[PATCH] D20315: [LV] For some induction variables, use vector phis instead of widening the scalar in the loop body

[Xinliang David Li via llvm-commits]

On Tue, May 17, 2016 at 11:12 AM, Michael Kuperstein <mkuper at google.com>
wrote:

> mkuper added a comment.
>
> Right, I'll add an explicit test (the test in induction_plus is *sort of*
> that, but not quite), thanks David!
>
> Regarding the extra movdqa - I think the copy may be necessary.
> The problem is that the loop body needs both to modify the current IV
> (because of two-address instructions) and keep it so that it can generate
> the new IV.
>
>
You are right :)

David



> GCC does something similar:
>
>   jmp   .L3
>   [...]
>   .L5:
>         movdqa  %xmm4, %xmm1
>   .L3:
>         movdqa  %xmm1, %xmm4
>         pxor    %xmm6, %xmm1
>         movdqa  %xmm5, %xmm2
>         addl    $1, %eax
>         cmpl    $250, %eax
>         paddd   %xmm7, %xmm4
>         pcmpgtd %xmm1, %xmm2
>         movdqa  %xmm1, %xmm3
>         punpckhdq       %xmm2, %xmm1
>         punpckldq       %xmm2, %xmm3
>         paddq   %xmm3, %xmm0
>         paddq   %xmm1, %xmm0
>         jne     .L5
>
> The difference is that the loop is rotated, so there is no copy on the
> first iteration, but other than that, we still have the same two movdqas
> per iteration.
>
> In any case, the extra mov disappears once we have AVX and three-address
> instructions, so we no longer update the current IV destructively.
>
>
> http://reviews.llvm.org/D20315
>
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160517/1233c087/attachment.html>