[x86] Add a feature bit: Fast_Unaligned_Copy

On AMD processors, memcpy optimized with unaligned SSE load is
slower than emcpy optimized with aligned SSSE3 while other string
functions are faster with unaligned SSE load.  A feature bit,
Fast_Unaligned_Copy, is added to select memcpy optimized with
unaligned SSE load.

	[BZ #19583]
	* sysdeps/x86/cpu-features.c (init_cpu_features): Set
	Fast_Unaligned_Copy with Fast_Unaligned_Load for Intel
	processors.  Set Fast_Copy_Backward for AMD Excavator
	processors.
	* sysdeps/x86/cpu-features.h (bit_arch_Fast_Unaligned_Copy):
	New.
	(index_arch_Fast_Unaligned_Copy): Likewise.
	* sysdeps/x86_64/multiarch/memcpy.S (__new_memcpy): Check
	Fast_Unaligned_Copy instead of Fast_Unaligned_Load.

ChangeLog

@@ -1,3 +1,17 @@
+2016-03-28   H.J. Lu  <hongjiu.lu@intel.com>
+	     Amit Pawar  <Amit.Pawar@amd.com>
+
+	[BZ #19583]
+	* sysdeps/x86/cpu-features.c (init_cpu_features): Set
+	Fast_Unaligned_Copy with Fast_Unaligned_Load for Intel
+	processors.  Set Fast_Copy_Backward for AMD Excavator
+	processors.
+	* sysdeps/x86/cpu-features.h (bit_arch_Fast_Unaligned_Copy):
+	New.
+	(index_arch_Fast_Unaligned_Copy): Likewise.
+	* sysdeps/x86_64/multiarch/memcpy.S (__new_memcpy): Check
+	Fast_Unaligned_Copy instead of Fast_Unaligned_Load.
+
 2016-03-25  Florian Weimer  <fweimer@redhat.com>
 
 	[BZ #19791]

sysdeps/x86/cpu-features.c

@@ -152,9 +152,13 @@ init_cpu_features (struct cpu_features *cpu_features)
 #endif
 #if index_arch_Fast_Unaligned_Load != index_arch_Slow_SSE4_2
 # error index_arch_Fast_Unaligned_Load != index_arch_Slow_SSE4_2
+#endif
+#if index_arch_Fast_Unaligned_Load != index_arch_Fast_Unaligned_Copy
+# error index_arch_Fast_Unaligned_Load != index_arch_Fast_Unaligned_Copy
 #endif
 	      cpu_features->feature[index_arch_Fast_Unaligned_Load]
 		|= (bit_arch_Fast_Unaligned_Load
+		    | bit_arch_Fast_Unaligned_Copy
 		    | bit_arch_Prefer_PMINUB_for_stringop
 		    | bit_arch_Slow_SSE4_2);
 	      break;
@@ -182,11 +186,15 @@ init_cpu_features (struct cpu_features *cpu_features)
 #endif
 #if index_arch_Fast_Rep_String != index_arch_Prefer_PMINUB_for_stringop
 # error index_arch_Fast_Rep_String != index_arch_Prefer_PMINUB_for_stringop
+#endif
+#if index_arch_Fast_Rep_String != index_arch_Fast_Unaligned_Copy
+# error index_arch_Fast_Rep_String != index_arch_Fast_Unaligned_Copy
 #endif
 	      cpu_features->feature[index_arch_Fast_Rep_String]
 		|= (bit_arch_Fast_Rep_String
 		    | bit_arch_Fast_Copy_Backward
 		    | bit_arch_Fast_Unaligned_Load
+		    | bit_arch_Fast_Unaligned_Copy
 		    | bit_arch_Prefer_PMINUB_for_stringop);
 	      break;
 	    }
@@ -220,10 +228,14 @@ init_cpu_features (struct cpu_features *cpu_features)
 
       if (family == 0x15)
 	{
+#if index_arch_Fast_Unaligned_Load != index_arch_Fast_Copy_Backward
+# error index_arch_Fast_Unaligned_Load != index_arch_Fast_Copy_Backward
+#endif
 	  /* "Excavator"   */
 	  if (model >= 0x60 && model <= 0x7f)
 	    cpu_features->feature[index_arch_Fast_Unaligned_Load]
-	      |= bit_arch_Fast_Unaligned_Load;
+	      |= (bit_arch_Fast_Unaligned_Load
+		  | bit_arch_Fast_Copy_Backward);
 	}
     }
   else

sysdeps/x86/cpu-features.h

@@ -35,6 +35,7 @@
 #define bit_arch_I686				(1 << 15)
 #define bit_arch_Prefer_MAP_32BIT_EXEC		(1 << 16)
 #define bit_arch_Prefer_No_VZEROUPPER		(1 << 17)
+#define bit_arch_Fast_Unaligned_Copy		(1 << 18)
 
 /* CPUID Feature flags.  */
 
@@ -101,6 +102,7 @@
 # define index_arch_I686		FEATURE_INDEX_1*FEATURE_SIZE
 # define index_arch_Prefer_MAP_32BIT_EXEC FEATURE_INDEX_1*FEATURE_SIZE
 # define index_arch_Prefer_No_VZEROUPPER FEATURE_INDEX_1*FEATURE_SIZE
+# define index_arch_Fast_Unaligned_Copy	FEATURE_INDEX_1*FEATURE_SIZE
 
 
 # if defined (_LIBC) && !IS_IN (nonlib)
@@ -265,6 +267,7 @@ extern const struct cpu_features *__get_cpu_features (void)
 # define index_arch_I686		FEATURE_INDEX_1
 # define index_arch_Prefer_MAP_32BIT_EXEC FEATURE_INDEX_1
 # define index_arch_Prefer_No_VZEROUPPER FEATURE_INDEX_1
+# define index_arch_Fast_Unaligned_Copy	FEATURE_INDEX_1
 
 #endif	/* !__ASSEMBLER__ */
 

sysdeps/x86_64/multiarch/memcpy.S

@@ -42,7 +42,7 @@ ENTRY(__new_memcpy)
 	HAS_ARCH_FEATURE (AVX_Fast_Unaligned_Load)
 	jnz	2f
 	lea	__memcpy_sse2_unaligned(%rip), %RAX_LP
-	HAS_ARCH_FEATURE (Fast_Unaligned_Load)
+	HAS_ARCH_FEATURE (Fast_Unaligned_Copy)
 	jnz	2f
 	lea	__memcpy_sse2(%rip), %RAX_LP
 	HAS_CPU_FEATURE (SSSE3)