[Bug target/56309] -O3 optimizer generates conditional moves instead of compare and branch resulting in almost 2x slower code

[steven at gcc dot gnu.org]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=56309



--- Comment #12 from Steven Bosscher <steven at gcc dot gnu.org> 2013-02-14 
17:10:02 UTC ---

A bit more clear with insn 195 added:



  195: flags:CC=cmp(r124:DI,r235:DI)

  197: r116:DI={(gtu(flags:CC,0))?r125:DI:r233:DI}

  199: {r110:DI=r110:DI+0x1;clobber flags:CC;}

  201: flags:CC=cmp(r124:DI,r235:DI)

  202: r221:DI={(gtu(flags:CC,0))?r126:DI:r124:DI}



insns 195 and 201 compute the same condition but GCC can't eliminate

the comparison in insns 201 because insn 199 clobbers the flags (i.e.

destroys the result from insn 195).



As for speed, of course I can measure that myself:



--- by-val-O3.s.orig    2013-02-14 18:06:56.000000000 +0100

+++ by-val-O3.s 2013-02-14 18:07:23.000000000 +0100

@@ -357,9 +357,8 @@

        shrq    $32, %rdi

        cmpq    %r8, %rdx

        cmovbe  %r11, %rdi

-       addq    $1, %rax

-       cmpq    %r8, %rdx

        cmovbe  %rdx, %rcx

+       addq    $1, %rax

        cmpq    %rbp, %rax

        movq    %rcx, -8(%rsi,%rax,8)

        jne     .L50



unmodified: Took 14.31 seconds total.

modified:   Took 13.04 seconds total.



So re. comment #9: it's not the problem but it'd be a small improvement.