llvm/llvm/test/CodeGen/X86/pr48215.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx      | FileCheck %s --check-prefixes=AVX1
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx2     | FileCheck %s --check-prefixes=AVX2
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx512vl | FileCheck %s --check-prefixes=AVX512

; FIXME: Ensure when we merge broadcasts to different widths that they come from the same SDValue.
define i32 @PR48215(i32 %a0, i32 %a1)  {
; AVX1-LABEL: PR48215:
; AVX1:       ## %bb.0:
; AVX1-NEXT:    movl %edi, %eax
; AVX1-NEXT:    cltd
; AVX1-NEXT:    idivl %esi
; AVX1-NEXT:    vmovd %edx, %xmm0
; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,0,0,0]
; AVX1-NEXT:    vpmovsxbd {{.*#+}} xmm1 = [4,5,6,7]
; AVX1-NEXT:    vmovd %eax, %xmm2
; AVX1-NEXT:    vpshufd {{.*#+}} xmm2 = xmm2[0,0,0,0]
; AVX1-NEXT:    vpcmpgtd %xmm2, %xmm1, %xmm3
; AVX1-NEXT:    vpmovsxbd {{.*#+}} xmm4 = [0,1,2,3]
; AVX1-NEXT:    vpcmpgtd %xmm2, %xmm4, %xmm2
; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm2, %ymm2
; AVX1-NEXT:    vmovmskps %ymm2, %ecx
; AVX1-NEXT:    vpcmpgtd %xmm0, %xmm1, %xmm0
; AVX1-NEXT:    vmovmskps %xmm0, %eax
; AVX1-NEXT:    addl %ecx, %eax
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX2-LABEL: PR48215:
; AVX2:       ## %bb.0:
; AVX2-NEXT:    movl %edi, %eax
; AVX2-NEXT:    cltd
; AVX2-NEXT:    idivl %esi
; AVX2-NEXT:    vmovd %eax, %xmm0
; AVX2-NEXT:    vpbroadcastd %xmm0, %ymm0
; AVX2-NEXT:    vmovd %edx, %xmm1
; AVX2-NEXT:    vpbroadcastd %xmm1, %xmm1
; AVX2-NEXT:    vpcmpgtd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %ymm0
; AVX2-NEXT:    vmovmskps %ymm0, %ecx
; AVX2-NEXT:    xorl $255, %ecx
; AVX2-NEXT:    vpcmpgtd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm0
; AVX2-NEXT:    vmovmskps %xmm0, %eax
; AVX2-NEXT:    xorl $15, %eax
; AVX2-NEXT:    addl %ecx, %eax
; AVX2-NEXT:    vzeroupper
; AVX2-NEXT:    retq
;
; AVX512-LABEL: PR48215:
; AVX512:       ## %bb.0:
; AVX512-NEXT:    movl %edi, %eax
; AVX512-NEXT:    cltd
; AVX512-NEXT:    idivl %esi
; AVX512-NEXT:    vpbroadcastd %eax, %ymm0
; AVX512-NEXT:    vpbroadcastd %edx, %xmm1
; AVX512-NEXT:    vpcmpltd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %k0
; AVX512-NEXT:    vpcmpltd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %k1
; AVX512-NEXT:    kmovw %k0, %eax
; AVX512-NEXT:    movzbl %al, %ecx
; AVX512-NEXT:    kmovw %k1, %eax
; AVX512-NEXT:    addl %ecx, %eax
; AVX512-NEXT:    vzeroupper
; AVX512-NEXT:    retq
  %d = sdiv i32 %a0, %a1
  %r = srem i32 %a0, %a1
  %dv0 = insertelement <8 x i32> undef, i32 %d, i32 0
  %rv0 = insertelement <4 x i32> undef, i32 %r, i32 0
  %dv1 = shufflevector <8 x i32> %dv0, <8 x i32> undef, <8 x i32> zeroinitializer
  %rv1 = shufflevector <4 x i32> %rv0, <4 x i32> undef, <4 x i32> zeroinitializer
  %dc0 = icmp slt <8 x i32> %dv1, <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
  %rc0 = icmp slt <4 x i32> %rv1, <i32 4, i32 5, i32 6, i32 7>
  %db0 = bitcast <8 x i1> %dc0 to i8
  %rb0 = bitcast <4 x i1> %rc0 to i4
  %db1 = zext i8 %db0 to i32
  %rb1 = zext i4 %rb0 to i32
  %res = add i32 %db1, %rb1
  ret i32 %res
}