From: Segher Boessenkool <segher@kernel.crashing.org>
To: "Paul A. Clarke" <pc@us.ibm.com>
Cc: gcc-patches@gcc.gnu.org, wschmidt@linux.ibm.com
Subject: Re: [PATCH v3 6/6] rs6000: Guard some x86 intrinsics implementations
Date: Mon, 11 Oct 2021 19:11:13 -0500 [thread overview]
Message-ID: <20211012001113.GF10333@gate.crashing.org> (raw)
In-Reply-To: <20210823190310.1679905-7-pc@us.ibm.com>
Hi!
On Mon, Aug 23, 2021 at 02:03:10PM -0500, Paul A. Clarke wrote:
> Some compatibility implementations of x86 intrinsics include
> Power intrinsics which require POWER8. Guard them.
> emmintrin.h:
> - _mm_cmpord_pd: Remove code which was ostensibly for pre-POWER8,
> but which indeed depended on POWER8 (vec_cmpgt(v2du)/vcmpgtud).
> The "POWER8" version works fine on pre-POWER8.
Huh. It just generates xvcmpeqdp I suppose?
> - _mm_mul_epu32: vec_mule(v4su) uses vmuleuw.
Did this fail on p7? If not, add a test that *does*?
> pmmintrin.h:
> - _mm_movehdup_ps: vec_mergeo(v4su) uses vmrgow.
> - _mm_moveldup_ps: vec_mergee(v4su) uses vmrgew.
Similar.
> smmintrin.h:
> - _mm_cmpeq_epi64: vec_cmpeq(v2di) uses vcmpequd.
> - _mm_mul_epi32: vec_mule(v4si) uses vmuluwm.
> - _mm_cmpgt_epi64: vec_cmpgt(v2di) uses vcmpgtsd.
> tmmintrin.h:
> - _mm_sign_epi8: vec_neg(v4si) uses vsububm.
> - _mm_sign_epi16: vec_neg(v4si) uses vsubuhm.
> - _mm_sign_epi32: vec_neg(v4si) uses vsubuwm.
> Note that the above three could actually be supported pre-POWER8,
> but current GCC does not support them before POWER8.
> - _mm_sign_pi8: depends on _mm_sign_epi8.
> - _mm_sign_pi16: depends on _mm_sign_epi16.
> - _mm_sign_pi32: depends on _mm_sign_epi32.
And more.
> gcc
> PR target/101893
This is a different bug (the vgbdd one)?
All looks good, but we need such failing tests :-)
Segher
next prev parent reply other threads:[~2021-10-12 0:13 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-23 19:03 [PATCH v3 0/6] rs6000: Support more SSE4 intrinsics Paul A. Clarke
2021-08-23 19:03 ` [PATCH v3 1/6] rs6000: Support SSE4.1 "round" intrinsics Paul A. Clarke
2021-08-27 13:44 ` Bill Schmidt
2021-08-27 13:47 ` Bill Schmidt
2021-08-30 21:16 ` Paul A. Clarke
2021-08-30 21:24 ` Bill Schmidt
2021-10-07 23:08 ` Segher Boessenkool
2021-10-07 23:39 ` Segher Boessenkool
2021-10-08 1:04 ` Paul A. Clarke
2021-10-08 17:39 ` Segher Boessenkool
2021-10-08 19:27 ` Paul A. Clarke
2021-10-08 22:31 ` Segher Boessenkool
2021-10-11 13:46 ` Paul A. Clarke
2021-10-11 16:28 ` Segher Boessenkool
2021-10-11 17:31 ` Paul A. Clarke
2021-10-11 22:04 ` Segher Boessenkool
2021-10-12 19:35 ` Paul A. Clarke
2021-10-12 22:25 ` Segher Boessenkool
2021-10-19 0:36 ` Paul A. Clarke
2021-08-23 19:03 ` [PATCH v3 2/6] rs6000: Support SSE4.1 "min" and "max" intrinsics Paul A. Clarke
2021-08-27 13:47 ` Bill Schmidt
2021-10-11 19:28 ` Segher Boessenkool
2021-10-12 1:42 ` [COMMITTED v4 " Paul A. Clarke
2021-08-23 19:03 ` [PATCH v3 3/6] rs6000: Simplify some SSE4.1 "test" intrinsics Paul A. Clarke
2021-08-27 13:48 ` Bill Schmidt
2021-10-11 20:50 ` Segher Boessenkool
2021-10-12 1:47 ` [COMMITTED v4 " Paul A. Clarke
2021-08-23 19:03 ` [PATCH v3 4/6] rs6000: Support SSE4.1 "cvt" intrinsics Paul A. Clarke
2021-08-27 13:49 ` Bill Schmidt
2021-10-11 21:52 ` Segher Boessenkool
2021-10-12 1:51 ` [COMMITTED v4 " Paul A. Clarke
2021-08-23 19:03 ` [PATCH v3 5/6] rs6000: Support more SSE4 "cmp", "mul", "pack" intrinsics Paul A. Clarke
2021-08-27 15:21 ` Bill Schmidt
2021-08-27 18:52 ` Paul A. Clarke
2021-10-11 23:07 ` Segher Boessenkool
2021-10-12 1:55 ` [COMMITTED v4 " Paul A. Clarke
2021-08-23 19:03 ` [PATCH v3 6/6] rs6000: Guard some x86 intrinsics implementations Paul A. Clarke
2021-08-27 15:25 ` Bill Schmidt
2021-10-12 0:11 ` Segher Boessenkool [this message]
2021-10-13 17:04 ` Paul A. Clarke
2021-10-13 23:47 ` Segher Boessenkool
2021-10-19 0:26 ` Paul A. Clarke
2021-09-16 14:59 ` [PATCH v3 0/6] rs6000: Support more SSE4 intrinsics Paul A. Clarke
2021-10-04 18:26 ` Paul A. Clarke
2021-10-07 22:25 ` Segher Boessenkool
2021-10-08 0:29 ` Paul A. Clarke
2021-10-12 0:15 ` Segher Boessenkool
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=20211012001113.GF10333@gate.crashing.org \
--to=segher@kernel.crashing.org \
--cc=gcc-patches@gcc.gnu.org \
--cc=pc@us.ibm.com \
--cc=wschmidt@linux.ibm.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).