[llvm-bugs] [Bug 28895] New: [x86, SSE] failed to simplify vector select with zero constant to 'and'

[via llvm-bugs]

https://llvm.org/bugs/show_bug.cgi?id=28895

            Bug ID: 28895
           Summary: [x86, SSE] failed to simplify vector select with zero
                    constant to 'and'
           Product: libraries
           Version: trunk
          Hardware: PC
                OS: All
            Status: NEW
          Severity: normal
          Priority: P
         Component: Backend: X86
          Assignee: unassignedbugs at nondot.org
          Reporter: spatel+llvm at rotateright.com
                CC: llvm-bugs at lists.llvm.org
    Classification: Unclassified

While looking at the select fold in https://reviews.llvm.org/D22975, I noticed
this problem:

define <4 x float> @fselvec(<4 x float> %x, <4 x float> %y) {
  %cmp = fcmp oeq <4 x float> %x, zeroinitializer
  %sel = select <4 x i1> %cmp, <4 x float> %y, <4 x float> zeroinitializer
  ret <4 x float> %sel
}

This should be an 'and' bitwise logic op, but:

$ ./llc  fsel.ll -o -  -mattr=avx
    vxorps    %xmm2, %xmm2, %xmm2
    vcmpeqps    %xmm2, %xmm0, %xmm0
    vblendvps    %xmm0, %xmm1, %xmm2, %xmm0
    retq


The optimization exists for AArch64:

$ ./llc  fsel.ll -o -  -mtriple=aarch64
    fcmeq    v0.4s, v0.4s, #0.0
    and    v0.16b, v1.16b, v0.16b
    ret

The optimization also exists for x86 FP scalar and x86 integer vector, so some
refactoring may be needed:

define float @fsel(float %x, float %y) {
  %cmp = fcmp oeq float %x, 0.0
  %sel = select i1 %cmp, float %y, float 0.0
  ret float %sel
}

define <4 x i32> @iselvec(<4 x i32> %x, <4 x i32> %y) {
  %cmp = icmp eq <4 x i32> %x, zeroinitializer
  %sel = select <4 x i1> %cmp, <4 x i32> %y, <4 x i32> zeroinitializer
  ret <4 x i32> %sel
}

_fsel:                                  ## @fsel
    vxorps    %xmm2, %xmm2, %xmm2
    vcmpeqss    %xmm2, %xmm0, %xmm0
    vandps    %xmm1, %xmm0, %xmm0
    retq

_iselvec:                               ## @iselvec
    vpxor    %xmm2, %xmm2, %xmm2
    vpcmpeqd    %xmm2, %xmm0, %xmm0
    vpand    %xmm1, %xmm0, %xmm0
    retq

-- 
You are receiving this mail because:
You are on the CC list for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-bugs/attachments/20160807/7eda2896/attachment.html>