[X86] vselect.ll - add vXi8 select-by-constant tests with repeated/broadcastable shuffle mask

Author: RKSimon

llvm/test/CodeGen/X86/vselect.ll

@@ -1,8 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefixes=SSE,SSE2
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefixes=SSE,SSE41
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX1
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2
 
 ; Verify that we don't emit packed vector shifts instructions if the
 ; condition used by the vector select is a vector of constants.
@@ -425,6 +425,79 @@ define <2 x i64> @test25(<2 x i64> %a, <2 x i64> %b) {
   ret <2 x i64> %1
 }
 
+define <16 x i8> @test26(<16 x i8> %a, <16 x i8> %b) {
+; SSE2-LABEL: test26:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movaps {{.*#+}} xmm2 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
+; SSE2-NEXT:    andps %xmm2, %xmm1
+; SSE2-NEXT:    andnps %xmm0, %xmm2
+; SSE2-NEXT:    orps %xmm1, %xmm2
+; SSE2-NEXT:    movaps %xmm2, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSE41-LABEL: test26:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movdqa %xmm0, %xmm2
+; SSE41-NEXT:    movaps {{.*#+}} xmm0 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
+; SSE41-NEXT:    pblendvb %xmm0, %xmm1, %xmm2
+; SSE41-NEXT:    movdqa %xmm2, %xmm0
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: test26:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vbroadcastss {{.*#+}} xmm2 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
+; AVX1-NEXT:    vpblendvb %xmm2, %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: test26:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vpbroadcastw {{.*#+}} xmm2 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
+; AVX2-NEXT:    vpblendvb %xmm2, %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    retq
+  %1 = select <16 x i1> <i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true>, <16 x i8> %a, <16 x i8> %b
+  ret <16 x i8> %1
+}
+
+define <32 x i8> @test27(<32 x i8> %a, <32 x i8> %b) {
+; SSE2-LABEL: test27:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movaps {{.*#+}} xmm4 = [255,0,0,255,255,0,0,255,255,0,0,255,255,0,0,255]
+; SSE2-NEXT:    movaps %xmm4, %xmm5
+; SSE2-NEXT:    andnps %xmm2, %xmm5
+; SSE2-NEXT:    andps %xmm4, %xmm0
+; SSE2-NEXT:    orps %xmm5, %xmm0
+; SSE2-NEXT:    andps %xmm4, %xmm1
+; SSE2-NEXT:    andnps %xmm3, %xmm4
+; SSE2-NEXT:    orps %xmm4, %xmm1
+; SSE2-NEXT:    retq
+;
+; SSE41-LABEL: test27:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movdqa %xmm0, %xmm4
+; SSE41-NEXT:    movaps {{.*#+}} xmm0 = [255,0,0,255,255,0,0,255,255,0,0,255,255,0,0,255]
+; SSE41-NEXT:    pblendvb %xmm0, %xmm4, %xmm2
+; SSE41-NEXT:    pblendvb %xmm0, %xmm1, %xmm3
+; SSE41-NEXT:    movdqa %xmm2, %xmm0
+; SSE41-NEXT:    movdqa %xmm3, %xmm1
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: test27:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vbroadcastss {{.*#+}} ymm2 = [255,0,0,255,255,0,0,255,255,0,0,255,255,0,0,255,255,0,0,255,255,0,0,255,255,0,0,255,255,0,0,255]
+; AVX1-NEXT:    vandnps %ymm1, %ymm2, %ymm1
+; AVX1-NEXT:    vandps %ymm2, %ymm0, %ymm0
+; AVX1-NEXT:    vorps %ymm1, %ymm0, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: test27:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vpbroadcastd {{.*#+}} ymm2 = [255,0,0,255,255,0,0,255,255,0,0,255,255,0,0,255,255,0,0,255,255,0,0,255,255,0,0,255,255,0,0,255]
+; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
+; AVX2-NEXT:    retq
+  %1 = select <32 x i1> <i1 true, i1 false, i1 false, i1 true, i1 true, i1 false, i1 false, i1 true, i1 true, i1 false, i1 false, i1 true, i1 true, i1 false, i1 false, i1 true, i1 true, i1 false, i1 false, i1 true, i1 true, i1 false, i1 false, i1 true, i1 true, i1 false, i1 false, i1 true, i1 true, i1 false, i1 false, i1 true>, <32 x i8> %a, <32 x i8> %b
+  ret <32 x i8> %1
+}
+
 define <4 x float> @select_of_shuffles_0(<2 x float> %a0, <2 x float> %b0, <2 x float> %a1, <2 x float> %b1) {
 ; SSE-LABEL: select_of_shuffles_0:
 ; SSE:       # %bb.0: