[X86] vector-reduce-add-mask.ll - add missing AVX512BW/BWVL check prefixes

Author: RKSimon

llvm/test/CodeGen/X86/vector-reduce-add-mask.ll

@@ -4,8 +4,8 @@
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX1,AVX1-SLOW
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+fast-hops | FileCheck %s --check-prefixes=AVX,AVX1,AVX1-FAST
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=AVX,AVX512
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw,+avx512vl | FileCheck %s --check-prefixes=AVX,AVX512
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=AVX,AVX512,AVX512BW
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw,+avx512vl | FileCheck %s --check-prefixes=AVX,AVX512,AVX512BWVL
 
 ;
 ; vXi64
@@ -860,6 +860,31 @@ define i16 @test_v4i16_v4i8(<4 x i16> %a0) {
 ; AVX2-NEXT:    vmovd %xmm0, %eax
 ; AVX2-NEXT:    # kill: def $ax killed $ax killed $eax
 ; AVX2-NEXT:    retq
+;
+; AVX512BW-LABEL: test_v4i16_v4i8:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; AVX512BW-NEXT:    vmovdqa {{.*#+}} xmm1 = <0,1,2,3,u,u,u,u>
+; AVX512BW-NEXT:    vpsrlvw %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
+; AVX512BW-NEXT:    vpaddw %xmm1, %xmm0, %xmm0
+; AVX512BW-NEXT:    vpsrld $16, %xmm0, %xmm1
+; AVX512BW-NEXT:    vpaddw %xmm1, %xmm0, %xmm0
+; AVX512BW-NEXT:    vmovd %xmm0, %eax
+; AVX512BW-NEXT:    # kill: def $ax killed $ax killed $eax
+; AVX512BW-NEXT:    vzeroupper
+; AVX512BW-NEXT:    retq
+;
+; AVX512BWVL-LABEL: test_v4i16_v4i8:
+; AVX512BWVL:       # %bb.0:
+; AVX512BWVL-NEXT:    vpsrlvw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
+; AVX512BWVL-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
+; AVX512BWVL-NEXT:    vpaddw %xmm1, %xmm0, %xmm0
+; AVX512BWVL-NEXT:    vpsrld $16, %xmm0, %xmm1
+; AVX512BWVL-NEXT:    vpaddw %xmm1, %xmm0, %xmm0
+; AVX512BWVL-NEXT:    vmovd %xmm0, %eax
+; AVX512BWVL-NEXT:    # kill: def $ax killed $ax killed $eax
+; AVX512BWVL-NEXT:    retq
   %1 = lshr <4 x i16> %a0, <i16 0, i16 1, i16 2, i16 3>
   %2 = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> %1)
   ret i16 %2