diff options
Diffstat (limited to 'llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle.ll')
| -rw-r--r-- | llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle.ll | 47 |
1 files changed, 13 insertions, 34 deletions
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle.ll b/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle.ll index 776f32dee74..9189fb4d18e 100644 --- a/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle.ll +++ b/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle.ll @@ -22,19 +22,9 @@ define <2 x i8> @g(<2 x i8> %x, <2 x i8> %y) { define <4 x i8> @h(<4 x i8> %x, <4 x i8> %y) { ; CHECK-LABEL: @h( -; CHECK-NEXT: [[X0:%.*]] = extractelement <4 x i8> [[X:%.*]], i32 0 -; CHECK-NEXT: [[X3:%.*]] = extractelement <4 x i8> [[X]], i32 3 -; CHECK-NEXT: [[Y1:%.*]] = extractelement <4 x i8> [[Y:%.*]], i32 1 -; CHECK-NEXT: [[Y2:%.*]] = extractelement <4 x i8> [[Y]], i32 2 -; CHECK-NEXT: [[X0X0:%.*]] = mul i8 [[X0]], [[X0]] -; CHECK-NEXT: [[X3X3:%.*]] = mul i8 [[X3]], [[X3]] -; CHECK-NEXT: [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]] -; CHECK-NEXT: [[Y2Y2:%.*]] = mul i8 [[Y2]], [[Y2]] -; CHECK-NEXT: [[INS1:%.*]] = insertelement <4 x i8> undef, i8 [[X0X0]], i32 0 -; CHECK-NEXT: [[INS2:%.*]] = insertelement <4 x i8> [[INS1]], i8 [[X3X3]], i32 1 -; CHECK-NEXT: [[INS3:%.*]] = insertelement <4 x i8> [[INS2]], i8 [[Y1Y1]], i32 2 -; CHECK-NEXT: [[INS4:%.*]] = insertelement <4 x i8> [[INS3]], i8 [[Y2Y2]], i32 3 -; CHECK-NEXT: ret <4 x i8> [[INS4]] +; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x i8> [[X:%.*]], <4 x i8> [[Y:%.*]], <4 x i32> <i32 0, i32 3, i32 5, i32 6> +; CHECK-NEXT: [[TMP2:%.*]] = mul <4 x i8> [[TMP1]], [[TMP1]] +; CHECK-NEXT: ret <4 x i8> [[TMP2]] ; %x0 = extractelement <4 x i8> %x, i32 0 %x3 = extractelement <4 x i8> %x, i32 3 @@ -53,16 +43,9 @@ define <4 x i8> @h(<4 x i8> %x, <4 x i8> %y) { define <4 x i8> @h_undef(<4 x i8> %x, <4 x i8> %y) { ; CHECK-LABEL: @h_undef( -; CHECK-NEXT: [[X3:%.*]] = extractelement <4 x i8> [[X:%.*]], i32 3 -; CHECK-NEXT: [[Y1:%.*]] = extractelement <4 x i8> [[Y:%.*]], i32 1 -; CHECK-NEXT: [[Y2:%.*]] = extractelement <4 x i8> [[Y]], i32 2 -; CHECK-NEXT: [[X3X3:%.*]] = mul i8 [[X3]], [[X3]] -; CHECK-NEXT: [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]] -; CHECK-NEXT: [[Y2Y2:%.*]] = mul i8 [[Y2]], [[Y2]] -; CHECK-NEXT: [[INS2:%.*]] = insertelement <4 x i8> undef, i8 [[X3X3]], i32 1 -; CHECK-NEXT: [[INS3:%.*]] = insertelement <4 x i8> [[INS2]], i8 [[Y1Y1]], i32 2 -; CHECK-NEXT: [[INS4:%.*]] = insertelement <4 x i8> [[INS3]], i8 [[Y2Y2]], i32 3 -; CHECK-NEXT: ret <4 x i8> [[INS4]] +; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x i8> [[X:%.*]], <4 x i8> [[Y:%.*]], <4 x i32> <i32 undef, i32 3, i32 5, i32 6> +; CHECK-NEXT: [[TMP2:%.*]] = mul <4 x i8> [[TMP1]], [[TMP1]] +; CHECK-NEXT: ret <4 x i8> [[TMP2]] ; %x0 = extractelement <4 x i8> undef, i32 0 %x3 = extractelement <4 x i8> %x, i32 3 @@ -81,17 +64,13 @@ define <4 x i8> @h_undef(<4 x i8> %x, <4 x i8> %y) { define i8 @i(<4 x i8> %x, <4 x i8> %y) { ; CHECK-LABEL: @i( -; CHECK-NEXT: [[X0:%.*]] = extractelement <4 x i8> [[X:%.*]], i32 0 -; CHECK-NEXT: [[X3:%.*]] = extractelement <4 x i8> [[X]], i32 3 -; CHECK-NEXT: [[Y1:%.*]] = extractelement <4 x i8> [[Y:%.*]], i32 1 -; CHECK-NEXT: [[Y2:%.*]] = extractelement <4 x i8> [[Y]], i32 2 -; CHECK-NEXT: [[X0X0:%.*]] = mul i8 [[X0]], [[X0]] -; CHECK-NEXT: [[X3X3:%.*]] = mul i8 [[X3]], [[X3]] -; CHECK-NEXT: [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]] -; CHECK-NEXT: [[Y2Y2:%.*]] = mul i8 [[Y2]], [[Y2]] -; CHECK-NEXT: [[TMP1:%.*]] = add i8 [[X0X0]], [[X3X3]] -; CHECK-NEXT: [[TMP2:%.*]] = add i8 [[Y1Y1]], [[Y2Y2]] -; CHECK-NEXT: [[TMP3:%.*]] = add i8 [[TMP1]], [[TMP2]] +; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x i8> [[X:%.*]], <4 x i8> [[Y:%.*]], <4 x i32> <i32 0, i32 3, i32 5, i32 6> +; CHECK-NEXT: [[TMP2:%.*]] = mul <4 x i8> [[TMP1]], [[TMP1]] +; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i8> [[TMP2]], <4 x i8> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef> +; CHECK-NEXT: [[BIN_RDX:%.*]] = add <4 x i8> [[TMP2]], [[RDX_SHUF]] +; CHECK-NEXT: [[RDX_SHUF1:%.*]] = shufflevector <4 x i8> [[BIN_RDX]], <4 x i8> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> +; CHECK-NEXT: [[BIN_RDX2:%.*]] = add <4 x i8> [[BIN_RDX]], [[RDX_SHUF1]] +; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x i8> [[BIN_RDX2]], i32 0 ; CHECK-NEXT: ret i8 [[TMP3]] ; %x0 = extractelement <4 x i8> %x, i32 0 |
