* [PATCH] Initial Enhanced REP MOVSB/STOSB (ERMS) support
@ 2016-03-28 20:48 H.J. Lu
2016-03-28 21:57 ` Roland McGrath
0 siblings, 1 reply; 3+ messages in thread
From: H.J. Lu @ 2016-03-28 20:48 UTC (permalink / raw)
To: GNU C Library
The newer Intel processors support Enhanced REP MOVSB/STOSB (ERMS) which
has a feature bit in CPUID. This patch adds the Enhanced REP MOVSB/STOSB
(ERMS) bit to x86 cpu-features.
I will use this in followup patches to optimize memcpy/memset with ERMS.
Any comments?
H.J.
* sysdeps/x86/cpu-features.h (bit_cpu_ERMS): New.
(index_cpu_ERMS): Likewise.
(reg_ERMS): Likewise.
---
sysdeps/x86/cpu-features.h | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/sysdeps/x86/cpu-features.h b/sysdeps/x86/cpu-features.h
index bfe1f4c..8f946c4 100644
--- a/sysdeps/x86/cpu-features.h
+++ b/sysdeps/x86/cpu-features.h
@@ -53,6 +53,7 @@
#define bit_cpu_FMA4 (1 << 16)
/* COMMON_CPUID_INDEX_7. */
+#define bit_cpu_ERMS (1 << 9)
#define bit_cpu_RTM (1 << 11)
#define bit_cpu_AVX2 (1 << 5)
#define bit_cpu_AVX512F (1 << 16)
@@ -84,6 +85,7 @@
# define index_cpu_SSE4_2 COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET
# define index_cpu_AVX COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET
# define index_cpu_AVX2 COMMON_CPUID_INDEX_7*CPUID_SIZE+CPUID_EBX_OFFSET
+# define index_cpu_ERMS COMMON_CPUID_INDEX_7*CPUID_SIZE+CPUID_EBX_OFFSET
# define index_arch_Fast_Rep_String FEATURE_INDEX_1*FEATURE_SIZE
# define index_arch_Fast_Copy_Backward FEATURE_INDEX_1*FEATURE_SIZE
@@ -228,6 +230,7 @@ extern const struct cpu_features *__get_cpu_features (void)
# define index_cpu_AVX2 COMMON_CPUID_INDEX_7
# define index_cpu_AVX512F COMMON_CPUID_INDEX_7
# define index_cpu_AVX512DQ COMMON_CPUID_INDEX_7
+# define index_cpu_ERMS COMMON_CPUID_INDEX_7
# define index_cpu_RTM COMMON_CPUID_INDEX_7
# define index_cpu_FMA COMMON_CPUID_INDEX_1
# define index_cpu_FMA4 COMMON_CPUID_INDEX_80000001
@@ -244,6 +247,7 @@ extern const struct cpu_features *__get_cpu_features (void)
# define reg_AVX2 ebx
# define reg_AVX512F ebx
# define reg_AVX512DQ ebx
+# define reg_ERMS ebx
# define reg_RTM ebx
# define reg_FMA ecx
# define reg_FMA4 ecx
--
2.5.5
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH] Initial Enhanced REP MOVSB/STOSB (ERMS) support
2016-03-28 20:48 [PATCH] Initial Enhanced REP MOVSB/STOSB (ERMS) support H.J. Lu
@ 2016-03-28 21:57 ` Roland McGrath
2016-03-29 2:27 ` H.J. Lu
0 siblings, 1 reply; 3+ messages in thread
From: Roland McGrath @ 2016-03-28 21:57 UTC (permalink / raw)
To: H.J. Lu; +Cc: GNU C Library
Looks fine.
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH] Initial Enhanced REP MOVSB/STOSB (ERMS) support
2016-03-28 21:57 ` Roland McGrath
@ 2016-03-29 2:27 ` H.J. Lu
0 siblings, 0 replies; 3+ messages in thread
From: H.J. Lu @ 2016-03-29 2:27 UTC (permalink / raw)
To: Roland McGrath; +Cc: GNU C Library
On Mon, Mar 28, 2016 at 2:57 PM, Roland McGrath <roland@hack.frob.com> wrote:
> Looks fine.
Checked in.
--
H.J.
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2016-03-29 2:27 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2016-03-28 20:48 [PATCH] Initial Enhanced REP MOVSB/STOSB (ERMS) support H.J. Lu
2016-03-28 21:57 ` Roland McGrath
2016-03-29 2:27 ` H.J. Lu
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).