From: "H.J. Lu" <hjl.tools@gmail.com>
To: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Cc: Joseph Myers <joseph@codesourcery.com>,
GNU C Library <libc-alpha@sourceware.org>
Subject: Re: [PATCH] x86-64: Add sinf with FMA
Date: Tue, 05 Dec 2017 16:56:00 -0000 [thread overview]
Message-ID: <CAMe9rOrRyf0JQbo2cRgOOO9vv8V0BUb1z2y5939+BBuGR_pcJw@mail.gmail.com> (raw)
In-Reply-To: <a505c43a-1a44-34fc-f36b-243e328b34af@linaro.org>
On Tue, Dec 5, 2017 at 5:47 AM, Adhemerval Zanella
<adhemerval.zanella@linaro.org> wrote:
> And with a simple modification to avoid int to fp conversion:
>
> ---
> diff --git a/sysdeps/ieee754/flt-32/s_sinf.c b/sysdeps/ieee754/flt-32/s_sinf.c
> index 40d3d19..a2fd3cf 100644
> --- a/sysdeps/ieee754/flt-32/s_sinf.c
> +++ b/sysdeps/ieee754/flt-32/s_sinf.c
> @@ -75,7 +75,7 @@ static const double invpio4_table[] = {
> 0x1.0e4107cp-169
> };
>
> -static const int ones[] = { +1, -1 };
> +static const double ones[] = { 1.0, -1.0 };
>
> /* Compute the sine value using Chebyshev polynomials where
> THETA is the range reduced absolute value of the input
> @@ -92,7 +92,7 @@ reduced (const double theta, const unsigned long int n,
> const double theta2 = theta * theta;
> /* We are operating on |x|, so we need to add back the original
> signbit for sinf. */
> - int sign;
> + double sign;
> /* Determine positive or negative primary interval. */
> sign = ones[((n >> 2) & 1) ^ signbit];
> /* Are we in the primary interval of sin or cos? */
> ---
>
> I get:
>
> "sinf": {
> "": {
> "duration": 4.0015e+10,
> "iterations": 1.4535e+09,
> "max": 640.456,
> "min": 11.437,
> "mean": 27.5301
> }
>
> Which is roughly 3% on mean and 11.5% on min. I think we can improve it
> even more by avoiding the int to fp conversion to get the sign right
> and try operate with sign as double argument.
I tried it on Skylake with the current master. Before:
"sinf": {
"": {
"duration": 3.4044e+10,
"iterations": 1.9942e+09,
"max": 141.106,
"min": 7.704,
"mean": 17.0715
}
}
After:
"sinf": {
"": {
"duration": 3.40665e+10,
"iterations": 2.03199e+09,
"max": 95.994,
"min": 7.704,
"mean": 16.765
}
}
Generic is faster than asm now:
"sinf": {
"": {
"duration": 3.40417e+10,
"iterations": 1.87792e+09,
"max": 138.868,
"min": 8.546,
"mean": 18.1273
}
}
Can you submit your patch?
Thanks.
--
H.J.
next prev parent reply other threads:[~2017-12-05 16:56 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-12-04 18:09 H.J. Lu
2017-12-04 18:38 ` Adhemerval Zanella
2017-12-04 18:51 ` H.J. Lu
2017-12-04 18:57 ` Joseph Myers
2017-12-04 19:41 ` H.J. Lu
2017-12-04 20:59 ` Joseph Myers
2017-12-04 22:42 ` H.J. Lu
2017-12-05 13:47 ` Adhemerval Zanella
2017-12-05 13:57 ` Joseph Myers
2017-12-05 17:06 ` Adhemerval Zanella
2017-12-05 16:56 ` H.J. Lu [this message]
2017-12-05 17:09 ` Adhemerval Zanella
2017-12-05 19:03 ` H.J. Lu
2017-12-07 12:20 ` Adhemerval Zanella
2017-12-07 18:13 ` H.J. Lu
2017-12-05 13:44 ` Florian Weimer
2017-12-08 16:02 ` Nick Alcock
2017-12-08 16:04 ` Arjan van de Ven
2017-12-08 16:07 ` Arjan van de Ven
2017-12-08 16:11 ` H.J. Lu
2017-12-08 16:16 ` Nix
2017-12-08 16:32 ` Arjan van de Ven
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=CAMe9rOrRyf0JQbo2cRgOOO9vv8V0BUb1z2y5939+BBuGR_pcJw@mail.gmail.com \
--to=hjl.tools@gmail.com \
--cc=adhemerval.zanella@linaro.org \
--cc=joseph@codesourcery.com \
--cc=libc-alpha@sourceware.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;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).