From: Rich Felker <dalias@libc.org>
To: musl@lists.openwall.com
Subject: Re: [PATCH v2 5/6] dynlink.c: compute modulus via magic multiplication
Date: Tue, 30 Jun 2015 13:51:17 -0400 [thread overview]
Message-ID: <20150630175117.GW1173@brightrain.aerifal.cx> (raw)
In-Reply-To: <1435448915-28419-6-git-send-email-amonakov@ispras.ru>
[-- Attachment #1: Type: text/plain, Size: 757 bytes --]
On Sun, Jun 28, 2015 at 02:48:34AM +0300, Alexander Monakov wrote:
> Based on http://ridiculousfish.com/blog/posts/labor-of-division-episode-iii.html
>
> Do a little hand-holding for the compiler and fold magic post-shift into
> 32-bit high word -> low word shift on 64-bit platforms.
> ---
On 32-bit Atom, I was able to get an improvement from 116ms to 113ms
running an empty program linked with a .so produced using the attached
script. This is probably roughly best-case improvement, so the umod
stuff is probably not likely to be worthwhile unless/until we can
improve the areas that are currently dominating the runtime. That's
rather disappointing, but maybe we can improve enough other stuff for
it to make sense to do the umod optimization.
Rich
[-- Attachment #2: gen.sh --]
[-- Type: application/x-sh, Size: 112 bytes --]
next prev parent reply other threads:[~2015-06-30 17:51 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-06-23 23:24 [PATCH 0/5] gnu-hash speedups Alexander Monakov
2015-06-23 23:24 ` [PATCH 1/5] dynlink.c: use bloom filter in gnu hash lookup Alexander Monakov
2015-06-24 5:39 ` Rich Felker
2015-06-24 6:29 ` Alexander Monakov
2015-06-24 6:32 ` Alexander Monakov
2015-06-24 6:50 ` Rich Felker
2015-06-23 23:24 ` [PATCH 2/5] dynlink.c: compute modulus via magic multiplication Alexander Monakov
2015-06-24 4:18 ` Alexander Monakov
2015-06-24 4:19 ` Rich Felker
2015-06-24 4:24 ` Rich Felker
2015-06-24 4:32 ` Alexander Monakov
2015-06-24 5:13 ` Rich Felker
2015-06-24 6:08 ` Alexander Monakov
2015-06-24 6:39 ` Rich Felker
2015-06-23 23:24 ` [PATCH 3/5] dynlink.c: slim down gnu_lookup Alexander Monakov
2015-06-23 23:24 ` [PATCH 4/5] dynlink.c: pass gnu-hash table pointer to gnu_lookup Alexander Monakov
2015-06-23 23:24 ` [PATCH 5/5] dynlink.c: use a faster expression in gnu_hash Alexander Monakov
2015-06-27 23:48 ` [PATCH v2 0/6] gnu-hash speedups Alexander Monakov
2015-06-27 23:48 ` [PATCH v2 1/6] dynlink.c: use a faster expression in gnu_hash Alexander Monakov
2015-06-27 23:48 ` [PATCH v2 2/6] dynlink.c: use bloom filter in gnu hash lookup Alexander Monakov
2015-06-27 23:48 ` [PATCH v2 3/6] dynlink.c: slim down gnu_lookup Alexander Monakov
2015-06-27 23:48 ` [PATCH v2 4/6] dynlink.c: pass gnu-hash table pointer to gnu_lookup Alexander Monakov
2015-06-28 0:05 ` Alexander Monakov
2015-06-28 8:59 ` Alexander Monakov
2015-06-27 23:48 ` [PATCH v2 5/6] dynlink.c: compute modulus via magic multiplication Alexander Monakov
2015-06-30 17:51 ` Rich Felker [this message]
2015-06-27 23:48 ` [PATCH v2 6/6] dynlink.c: store bloom filter size in struct dso Alexander Monakov
2015-06-28 2:45 ` [PATCH v2 0/6] gnu-hash speedups 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=20150630175117.GW1173@brightrain.aerifal.cx \
--to=dalias@libc.org \
--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).