public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
* [Bug rtl-optimization/22563] New: performance regression for gcc newer than 2.95
@ 2005-07-19 19:20 danalis at cis dot udel dot edu
  2005-07-19 19:57 ` [Bug rtl-optimization/22563] [3.4/4.0/4.1 Regression] " pinskia at gcc dot gnu dot org
                   ` (4 more replies)
  0 siblings, 5 replies; 19+ messages in thread
From: danalis at cis dot udel dot edu @ 2005-07-19 19:20 UTC (permalink / raw)
  To: gcc-bugs

We ran bench++ to look for c++ samples that ran slower at -O3 with
gcc-[34].x than with gcc-2.95.  We're attaching one such case,
minimized as far as we can (so it might not be testing the same
thing as the original code).  It consists of a simple function that
accesses bitfields, called in a loop from main. 
gcc-3.4.3/gcc-4.0.0/gcc-4.1-20050627 all produce binaries that seem
to be ten times slower on this than those produced by gcc-2.95.3.
All the compilers happily inlined
the function, which is fine.

Here's the code from the older compiler:

.L12:
        movb $86,%dl
        movb %dl,b_rec
        movb %dl,%al
        andb $7,%al
        cmpb $6,%al
        je .L14
        call abort
        .align 4
.L14:
        andb $240,%dl
        cmpb $80,%dl
        je .L11
        call abort
        .align 4
.L11:
        decl %ecx
        testl %ecx,%ecx
        jg .L12

And here's code from gcc-4.1-20050625:
        jmp     .L16
        .p2align 4,,7
.L27:
        andb    $-16, %dl
        cmpb    $80, %dl
        jne     .L25
        decl    %ebx
        je      .L26
.L16:
        movl    %ecx, %eax
        andl    $-8, %eax
        orl     $6, %eax
        movl    %eax, b_rec
        andb    $-9, b_rec
        movl    b_rec, %eax
        andl    $-241, %eax
        orl     $80, %eax
        movl    %eax, b_rec
        movl    %eax, %ecx
        movzbl  b_rec, %edx
        movb    %dl, %al
        andb    $7, %al
        cmpb    $6, %al
        je      .L27

We'll attach the preprocessed source.

-- 
           Summary: performance regression for gcc newer than 2.95
           Product: gcc
           Version: 4.0.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P2
         Component: rtl-optimization
        AssignedTo: unassigned at gcc dot gnu dot org
        ReportedBy: danalis at cis dot udel dot edu
                CC: gcc-bugs at gcc dot gnu dot org
GCC target triplet: i686-linux


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=22563


^ permalink raw reply	[flat|nested] 19+ messages in thread
end of thread, other threads:[~2007-02-03 15:33 UTC | newest]

Thread overview: 19+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
     [not found] <bug-22563-10914@http.gcc.gnu.org/bugzilla/>
2005-10-27  0:20 ` [Bug rtl-optimization/22563] [3.4/4.0/4.1 Regression] performance regression for gcc newer than 2.95 pinskia at gcc dot gnu dot org
2005-10-31  4:12 ` mmitchel at gcc dot gnu dot org
2005-11-03 22:54 ` hubicka at gcc dot gnu dot org
2006-02-16  2:08 ` [Bug rtl-optimization/22563] [3.4/4.0/4.1/4.2 " ian at airs dot com
2006-02-24  0:26 ` mmitchel at gcc dot gnu dot org
2006-04-06  1:33 ` pinskia at gcc dot gnu dot org
2006-04-06  2:46 ` ian at airs dot com
2006-05-09 11:59 ` [Bug rtl-optimization/22563] [4.0/4.1/4.2 " hubicka at gcc dot gnu dot org
2006-05-14 15:48 ` sayle at gcc dot gnu dot org
2006-05-14 19:03 ` [Bug rtl-optimization/22563] [4.0/4.1 " pinskia at gcc dot gnu dot org
2006-05-15  4:43 ` sayle at gcc dot gnu dot org
2006-05-15 16:55 ` [Bug rtl-optimization/22563] [4.0 " pinskia at gcc dot gnu dot org
2006-05-16  1:17 ` sayle at gcc dot gnu dot org
2007-02-03 15:33 ` gdr at gcc dot gnu dot org
2005-07-19 19:20 [Bug rtl-optimization/22563] New: " danalis at cis dot udel dot edu
2005-07-19 19:57 ` [Bug rtl-optimization/22563] [3.4/4.0/4.1 Regression] " pinskia at gcc dot gnu dot org
2005-07-22 21:18 ` pinskia at gcc dot gnu dot org
2005-08-04 19:16 ` danalis at cis dot udel dot edu
2005-08-25  3:26 ` dann at godzilla dot ics dot uci dot edu
2005-09-27 15:59 ` mmitchel at gcc dot gnu dot org

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).