From: Marc Glisse <marc.glisse@inria.fr>
To: gcc-patches@gcc.gnu.org
Cc: ubizjak@gmail.com
Subject: [i386] scalar ops that preserve the high part of a vector
Date: Sat, 13 Oct 2012 09:33:00 -0000 [thread overview]
Message-ID: <alpine.DEB.2.02.1210131032460.9651@stedding.saclay.inria.fr> (raw)
[-- Attachment #1: Type: TEXT/PLAIN, Size: 573 bytes --]
Hello,
this patch provides an alternate pattern to let combine recognize scalar
operations that preserve the high part of a vector. If the strategy is all
right, I could do the same for more operations (mul, div, ...). Something
similar is also possible for V4SF (different pattern though), but probably
not as useful.
bootstrap+testsuite ok.
2012-10-13 Marc Glisse <marc.glisse@inria.fr>
PR target/54855
gcc/
* config/i386/sse.md (*sse2_vm<plusminus_insn>v2df3): New define_insn.
gcc/testsuite/
* gcc.target/i386/pr54855.c: New testcase.
--
Marc Glisse
[-- Attachment #2: Type: TEXT/PLAIN, Size: 2294 bytes --]
Index: config/i386/sse.md
===================================================================
--- config/i386/sse.md (revision 192420)
+++ config/i386/sse.md (working copy)
@@ -812,20 +812,38 @@
(const_int 1)))]
"TARGET_SSE"
"@
<plusminus_mnemonic><ssescalarmodesuffix>\t{%2, %0|%0, %2}
v<plusminus_mnemonic><ssescalarmodesuffix>\t{%2, %1, %0|%0, %1, %2}"
[(set_attr "isa" "noavx,avx")
(set_attr "type" "sseadd")
(set_attr "prefix" "orig,vex")
(set_attr "mode" "<ssescalarmode>")])
+(define_insn "*sse2_vm<plusminus_insn>v2df3"
+ [(set (match_operand:V2DF 0 "register_operand" "=x,x")
+ (vec_concat:V2DF
+ (plusminus:DF
+ (vec_select:DF
+ (match_operand:V2DF 1 "register_operand" "0,x")
+ (parallel [(const_int 0)]))
+ (match_operand:DF 2 "nonimmediate_operand" "xm,xm"))
+ (vec_select:DF (match_dup 1) (parallel [(const_int 1)]))))]
+ "TARGET_SSE2"
+ "@
+ <plusminus_mnemonic>sd\t{%2, %0|%0, %2}
+ v<plusminus_mnemonic>sd\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "noavx,avx")
+ (set_attr "type" "sseadd")
+ (set_attr "prefix" "orig,vex")
+ (set_attr "mode" "DF")])
+
(define_expand "mul<mode>3"
[(set (match_operand:VF 0 "register_operand")
(mult:VF
(match_operand:VF 1 "nonimmediate_operand")
(match_operand:VF 2 "nonimmediate_operand")))]
"TARGET_SSE"
"ix86_fixup_binary_operands_no_copy (MULT, <MODE>mode, operands);")
(define_insn "*mul<mode>3"
[(set (match_operand:VF 0 "register_operand" "=x,x")
Index: testsuite/gcc.target/i386/pr54855.c
===================================================================
--- testsuite/gcc.target/i386/pr54855.c (revision 0)
+++ testsuite/gcc.target/i386/pr54855.c (revision 0)
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-O -msse2" } */
+
+typedef double vec __attribute__((vector_size(16)));
+
+vec f (vec x)
+{
+ x[0] += 2;
+ return x;
+}
+
+vec g (vec x)
+{
+ x[0] -= 1;
+ return x;
+}
+
+/* { dg-final { scan-assembler-not "mov" } } */
Property changes on: testsuite/gcc.target/i386/pr54855.c
___________________________________________________________________
Added: svn:keywords
+ Author Date Id Revision URL
Added: svn:eol-style
+ native
next reply other threads:[~2012-10-13 8:52 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-10-13 9:33 Marc Glisse [this message]
2012-10-14 9:54 ` Uros Bizjak
2012-10-14 12:52 ` Marc Glisse
2012-11-30 12:36 ` Marc Glisse
2012-11-30 13:55 ` Uros Bizjak
2012-11-30 22:36 ` Marc Glisse
2012-12-01 17:27 ` Marc Glisse
2012-12-02 10:51 ` Uros Bizjak
2012-12-02 12:30 ` Marc Glisse
2012-12-03 8:53 ` Uros Bizjak
2012-12-03 15:34 ` Marc Glisse
2012-12-03 17:55 ` Uros Bizjak
2012-12-04 14:05 ` Marc Glisse
2012-12-04 16:28 ` Marc Glisse
2012-12-04 18:06 ` Uros Bizjak
2012-12-04 18:12 ` H.J. Lu
2012-12-06 13:42 ` Kirill Yukhin
2012-12-07 6:50 ` Michael Zolotukhin
2012-12-07 8:46 ` Uros Bizjak
2012-12-07 8:49 ` Marc Glisse
2012-12-07 10:52 ` Michael Zolotukhin
2012-12-07 14:02 ` Marc Glisse
2012-12-07 14:43 ` Richard Henderson
2012-12-07 14:47 ` Jakub Jelinek
2012-12-07 14:53 ` Richard Henderson
2012-12-07 15:00 ` Marc Glisse
2012-12-07 15:06 ` Richard Henderson
2012-12-07 15:12 ` Marc Glisse
2012-12-07 16:24 ` Richard Henderson
2012-12-07 17:23 ` Marc Glisse
2012-12-08 5:47 ` Marc Glisse
2012-12-12 15:48 ` Richard Henderson
2012-12-05 14:22 ` Marc Glisse
2012-12-05 17:07 ` Paolo Bonzini
2012-12-05 20:22 ` Marc Glisse
2012-12-05 21:05 ` Eric Botcazou
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=alpine.DEB.2.02.1210131032460.9651@stedding.saclay.inria.fr \
--to=marc.glisse@inria.fr \
--cc=gcc-patches@gcc.gnu.org \
--cc=ubizjak@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).