mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Andi Kleen" <andi@firstfloor.org>
To: "Fenghua Yu" <fenghua.yu@intel.com>
Cc: "Ingo Molnar" <mingo@elte.hu>,
	"Thomas Gleixner" <tglx@linutronix.de>,
	"H Peter Anvin" <hpa@zytor.com>,
	"Asit K Mallick" <asit.k.mallick@intel.com>,
	"Linus Torvalds" <torvalds@linux-foundation.org>,
	"Avi Kivity" <avi@redhat.com>,
	"Arjan van de Ven" <arjan@infradead.org>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"Andi Kleen" <andi@firstfloor.org>,
	"linux-kernel" <linux-kernel@vger.kernel.org>,
	"Fenghua Yu" <fenghua.yu@intel.com>
Subject: Re: [PATCH 9/9] x86/lib/memset_64.S: Optimize memset by enhanced REP MOVSB/STOSB
Date: Wed, 18 May 2011 04:57:45 +0200	[thread overview]
Message-ID: <08d8c27c0495452cad52b62b362dd1d1.squirrel@www.firstfloor.org> (raw)
In-Reply-To: <1305671358-14478-10-git-send-email-fenghua.yu@intel.com>

> From: Fenghua Yu <fenghua.yu@intel.com>
>
> Support memset() with enhanced rep stosb. On processors supporting
> enhanced
> REP MOVSB/STOSB, the alternative memset_c_e function using enhanced rep
> stosb
> overrides the fast string alternative memset_c and the original function.

FWIW most memsets and memcpys are generated by modern gccs as inline code,
depending on alignment etc., so will never call your new function.
Same may be true for memmove (not fully sure)

One way to work around this would be to add suitable logic
to the string.h macros and make sure the out of line code is always
called for large copies if the count is constant and large enough.

There used to be such logic, but it was removed partly later.

The only problem is that it's hard to decide if the count is variable
and where a good threshold is.

Or maybe it would be better to just fix gcc to use the new instructions,
but then it would be difficult to patch them in.

-Andi



  reply	other threads:[~2011-05-18  2:57 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-05-17 22:29 [PATCH 0/9] Optimize string operations " Fenghua Yu
2011-05-17 22:29 ` [PATCH 1/9] x86, cpu: Enable enhanced REP MOVSB/STOSB feature Fenghua Yu
2011-05-17 23:13   ` [tip:x86/cpufeature] x86, cpufeature: Add CPU feature bit for enhanced REP MOVSB/STOSB tip-bot for Fenghua Yu
2011-05-17 22:29 ` [PATCH 2/9] x86/kernel/cpu/intel.c: Initialize Enhanced REP MOVSB/STOSBenhanced Fenghua Yu
2011-05-18  2:46   ` Andi Kleen
2011-05-18  3:47     ` H. Peter Anvin
2011-05-18 20:40   ` [tip:perf/core] x86, mem, intel: Initialize Enhanced REP MOVSB/STOSB tip-bot for Fenghua Yu
2011-05-17 22:29 ` [PATCH 3/9] x86/kernel/alternative.c: Add comment for applying alternatives order Fenghua Yu
2011-05-18 20:40   ` [tip:perf/core] x86, alternative, doc: " tip-bot for Fenghua Yu
2011-05-17 22:29 ` [PATCH 4/9] x86, alternative-asm.h: Add altinstruction_entry macro Fenghua Yu
2011-05-18 20:41   ` [tip:perf/core] x86, alternative: " tip-bot for Fenghua Yu
2011-05-17 22:29 ` [PATCH 5/9] x86/lib/clear_page_64.S: Support clear_page() with enhanced REP MOVSB/STOSB Fenghua Yu
2011-05-18 20:41   ` [tip:perf/core] x86, mem: clear_page_64.S: " tip-bot for Fenghua Yu
2011-05-17 22:29 ` [PATCH 6/9] x86/lib/copy_user_64.S: Support copy_to_user/copy_from_user by " Fenghua Yu
2011-05-18 20:42   ` [tip:perf/core] x86, mem: copy_user_64.S: Support copy_to/from_user " tip-bot for Fenghua Yu
2011-05-17 22:29 ` [PATCH 7/9] x86/lib/memcpy_64.S: Optimize memcpy " Fenghua Yu
2011-05-18  6:35   ` Ingo Molnar
2011-05-18 19:04     ` Yu, Fenghua
2011-05-18 20:42   ` [tip:perf/core] x86, mem: memcpy_64.S: " tip-bot for Fenghua Yu
2011-05-17 22:29 ` [PATCH 8/9] x86/lib/memmove_64.S: Optimize memmove " Fenghua Yu
2011-05-18 20:43   ` [tip:perf/core] x86, mem: memmove_64.S: " tip-bot for Fenghua Yu
2011-05-17 22:29 ` [PATCH 9/9] x86/lib/memset_64.S: Optimize memset " Fenghua Yu
2011-05-18  2:57   ` Andi Kleen [this message]
2011-05-18  3:09     ` Yu, Fenghua
2011-05-18  4:05       ` Andi Kleen
2011-05-18 18:33         ` Yu, Fenghua
2011-05-18 18:39           ` Andi Kleen
2011-05-18 18:47             ` Ingo Molnar
2011-05-18 18:49             ` Yu, Fenghua
2011-05-18 20:43   ` [tip:perf/core] x86, mem: memset_64.S: " tip-bot for Fenghua Yu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=08d8c27c0495452cad52b62b362dd1d1.squirrel@www.firstfloor.org \
    --to=andi@firstfloor.org \
    --cc=akpm@linux-foundation.org \
    --cc=arjan@infradead.org \
    --cc=asit.k.mallick@intel.com \
    --cc=avi@redhat.com \
    --cc=fenghua.yu@intel.com \
    --cc=hpa@zytor.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®