public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Denis Vlasenko <vda.linux@googlemail.com>
To: Oleg Verych <olecom@flower.upol.cz>
Cc: Andi Kleen <ak@suse.de>,
	jh@suse.cz, patches@x86-64.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] [9/58] x86_64: Always use builtin memcpy on gcc 4.3
Date: Sun, 22 Jul 2007 01:29:50 +0100	[thread overview]
Message-ID: <200707220129.50223.vda.linux@googlemail.com> (raw)
In-Reply-To: <E1ICOBm-0003zf-Ms@flower>

On Sunday 22 July 2007 00:16, Oleg Verych wrote:
> * From: Andi Kleen <ak@suse.de>
> * Date: Thu, 19 Jul 2007 11:54:53 +0200 (CEST)
> >
> > Jan asked to always use the builtin memcpy on gcc 4.3 mainline because
> > it should generate better code than the old macro. Let's try it.
> 
> Unfortunately such info is hard to find. The discuss@x86-64 list is
> empty. So, let me ask how this memcpy relates to recently submitted
> for glibc one [0]?
> 
> [0] <http://permalink.gmane.org/gmane.comp.lib.glibc.alpha/12217>

Am I stupid or the files attached to that post demonstrate than "new"
code isn't much better and sometimes worse (aligned 4096 byte memcpy
went from 558 to 648 for Core 2)?

Beware that text files in test-memcpy.tar.bz2 seem to have
simple_memcpy / builtin_memcpy / memcpy columns swapped
(-old and -new files have them in different order).
--
vda

  parent reply	other threads:[~2007-07-22  0:30 UTC|newest]

Thread overview: 119+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-07-19  9:54 [PATCH] [0/58] First batch of x86 patches for .23 Andi Kleen
2007-07-19  9:54 ` [PATCH] [1/58] x86: Always flush pages in change_page_attr Andi Kleen
2007-08-06 10:15   ` [patches] " Jan Beulich
2007-08-06 10:36     ` Andi Kleen
2007-08-06 10:49       ` Jan Beulich
2007-07-19  9:54 ` [PATCH] [2/58] x86_64: Tell gcc to only align stack to 8 bytes Andi Kleen
2007-07-19 11:50   ` Serge Belyshev
2007-07-19 12:06     ` Andi Kleen
2007-07-19 14:42   ` Chuck Ebbert
2007-07-19  9:54 ` [PATCH] [3/58] x86_64: asm/ptrace.h needs linux/compiler.h Andi Kleen
2007-07-19  9:54 ` [PATCH] [4/58] x86_64: Don't rely on a unique IO-APIC ID Andi Kleen
2007-07-19  9:54 ` [PATCH] [5/58] x86_64: Report the pending irq if available in smp_affinity Andi Kleen
2007-07-19 10:23   ` Ingo Molnar
2007-07-19  9:54 ` [PATCH] [6/58] x86_64: Use LOCAL_DISTANCE and REMOTE_DISTANCE in x86_64 ACPI code Andi Kleen
2007-07-19  9:54 ` [PATCH] [7/58] x86_64: various cleanups in NUMA scan node Andi Kleen
2007-07-19 17:15   ` Yinghai Lu
2007-07-19 17:21     ` Andi Kleen
2007-07-19 17:38       ` Yinghai Lu
2007-07-19 20:00         ` Andi Kleen
2007-07-19 21:01     ` David Rientjes
2007-07-19  9:54 ` [PATCH] [8/58] x86_64: Use string instruction memcpy/memset on AMD Fam10 Andi Kleen
2007-07-19 16:43   ` Jan Engelhardt
2007-07-19 17:00     ` Yinghai Lu
2007-07-19  9:54 ` [PATCH] [9/58] x86_64: Always use builtin memcpy on gcc 4.3 Andi Kleen
2007-07-21 23:16   ` Oleg Verych
2007-07-21 23:27     ` Andi Kleen
2007-07-22  0:29     ` Denis Vlasenko [this message]
2007-07-19  9:54 ` [PATCH] [10/58] i386: Move all simple string operations out of line Andi Kleen
2007-07-19  9:54 ` [PATCH] [11/58] x86: Support __attribute__((__cold__)) in gcc 4.3 Andi Kleen
2007-07-19  9:54 ` [PATCH] [12/58] x86_64: Add vDSO for x86-64 with gettimeofday/clock_gettime/getcpu Andi Kleen
2007-08-21 16:25   ` Daniel Walker
2007-08-21 18:45     ` Andi Kleen
2007-08-21 18:40       ` Andrew Morton
2007-07-19  9:54 ` [PATCH] [13/58] x86: Separate checking of unsynchronized and unstable TSC Andi Kleen
2007-07-19  9:54 ` [PATCH] [14/58] x86_64: Add on_cpu_single Andi Kleen
2007-07-19 11:09   ` Satyam Sharma
2007-07-19 12:07     ` Andi Kleen
2007-07-19  9:54 ` [PATCH] [15/58] i386: Rewrite sched_clock Andi Kleen
2007-07-19 16:51   ` Daniel Walker
2007-07-19 17:13     ` Andi Kleen
2007-07-19 17:15       ` Daniel Walker
2007-07-19 17:22         ` Andi Kleen
2007-07-19 17:31           ` Daniel Walker
2007-07-19 17:38             ` Andi Kleen
2007-07-19 17:43               ` Daniel Walker
2007-07-19 18:00                 ` Andi Kleen
2007-07-19 18:00                   ` Daniel Walker
2007-07-20  3:11     ` Mathieu Desnoyers
2007-07-20  3:47       ` Mathieu Desnoyers
2007-07-20  4:18         ` [PATCH] [15/58] i386: Rewrite sched_clock (cmpxchg8b) Mathieu Desnoyers
2007-07-20  5:07           ` Nick Piggin
2007-07-20  5:47             ` Mathieu Desnoyers
2007-07-20  8:27       ` [PATCH] [15/58] i386: Rewrite sched_clock Andi Kleen
2007-07-20 14:12         ` Mathieu Desnoyers
2007-07-20 14:39           ` Mathieu Desnoyers
2007-07-20 15:14           ` Andi Kleen
2007-07-20 15:22             ` Mathieu Desnoyers
2007-07-20 16:49             ` [PATCH] 80386 and 80486 cmpxchg64 and cmpxchg64_local fallback Mathieu Desnoyers
2007-07-19  9:55 ` [PATCH] [16/58] x86_64: Use new shared sched_clock in x86-64 too Andi Kleen
2007-07-19  9:55 ` [PATCH] [17/58] i386: Add L3 cache support to AMD CPUID4 emulation Andi Kleen
2007-07-20 17:00   ` [patches] " Andreas Herrmann
2007-07-20 17:15   ` Andreas Herrmann
2007-07-19  9:55 ` [PATCH] [18/58] x86_64: remove extra extern declaring about dmi_ioremap Andi Kleen
2007-07-19  9:55 ` [PATCH] [19/58] x86_64: Don't use softirq save locks in smp_call_function Andi Kleen
2007-07-19 12:16   ` Satyam Sharma
2007-07-19 12:19     ` Andi Kleen
2007-07-19  9:55 ` [PATCH] [20/58] x86: Always probe the NMI watchdog Andi Kleen
2007-07-19 10:24   ` Björn Steinbrink
2007-07-19 10:42     ` Andi Kleen
2007-07-19  9:55 ` [PATCH] [21/58] i386: Reserve the right performance counter for the Intel PerfMon " Andi Kleen
2007-07-19 10:21   ` Björn Steinbrink
2007-07-19 10:45     ` Andi Kleen
2007-07-19  9:55 ` [PATCH] [22/58] x86_64: hpet tsc calibration fix broken smi detection logic Andi Kleen
2007-07-19  9:55 ` [PATCH] [23/58] i386: remove pit_interrupt_hook Andi Kleen
2007-07-19  9:55 ` [PATCH] [24/58] x86_64: Untangle asm/hpet.h from asm/timex.h Andi Kleen
2007-07-19  9:55 ` [PATCH] [25/58] x86_64: use generic cmos update Andi Kleen
2007-07-19  9:55 ` [PATCH] [26/58] x86_64: Use generic xtime init Andi Kleen
2007-07-19  9:55 ` [PATCH] [27/58] x86_64: Remove dead code and other janitor work in tsc.c Andi Kleen
2007-07-19  9:55 ` [PATCH] [28/58] x86_64: Fix APIC typo Andi Kleen
2007-07-19  9:55 ` [PATCH] [29/58] x86_64: fiuxp pt_reqs leftovers Andi Kleen
2007-07-19  9:55 ` [PATCH] [30/58] x86: share hpet.h with i386 Andi Kleen
2007-07-19  9:55 ` [PATCH] [31/58] x86_64: apic.c coding style janitor work Andi Kleen
2007-07-19  9:55 ` [PATCH] [32/58] x86_64: time.c white space wreckage cleanup Andi Kleen
2007-07-19  9:55 ` [PATCH] [33/58] x86_64: Avoid too many remote cpu references due to /proc/stat Andi Kleen
2007-07-19 10:21   ` Christoph Hellwig
2007-07-19 10:41     ` Andi Kleen
2007-07-19 10:55       ` Adrian Bunk
2007-07-19  9:55 ` [PATCH] [34/58] x86_64: ia32entry adjustments Andi Kleen
2007-07-19 14:46   ` Jeff Garzik
2007-08-06 10:43     ` Jan Beulich
2007-07-19  9:55 ` [PATCH] [35/58] i386: allow debuggers to access the vsyscall page with compat vDSO Andi Kleen
2007-07-19  9:55 ` [PATCH] [36/58] x86_64: minor exception trace variables cleanup Andi Kleen
2007-07-19  9:55 ` [PATCH] [37/58] x86_64: remove unused variable maxcpus Andi Kleen
2007-07-19  9:55 ` [PATCH] [38/58] i386: smp-alt-once option is only useful with HOTPLUG_CPU Andi Kleen
2007-07-19  9:55 ` [PATCH] [39/58] i386: minor nx handling adjustment Andi Kleen
2007-07-19  9:55 ` [PATCH] [40/58] i386: remapped_pgdat_init() static Andi Kleen
2007-07-19  9:55 ` [PATCH] [41/58] i386: arch/i386/kernel/i8253.c should #include <asm/timer.h> Andi Kleen
2007-07-19  9:55 ` [PATCH] [42/58] i386: timer_irq_works() static again Andi Kleen
2007-07-19  9:55 ` [PATCH] [43/58] x86_64: Quicklist support for x86_64 Andi Kleen
2007-07-19  9:55 ` [PATCH] [44/58] x86_64: extract helper function from e820_register_active_regions Andi Kleen
2007-07-19  9:55 ` [PATCH] [45/58] x86_64: fake pxm-to-node mapping for fake numa Andi Kleen
2007-07-19  9:55 ` [PATCH] [46/58] x86_64: fake apicid_to_node " Andi Kleen
2007-07-19  9:55 ` [PATCH] [47/58] i386: insert unclaimed MMCONFIG resources Andi Kleen
2007-07-19  9:55 ` [PATCH] [48/58] x86_64: O_EXCL on /dev/mcelog Andi Kleen
2007-07-19  9:55 ` [PATCH] [49/58] x86_64: support poll() " Andi Kleen
2007-07-19  9:55 ` [PATCH] [50/58] x86_64: mcelog tolerant level cleanup Andi Kleen
2007-07-19  9:55 ` [PATCH] [51/58] i386: fix machine rebooting Andi Kleen
2007-07-19  9:55 ` [PATCH] [52/58] i386: fix section mismatch warnings in mtrr Andi Kleen
2007-07-19  9:55 ` [PATCH] [53/58] x86: PM_TRACE support Andi Kleen
2007-07-19  9:55 ` [PATCH] [54/58] x86: Make Alt-SysRq-p display the debug register contents Andi Kleen
2007-07-19  9:55 ` [PATCH] [55/58] i386: add reference to the arguments Andi Kleen
2007-07-19  9:55 ` [PATCH] [56/58] x86: round_jiffies() for i386 and x86-64 non-critical/corrected MCE polling Andi Kleen
2007-07-19  9:55 ` [PATCH] [57/58] x86_64: check remote IRR bit before migrating level triggered irq Andi Kleen
2007-07-19  9:55 ` [PATCH] [58/58] x86: remove support for the Rise CPU Andi Kleen
2007-07-19 10:45   ` Alan Cox
2007-07-19 10:48     ` Adrian Bunk
2007-07-19 11:13       ` Alan Cox
2007-07-19 12:03         ` Andi Kleen
2007-07-19 14:56           ` Jeff Garzik

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=200707220129.50223.vda.linux@googlemail.com \
    --to=vda.linux@googlemail.com \
    --cc=ak@suse.de \
    --cc=jh@suse.cz \
    --cc=linux-kernel@vger.kernel.org \
    --cc=olecom@flower.upol.cz \
    --cc=patches@x86-64.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