[Bug tree-optimization/34011] Memory load is not eliminated from tight vectorized loop

[rguenth at gcc dot gnu dot org]

------- Comment #4 from rguenth at gcc dot gnu dot org  2009-09-15 14:07 -------
With the alias issue fixed I get

good:
.LFB0:
        .cfi_startproc
        movd    srcshift(%rip), %xmm1
        xorl    %eax, %eax
        .p2align 4,,10
        .p2align 3
.L2:
        movdqu  (%rdi,%rax), %xmm0
        pslld   %xmm1, %xmm0
        movdqu  %xmm0, (%rsi,%rax)
        addq    $16, %rax
        cmpq    $1024, %rax
        jne     .L2
        rep
        ret

bad:
.LFB1:
        .cfi_startproc
        movd    srcshift(%rip), %xmm2
        leaq    1024(%rsi), %rax
        .p2align 4,,10
        .p2align 3
.L6:
        movdqu  (%rdi), %xmm0
        addq    $16, %rdi
        movdqu  (%rsi), %xmm1
        pslld   %xmm2, %xmm0
        por     %xmm1, %xmm0
        movdqu  %xmm0, (%rsi)
        addq    $16, %rsi
        cmpq    %rax, %rsi
        jne     .L6
        rep
        ret

which looks good in both cases.

For the original testcase which results in a runtime alias check we get

bad:
.LFB1:
        .cfi_startproc
        leaq    16(%rdi), %rax
        cmpq    %rax, %rsi
        leaq    16(%rsi), %rax
        seta    %dl
        cmpq    %rax, %rdi
        seta    %al
        orb     %al, %dl
        je      .L10
        leaq    1024(%rsi), %rax
        .p2align 4,,10
        .p2align 3
.L11:
        movdqu  (%rdi), %xmm0
        addq    $16, %rdi
        movd    srcshift(%rip), %xmm1
        pslld   %xmm1, %xmm0
        movdqu  (%rsi), %xmm1
        por     %xmm1, %xmm0
        movdqu  %xmm0, (%rsi)
        addq    $16, %rsi
        cmpq    %rax, %rsi
        jne     .L11
        rep
        ret
.L10:
        movzbl  srcshift(%rip), %ecx
        xorl    %eax, %eax
        .p2align 4,,10
        .p2align 3
.L13:
        movl    (%rdi,%rax), %edx
        sall    %cl, %edx
        orl     %edx, (%rsi,%rax)
        addq    $4, %rax
        cmpq    $1024, %rax
        jne     .L13
        rep
        ret

thus still bad.  It is IRA / reload that moves the srcshift load back into
the loop for some reason.


-- 

rguenth at gcc dot gnu dot org changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |vmakarov at gcc dot gnu dot
                   |                            |org


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=34011