diff options
Diffstat (limited to 'llvm/test/Transforms/SLPVectorizer/X86/jumbled-load.ll')
-rw-r--r-- | llvm/test/Transforms/SLPVectorizer/X86/jumbled-load.ll | 51 |
1 files changed, 23 insertions, 28 deletions
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/jumbled-load.ll b/llvm/test/Transforms/SLPVectorizer/X86/jumbled-load.ll index 779ca53b4df..4887fe6c5f9 100644 --- a/llvm/test/Transforms/SLPVectorizer/X86/jumbled-load.ll +++ b/llvm/test/Transforms/SLPVectorizer/X86/jumbled-load.ll @@ -6,33 +6,26 @@ define i32 @jumbled-load(i32* noalias nocapture %in, i32* noalias nocapture %inn, i32* noalias nocapture %out) { ; CHECK-LABEL: @jumbled-load( ; CHECK-NEXT: [[IN_ADDR:%.*]] = getelementptr inbounds i32, i32* [[IN:%.*]], i64 0 -; CHECK-NEXT: [[LOAD_1:%.*]] = load i32, i32* [[IN_ADDR]], align 4 ; CHECK-NEXT: [[GEP_1:%.*]] = getelementptr inbounds i32, i32* [[IN_ADDR]], i64 3 -; CHECK-NEXT: [[LOAD_2:%.*]] = load i32, i32* [[GEP_1]], align 4 ; CHECK-NEXT: [[GEP_2:%.*]] = getelementptr inbounds i32, i32* [[IN_ADDR]], i64 1 -; CHECK-NEXT: [[LOAD_3:%.*]] = load i32, i32* [[GEP_2]], align 4 ; CHECK-NEXT: [[GEP_3:%.*]] = getelementptr inbounds i32, i32* [[IN_ADDR]], i64 2 -; CHECK-NEXT: [[LOAD_4:%.*]] = load i32, i32* [[GEP_3]], align 4 +; CHECK-NEXT: [[TMP1:%.*]] = bitcast i32* [[IN_ADDR]] to <4 x i32>* +; CHECK-NEXT: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP1]], align 4 +; CHECK-NEXT: [[REORDER_SHUFFLE:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 2, i32 0> ; CHECK-NEXT: [[INN_ADDR:%.*]] = getelementptr inbounds i32, i32* [[INN:%.*]], i64 0 -; CHECK-NEXT: [[LOAD_5:%.*]] = load i32, i32* [[INN_ADDR]], align 4 ; CHECK-NEXT: [[GEP_4:%.*]] = getelementptr inbounds i32, i32* [[INN_ADDR]], i64 2 -; CHECK-NEXT: [[LOAD_6:%.*]] = load i32, i32* [[GEP_4]], align 4 ; CHECK-NEXT: [[GEP_5:%.*]] = getelementptr inbounds i32, i32* [[INN_ADDR]], i64 3 -; CHECK-NEXT: [[LOAD_7:%.*]] = load i32, i32* [[GEP_5]], align 4 ; CHECK-NEXT: [[GEP_6:%.*]] = getelementptr inbounds i32, i32* [[INN_ADDR]], i64 1 -; CHECK-NEXT: [[LOAD_8:%.*]] = load i32, i32* [[GEP_6]], align 4 -; CHECK-NEXT: [[MUL_1:%.*]] = mul i32 [[LOAD_3]], [[LOAD_5]] -; CHECK-NEXT: [[MUL_2:%.*]] = mul i32 [[LOAD_2]], [[LOAD_8]] -; CHECK-NEXT: [[MUL_3:%.*]] = mul i32 [[LOAD_4]], [[LOAD_7]] -; CHECK-NEXT: [[MUL_4:%.*]] = mul i32 [[LOAD_1]], [[LOAD_6]] +; CHECK-NEXT: [[TMP3:%.*]] = bitcast i32* [[INN_ADDR]] to <4 x i32>* +; CHECK-NEXT: [[TMP4:%.*]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4 +; CHECK-NEXT: [[REORDER_SHUFFLE1:%.*]] = shufflevector <4 x i32> [[TMP4]], <4 x i32> undef, <4 x i32> <i32 0, i32 1, i32 3, i32 2> +; CHECK-NEXT: [[TMP5:%.*]] = mul <4 x i32> [[REORDER_SHUFFLE]], [[REORDER_SHUFFLE1]] ; CHECK-NEXT: [[GEP_7:%.*]] = getelementptr inbounds i32, i32* [[OUT:%.*]], i64 0 -; CHECK-NEXT: store i32 [[MUL_1]], i32* [[GEP_7]], align 4 ; CHECK-NEXT: [[GEP_8:%.*]] = getelementptr inbounds i32, i32* [[OUT]], i64 1 -; CHECK-NEXT: store i32 [[MUL_2]], i32* [[GEP_8]], align 4 ; CHECK-NEXT: [[GEP_9:%.*]] = getelementptr inbounds i32, i32* [[OUT]], i64 2 -; CHECK-NEXT: store i32 [[MUL_3]], i32* [[GEP_9]], align 4 ; CHECK-NEXT: [[GEP_10:%.*]] = getelementptr inbounds i32, i32* [[OUT]], i64 3 -; CHECK-NEXT: store i32 [[MUL_4]], i32* [[GEP_10]], align 4 +; CHECK-NEXT: [[TMP6:%.*]] = bitcast i32* [[GEP_7]] to <4 x i32>* +; CHECK-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP6]], align 4 ; CHECK-NEXT: ret i32 undef ; %in.addr = getelementptr inbounds i32, i32* %in, i64 0 @@ -71,25 +64,27 @@ define i32 @jumbled-load(i32* noalias nocapture %in, i32* noalias nocapture %inn define i32 @jumbled-load-multiuses(i32* noalias nocapture %in, i32* noalias nocapture %out) { ; CHECK-LABEL: @jumbled-load-multiuses( ; CHECK-NEXT: [[IN_ADDR:%.*]] = getelementptr inbounds i32, i32* [[IN:%.*]], i64 0 -; CHECK-NEXT: [[LOAD_1:%.*]] = load i32, i32* [[IN_ADDR]], align 4 ; CHECK-NEXT: [[GEP_1:%.*]] = getelementptr inbounds i32, i32* [[IN_ADDR]], i64 3 -; CHECK-NEXT: [[LOAD_2:%.*]] = load i32, i32* [[GEP_1]], align 4 ; CHECK-NEXT: [[GEP_2:%.*]] = getelementptr inbounds i32, i32* [[IN_ADDR]], i64 1 -; CHECK-NEXT: [[LOAD_3:%.*]] = load i32, i32* [[GEP_2]], align 4 ; CHECK-NEXT: [[GEP_3:%.*]] = getelementptr inbounds i32, i32* [[IN_ADDR]], i64 2 -; CHECK-NEXT: [[LOAD_4:%.*]] = load i32, i32* [[GEP_3]], align 4 -; CHECK-NEXT: [[MUL_1:%.*]] = mul i32 [[LOAD_3]], [[LOAD_4]] -; CHECK-NEXT: [[MUL_2:%.*]] = mul i32 [[LOAD_2]], [[LOAD_2]] -; CHECK-NEXT: [[MUL_3:%.*]] = mul i32 [[LOAD_4]], [[LOAD_1]] -; CHECK-NEXT: [[MUL_4:%.*]] = mul i32 [[LOAD_1]], [[LOAD_3]] +; CHECK-NEXT: [[TMP1:%.*]] = bitcast i32* [[IN_ADDR]] to <4 x i32>* +; CHECK-NEXT: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP1]], align 4 +; CHECK-NEXT: [[REORDER_SHUFFLE:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 2, i32 0> +; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x i32> [[REORDER_SHUFFLE]], i32 2 +; CHECK-NEXT: [[TMP4:%.*]] = insertelement <4 x i32> undef, i32 [[TMP3]], i32 0 +; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x i32> [[REORDER_SHUFFLE]], i32 1 +; CHECK-NEXT: [[TMP6:%.*]] = insertelement <4 x i32> [[TMP4]], i32 [[TMP5]], i32 1 +; CHECK-NEXT: [[TMP7:%.*]] = extractelement <4 x i32> [[REORDER_SHUFFLE]], i32 3 +; CHECK-NEXT: [[TMP8:%.*]] = insertelement <4 x i32> [[TMP6]], i32 [[TMP7]], i32 2 +; CHECK-NEXT: [[TMP9:%.*]] = extractelement <4 x i32> [[REORDER_SHUFFLE]], i32 0 +; CHECK-NEXT: [[TMP10:%.*]] = insertelement <4 x i32> [[TMP8]], i32 [[TMP9]], i32 3 +; CHECK-NEXT: [[TMP11:%.*]] = mul <4 x i32> [[REORDER_SHUFFLE]], [[TMP10]] ; CHECK-NEXT: [[GEP_7:%.*]] = getelementptr inbounds i32, i32* [[OUT:%.*]], i64 0 -; CHECK-NEXT: store i32 [[MUL_1]], i32* [[GEP_7]], align 4 ; CHECK-NEXT: [[GEP_8:%.*]] = getelementptr inbounds i32, i32* [[OUT]], i64 1 -; CHECK-NEXT: store i32 [[MUL_2]], i32* [[GEP_8]], align 4 ; CHECK-NEXT: [[GEP_9:%.*]] = getelementptr inbounds i32, i32* [[OUT]], i64 2 -; CHECK-NEXT: store i32 [[MUL_3]], i32* [[GEP_9]], align 4 ; CHECK-NEXT: [[GEP_10:%.*]] = getelementptr inbounds i32, i32* [[OUT]], i64 3 -; CHECK-NEXT: store i32 [[MUL_4]], i32* [[GEP_10]], align 4 +; CHECK-NEXT: [[TMP12:%.*]] = bitcast i32* [[GEP_7]] to <4 x i32>* +; CHECK-NEXT: store <4 x i32> [[TMP11]], <4 x i32>* [[TMP12]], align 4 ; CHECK-NEXT: ret i32 undef ; %in.addr = getelementptr inbounds i32, i32* %in, i64 0 |