From: "H.J. Lu" <hjl.tools@gmail.com>
To: Richard Henderson <richard.henderson@linaro.org>
Cc: Sunil K Pandey <skpgkp2@gmail.com>, libc-alpha@sourceware.org
Subject: Re: [PATCH] x86_64: Optimize ffsll function code size.
Date: Wed, 26 Jul 2023 09:50:34 -0700 [thread overview]
Message-ID: <CAMe9rOodCqfCO3mSPtHbng-goXOAnCsL6qsAjyM7HF3AtU10fg@mail.gmail.com> (raw)
In-Reply-To: <c86499dd-dccb-db83-d710-bd0ee0d83576@linaro.org>
On Wed, Jul 26, 2023 at 9:38 AM Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> On 7/26/23 09:05, Sunil K Pandey via Libc-alpha wrote:
> > Ffsll function size is 17 byte, this patch optimizes size to 16 byte.
> > Currently ffsll function randomly regress by ~20%, depending on how
> > code get aligned.
> >
> > This patch fixes ffsll function random performance regression.
> > ---
> > sysdeps/x86_64/ffsll.c | 2 +-
> > 1 file changed, 1 insertion(+), 1 deletion(-)
> >
> > diff --git a/sysdeps/x86_64/ffsll.c b/sysdeps/x86_64/ffsll.c
> > index a1c13d4906..dbded6f0a1 100644
> > --- a/sysdeps/x86_64/ffsll.c
> > +++ b/sysdeps/x86_64/ffsll.c
> > @@ -29,7 +29,7 @@ ffsll (long long int x)
> > long long int tmp;
> >
> > asm ("bsfq %2,%0\n" /* Count low bits in X and store in %1. */
> > - "cmoveq %1,%0\n" /* If number was zero, use -1 as result. */
> > + "cmove %k1,%k0\n" /* If number was zero, use -1 as result. */
>
> This no longer produces -1, but 0xffffffff in cnt. However, since the return type is
> 'int', cnt need not be 'long long int' either. I'm not sure why tmp exists at all, since
> cnt is the only register modified.
>
>
> r~
tmp was initialized to -1 with
: "=&r" (cnt), "=r" (tmp) : "rm" (x), "1" (-1));
H.J.
next prev parent reply other threads:[~2023-07-26 16:51 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-07-26 16:05 Sunil K Pandey
2023-07-26 16:38 ` Richard Henderson
2023-07-26 16:50 ` H.J. Lu [this message]
2023-07-26 16:51 ` Noah Goldstein
2023-07-26 16:51 ` Sunil Pandey
2023-07-26 16:59 ` Noah Goldstein
2023-07-26 17:11 ` Adhemerval Zanella Netto
2023-07-27 0:31 ` Cristian Rodríguez
2023-07-26 20:43 ` Sunil Pandey
2023-07-26 21:05 ` Noah Goldstein
2023-07-26 22:37 ` Sunil Pandey
2023-07-27 0:00 ` Noah Goldstein
2023-07-27 8:16 ` Florian Weimer
2023-07-27 11:46 ` Alexander Monakov
2023-07-27 12:10 ` Florian Weimer
2023-07-27 13:59 ` Cristian Rodríguez
2023-07-27 14:00 ` Alexander Monakov
2023-07-27 15:13 ` Sunil Pandey
2023-07-27 15:50 ` Alexander Monakov
2023-07-27 16:24 ` Florian Weimer
2023-07-27 16:35 ` Adhemerval Zanella Netto
2023-07-27 17:09 ` Florian Weimer
2023-07-27 17:25 ` Sunil Pandey
2023-07-31 18:35 ` [PATCH v2] " Sunil K Pandey
2023-07-31 20:12 ` Adhemerval Zanella Netto
2023-07-31 20:58 ` Sunil Pandey
2023-07-31 22:57 ` Adhemerval Zanella Netto
2023-07-31 23:44 ` Sunil Pandey
2023-07-31 23:54 ` Noah Goldstein
2023-08-01 6:47 ` Andreas Schwab
2023-08-01 13:46 ` Adhemerval Zanella Netto
2023-08-01 18:25 ` Cristian Rodríguez
2024-01-10 19:19 ` Carlos O'Donell
2024-01-25 3:10 ` Sunil Pandey
2023-07-27 16:40 ` [PATCH] " Sunil Pandey
2023-07-26 17:04 ` Noah Goldstein
2023-07-26 17:25 ` Andrew Pinski
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=CAMe9rOodCqfCO3mSPtHbng-goXOAnCsL6qsAjyM7HF3AtU10fg@mail.gmail.com \
--to=hjl.tools@gmail.com \
--cc=libc-alpha@sourceware.org \
--cc=richard.henderson@linaro.org \
--cc=skpgkp2@gmail.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.
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).