/sysdeps/x86_64/multiarch/memcpy_chk.S b/sysdeps/x86_64/multiarch/memcpy_chk.S
index 54923420f1..8737fb9755 100644
--- a/sysdeps/x86_64/multiarch/memcpy_chk.S
+++ b/sysdeps/x86_64/multiarch/memcpy_chk.S
@@ -30,6 +30,8 @@
 ENTRY(__memcpy_chk)
 	.type	__memcpy_chk, @gnu_indirect_function
 	LOAD_RTLD_GLOBAL_RO_RDX
+	HAS_ARCH_FEATURE (Prefer_No_AVX512)
+	jnz	1f
 	HAS_ARCH_FEATURE (AVX512F_Usable)
 	jz	1f
 	lea	__memcpy_chk_avx512_no_vzeroupper(%rip), %RAX_LP
diff --git a/sysdeps/x86_64/multiarch/memmove.S b/sysdeps/x86_64/multiarch/memmove.S
index 2021bfc30c..8c534e83e0 100644
--- a/sysdeps/x86_64/multiarch/memmove.S
+++ b/sysdeps/x86_64/multiarch/memmove.S
@@ -30,6 +30,8 @@ ENTRY(__libc_memmove)
 	lea	__memmove_erms(%rip), %RAX_LP
 	HAS_ARCH_FEATURE (Prefer_ERMS)
 	jnz	2f
+	HAS_ARCH_FEATURE (Prefer_No_AVX512)
+	jnz	1f
 	HAS_ARCH_FEATURE (AVX512F_Usable)
 	jz	1f
 	lea	__memmove_avx512_no_vzeroupper(%rip), %RAX_LP
diff --git a/sysdeps/x86_64/multiarch/memmove_chk.S b/sysdeps/x86_64/multiarch/memmove_chk.S
index 8a252adcae..7870dd0247 100644
--- a/sysdeps/x86_64/multiarch/memmove_chk.S
+++ b/sysdeps/x86_64/multiarch/memmove_chk.S
@@ -29,6 +29,8 @@
 ENTRY(__memmove_chk)
 	.type	__memmove_chk, @gnu_indirect_function
 	LOAD_RTLD_GLOBAL_RO_RDX
+	HAS_ARCH_FEATURE (Prefer_No_AVX512)
+	jnz	1f
 	HAS_ARCH_FEATURE (AVX512F_Usable)
 	jz	1f
 	lea	__memmove_chk_avx512_no_vzeroupper(%rip), %RAX_LP
diff --git a/sysdeps/x86_64/multiarch/mempcpy.S b/sysdeps/x86_64/multiarch/mempcpy.S
index 79c840d075..b8b2b28094 100644
--- a/sysdeps/x86_64/multiarch/mempcpy.S
+++ b/sysdeps/x86_64/multiarch/mempcpy.S
@@ -32,6 +32,8 @@ ENTRY(__mempcpy)
 	lea	__mempcpy_erms(%rip), %RAX_LP
 	HAS_ARCH_FEATURE (Prefer_ERMS)
 	jnz	2f
+	HAS_ARCH_FEATURE (Prefer_No_AVX512)
+	jnz	1f
 	HAS_ARCH_FEATURE (AVX512F_Usable)
 	jz	1f
 	lea	__mempcpy_avx512_no_vzeroupper(%rip), %RAX_LP
diff --git a/sysdeps/x86_64/multiarch/mempcpy_chk.S b/sysdeps/x86_64/multiarch/mempcpy_chk.S
index 6927962e81..072b22c49f 100644
--- a/sysdeps/x86_64/multiarch/mempcpy_chk.S
+++ b/sysdeps/x86_64/multiarch/mempcpy_chk.S
@@ -30,6 +30,8 @@
 ENTRY(__mempcpy_chk)
 	.type	__mempcpy_chk, @gnu_indirect_function
 	LOAD_RTLD_GLOBAL_RO_RDX
+	HAS_ARCH_FEATURE (Prefer_No_AVX512)
+	jnz	1f
 	HAS_ARCH_FEATURE (AVX512F_Usable)
 	jz	1f
 	lea	__mempcpy_chk_avx512_no_vzeroupper(%rip), %RAX_LP
diff --git a/sysdeps/x86_64/multiarch/memset.S b/sysdeps/x86_64/multiarch/memset.S
index c958b2f49f..9d33118cf8 100644
--- a/sysdeps/x86_64/multiarch/memset.S
+++ b/sysdeps/x86_64/multiarch/memset.S
@@ -41,6 +41,8 @@ ENTRY(memset)
 	jnz	L(AVX512F)
 	lea	__memset_avx2_unaligned(%rip), %RAX_LP
 L(AVX512F):
+	HAS_ARCH_FEATURE (Prefer_No_AVX512)
+	jnz	2f
 	HAS_ARCH_FEATURE (AVX512F_Usable)
 	jz	2f
 	lea	__memset_avx512_no_vzeroupper(%rip), %RAX_LP
diff --git a/sysdeps/x86_64/multiarch/memset_chk.S b/sysdeps/x86_64/multiarch/memset_chk.S
index 79eaa37bb6..7e08311cdf 100644
--- a/sysdeps/x86_64/multiarch/memset_chk.S
+++ b/sysdeps/x86_64/multiarch/memset_chk.S
@@ -38,6 +38,8 @@ ENTRY(__memset_chk)
 	jnz	L(AVX512F)
 	lea	__memset_chk_avx2_unaligned(%rip), %RAX_LP
 L(AVX512F):
+	HAS_ARCH_FEATURE (Prefer_No_AVX512)
+	jnz	2f
 	HAS_ARCH_FEATURE (AVX512F_Usable)
 	jz	2f
 	lea	__memset_chk_avx512_no_vzeroupper(%rip), %RAX_LP