[X86] Add test coverage for #141475

Author: RKSimon

llvm/test/CodeGen/X86/vector-shuffle-combining.ll

@@ -3546,6 +3546,65 @@ define <16 x i8> @PR107289(<16 x i8> %0) {
   ret <16 x i8> %res
 }
 
+define <8 x i16> @PR141475(i32 %in) {
+; SSE2-LABEL: PR141475:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movd %edi, %xmm0
+; SSE2-NEXT:    pslld $1, %xmm0
+; SSE2-NEXT:    xorps %xmm1, %xmm1
+; SSE2-NEXT:    movss {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3]
+; SSE2-NEXT:    pshuflw {{.*#+}} xmm0 = xmm1[0,0,0,0,4,5,6,7]
+; SSE2-NEXT:    retq
+;
+; SSSE3-LABEL: PR141475:
+; SSSE3:       # %bb.0:
+; SSSE3-NEXT:    movd %edi, %xmm0
+; SSSE3-NEXT:    pslld $1, %xmm0
+; SSSE3-NEXT:    xorps %xmm1, %xmm1
+; SSSE3-NEXT:    movss {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3]
+; SSSE3-NEXT:    pshuflw {{.*#+}} xmm0 = xmm1[0,0,0,0,4,5,6,7]
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: PR141475:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movd %edi, %xmm0
+; SSE41-NEXT:    pslld $1, %xmm0
+; SSE41-NEXT:    pxor %xmm1, %xmm1
+; SSE41-NEXT:    pblendw {{.*#+}} xmm1 = xmm0[0,1],xmm1[2,3,4,5,6,7]
+; SSE41-NEXT:    pshuflw {{.*#+}} xmm0 = xmm1[0,0,0,0,4,5,6,7]
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: PR141475:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovd %edi, %xmm0
+; AVX1-NEXT:    vpslld $1, %xmm0, %xmm0
+; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3,4,5,6,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    retq
+;
+; AVX2-SLOW-LABEL: PR141475:
+; AVX2-SLOW:       # %bb.0:
+; AVX2-SLOW-NEXT:    vmovd %edi, %xmm0
+; AVX2-SLOW-NEXT:    vpslld $1, %xmm0, %xmm0
+; AVX2-SLOW-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX2-SLOW-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3,4,5,6,7]
+; AVX2-SLOW-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
+; AVX2-SLOW-NEXT:    retq
+;
+; AVX2-FAST-LABEL: PR141475:
+; AVX2-FAST:       # %bb.0:
+; AVX2-FAST-NEXT:    vmovd %edi, %xmm0
+; AVX2-FAST-NEXT:    vpslld $1, %xmm0, %xmm0
+; AVX2-FAST-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX2-FAST-NEXT:    retq
+  %mul = shl i32 %in, 1
+  %vecinit = insertelement <4 x i32> zeroinitializer, i32 %mul, i64 0
+  %cast = bitcast <4 x i32> %vecinit to <8 x i16>
+  %shuf = shufflevector <8 x i16> %cast, <8 x i16> poison, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 5, i32 6, i32 7>
+  ret <8 x i16> %shuf
+}
+
 ; Test case reported on D105827
 define void @SpinningCube() {
 ; SSE2-LABEL: SpinningCube:
@@ -3654,9 +3713,9 @@ define void @autogen_SD25931() {
 ; CHECK-LABEL: autogen_SD25931:
 ; CHECK:       # %bb.0: # %BB
 ; CHECK-NEXT:    .p2align 4
-; CHECK-NEXT:  .LBB142_1: # %CF242
+; CHECK-NEXT:  .LBB143_1: # %CF242
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    jmp .LBB142_1
+; CHECK-NEXT:    jmp .LBB143_1
 BB:
   %Cmp16 = icmp uge <2 x i1> zeroinitializer, zeroinitializer
   %Shuff19 = shufflevector <2 x i1> zeroinitializer, <2 x i1> %Cmp16, <2 x i32> <i32 3, i32 1>