From: Andre Renaud <andre@bluewatersys.com>
To: musl@lists.openwall.com
Subject: Re: Thinking about release
Date: Fri, 12 Jul 2013 15:36:42 +1200 [thread overview]
Message-ID: <CAPfzE3a8hRbpcmD55D-y9nwaJn6YaD7BA9dhxM7OkwpnHeEc5w@mail.gmail.com> (raw)
In-Reply-To: <20130712031615.GS29800@brightrain.aerifal.cx>
> I was unable to measure any difference in performance of your version
> with the prefetch hack versus simply:
>
> __asm__ __volatile__(
> "ldmia %1!,{a4,v1,v2,v3,v4,v5,v6,v7}\n\t"
> "stmia %0!,{a4,v1,v2,v3,v4,v5,v6,v7}\n\t"
> : "+r"(d), "+r"(s) :
> : "a4", "v1", "v2", "v3", "v4", "v5", "v6", "v7", "memory");
What kind of machine were you using? I see a change of 115MB/s ->
105MB/s when I drop the prefetch, even using the code that you
suggested. This is on an Atmel AT91sam9g45 (ARM926ejs @ 400MHz). I'm
assuming this is some subtlety about how the cache is operating?
Sticking the ldrhi back in brings the speed back, ie:
__asm__ __volatile__(
"ldmia %1!,{a4,v1,v2,v3,v4,v5,v6,v7}\n\t"
"ldrhi r12, [%1]\n"
"stmia %0!,{a4,v1,v2,v3,v4,v5,v6,v7}\n\t"
: "+r"(d), "+r"(s) :
: "a4", "v1", "v2", "v3", "v4", "v5",
"v6", "v7", "r12", "memory");
Regards,
Andre
next prev parent reply other threads:[~2013-07-12 3:36 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-06-13 1:25 Rich Felker
2013-06-13 1:33 ` Andre Renaud
2013-06-13 1:43 ` Rich Felker
2013-07-09 5:06 ` Andre Renaud
2013-07-09 5:37 ` Rich Felker
2013-07-09 6:24 ` Harald Becker
2013-07-09 21:28 ` Andre Renaud
2013-07-09 22:26 ` Andre Renaud
2013-07-10 6:42 ` Jens Gustedt
2013-07-10 7:50 ` Rich Felker
2013-07-10 22:44 ` Andre Renaud
2013-07-11 3:37 ` Rich Felker
2013-07-11 4:04 ` Andre Renaud
2013-07-11 5:10 ` Andre Renaud
2013-07-11 12:46 ` Rich Felker
2013-07-11 22:34 ` Andre Renaud
2013-07-12 3:16 ` Rich Felker
2013-07-12 3:36 ` Andre Renaud [this message]
2013-07-12 4:16 ` Rich Felker
2013-07-24 1:34 ` Andre Renaud
2013-07-24 3:48 ` Rich Felker
2013-07-24 4:40 ` Andre Renaud
2013-07-28 8:09 ` Rich Felker
2013-07-11 5:27 ` Daniel Cegiełka
2013-07-11 12:49 ` Rich Felker
2013-07-15 4:25 ` Rob Landley
2013-07-10 19:42 ` Rich Felker
2013-07-14 6:37 ` Rob Landley
2013-07-11 4:30 ` Strake
2013-07-11 4:33 ` Rich Felker
2013-07-10 19:38 ` Rob Landley
2013-07-10 20:34 ` Andre Renaud
2013-07-10 20:49 ` Nathan McSween
2013-07-10 21:01 ` Rich Felker
2013-06-13 15:46 ` Isaac
2013-06-26 1:44 ` Rich Felker
2013-06-26 10:19 ` Szabolcs Nagy
2013-06-26 14:21 ` Rich Felker
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=CAPfzE3a8hRbpcmD55D-y9nwaJn6YaD7BA9dhxM7OkwpnHeEc5w@mail.gmail.com \
--to=andre@bluewatersys.com \
--cc=musl@lists.openwall.com \
/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.
Code repositories for project(s) associated with this public inbox
https://git.vuxu.org/mirror/musl/
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 NNTP newsgroup(s).