[llvm-bugs] [Bug 40332] New: [x86, AVX512] failed to merge mask select across extract_subvector

[via llvm-bugs]

https://bugs.llvm.org/show_bug.cgi?id=40332

            Bug ID: 40332
           Summary: [x86, AVX512] failed to merge mask select across
                    extract_subvector
           Product: libraries
           Version: trunk
          Hardware: PC
                OS: All
            Status: NEW
          Severity: enhancement
          Priority: P
         Component: Backend: X86
          Assignee: unassignedbugs at nondot.org
          Reporter: spatel+llvm at rotateright.com
                CC: craig.topper at gmail.com, llvm-bugs at lists.llvm.org,
                    llvm-dev at redking.me.uk, spatel+llvm at rotateright.com

As noted in https://reviews.llvm.org/D56756 - we have this and similar
regression tests in test/CodeGen/X86/avx512-shuffles/partial_permute.ll:

define <4 x i32> @test_masked_z_8xi32_to_4xi32_perm_mask3(<8 x i32> %vec, <4 x
i32> %mask) {
; CHECK-LABEL: test_masked_z_8xi32_to_4xi32_perm_mask3:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovdqa {{.*#+}} ymm2 = <5,3,2,5,u,u,u,u>
; CHECK-NEXT:    vpermd %ymm0, %ymm2, %ymm0
; CHECK-NEXT:    vptestnmd %xmm1, %xmm1, %k1
; CHECK-NEXT:    vmovdqa32 %xmm0, %xmm0 {%k1} {z}
; CHECK-NEXT:    vzeroupper
; CHECK-NEXT:    retq
  %shuf = shufflevector <8 x i32> %vec, <8 x i32> undef, <4 x i32> <i32 5, i32
3, i32 2, i32 5>
  %cmp = icmp eq <4 x i32> %mask, zeroinitializer
  %res = select <4 x i1> %cmp, <4 x i32> %shuf, <4 x i32> zeroinitializer
  ret <4 x i32> %res
}

Ideally, the masking would be included in the shuffle:

vmovdqa {{.*#+}} ymm2 = <5,3,2,5,u,u,u,u>
vptestnmd %xmm1, %xmm1, %k1
vpermd %ymm0, %ymm2, %ymm0 {%k1} {z}

-- 
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/20190116/22de141e/attachment.html>