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

[arturomdn at gmail dot com]

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



--- Comment #16 from arturomdn at gmail dot com 2013-02-14 17:42:55 UTC ---

With -ftree-vectorize -fno-tree-loop-if-convert flags it generated this for the

loop in question:



.L39:

        movq    %rdi, %rdx

        addq    (%rsi,%rax,8), %rcx

        imulq   (%r9,%rax,8), %rdx

        addq    %rcx, %rdx

        xorl    %ecx, %ecx

        cmpq    %r10, %rdx

        jbe     .L38

        movq    %rdx, %rcx

        andl    $4294967295, %edx

        shrq    $32, %rcx

.L38:

        addq    $1, %rax

        cmpq    %r8, %rax

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

        jne     .L39



And it executed fast:



./by-val-O3-flags

Took 6.74 seconds total.