aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorAmit Pawar <Amit.Pawar@amd.com>2016-01-14 20:06:02 +0530
committerH.J. Lu <hjl.tools@gmail.com>2016-01-14 08:14:31 -0800
commitd7890e6947114785755ae5b1cf5310491092ee0b (patch)
treed69fa16cd7eec8008f4224a8006128555916262c
parenta4b5177ca83ca97c562a7138923dafe0cb92d1a0 (diff)
downloadtermbaud-d7890e6947114785755ae5b1cf5310491092ee0b.tar.gz
termbaud-d7890e6947114785755ae5b1cf5310491092ee0b.tar.xz
termbaud-d7890e6947114785755ae5b1cf5310491092ee0b.zip
Set index_Fast_Unaligned_Load for Excavator family CPUs
GLIBC benchtest testcases shows SSE2_Unaligned based implementations are performing faster compare to SSE2 based implementations for routines: strcmp, strcat, strncat, stpcpy, stpncpy, strcpy, strncpy and strstr. Flag index_Fast_Unaligned_Load is set for Excavator family 0x15h CPU's. This makes SSE2_Unaligned based implementations as default for these routines. [BZ #19467] * sysdeps/x86/cpu-features.c (init_cpu_features): Set index_Fast_Unaligned_Load flag for Excavator family CPUs.
-rw-r--r--ChangeLog6
-rw-r--r--sysdeps/x86/cpu-features.c8
2 files changed, 14 insertions, 0 deletions
diff --git a/ChangeLog b/ChangeLog
index 424f7312c51..054998fd428 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,9 @@
+2016-01-14 Amit Pawar <amit.pawar@amd.com>
+
+ [BZ #19467]
+ * sysdeps/x86/cpu-features.c (init_cpu_features): Set
+ index_Fast_Unaligned_Load flag for Excavator family CPUs.
+
2016-01-02 Marcin KoĊ›cielnicki <koriakin@0x04.net>
* sysdeps/s390/nptl/tls.h (struct tcbhead_t): Add __private_ss field.
diff --git a/sysdeps/x86/cpu-features.c b/sysdeps/x86/cpu-features.c
index e6bd4c909f5..218ff2bd86b 100644
--- a/sysdeps/x86/cpu-features.c
+++ b/sysdeps/x86/cpu-features.c
@@ -154,6 +154,14 @@ init_cpu_features (struct cpu_features *cpu_features)
cpu_features->cpuid[COMMON_CPUID_INDEX_80000001].ebx,
cpu_features->cpuid[COMMON_CPUID_INDEX_80000001].ecx,
cpu_features->cpuid[COMMON_CPUID_INDEX_80000001].edx);
+
+ if (family == 0x15)
+ {
+ /* "Excavator" */
+ if (model >= 0x60 && model <= 0x7f)
+ cpu_features->feature[index_Fast_Unaligned_Load]
+ |= bit_Fast_Unaligned_Load;
+ }
}
else
kind = arch_kind_other;