public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
From: "unlvsur at live dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/107563] __builtin_shufflevector fails to pshufd instructions under default x86_64 compilation toggle which is the sse2 one
Date: Tue, 08 Nov 2022 06:11:08 +0000	[thread overview]
Message-ID: <bug-107563-4-YoahemLfXe@http.gcc.gnu.org/bugzilla/> (raw)
In-Reply-To: <bug-107563-4@http.gcc.gnu.org/bugzilla/>

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107563

--- Comment #7 from cqwrteur <unlvsur at live dot com> ---
(In reply to Hongtao.liu from comment #6)
> Shufd only handles
> 
> void foo1(temp_vec_type& v) noexcept
> {
> 	v=__builtin_shufflevector(v,v,12,13,14,15,8,9,10,11,4,5,6,7,0,1,2,3);
> }
> 
> Not the case in #c0.

I am using it for byte swap

actually, clang has a solution

                        using x86_64_v4si [[__gnu__::__vector_size__ (16)]] =
int;
                        using x86_64_v16qi [[__gnu__::__vector_size__ (16)]] =
char;
                        using x86_64_v8hi [[__gnu__::__vector_size__ (16)]] =
short;
                        constexpr x86_64_v16qi zero{};
                        if constexpr(sizeof(T)==8)
                        {
                                auto
res0{__builtin_ia32_punpcklbw128(temp_vec,zero)};
                                auto
res1{__builtin_ia32_pshufd((x86_64_v4si)res0,78)};
                                auto
res2{__builtin_ia32_pshuflw((x86_64_v8hi)res1,27)};
                                auto res3{__builtin_ia32_pshufhw(res2,27)};
                                auto
res4{__builtin_ia32_punpckhbw128(temp_vec,zero)};
                                auto
res5{__builtin_ia32_pshufd((x86_64_v4si)res4,78)};
                                auto
res6{__builtin_ia32_pshuflw((x86_64_v8hi)res5,27)};
                                auto res7{__builtin_ia32_pshufhw(res6,27)};
                                temp_vec=__builtin_ia32_packuswb128(res3,res7);
                        }
                        else if constexpr(sizeof(T)==4)
                        {
                                auto
res0{__builtin_ia32_punpcklbw128(temp_vec,zero)};
                                auto
res2{__builtin_ia32_pshuflw((x86_64_v8hi)res0,27)};
                                auto res3{__builtin_ia32_pshufhw(res2,27)};
                                auto
res4{__builtin_ia32_punpckhbw128(temp_vec,zero)};
                                auto
res6{__builtin_ia32_pshuflw((x86_64_v8hi)res4,27)};
                                auto res7{__builtin_ia32_pshufhw(res6,27)};
                                temp_vec=__builtin_ia32_packuswb128(res3,res7);
                        }
                        else if constexpr(sizeof(T)==2)
                        {
                                using x86_64_v8hu [[__gnu__::__vector_size__
(16)]] = unsigned short;
                                auto res0{(x86_64_v8hu)temp_vec};
                                temp_vec=(x86_64_v16qi)((res0>>8)|(res0<<8));
                        }

  parent reply	other threads:[~2022-11-08  6:11 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-11-07 22:56 [Bug rtl-optimization/107563] New: __builtin_shufflevector fails to use pshufb and " unlvsur at live dot com
2022-11-07 23:00 ` [Bug target/107563] " unlvsur at live dot com
2022-11-07 23:05 ` [Bug target/107563] __builtin_shufflevector fails to " unlvsur at live dot com
2022-11-08  0:11 ` unlvsur at live dot com
2022-11-08  0:11 ` unlvsur at live dot com
2022-11-08  3:23 ` crazylht at gmail dot com
2022-11-08  3:33 ` crazylht at gmail dot com
2022-11-08  6:11 ` unlvsur at live dot com [this message]
2022-11-08  6:11 ` unlvsur at live dot com
2022-11-08  6:14 ` unlvsur at live dot com
2022-11-08  8:28 ` crazylht at gmail dot com
2024-05-15  4:47 ` cvs-commit at gcc dot gnu.org
2024-05-18 15:17 ` admin at levyhsu dot com

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=bug-107563-4-YoahemLfXe@http.gcc.gnu.org/bugzilla/ \
    --to=gcc-bugzilla@gcc.gnu.org \
    --cc=gcc-bugs@gcc.gnu.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).