about summary refs log tree commit diff
path: root/sysdeps/x86_64
diff options
context:
space:
mode:
authorSihai Yao <sihai.ysh@alibaba-inc.com>2014-04-17 08:00:21 -0700
committerH.J. Lu <hjl.tools@gmail.com>2014-04-17 08:00:21 -0700
commitf9281df9955fdd11799041ebebd7dc6e4870449a (patch)
treebfd7b1a7e35688d8d0bd6ef90dc84dbe3fb641aa /sysdeps/x86_64
parent7c6776620db8e48fca492dbcac88d1c0f239dcde (diff)
downloadglibc-f9281df9955fdd11799041ebebd7dc6e4870449a.tar.gz
glibc-f9281df9955fdd11799041ebebd7dc6e4870449a.tar.xz
glibc-f9281df9955fdd11799041ebebd7dc6e4870449a.zip
Detect if AVX2 is usable
This patch checks and sets bit_AVX2_Usable in __cpu_features.feature.

	* sysdeps/x86_64/multiarch/ifunc-defines.sym (COMMON_CPUID_INDEX_7):
	New.
	* sysdeps/x86_64/multiarch/init-arch.c (__init_cpu_features):
	Check and set bit_AVX2_Usable.
	* sysdeps/x86_64/multiarch/init-arch.h (bit_AVX2_Usable): New
	macro.
	(bit_AVX2): Likewise.
	(index_AVX2_Usable): Likewise.
	(CPUID_AVX2): Likewise.
	(HAS_AVX2): Likewise.
Diffstat (limited to 'sysdeps/x86_64')
-rw-r--r--sysdeps/x86_64/multiarch/ifunc-defines.sym1
-rw-r--r--sysdeps/x86_64/multiarch/init-arch.c3
-rw-r--r--sysdeps/x86_64/multiarch/init-arch.h8
3 files changed, 12 insertions, 0 deletions
diff --git a/sysdeps/x86_64/multiarch/ifunc-defines.sym b/sysdeps/x86_64/multiarch/ifunc-defines.sym
index eb1538abcc..a410d8808f 100644
--- a/sysdeps/x86_64/multiarch/ifunc-defines.sym
+++ b/sysdeps/x86_64/multiarch/ifunc-defines.sym
@@ -17,4 +17,5 @@ FEATURE_OFFSET		offsetof (struct cpu_features, feature)
 FEATURE_SIZE		sizeof (unsigned int)
 
 COMMON_CPUID_INDEX_1
+COMMON_CPUID_INDEX_7
 FEATURE_INDEX_1
diff --git a/sysdeps/x86_64/multiarch/init-arch.c b/sysdeps/x86_64/multiarch/init-arch.c
index db74d977f2..2a6dcb78d8 100644
--- a/sysdeps/x86_64/multiarch/init-arch.c
+++ b/sysdeps/x86_64/multiarch/init-arch.c
@@ -167,6 +167,9 @@ __init_cpu_features (void)
 	  /* Determine if AVX is usable.  */
 	  if (CPUID_AVX)
 	    __cpu_features.feature[index_AVX_Usable] |= bit_AVX_Usable;
+	  /* Determine if AVX2 is usable.  */
+	  if (CPUID_AVX2)
+	    __cpu_features.feature[index_AVX2_Usable] |= bit_AVX2_Usable;
 	  /* Determine if FMA is usable.  */
 	  if (CPUID_FMA)
 	    __cpu_features.feature[index_FMA_Usable] |= bit_FMA_Usable;
diff --git a/sysdeps/x86_64/multiarch/init-arch.h b/sysdeps/x86_64/multiarch/init-arch.h
index 793707a4da..813b6de3be 100644
--- a/sysdeps/x86_64/multiarch/init-arch.h
+++ b/sysdeps/x86_64/multiarch/init-arch.h
@@ -24,6 +24,7 @@
 #define bit_FMA_Usable			(1 << 7)
 #define bit_FMA4_Usable			(1 << 8)
 #define bit_Slow_SSE4_2			(1 << 9)
+#define bit_AVX2_Usable			(1 << 10)
 
 /* CPUID Feature flags.  */
 
@@ -40,6 +41,7 @@
 
 /* COMMON_CPUID_INDEX_7.  */
 #define bit_RTM		(1 << 11)
+#define bit_AVX2	(1 << 5)
 
 /* XCR0 Feature flags.  */
 #define bit_XMM_state  (1 << 1)
@@ -54,6 +56,7 @@
 # define index_SSE4_1	COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET
 # define index_SSE4_2	COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET
 # define index_AVX	COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET
+# define index_AVX2	COMMON_CPUID_INDEX_7*CPUID_SIZE+CPUID_EBX_OFFSET
 
 # define index_Fast_Rep_String		FEATURE_INDEX_1*FEATURE_SIZE
 # define index_Fast_Copy_Backward	FEATURE_INDEX_1*FEATURE_SIZE
@@ -64,6 +67,7 @@
 # define index_FMA_Usable		FEATURE_INDEX_1*FEATURE_SIZE
 # define index_FMA4_Usable		FEATURE_INDEX_1*FEATURE_SIZE
 # define index_Slow_SSE4_2		FEATURE_INDEX_1*FEATURE_SIZE
+# define index_AVX2_Usable		FEATURE_INDEX_1*FEATURE_SIZE
 
 #else	/* __ASSEMBLER__ */
 
@@ -145,6 +149,8 @@ extern const struct cpu_features *__get_cpu_features (void)
   HAS_CPUID_FLAG (COMMON_CPUID_INDEX_80000001, ecx, bit_FMA4)
 # define CPUID_RTM \
   HAS_CPUID_FLAG (COMMON_CPUID_INDEX_7, ebx, bit_RTM)
+# define CPUID_AVX2 \
+  HAS_CPUID_FLAG (COMMON_CPUID_INDEX_7, ebx, bit_AVX2)
 
 /* HAS_* evaluates to true if we may use the feature at runtime.  */
 # define HAS_SSE2	HAS_CPU_FEATURE (COMMON_CPUID_INDEX_1, edx, bit_SSE2)
@@ -153,6 +159,7 @@ extern const struct cpu_features *__get_cpu_features (void)
 # define HAS_SSE4_1	HAS_CPU_FEATURE (COMMON_CPUID_INDEX_1, ecx, bit_SSE4_1)
 # define HAS_SSE4_2	HAS_CPU_FEATURE (COMMON_CPUID_INDEX_1, ecx, bit_SSE4_2)
 # define HAS_RTM	HAS_CPU_FEATURE (COMMON_CPUID_INDEX_7, ebx, bit_RTM)
+# define HAS_AVX2	HAS_CPU_FEATURE (COMMON_CPUID_INDEX_7, ebx, bit_AVX2)
 
 # define index_Fast_Rep_String		FEATURE_INDEX_1
 # define index_Fast_Copy_Backward	FEATURE_INDEX_1
@@ -163,6 +170,7 @@ extern const struct cpu_features *__get_cpu_features (void)
 # define index_FMA_Usable		FEATURE_INDEX_1
 # define index_FMA4_Usable		FEATURE_INDEX_1
 # define index_Slow_SSE4_2		FEATURE_INDEX_1
+# define index_AVX2_Usable		FEATURE_INDEX_1
 
 # define HAS_ARCH_FEATURE(name) \
   ((__get_cpu_features ()->feature[index_##name] & (bit_##name)) != 0)