68 changes: 34 additions & 34 deletions llvm/test/Transforms/SLPVectorizer/AArch64/matmul.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -17,58 +17,58 @@ define void @wrap_mul4(double* nocapture %Out, [2 x double]* nocapture readonly
; CHECK-NEXT: [[TEMP2:%.*]] = load double, double* [[ARRAYIDX5_I]], align 8
; CHECK-NEXT: [[ARRAYIDX7_I:%.*]] = getelementptr inbounds [4 x double], [4 x double]* [[B]], i64 1, i64 0
; CHECK-NEXT: [[ARRAYIDX13_I:%.*]] = getelementptr inbounds [4 x double], [4 x double]* [[B]], i64 0, i64 1
; CHECK-NEXT: [[ARRAYIDX18_I:%.*]] = getelementptr inbounds [4 x double], [4 x double]* [[B]], i64 1, i64 1
; CHECK-NEXT: [[ARRAYIDX25_I:%.*]] = getelementptr inbounds [4 x double], [4 x double]* [[B]], i64 0, i64 2
; CHECK-NEXT: [[ARRAYIDX30_I:%.*]] = getelementptr inbounds [4 x double], [4 x double]* [[B]], i64 1, i64 2
; CHECK-NEXT: [[ARRAYIDX37_I:%.*]] = getelementptr inbounds [4 x double], [4 x double]* [[B]], i64 0, i64 3
; CHECK-NEXT: [[ARRAYIDX42_I:%.*]] = getelementptr inbounds [4 x double], [4 x double]* [[B]], i64 1, i64 3
; CHECK-NEXT: [[ARRAYIDX47_I:%.*]] = getelementptr inbounds [2 x double], [2 x double]* [[A]], i64 1, i64 0
; CHECK-NEXT: [[TEMP10:%.*]] = load double, double* [[ARRAYIDX47_I]], align 8
; CHECK-NEXT: [[ARRAYIDX52_I:%.*]] = getelementptr inbounds [2 x double], [2 x double]* [[A]], i64 1, i64 1
; CHECK-NEXT: [[TEMP11:%.*]] = load double, double* [[ARRAYIDX52_I]], align 8
; CHECK-NEXT: [[RES_I_SROA_4_0_OUT2_I_SROA_IDX2:%.*]] = getelementptr inbounds double, double* [[OUT:%.*]], i64 1
; CHECK-NEXT: [[TMP1:%.*]] = bitcast double* [[ARRAYIDX3_I]] to <2 x double>*
; CHECK-NEXT: [[TMP2:%.*]] = load <2 x double>, <2 x double>* [[TMP1]], align 8
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <2 x double> poison, double [[TEMP]], i32 0
; CHECK-NEXT: [[TMP4:%.*]] = insertelement <2 x double> [[TMP3]], double [[TEMP]], i32 1
; CHECK-NEXT: [[TMP5:%.*]] = fmul <2 x double> [[TMP4]], [[TMP2]]
; CHECK-NEXT: [[ARRAYIDX18_I:%.*]] = getelementptr inbounds [4 x double], [4 x double]* [[B]], i64 1, i64 1
; CHECK-NEXT: [[TMP6:%.*]] = bitcast double* [[ARRAYIDX7_I]] to <2 x double>*
; CHECK-NEXT: [[TMP7:%.*]] = load <2 x double>, <2 x double>* [[TMP6]], align 8
; CHECK-NEXT: [[TMP8:%.*]] = insertelement <2 x double> poison, double [[TEMP2]], i32 0
; CHECK-NEXT: [[TMP9:%.*]] = insertelement <2 x double> [[TMP8]], double [[TEMP2]], i32 1
; CHECK-NEXT: [[TMP10:%.*]] = fmul <2 x double> [[TMP9]], [[TMP7]]
; CHECK-NEXT: [[TMP11:%.*]] = fadd <2 x double> [[TMP5]], [[TMP10]]
; CHECK-NEXT: [[ARRAYIDX25_I:%.*]] = getelementptr inbounds [4 x double], [4 x double]* [[B]], i64 0, i64 2
; CHECK-NEXT: [[ARRAYIDX30_I:%.*]] = getelementptr inbounds [4 x double], [4 x double]* [[B]], i64 1, i64 2
; CHECK-NEXT: [[ARRAYIDX37_I:%.*]] = getelementptr inbounds [4 x double], [4 x double]* [[B]], i64 0, i64 3
; CHECK-NEXT: [[TMP12:%.*]] = bitcast double* [[ARRAYIDX25_I]] to <2 x double>*
; CHECK-NEXT: [[TMP13:%.*]] = load <2 x double>, <2 x double>* [[TMP12]], align 8
; CHECK-NEXT: [[TMP14:%.*]] = fmul <2 x double> [[TMP4]], [[TMP13]]
; CHECK-NEXT: [[ARRAYIDX42_I:%.*]] = getelementptr inbounds [4 x double], [4 x double]* [[B]], i64 1, i64 3
; CHECK-NEXT: [[TMP15:%.*]] = bitcast double* [[ARRAYIDX30_I]] to <2 x double>*
; CHECK-NEXT: [[TMP16:%.*]] = load <2 x double>, <2 x double>* [[TMP15]], align 8
; CHECK-NEXT: [[TMP17:%.*]] = fmul <2 x double> [[TMP9]], [[TMP16]]
; CHECK-NEXT: [[TMP18:%.*]] = fadd <2 x double> [[TMP14]], [[TMP17]]
; CHECK-NEXT: [[ARRAYIDX47_I:%.*]] = getelementptr inbounds [2 x double], [2 x double]* [[A]], i64 1, i64 0
; CHECK-NEXT: [[TEMP10:%.*]] = load double, double* [[ARRAYIDX47_I]], align 8
; CHECK-NEXT: [[ARRAYIDX52_I:%.*]] = getelementptr inbounds [2 x double], [2 x double]* [[A]], i64 1, i64 1
; CHECK-NEXT: [[TEMP11:%.*]] = load double, double* [[ARRAYIDX52_I]], align 8
; CHECK-NEXT: [[TMP19:%.*]] = insertelement <2 x double> poison, double [[TEMP10]], i32 0
; CHECK-NEXT: [[TMP20:%.*]] = insertelement <2 x double> [[TMP19]], double [[TEMP10]], i32 1
; CHECK-NEXT: [[TMP21:%.*]] = fmul <2 x double> [[TMP2]], [[TMP20]]
; CHECK-NEXT: [[TMP22:%.*]] = insertelement <2 x double> poison, double [[TEMP11]], i32 0
; CHECK-NEXT: [[TMP23:%.*]] = insertelement <2 x double> [[TMP22]], double [[TEMP11]], i32 1
; CHECK-NEXT: [[TMP24:%.*]] = fmul <2 x double> [[TMP7]], [[TMP23]]
; CHECK-NEXT: [[TMP25:%.*]] = fadd <2 x double> [[TMP21]], [[TMP24]]
; CHECK-NEXT: [[TMP26:%.*]] = fmul <2 x double> [[TMP13]], [[TMP20]]
; CHECK-NEXT: [[TMP27:%.*]] = fmul <2 x double> [[TMP16]], [[TMP23]]
; CHECK-NEXT: [[TMP28:%.*]] = fadd <2 x double> [[TMP26]], [[TMP27]]
; CHECK-NEXT: [[RES_I_SROA_4_0_OUT2_I_SROA_IDX2:%.*]] = getelementptr inbounds double, double* [[OUT:%.*]], i64 1
; CHECK-NEXT: [[TMP29:%.*]] = bitcast double* [[OUT]] to <2 x double>*
; CHECK-NEXT: store <2 x double> [[TMP11]], <2 x double>* [[TMP29]], align 8
; CHECK-NEXT: [[TMP12:%.*]] = bitcast double* [[OUT]] to <2 x double>*
; CHECK-NEXT: [[RES_I_SROA_5_0_OUT2_I_SROA_IDX4:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 2
; CHECK-NEXT: [[RES_I_SROA_6_0_OUT2_I_SROA_IDX6:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 3
; CHECK-NEXT: [[TMP30:%.*]] = bitcast double* [[RES_I_SROA_5_0_OUT2_I_SROA_IDX4]] to <2 x double>*
; CHECK-NEXT: store <2 x double> [[TMP18]], <2 x double>* [[TMP30]], align 8
; CHECK-NEXT: [[TMP13:%.*]] = bitcast double* [[ARRAYIDX25_I]] to <2 x double>*
; CHECK-NEXT: [[TMP14:%.*]] = load <2 x double>, <2 x double>* [[TMP13]], align 8
; CHECK-NEXT: [[TMP15:%.*]] = fmul <2 x double> [[TMP4]], [[TMP14]]
; CHECK-NEXT: [[TMP16:%.*]] = bitcast double* [[ARRAYIDX30_I]] to <2 x double>*
; CHECK-NEXT: [[TMP17:%.*]] = load <2 x double>, <2 x double>* [[TMP16]], align 8
; CHECK-NEXT: [[TMP18:%.*]] = fmul <2 x double> [[TMP9]], [[TMP17]]
; CHECK-NEXT: [[TMP19:%.*]] = fadd <2 x double> [[TMP15]], [[TMP18]]
; CHECK-NEXT: store <2 x double> [[TMP11]], <2 x double>* [[TMP12]], align 8
; CHECK-NEXT: [[TMP20:%.*]] = bitcast double* [[RES_I_SROA_5_0_OUT2_I_SROA_IDX4]] to <2 x double>*
; CHECK-NEXT: store <2 x double> [[TMP19]], <2 x double>* [[TMP20]], align 8
; CHECK-NEXT: [[RES_I_SROA_7_0_OUT2_I_SROA_IDX8:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 4
; CHECK-NEXT: [[RES_I_SROA_8_0_OUT2_I_SROA_IDX10:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 5
; CHECK-NEXT: [[TMP31:%.*]] = bitcast double* [[RES_I_SROA_7_0_OUT2_I_SROA_IDX8]] to <2 x double>*
; CHECK-NEXT: store <2 x double> [[TMP25]], <2 x double>* [[TMP31]], align 8
; CHECK-NEXT: [[TMP21:%.*]] = insertelement <2 x double> poison, double [[TEMP10]], i32 0
; CHECK-NEXT: [[TMP22:%.*]] = insertelement <2 x double> [[TMP21]], double [[TEMP10]], i32 1
; CHECK-NEXT: [[TMP23:%.*]] = fmul <2 x double> [[TMP2]], [[TMP22]]
; CHECK-NEXT: [[TMP24:%.*]] = insertelement <2 x double> poison, double [[TEMP11]], i32 0
; CHECK-NEXT: [[TMP25:%.*]] = insertelement <2 x double> [[TMP24]], double [[TEMP11]], i32 1
; CHECK-NEXT: [[TMP26:%.*]] = fmul <2 x double> [[TMP7]], [[TMP25]]
; CHECK-NEXT: [[TMP27:%.*]] = fadd <2 x double> [[TMP23]], [[TMP26]]
; CHECK-NEXT: [[TMP28:%.*]] = bitcast double* [[RES_I_SROA_7_0_OUT2_I_SROA_IDX8]] to <2 x double>*
; CHECK-NEXT: store <2 x double> [[TMP27]], <2 x double>* [[TMP28]], align 8
; CHECK-NEXT: [[RES_I_SROA_9_0_OUT2_I_SROA_IDX12:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 6
; CHECK-NEXT: [[RES_I_SROA_10_0_OUT2_I_SROA_IDX14:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 7
; CHECK-NEXT: [[TMP29:%.*]] = fmul <2 x double> [[TMP14]], [[TMP22]]
; CHECK-NEXT: [[TMP30:%.*]] = fmul <2 x double> [[TMP17]], [[TMP25]]
; CHECK-NEXT: [[TMP31:%.*]] = fadd <2 x double> [[TMP29]], [[TMP30]]
; CHECK-NEXT: [[TMP32:%.*]] = bitcast double* [[RES_I_SROA_9_0_OUT2_I_SROA_IDX12]] to <2 x double>*
; CHECK-NEXT: store <2 x double> [[TMP28]], <2 x double>* [[TMP32]], align 8
; CHECK-NEXT: store <2 x double> [[TMP31]], <2 x double>* [[TMP32]], align 8
; CHECK-NEXT: ret void
;
%arrayidx1.i = getelementptr inbounds [2 x double], [2 x double]* %A, i64 0, i64 0
Expand Down
12 changes: 6 additions & 6 deletions llvm/test/Transforms/SLPVectorizer/AArch64/memory-runtime-checks.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -326,10 +326,10 @@ define void @no_version(i32* nocapture %dst, i32* nocapture readonly %src) {
; CHECK-LABEL: @no_version(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[SRC_GEP_1:%.*]] = getelementptr inbounds i32, i32* [[SRC:%.*]], i64 1
; CHECK-NEXT: [[DST_GEP_1:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 1
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[SRC]] to <2 x i32>*
; CHECK-NEXT: [[TMP1:%.*]] = load <2 x i32>, <2 x i32>* [[TMP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = ashr <2 x i32> [[TMP1]], <i32 16, i32 16>
; CHECK-NEXT: [[DST_GEP_1:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 1
; CHECK-NEXT: [[TMP3:%.*]] = bitcast i32* [[DST]] to <2 x i32>*
; CHECK-NEXT: store <2 x i32> [[TMP2]], <2 x i32>* [[TMP3]], align 4
; CHECK-NEXT: ret void
Expand Down Expand Up @@ -902,12 +902,7 @@ define i32 @block_partly_vectorized_without_versioning(%struct.spam* readonly %a
; CHECK-NEXT: [[A_GEP_14:%.*]] = getelementptr i8, i8* [[A]], i64 14
; CHECK-NEXT: [[B_GEP_14:%.*]] = getelementptr i8, i8* [[B]], i64 14
; CHECK-NEXT: [[A_GEP_15:%.*]] = getelementptr i8, i8* [[A]], i64 15
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[A_GEP_0]] to <16 x i8>*
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* [[TMP0]], align 1
; CHECK-NEXT: [[B_GEP_15:%.*]] = getelementptr i8, i8* [[B]], i64 15
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i8* [[B_GEP_0]] to <16 x i8>*
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* [[TMP2]], align 1
; CHECK-NEXT: [[TMP4:%.*]] = xor <16 x i8> [[TMP1]], [[TMP3]]
; CHECK-NEXT: [[R_GEP_0:%.*]] = getelementptr i8, i8* [[ARG1]], i64 0
; CHECK-NEXT: [[R_GEP_1:%.*]] = getelementptr i8, i8* [[ARG1]], i64 1
; CHECK-NEXT: [[R_GEP_2:%.*]] = getelementptr i8, i8* [[ARG1]], i64 2
Expand All @@ -924,6 +919,11 @@ define i32 @block_partly_vectorized_without_versioning(%struct.spam* readonly %a
; CHECK-NEXT: [[R_GEP_13:%.*]] = getelementptr i8, i8* [[ARG1]], i64 13
; CHECK-NEXT: [[R_GEP_14:%.*]] = getelementptr i8, i8* [[ARG1]], i64 14
; CHECK-NEXT: [[R_GEP_15:%.*]] = getelementptr i8, i8* [[ARG1]], i64 15
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[A_GEP_0]] to <16 x i8>*
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* [[TMP0]], align 1
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i8* [[B_GEP_0]] to <16 x i8>*
; CHECK-NEXT: [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* [[TMP2]], align 1
; CHECK-NEXT: [[TMP4:%.*]] = xor <16 x i8> [[TMP1]], [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = bitcast i8* [[R_GEP_0]] to <16 x i8>*
; CHECK-NEXT: store <16 x i8> [[TMP4]], <16 x i8>* [[TMP5]], align 1
; CHECK-NEXT: [[T21:%.*]] = getelementptr inbounds i8, i8* [[ARG3]], i64 15
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/Transforms/SLPVectorizer/AArch64/sdiv-pow2.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -13,14 +13,14 @@ define void @test1(i32* noalias nocapture %a, i32* noalias nocapture readonly %b
; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 2
; CHECK-NEXT: [[ARRAYIDX12:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 2
; CHECK-NEXT: [[ARRAYIDX13:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 3
; CHECK-NEXT: [[ARRAYIDX14:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 3
; CHECK-NEXT: [[ARRAYIDX17:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 3
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[B]] to <4 x i32>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
; CHECK-NEXT: [[ARRAYIDX14:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 3
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[C]] to <4 x i32>*
; CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP2]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = add nsw <4 x i32> [[TMP3]], [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = sdiv <4 x i32> [[TMP4]], <i32 2, i32 2, i32 2, i32 2>
; CHECK-NEXT: [[ARRAYIDX17:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 3
; CHECK-NEXT: [[TMP6:%.*]] = bitcast i32* [[A]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP6]], align 4
; CHECK-NEXT: ret void
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/Transforms/SLPVectorizer/AArch64/slp-and-reduction.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -21,9 +21,9 @@ define i8 @reduce_and(%struct.buf* %a, %struct.buf* %b) {
; CHECK-NEXT: [[ARRAYIDX_6:%.*]] = getelementptr inbounds [[STRUCT_BUF]], %struct.buf* [[A]], i64 0, i32 0, i64 6
; CHECK-NEXT: [[ARRAYIDX3_6:%.*]] = getelementptr inbounds [[STRUCT_BUF]], %struct.buf* [[B]], i64 0, i32 0, i64 6
; CHECK-NEXT: [[ARRAYIDX_7:%.*]] = getelementptr inbounds [[STRUCT_BUF]], %struct.buf* [[A]], i64 0, i32 0, i64 7
; CHECK-NEXT: [[ARRAYIDX3_7:%.*]] = getelementptr inbounds [[STRUCT_BUF]], %struct.buf* [[B]], i64 0, i32 0, i64 7
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[ARRAYIDX]] to <8 x i8>*
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i8>, <8 x i8>* [[TMP0]], align 1
; CHECK-NEXT: [[ARRAYIDX3_7:%.*]] = getelementptr inbounds [[STRUCT_BUF]], %struct.buf* [[B]], i64 0, i32 0, i64 7
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i8* [[ARRAYIDX3]] to <8 x i8>*
; CHECK-NEXT: [[TMP3:%.*]] = load <8 x i8>, <8 x i8>* [[TMP2]], align 1
; CHECK-NEXT: [[TMP4:%.*]] = xor <8 x i8> [[TMP3]], [[TMP1]]
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/Transforms/SLPVectorizer/AArch64/slp-or-reduction.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -21,9 +21,9 @@ define i8 @reduce_or(%struct.buf* %a, %struct.buf* %b) {
; CHECK-NEXT: [[ARRAYIDX_6:%.*]] = getelementptr inbounds [[STRUCT_BUF]], %struct.buf* [[A]], i64 0, i32 0, i64 6
; CHECK-NEXT: [[ARRAYIDX3_6:%.*]] = getelementptr inbounds [[STRUCT_BUF]], %struct.buf* [[B]], i64 0, i32 0, i64 6
; CHECK-NEXT: [[ARRAYIDX_7:%.*]] = getelementptr inbounds [[STRUCT_BUF]], %struct.buf* [[A]], i64 0, i32 0, i64 7
; CHECK-NEXT: [[ARRAYIDX3_7:%.*]] = getelementptr inbounds [[STRUCT_BUF]], %struct.buf* [[B]], i64 0, i32 0, i64 7
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[ARRAYIDX]] to <8 x i8>*
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i8>, <8 x i8>* [[TMP0]], align 1
; CHECK-NEXT: [[ARRAYIDX3_7:%.*]] = getelementptr inbounds [[STRUCT_BUF]], %struct.buf* [[B]], i64 0, i32 0, i64 7
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i8* [[ARRAYIDX3]] to <8 x i8>*
; CHECK-NEXT: [[TMP3:%.*]] = load <8 x i8>, <8 x i8>* [[TMP2]], align 1
; CHECK-NEXT: [[TMP4:%.*]] = xor <8 x i8> [[TMP3]], [[TMP1]]
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/Transforms/SLPVectorizer/AArch64/slp-xor-reduction.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -21,9 +21,9 @@ define i8 @reduce_xor(%struct.buf* %a, %struct.buf* %b) {
; CHECK-NEXT: [[ARRAYIDX_6:%.*]] = getelementptr inbounds [[STRUCT_BUF]], %struct.buf* [[A]], i64 0, i32 0, i64 6
; CHECK-NEXT: [[ARRAYIDX3_6:%.*]] = getelementptr inbounds [[STRUCT_BUF]], %struct.buf* [[B]], i64 0, i32 0, i64 6
; CHECK-NEXT: [[ARRAYIDX_7:%.*]] = getelementptr inbounds [[STRUCT_BUF]], %struct.buf* [[A]], i64 0, i32 0, i64 7
; CHECK-NEXT: [[ARRAYIDX3_7:%.*]] = getelementptr inbounds [[STRUCT_BUF]], %struct.buf* [[B]], i64 0, i32 0, i64 7
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[ARRAYIDX]] to <8 x i8>*
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i8>, <8 x i8>* [[TMP0]], align 1
; CHECK-NEXT: [[ARRAYIDX3_7:%.*]] = getelementptr inbounds [[STRUCT_BUF]], %struct.buf* [[B]], i64 0, i32 0, i64 7
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i8* [[ARRAYIDX3]] to <8 x i8>*
; CHECK-NEXT: [[TMP3:%.*]] = load <8 x i8>, <8 x i8>* [[TMP2]], align 1
; CHECK-NEXT: [[TMP4:%.*]] = and <8 x i8> [[TMP3]], [[TMP1]]
Expand Down
10 changes: 5 additions & 5 deletions llvm/test/Transforms/SLPVectorizer/AArch64/spillcost-di.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -15,13 +15,13 @@ define void @patatino(i64 %n, i64 %i, %struct.S* %p) !dbg !7 {
; CHECK-NEXT: [[X1:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[P]], i64 [[N]], i32 0, !dbg [[DBG26:![0-9]+]]
; CHECK-NEXT: call void @llvm.dbg.value(metadata i64 undef, metadata [[META21:![0-9]+]], metadata !DIExpression()), !dbg [[DBG27:![0-9]+]]
; CHECK-NEXT: [[Y3:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[P]], i64 [[N]], i32 1, !dbg [[DBG28:![0-9]+]]
; CHECK-NEXT: call void @llvm.dbg.value(metadata i64 undef, metadata [[META22:![0-9]+]], metadata !DIExpression()), !dbg [[DBG29:![0-9]+]]
; CHECK-NEXT: [[X5:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[P]], i64 [[I]], i32 0, !dbg [[DBG30:![0-9]+]]
; CHECK-NEXT: [[Y7:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[P]], i64 [[I]], i32 1, !dbg [[DBG31:![0-9]+]]
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i64* [[X1]] to <2 x i64>*, !dbg [[DBG26]]
; CHECK-NEXT: [[TMP1:%.*]] = load <2 x i64>, <2 x i64>* [[TMP0]], align 8, !dbg [[DBG26]], !tbaa [[TBAA29:![0-9]+]]
; CHECK-NEXT: call void @llvm.dbg.value(metadata i64 undef, metadata [[META22:![0-9]+]], metadata !DIExpression()), !dbg [[DBG33:![0-9]+]]
; CHECK-NEXT: [[X5:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[P]], i64 [[I]], i32 0, !dbg [[DBG34:![0-9]+]]
; CHECK-NEXT: [[Y7:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[P]], i64 [[I]], i32 1, !dbg [[DBG35:![0-9]+]]
; CHECK-NEXT: [[TMP1:%.*]] = load <2 x i64>, <2 x i64>* [[TMP0]], align 8, !dbg [[DBG26]], !tbaa [[TBAA32:![0-9]+]]
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i64* [[X5]] to <2 x i64>*, !dbg [[DBG36:![0-9]+]]
; CHECK-NEXT: store <2 x i64> [[TMP1]], <2 x i64>* [[TMP2]], align 8, !dbg [[DBG36]], !tbaa [[TBAA29]]
; CHECK-NEXT: store <2 x i64> [[TMP1]], <2 x i64>* [[TMP2]], align 8, !dbg [[DBG36]], !tbaa [[TBAA32]]
; CHECK-NEXT: ret void, !dbg [[DBG37:![0-9]+]]
;
entry:
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/Transforms/SLPVectorizer/AArch64/spillcost-order.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -15,15 +15,15 @@ define void @test(i64* %ptr, i64* noalias %res) {
; CHECK-NEXT: [[CALL_I_I:%.*]] = call i32* @get_ptr()
; CHECK-NEXT: [[GEP_1:%.*]] = getelementptr i32, i32* [[CALL_I_I]], i32 2
; CHECK-NEXT: [[GEP_2:%.*]] = getelementptr i32, i32* [[CALL_I_I]], i32 1
; CHECK-NEXT: [[GEP_3:%.*]] = getelementptr i32, i32* [[CALL_I_I]], i32 3
; CHECK-NEXT: [[RES_1:%.*]] = getelementptr i64, i64* [[RES:%.*]], i64 1
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[CALL_I_I]] to <2 x i32>*
; CHECK-NEXT: [[TMP1:%.*]] = load <2 x i32>, <2 x i32>* [[TMP0]], align 2
; CHECK-NEXT: [[GEP_3:%.*]] = getelementptr i32, i32* [[CALL_I_I]], i32 3
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[GEP_1]] to <2 x i32>*
; CHECK-NEXT: [[TMP3:%.*]] = load <2 x i32>, <2 x i32>* [[TMP2]], align 2
; CHECK-NEXT: [[TMP4:%.*]] = zext <2 x i32> [[TMP1]] to <2 x i64>
; CHECK-NEXT: [[TMP5:%.*]] = zext <2 x i32> [[TMP3]] to <2 x i64>
; CHECK-NEXT: [[TMP6:%.*]] = sub nsw <2 x i64> [[TMP4]], [[TMP5]]
; CHECK-NEXT: [[RES_1:%.*]] = getelementptr i64, i64* [[RES:%.*]], i64 1
; CHECK-NEXT: [[TMP7:%.*]] = bitcast i64* [[RES]] to <2 x i64>*
; CHECK-NEXT: store <2 x i64> [[TMP6]], <2 x i64>* [[TMP7]], align 8
; CHECK-NEXT: [[C:%.*]] = call i1 @cond()
Expand Down
24 changes: 12 additions & 12 deletions llvm/test/Transforms/SLPVectorizer/AArch64/transpose-inseltpoison.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -135,13 +135,13 @@ define <4 x i32> @build_vec_v4i32_reuse_1(<2 x i32> %v0, <2 x i32> %v1) {
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <2 x i32> [[V0]], i64 0
; CHECK-NEXT: [[TMP0_0:%.*]] = add i32 [[TMP4]], [[TMP2]]
; CHECK-NEXT: [[TMP0_1:%.*]] = add i32 [[TMP3]], [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = xor <2 x i32> [[V0]], [[V1]]
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x i32> poison, i32 [[TMP0_0]], i64 0
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x i32> poison, i32 [[TMP0_1]], i64 0
; CHECK-NEXT: [[TMP8:%.*]] = sub <2 x i32> [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> undef, <2 x i32> <i32 1, i32 0>
; CHECK-NEXT: [[TMP10:%.*]] = sub <2 x i32> [[TMP5]], [[TMP9]]
; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <2 x i32> [[TMP8]], <2 x i32> poison, <4 x i32> <i32 0, i32 0, i32 undef, i32 undef>
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <2 x i32> poison, i32 [[TMP0_0]], i64 0
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x i32> poison, i32 [[TMP0_1]], i64 0
; CHECK-NEXT: [[TMP7:%.*]] = sub <2 x i32> [[TMP5]], [[TMP6]]
; CHECK-NEXT: [[TMP8:%.*]] = xor <2 x i32> [[V0]], [[V1]]
; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <2 x i32> [[TMP8]], <2 x i32> undef, <2 x i32> <i32 1, i32 0>
; CHECK-NEXT: [[TMP10:%.*]] = sub <2 x i32> [[TMP8]], [[TMP9]]
; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <2 x i32> [[TMP7]], <2 x i32> poison, <4 x i32> <i32 0, i32 0, i32 undef, i32 undef>
; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <2 x i32> [[TMP10]], <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
; CHECK-NEXT: [[TMP2_31:%.*]] = shufflevector <4 x i32> [[TMP11]], <4 x i32> [[TMP12]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; CHECK-NEXT: ret <4 x i32> [[TMP2_31]]
Expand Down Expand Up @@ -171,12 +171,12 @@ define <4 x i32> @build_vec_v4i32_3_binops(<2 x i32> %v0, <2 x i32> %v1) {
; CHECK-NEXT: [[TMP2:%.*]] = mul <2 x i32> [[V0]], [[V1]]
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <2 x i32> [[TMP1]], <2 x i32> [[TMP2]], <2 x i32> <i32 1, i32 2>
; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <2 x i32> [[TMP1]], <2 x i32> [[TMP2]], <2 x i32> <i32 0, i32 3>
; CHECK-NEXT: [[TMP5:%.*]] = xor <2 x i32> [[V0]], [[V1]]
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> poison, <2 x i32> <i32 1, i32 0>
; CHECK-NEXT: [[TMP5:%.*]] = add <2 x i32> [[TMP4]], [[TMP3]]
; CHECK-NEXT: [[TMP6:%.*]] = xor <2 x i32> [[V0]], [[V1]]
; CHECK-NEXT: [[TMP7:%.*]] = add <2 x i32> [[TMP4]], [[TMP3]]
; CHECK-NEXT: [[TMP8:%.*]] = add <2 x i32> [[SHUFFLE]], [[TMP6]]
; CHECK-NEXT: [[TMP3_31:%.*]] = shufflevector <2 x i32> [[TMP7]], <2 x i32> [[TMP8]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x i32> [[TMP6]], <2 x i32> poison, <2 x i32> <i32 1, i32 0>
; CHECK-NEXT: [[TMP7:%.*]] = xor <2 x i32> [[V0]], [[V1]]
; CHECK-NEXT: [[TMP8:%.*]] = add <2 x i32> [[SHUFFLE]], [[TMP7]]
; CHECK-NEXT: [[TMP3_31:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> [[TMP8]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT: ret <4 x i32> [[TMP3_31]]
;
%v0.0 = extractelement <2 x i32> %v0, i32 0
Expand Down
24 changes: 12 additions & 12 deletions llvm/test/Transforms/SLPVectorizer/AArch64/transpose.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -135,13 +135,13 @@ define <4 x i32> @build_vec_v4i32_reuse_1(<2 x i32> %v0, <2 x i32> %v1) {
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <2 x i32> [[V0]], i64 0
; CHECK-NEXT: [[TMP0_0:%.*]] = add i32 [[TMP4]], [[TMP2]]
; CHECK-NEXT: [[TMP0_1:%.*]] = add i32 [[TMP3]], [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = xor <2 x i32> [[V0]], [[V1]]
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x i32> poison, i32 [[TMP0_0]], i64 0
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x i32> poison, i32 [[TMP0_1]], i64 0
; CHECK-NEXT: [[TMP8:%.*]] = sub <2 x i32> [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> undef, <2 x i32> <i32 1, i32 0>
; CHECK-NEXT: [[TMP10:%.*]] = sub <2 x i32> [[TMP5]], [[TMP9]]
; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <2 x i32> [[TMP8]], <2 x i32> poison, <4 x i32> <i32 0, i32 0, i32 undef, i32 undef>
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <2 x i32> poison, i32 [[TMP0_0]], i64 0
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x i32> poison, i32 [[TMP0_1]], i64 0
; CHECK-NEXT: [[TMP7:%.*]] = sub <2 x i32> [[TMP5]], [[TMP6]]
; CHECK-NEXT: [[TMP8:%.*]] = xor <2 x i32> [[V0]], [[V1]]
; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <2 x i32> [[TMP8]], <2 x i32> undef, <2 x i32> <i32 1, i32 0>
; CHECK-NEXT: [[TMP10:%.*]] = sub <2 x i32> [[TMP8]], [[TMP9]]
; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <2 x i32> [[TMP7]], <2 x i32> poison, <4 x i32> <i32 0, i32 0, i32 undef, i32 undef>
; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <2 x i32> [[TMP10]], <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
; CHECK-NEXT: [[TMP2_31:%.*]] = shufflevector <4 x i32> [[TMP11]], <4 x i32> [[TMP12]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; CHECK-NEXT: ret <4 x i32> [[TMP2_31]]
Expand Down Expand Up @@ -171,12 +171,12 @@ define <4 x i32> @build_vec_v4i32_3_binops(<2 x i32> %v0, <2 x i32> %v1) {
; CHECK-NEXT: [[TMP2:%.*]] = mul <2 x i32> [[V0]], [[V1]]
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <2 x i32> [[TMP1]], <2 x i32> [[TMP2]], <2 x i32> <i32 1, i32 2>
; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <2 x i32> [[TMP1]], <2 x i32> [[TMP2]], <2 x i32> <i32 0, i32 3>
; CHECK-NEXT: [[TMP5:%.*]] = xor <2 x i32> [[V0]], [[V1]]
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> poison, <2 x i32> <i32 1, i32 0>
; CHECK-NEXT: [[TMP5:%.*]] = add <2 x i32> [[TMP4]], [[TMP3]]
; CHECK-NEXT: [[TMP6:%.*]] = xor <2 x i32> [[V0]], [[V1]]
; CHECK-NEXT: [[TMP7:%.*]] = add <2 x i32> [[TMP4]], [[TMP3]]
; CHECK-NEXT: [[TMP8:%.*]] = add <2 x i32> [[SHUFFLE]], [[TMP6]]
; CHECK-NEXT: [[TMP3_31:%.*]] = shufflevector <2 x i32> [[TMP7]], <2 x i32> [[TMP8]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x i32> [[TMP6]], <2 x i32> poison, <2 x i32> <i32 1, i32 0>
; CHECK-NEXT: [[TMP7:%.*]] = xor <2 x i32> [[V0]], [[V1]]
; CHECK-NEXT: [[TMP8:%.*]] = add <2 x i32> [[SHUFFLE]], [[TMP7]]
; CHECK-NEXT: [[TMP3_31:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> [[TMP8]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT: ret <4 x i32> [[TMP3_31]]
;
%v0.0 = extractelement <2 x i32> %v0, i32 0
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/Transforms/SLPVectorizer/AArch64/tsc-s352.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -33,9 +33,9 @@ define i32 @s352() {
; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds [[STRUCT_GLOBALDATA]], %struct.GlobalData* @global_data, i64 0, i32 3, i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP0:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[ARRAYIDX10:%.*]] = getelementptr inbounds [[STRUCT_GLOBALDATA]], %struct.GlobalData* @global_data, i64 0, i32 0, i64 [[TMP0]]
; CHECK-NEXT: [[ARRAYIDX13:%.*]] = getelementptr inbounds [[STRUCT_GLOBALDATA]], %struct.GlobalData* @global_data, i64 0, i32 3, i64 [[TMP0]]
; CHECK-NEXT: [[TMP1:%.*]] = bitcast float* [[ARRAYIDX]] to <2 x float>*
; CHECK-NEXT: [[TMP2:%.*]] = load <2 x float>, <2 x float>* [[TMP1]], align 4
; CHECK-NEXT: [[ARRAYIDX13:%.*]] = getelementptr inbounds [[STRUCT_GLOBALDATA]], %struct.GlobalData* @global_data, i64 0, i32 3, i64 [[TMP0]]
; CHECK-NEXT: [[TMP3:%.*]] = bitcast float* [[ARRAYIDX6]] to <2 x float>*
; CHECK-NEXT: [[TMP4:%.*]] = load <2 x float>, <2 x float>* [[TMP3]], align 4
; CHECK-NEXT: [[TMP5:%.*]] = fmul <2 x float> [[TMP2]], [[TMP4]]
Expand All @@ -48,9 +48,9 @@ define i32 @s352() {
; CHECK-NEXT: [[ARRAYIDX21:%.*]] = getelementptr inbounds [[STRUCT_GLOBALDATA]], %struct.GlobalData* @global_data, i64 0, i32 3, i64 [[TMP8]]
; CHECK-NEXT: [[TMP9:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 3
; CHECK-NEXT: [[ARRAYIDX26:%.*]] = getelementptr inbounds [[STRUCT_GLOBALDATA]], %struct.GlobalData* @global_data, i64 0, i32 0, i64 [[TMP9]]
; CHECK-NEXT: [[ARRAYIDX29:%.*]] = getelementptr inbounds [[STRUCT_GLOBALDATA]], %struct.GlobalData* @global_data, i64 0, i32 3, i64 [[TMP9]]
; CHECK-NEXT: [[TMP10:%.*]] = bitcast float* [[ARRAYIDX18]] to <2 x float>*
; CHECK-NEXT: [[TMP11:%.*]] = load <2 x float>, <2 x float>* [[TMP10]], align 4
; CHECK-NEXT: [[ARRAYIDX29:%.*]] = getelementptr inbounds [[STRUCT_GLOBALDATA]], %struct.GlobalData* @global_data, i64 0, i32 3, i64 [[TMP9]]
; CHECK-NEXT: [[TMP12:%.*]] = bitcast float* [[ARRAYIDX21]] to <2 x float>*
; CHECK-NEXT: [[TMP13:%.*]] = load <2 x float>, <2 x float>* [[TMP12]], align 4
; CHECK-NEXT: [[TMP14:%.*]] = fmul <2 x float> [[TMP11]], [[TMP13]]
Expand Down
22 changes: 11 additions & 11 deletions llvm/test/Transforms/SLPVectorizer/AArch64/widen.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -25,14 +25,6 @@ define void @PR50256(i8* %a, i16* %b, i32 %n) {
; CHECK-NEXT: [[ARRAYIDX_13:%.*]] = getelementptr inbounds i8, i8* [[A]], i64 13
; CHECK-NEXT: [[ARRAYIDX_14:%.*]] = getelementptr inbounds i8, i8* [[A]], i64 14
; CHECK-NEXT: [[ARRAYIDX_15:%.*]] = getelementptr inbounds i8, i8* [[A]], i64 15
; CHECK-NEXT: [[TMP1:%.*]] = bitcast i8* [[A]] to <8 x i8>*
; CHECK-NEXT: [[TMP2:%.*]] = load <8 x i8>, <8 x i8>* [[TMP1]], align 1
; CHECK-NEXT: [[TMP3:%.*]] = bitcast i8* [[ARRAYIDX_8]] to <8 x i8>*
; CHECK-NEXT: [[TMP4:%.*]] = load <8 x i8>, <8 x i8>* [[TMP3]], align 1
; CHECK-NEXT: [[TMP5:%.*]] = zext <8 x i8> [[TMP2]] to <8 x i16>
; CHECK-NEXT: [[TMP6:%.*]] = zext <8 x i8> [[TMP4]] to <8 x i16>
; CHECK-NEXT: [[TMP7:%.*]] = shl nuw <8 x i16> [[TMP5]], <i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8>
; CHECK-NEXT: [[TMP8:%.*]] = shl nuw <8 x i16> [[TMP6]], <i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8>
; CHECK-NEXT: [[ARRAYIDX3_1:%.*]] = getelementptr inbounds i16, i16* [[B:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX3_2:%.*]] = getelementptr inbounds i16, i16* [[B]], i64 2
; CHECK-NEXT: [[ARRAYIDX3_3:%.*]] = getelementptr inbounds i16, i16* [[B]], i64 3
Expand All @@ -48,10 +40,18 @@ define void @PR50256(i8* %a, i16* %b, i32 %n) {
; CHECK-NEXT: [[ARRAYIDX3_13:%.*]] = getelementptr inbounds i16, i16* [[B]], i64 13
; CHECK-NEXT: [[ARRAYIDX3_14:%.*]] = getelementptr inbounds i16, i16* [[B]], i64 14
; CHECK-NEXT: [[ARRAYIDX3_15:%.*]] = getelementptr inbounds i16, i16* [[B]], i64 15
; CHECK-NEXT: [[TMP9:%.*]] = bitcast i16* [[B]] to <8 x i16>*
; CHECK-NEXT: store <8 x i16> [[TMP7]], <8 x i16>* [[TMP9]], align 2
; CHECK-NEXT: [[TMP1:%.*]] = bitcast i8* [[A]] to <8 x i8>*
; CHECK-NEXT: [[TMP2:%.*]] = load <8 x i8>, <8 x i8>* [[TMP1]], align 1
; CHECK-NEXT: [[TMP3:%.*]] = zext <8 x i8> [[TMP2]] to <8 x i16>
; CHECK-NEXT: [[TMP4:%.*]] = shl nuw <8 x i16> [[TMP3]], <i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8>
; CHECK-NEXT: [[TMP5:%.*]] = bitcast i16* [[B]] to <8 x i16>*
; CHECK-NEXT: [[TMP6:%.*]] = bitcast i8* [[ARRAYIDX_8]] to <8 x i8>*
; CHECK-NEXT: [[TMP7:%.*]] = load <8 x i8>, <8 x i8>* [[TMP6]], align 1
; CHECK-NEXT: [[TMP8:%.*]] = zext <8 x i8> [[TMP7]] to <8 x i16>
; CHECK-NEXT: [[TMP9:%.*]] = shl nuw <8 x i16> [[TMP8]], <i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8>
; CHECK-NEXT: store <8 x i16> [[TMP4]], <8 x i16>* [[TMP5]], align 2
; CHECK-NEXT: [[TMP10:%.*]] = bitcast i16* [[ARRAYIDX3_8]] to <8 x i16>*
; CHECK-NEXT: store <8 x i16> [[TMP8]], <8 x i16>* [[TMP10]], align 2
; CHECK-NEXT: store <8 x i16> [[TMP9]], <8 x i16>* [[TMP10]], align 2
; CHECK-NEXT: ret void
;
%arrayidx.1 = getelementptr inbounds i8, i8* %a, i64 1
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/Transforms/SLPVectorizer/AMDGPU/packed-math.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -191,10 +191,10 @@ define amdgpu_kernel void @test1_fabs_scalar_fma_v2f16(half addrspace(3)* %a, ha
; GCN-LABEL: @test1_fabs_scalar_fma_v2f16(
; GCN-NEXT: [[I1:%.*]] = load half, half addrspace(3)* [[B:%.*]], align 2
; GCN-NEXT: [[I1_FABS:%.*]] = call half @llvm.fabs.f16(half [[I1]])
; GCN-NEXT: [[TMP1:%.*]] = bitcast half addrspace(3)* [[A:%.*]] to <2 x half> addrspace(3)*
; GCN-NEXT: [[TMP2:%.*]] = load <2 x half>, <2 x half> addrspace(3)* [[TMP1]], align 2
; GCN-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds half, half addrspace(3)* [[B]], i64 1
; GCN-NEXT: [[I4:%.*]] = load half, half addrspace(3)* [[ARRAYIDX4]], align 2
; GCN-NEXT: [[TMP1:%.*]] = bitcast half addrspace(3)* [[A:%.*]] to <2 x half> addrspace(3)*
; GCN-NEXT: [[TMP2:%.*]] = load <2 x half>, <2 x half> addrspace(3)* [[TMP1]], align 2
; GCN-NEXT: [[TMP3:%.*]] = bitcast half addrspace(3)* [[C:%.*]] to <2 x half> addrspace(3)*
; GCN-NEXT: [[TMP4:%.*]] = load <2 x half>, <2 x half> addrspace(3)* [[TMP3]], align 2
; GCN-NEXT: [[TMP5:%.*]] = insertelement <2 x half> poison, half [[I1_FABS]], i32 0
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/Transforms/SLPVectorizer/NVPTX/v2f16.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -14,11 +14,11 @@ define void @fusion(i8* noalias nocapture align 256 dereferenceable(19267584) %a
; CHECK-NEXT: [[TMP15:%.*]] = bitcast i8* [[ARG:%.*]] to half*
; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds half, half* [[TMP15]], i64 [[TMP6]]
; CHECK-NEXT: [[TMP17:%.*]] = getelementptr inbounds half, half* [[TMP10]], i64 [[TMP7]]
; CHECK-NEXT: [[TMP21:%.*]] = getelementptr inbounds half, half* [[TMP15]], i64 [[TMP7]]
; CHECK-NEXT: [[TMP1:%.*]] = bitcast half* [[TMP11]] to <2 x half>*
; CHECK-NEXT: [[TMP2:%.*]] = load <2 x half>, <2 x half>* [[TMP1]], align 8
; CHECK-NEXT: [[TMP3:%.*]] = fmul fast <2 x half> [[TMP2]], <half 0xH5380, half 0xH5380>
; CHECK-NEXT: [[TMP4:%.*]] = fadd fast <2 x half> [[TMP3]], <half 0xH57F0, half 0xH57F0>
; CHECK-NEXT: [[TMP21:%.*]] = getelementptr inbounds half, half* [[TMP15]], i64 [[TMP7]]
; CHECK-NEXT: [[TMP5:%.*]] = bitcast half* [[TMP16]] to <2 x half>*
; CHECK-NEXT: store <2 x half> [[TMP4]], <2 x half>* [[TMP5]], align 8
; CHECK-NEXT: ret void
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/Transforms/SLPVectorizer/SystemZ/pr34619.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -14,13 +14,13 @@ define void @foo() local_unnamed_addr {
; CHECK-NEXT: [[ARRAYIDX372_1:%.*]] = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 1
; CHECK-NEXT: [[ARRAYIDX372_2:%.*]] = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 2
; CHECK-NEXT: [[TMP1:%.*]] = load <2 x i32>, <2 x i32>* bitcast (i32* getelementptr inbounds ([4 x [4 x i32]], [4 x [4 x i32]]* @bar, i64 0, i64 3, i64 2) to <2 x i32>*), align 4
; CHECK-NEXT: [[ARRAYIDX372_3:%.*]] = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 3
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <4 x i32> poison, i32 [[TMP0]], i32 0
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <4 x i32> [[TMP2]], i32 [[ADD277]], i32 1
; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <2 x i32> [[TMP1]], <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> [[TMP4]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; CHECK-NEXT: [[TMP6:%.*]] = add nsw <4 x i32> poison, [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = ashr <4 x i32> [[TMP6]], <i32 6, i32 6, i32 6, i32 6>
; CHECK-NEXT: [[ARRAYIDX372_3:%.*]] = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 3
; CHECK-NEXT: [[TMP8:%.*]] = bitcast i32* [[ARRAYIDX372]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP7]], <4 x i32>* [[TMP8]], align 4
; CHECK-NEXT: unreachable
Expand Down
18 changes: 9 additions & 9 deletions llvm/test/Transforms/SLPVectorizer/X86/PR32086.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -4,12 +4,12 @@
define void @i64_simplified(i64* noalias %st, i64* noalias %ld) {
; CHECK-LABEL: @i64_simplified(
; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, i64* [[LD:%.*]], i64 1
; CHECK-NEXT: [[TMP1:%.*]] = bitcast i64* [[LD]] to <2 x i64>*
; CHECK-NEXT: [[TMP2:%.*]] = load <2 x i64>, <2 x i64>* [[TMP1]], align 8
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x i64> [[TMP2]], <2 x i64> poison, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i64, i64* [[ST:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i64, i64* [[ST]], i64 2
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i64, i64* [[ST]], i64 3
; CHECK-NEXT: [[TMP1:%.*]] = bitcast i64* [[LD]] to <2 x i64>*
; CHECK-NEXT: [[TMP2:%.*]] = load <2 x i64>, <2 x i64>* [[TMP1]], align 8
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x i64> [[TMP2]], <2 x i64> poison, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
; CHECK-NEXT: [[TMP3:%.*]] = bitcast i64* [[ST]] to <4 x i64>*
; CHECK-NEXT: store <4 x i64> [[SHUFFLE]], <4 x i64>* [[TMP3]], align 8
; CHECK-NEXT: ret void
Expand All @@ -33,12 +33,12 @@ define void @i64_simplified(i64* noalias %st, i64* noalias %ld) {
define void @i64_simplifiedi_reversed(i64* noalias %st, i64* noalias %ld) {
; CHECK-LABEL: @i64_simplifiedi_reversed(
; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, i64* [[LD:%.*]], i64 1
; CHECK-NEXT: [[TMP1:%.*]] = bitcast i64* [[LD]] to <2 x i64>*
; CHECK-NEXT: [[TMP2:%.*]] = load <2 x i64>, <2 x i64>* [[TMP1]], align 8
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x i64> [[TMP2]], <2 x i64> poison, <4 x i32> <i32 1, i32 0, i32 1, i32 0>
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i64, i64* [[ST:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i64, i64* [[ST]], i64 2
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i64, i64* [[ST]], i64 3
; CHECK-NEXT: [[TMP1:%.*]] = bitcast i64* [[LD]] to <2 x i64>*
; CHECK-NEXT: [[TMP2:%.*]] = load <2 x i64>, <2 x i64>* [[TMP1]], align 8
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x i64> [[TMP2]], <2 x i64> poison, <4 x i32> <i32 1, i32 0, i32 1, i32 0>
; CHECK-NEXT: [[TMP3:%.*]] = bitcast i64* [[ST]] to <4 x i64>*
; CHECK-NEXT: store <4 x i64> [[SHUFFLE]], <4 x i64>* [[TMP3]], align 8
; CHECK-NEXT: ret void
Expand All @@ -62,12 +62,12 @@ define void @i64_simplifiedi_reversed(i64* noalias %st, i64* noalias %ld) {
define void @i64_simplifiedi_extract(i64* noalias %st, i64* noalias %ld) {
; CHECK-LABEL: @i64_simplifiedi_extract(
; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, i64* [[LD:%.*]], i64 1
; CHECK-NEXT: [[TMP1:%.*]] = bitcast i64* [[LD]] to <2 x i64>*
; CHECK-NEXT: [[TMP2:%.*]] = load <2 x i64>, <2 x i64>* [[TMP1]], align 8
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x i64> [[TMP2]], <2 x i64> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i64, i64* [[ST:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i64, i64* [[ST]], i64 2
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i64, i64* [[ST]], i64 3
; CHECK-NEXT: [[TMP1:%.*]] = bitcast i64* [[LD]] to <2 x i64>*
; CHECK-NEXT: [[TMP2:%.*]] = load <2 x i64>, <2 x i64>* [[TMP1]], align 8
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x i64> [[TMP2]], <2 x i64> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
; CHECK-NEXT: [[TMP3:%.*]] = bitcast i64* [[ST]] to <4 x i64>*
; CHECK-NEXT: store <4 x i64> [[SHUFFLE]], <4 x i64>* [[TMP3]], align 8
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <4 x i64> [[SHUFFLE]], i32 3
Expand Down
6 changes: 3 additions & 3 deletions llvm/test/Transforms/SLPVectorizer/X86/PR39774.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -54,9 +54,11 @@ define void @Test(i32) {
; FORCE_REDUCTION-NEXT: [[TMP1:%.*]] = phi <2 x i32> [ [[TMP12:%.*]], [[LOOP]] ], [ zeroinitializer, [[ENTRY:%.*]] ]
; FORCE_REDUCTION-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x i32> [[TMP1]], <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 1, i32 1>
; FORCE_REDUCTION-NEXT: [[TMP2:%.*]] = extractelement <4 x i32> [[SHUFFLE]], i32 1
; FORCE_REDUCTION-NEXT: [[TMP3:%.*]] = add <4 x i32> [[SHUFFLE]], <i32 0, i32 55, i32 285, i32 1240>
; FORCE_REDUCTION-NEXT: [[VAL_20:%.*]] = add i32 [[TMP2]], 1496
; FORCE_REDUCTION-NEXT: [[VAL_34:%.*]] = add i32 [[TMP2]], 8555
; FORCE_REDUCTION-NEXT: [[VAL_39:%.*]] = add i32 [[TMP2]], 12529
; FORCE_REDUCTION-NEXT: [[VAL_41:%.*]] = add i32 [[TMP2]], 13685
; FORCE_REDUCTION-NEXT: [[TMP3:%.*]] = add <4 x i32> [[SHUFFLE]], <i32 0, i32 55, i32 285, i32 1240>
; FORCE_REDUCTION-NEXT: [[TMP4:%.*]] = call i32 @llvm.vector.reduce.and.v4i32(<4 x i32> [[TMP3]])
; FORCE_REDUCTION-NEXT: [[TMP5:%.*]] = and i32 [[TMP4]], [[VAL_20]]
; FORCE_REDUCTION-NEXT: [[TMP6:%.*]] = and i32 [[TMP5]], [[VAL_34]]
Expand Down Expand Up @@ -88,9 +90,7 @@ define void @Test(i32) {
; FORCE_REDUCTION-NEXT: [[OP_EXTRA25:%.*]] = and i32 [[OP_EXTRA24]], [[TMP0]]
; FORCE_REDUCTION-NEXT: [[OP_EXTRA26:%.*]] = and i32 [[OP_EXTRA25]], [[TMP0]]
; FORCE_REDUCTION-NEXT: [[OP_EXTRA27:%.*]] = and i32 [[OP_EXTRA26]], [[TMP2]]
; FORCE_REDUCTION-NEXT: [[VAL_39:%.*]] = add i32 [[TMP2]], 12529
; FORCE_REDUCTION-NEXT: [[VAL_40:%.*]] = and i32 [[OP_EXTRA27]], [[VAL_39]]
; FORCE_REDUCTION-NEXT: [[VAL_41:%.*]] = add i32 [[TMP2]], 13685
; FORCE_REDUCTION-NEXT: [[TMP7:%.*]] = insertelement <2 x i32> poison, i32 [[VAL_40]], i32 0
; FORCE_REDUCTION-NEXT: [[TMP8:%.*]] = insertelement <2 x i32> [[TMP7]], i32 [[TMP2]], i32 1
; FORCE_REDUCTION-NEXT: [[TMP9:%.*]] = insertelement <2 x i32> <i32 poison, i32 14910>, i32 [[VAL_41]], i32 0
Expand Down
26 changes: 13 additions & 13 deletions llvm/test/Transforms/SLPVectorizer/X86/addsub.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -302,21 +302,21 @@ define void @reorder_alt_subTree() #0 {
define void @reorder_alt_rightsubTree(double* nocapture %c, double* noalias nocapture readonly %a, double* noalias nocapture readonly %b, double* noalias nocapture readonly %d) {
; CHECK-LABEL: @reorder_alt_rightsubTree(
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds double, double* [[D:%.*]], i64 1
; CHECK-NEXT: [[TMP2:%.*]] = bitcast double* [[D]] to <2 x double>*
; CHECK-NEXT: [[TMP3:%.*]] = load <2 x double>, <2 x double>* [[TMP2]], align 8
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds double, double* [[A:%.*]], i64 1
; CHECK-NEXT: [[TMP5:%.*]] = bitcast double* [[A]] to <2 x double>*
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds double, double* [[A:%.*]], i64 1
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds double, double* [[B:%.*]], i64 1
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds double, double* [[C:%.*]], i64 1
; CHECK-NEXT: [[TMP5:%.*]] = bitcast double* [[D]] to <2 x double>*
; CHECK-NEXT: [[TMP6:%.*]] = load <2 x double>, <2 x double>* [[TMP5]], align 8
; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds double, double* [[B:%.*]], i64 1
; CHECK-NEXT: [[TMP8:%.*]] = bitcast double* [[B]] to <2 x double>*
; CHECK-NEXT: [[TMP9:%.*]] = load <2 x double>, <2 x double>* [[TMP8]], align 8
; CHECK-NEXT: [[TMP10:%.*]] = fadd <2 x double> [[TMP6]], [[TMP9]]
; CHECK-NEXT: [[TMP11:%.*]] = fsub <2 x double> [[TMP10]], [[TMP3]]
; CHECK-NEXT: [[TMP12:%.*]] = fadd <2 x double> [[TMP10]], [[TMP3]]
; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <2 x double> [[TMP11]], <2 x double> [[TMP12]], <2 x i32> <i32 0, i32 3>
; CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds double, double* [[C:%.*]], i64 1
; CHECK-NEXT: [[TMP7:%.*]] = bitcast double* [[A]] to <2 x double>*
; CHECK-NEXT: [[TMP8:%.*]] = load <2 x double>, <2 x double>* [[TMP7]], align 8
; CHECK-NEXT: [[TMP9:%.*]] = bitcast double* [[B]] to <2 x double>*
; CHECK-NEXT: [[TMP10:%.*]] = load <2 x double>, <2 x double>* [[TMP9]], align 8
; CHECK-NEXT: [[TMP11:%.*]] = fadd <2 x double> [[TMP8]], [[TMP10]]
; CHECK-NEXT: [[TMP12:%.*]] = fsub <2 x double> [[TMP11]], [[TMP6]]
; CHECK-NEXT: [[TMP13:%.*]] = fadd <2 x double> [[TMP11]], [[TMP6]]
; CHECK-NEXT: [[TMP14:%.*]] = shufflevector <2 x double> [[TMP12]], <2 x double> [[TMP13]], <2 x i32> <i32 0, i32 3>
; CHECK-NEXT: [[TMP15:%.*]] = bitcast double* [[C]] to <2 x double>*
; CHECK-NEXT: store <2 x double> [[TMP13]], <2 x double>* [[TMP15]], align 8
; CHECK-NEXT: store <2 x double> [[TMP14]], <2 x double>* [[TMP15]], align 8
; CHECK-NEXT: ret void
;
%1 = load double, double* %a
Expand Down
6 changes: 3 additions & 3 deletions llvm/test/Transforms/SLPVectorizer/X86/align.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -12,9 +12,9 @@ define void @test1(double* %a, double* %b, double* %c) {
; CHECK-NEXT: [[STORE1:%.*]] = getelementptr inbounds [3 x double], [3 x double]* [[AGG_TMP_I_I_SROA_0]], i64 0, i64 1
; CHECK-NEXT: [[STORE2:%.*]] = getelementptr inbounds [3 x double], [3 x double]* [[AGG_TMP_I_I_SROA_0]], i64 0, i64 2
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds double, double* [[A:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds double, double* [[B:%.*]], i64 1
; CHECK-NEXT: [[TMP0:%.*]] = bitcast double* [[A]] to <2 x double>*
; CHECK-NEXT: [[TMP1:%.*]] = load <2 x double>, <2 x double>* [[TMP0]], align 8
; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds double, double* [[B:%.*]], i64 1
; CHECK-NEXT: [[TMP2:%.*]] = bitcast double* [[B]] to <2 x double>*
; CHECK-NEXT: [[TMP3:%.*]] = load <2 x double>, <2 x double>* [[TMP2]], align 8
; CHECK-NEXT: [[TMP4:%.*]] = fmul <2 x double> [[TMP1]], [[TMP3]]
Expand Down Expand Up @@ -48,11 +48,11 @@ define void @test2(float * %a, float * %b) {
; CHECK-NEXT: [[A1:%.*]] = getelementptr inbounds float, float* [[A:%.*]], i64 1
; CHECK-NEXT: [[A2:%.*]] = getelementptr inbounds float, float* [[A]], i64 2
; CHECK-NEXT: [[A3:%.*]] = getelementptr inbounds float, float* [[A]], i64 3
; CHECK-NEXT: [[TMP0:%.*]] = bitcast float* [[A]] to <4 x float>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
; CHECK-NEXT: [[B1:%.*]] = getelementptr inbounds float, float* [[B:%.*]], i64 1
; CHECK-NEXT: [[B2:%.*]] = getelementptr inbounds float, float* [[B]], i64 2
; CHECK-NEXT: [[B3:%.*]] = getelementptr inbounds float, float* [[B]], i64 3
; CHECK-NEXT: [[TMP0:%.*]] = bitcast float* [[A]] to <4 x float>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = bitcast float* [[B]] to <4 x float>*
; CHECK-NEXT: store <4 x float> [[TMP1]], <4 x float>* [[TMP2]], align 4
; CHECK-NEXT: ret void
Expand Down
192 changes: 96 additions & 96 deletions llvm/test/Transforms/SLPVectorizer/X86/arith-abs.ll
View file

Large diffs are not rendered by default.

216 changes: 108 additions & 108 deletions llvm/test/Transforms/SLPVectorizer/X86/arith-add-ssat.ll
View file

Large diffs are not rendered by default.

132 changes: 66 additions & 66 deletions llvm/test/Transforms/SLPVectorizer/X86/arith-add-usat.ll
View file

Large diffs are not rendered by default.

272 changes: 136 additions & 136 deletions llvm/test/Transforms/SLPVectorizer/X86/arith-add.ll
View file

Large diffs are not rendered by default.

192 changes: 96 additions & 96 deletions llvm/test/Transforms/SLPVectorizer/X86/arith-div.ll
View file

Large diffs are not rendered by default.

568 changes: 284 additions & 284 deletions llvm/test/Transforms/SLPVectorizer/X86/arith-fix.ll
View file

Large diffs are not rendered by default.

328 changes: 164 additions & 164 deletions llvm/test/Transforms/SLPVectorizer/X86/arith-mul.ll
View file

Large diffs are not rendered by default.

244 changes: 122 additions & 122 deletions llvm/test/Transforms/SLPVectorizer/X86/arith-smax.ll
View file

Large diffs are not rendered by default.

244 changes: 122 additions & 122 deletions llvm/test/Transforms/SLPVectorizer/X86/arith-smin.ll
View file

Large diffs are not rendered by default.

216 changes: 108 additions & 108 deletions llvm/test/Transforms/SLPVectorizer/X86/arith-sub-ssat.ll
View file

Large diffs are not rendered by default.

132 changes: 66 additions & 66 deletions llvm/test/Transforms/SLPVectorizer/X86/arith-sub-usat.ll
View file

Large diffs are not rendered by default.

272 changes: 136 additions & 136 deletions llvm/test/Transforms/SLPVectorizer/X86/arith-sub.ll
View file

Large diffs are not rendered by default.

244 changes: 122 additions & 122 deletions llvm/test/Transforms/SLPVectorizer/X86/arith-umax.ll
View file

Large diffs are not rendered by default.

244 changes: 122 additions & 122 deletions llvm/test/Transforms/SLPVectorizer/X86/arith-umin.ll
View file

Large diffs are not rendered by default.

32 changes: 16 additions & 16 deletions llvm/test/Transforms/SLPVectorizer/X86/bitreverse.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -40,10 +40,10 @@ define void @bitreverse_2i64() #0 {
define void @bitreverse_4i64() #0 {
; SSE-LABEL: @bitreverse_4i64(
; SSE-NEXT: [[TMP1:%.*]] = load <2 x i64>, <2 x i64>* bitcast ([4 x i64]* @src64 to <2 x i64>*), align 4
; SSE-NEXT: [[TMP2:%.*]] = load <2 x i64>, <2 x i64>* bitcast (i64* getelementptr inbounds ([4 x i64], [4 x i64]* @src64, i64 0, i64 2) to <2 x i64>*), align 4
; SSE-NEXT: [[TMP3:%.*]] = call <2 x i64> @llvm.bitreverse.v2i64(<2 x i64> [[TMP1]])
; SSE-NEXT: [[TMP4:%.*]] = call <2 x i64> @llvm.bitreverse.v2i64(<2 x i64> [[TMP2]])
; SSE-NEXT: store <2 x i64> [[TMP3]], <2 x i64>* bitcast ([4 x i64]* @dst64 to <2 x i64>*), align 4
; SSE-NEXT: [[TMP2:%.*]] = call <2 x i64> @llvm.bitreverse.v2i64(<2 x i64> [[TMP1]])
; SSE-NEXT: store <2 x i64> [[TMP2]], <2 x i64>* bitcast ([4 x i64]* @dst64 to <2 x i64>*), align 4
; SSE-NEXT: [[TMP3:%.*]] = load <2 x i64>, <2 x i64>* bitcast (i64* getelementptr inbounds ([4 x i64], [4 x i64]* @src64, i64 0, i64 2) to <2 x i64>*), align 4
; SSE-NEXT: [[TMP4:%.*]] = call <2 x i64> @llvm.bitreverse.v2i64(<2 x i64> [[TMP3]])
; SSE-NEXT: store <2 x i64> [[TMP4]], <2 x i64>* bitcast (i64* getelementptr inbounds ([4 x i64], [4 x i64]* @dst64, i64 0, i64 2) to <2 x i64>*), align 4
; SSE-NEXT: ret void
;
Expand Down Expand Up @@ -99,10 +99,10 @@ define void @bitreverse_4i32() #0 {
define void @bitreverse_8i32() #0 {
; SSE-LABEL: @bitreverse_8i32(
; SSE-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([8 x i32]* @src32 to <4 x i32>*), align 2
; SSE-NEXT: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @src32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE-NEXT: [[TMP3:%.*]] = call <4 x i32> @llvm.bitreverse.v4i32(<4 x i32> [[TMP1]])
; SSE-NEXT: [[TMP4:%.*]] = call <4 x i32> @llvm.bitreverse.v4i32(<4 x i32> [[TMP2]])
; SSE-NEXT: store <4 x i32> [[TMP3]], <4 x i32>* bitcast ([8 x i32]* @dst32 to <4 x i32>*), align 2
; SSE-NEXT: [[TMP2:%.*]] = call <4 x i32> @llvm.bitreverse.v4i32(<4 x i32> [[TMP1]])
; SSE-NEXT: store <4 x i32> [[TMP2]], <4 x i32>* bitcast ([8 x i32]* @dst32 to <4 x i32>*), align 2
; SSE-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @src32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE-NEXT: [[TMP4:%.*]] = call <4 x i32> @llvm.bitreverse.v4i32(<4 x i32> [[TMP3]])
; SSE-NEXT: store <4 x i32> [[TMP4]], <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @dst32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE-NEXT: ret void
;
Expand Down Expand Up @@ -182,10 +182,10 @@ define void @bitreverse_8i16() #0 {
define void @bitreverse_16i16() #0 {
; SSE-LABEL: @bitreverse_16i16(
; SSE-NEXT: [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* bitcast ([16 x i16]* @src16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP2:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @src16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: [[TMP3:%.*]] = call <8 x i16> @llvm.bitreverse.v8i16(<8 x i16> [[TMP1]])
; SSE-NEXT: [[TMP4:%.*]] = call <8 x i16> @llvm.bitreverse.v8i16(<8 x i16> [[TMP2]])
; SSE-NEXT: store <8 x i16> [[TMP3]], <8 x i16>* bitcast ([16 x i16]* @dst16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.bitreverse.v8i16(<8 x i16> [[TMP1]])
; SSE-NEXT: store <8 x i16> [[TMP2]], <8 x i16>* bitcast ([16 x i16]* @dst16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP3:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @src16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: [[TMP4:%.*]] = call <8 x i16> @llvm.bitreverse.v8i16(<8 x i16> [[TMP3]])
; SSE-NEXT: store <8 x i16> [[TMP4]], <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @dst16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: ret void
;
Expand Down Expand Up @@ -313,10 +313,10 @@ define void @bitreverse_16i8() #0 {
define void @bitreverse_32i8() #0 {
; SSE-LABEL: @bitreverse_32i8(
; SSE-NEXT: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([32 x i8]* @src8 to <16 x i8>*), align 1
; SSE-NEXT: [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT: [[TMP3:%.*]] = call <16 x i8> @llvm.bitreverse.v16i8(<16 x i8> [[TMP1]])
; SSE-NEXT: [[TMP4:%.*]] = call <16 x i8> @llvm.bitreverse.v16i8(<16 x i8> [[TMP2]])
; SSE-NEXT: store <16 x i8> [[TMP3]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
; SSE-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.bitreverse.v16i8(<16 x i8> [[TMP1]])
; SSE-NEXT: store <16 x i8> [[TMP2]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
; SSE-NEXT: [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT: [[TMP4:%.*]] = call <16 x i8> @llvm.bitreverse.v16i8(<16 x i8> [[TMP3]])
; SSE-NEXT: store <16 x i8> [[TMP4]], <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @dst8, i8 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT: ret void
;
Expand Down
32 changes: 16 additions & 16 deletions llvm/test/Transforms/SLPVectorizer/X86/bottom-to-top-reorder.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -11,22 +11,22 @@ define void @test(i32* %0, i32* %1, i32* %2) {
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 2
; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 6
; CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 3
; CHECK-NEXT: [[TMP12:%.*]] = bitcast i32* [[TMP1]] to <4 x i32>*
; CHECK-NEXT: [[TMP13:%.*]] = load <4 x i32>, <4 x i32>* [[TMP12]], align 4
; CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 3
; CHECK-NEXT: [[TMP15:%.*]] = bitcast i32* [[TMP0]] to <4 x i32>*
; CHECK-NEXT: [[TMP16:%.*]] = load <4 x i32>, <4 x i32>* [[TMP15]], align 4
; CHECK-NEXT: [[TMP17:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 7
; CHECK-NEXT: [[TMP18:%.*]] = bitcast i32* [[TMP4]] to <4 x i32>*
; CHECK-NEXT: [[TMP19:%.*]] = load <4 x i32>, <4 x i32>* [[TMP18]], align 4
; CHECK-NEXT: [[TMP20:%.*]] = sub <4 x i32> <i32 0, i32 0, i32 undef, i32 0>, [[TMP16]]
; CHECK-NEXT: [[TMP21:%.*]] = sub <4 x i32> [[TMP20]], [[TMP19]]
; CHECK-NEXT: [[TMP22:%.*]] = add <4 x i32> [[TMP21]], [[TMP13]]
; CHECK-NEXT: [[TMP23:%.*]] = getelementptr inbounds i32, i32* [[TMP2:%.*]], i64 2
; CHECK-NEXT: [[TMP24:%.*]] = getelementptr inbounds i32, i32* [[TMP2]], i64 1
; CHECK-NEXT: [[TMP25:%.*]] = getelementptr inbounds i32, i32* [[TMP2]], i64 3
; CHECK-NEXT: [[TMP26:%.*]] = add <4 x i32> [[TMP22]], <i32 0, i32 0, i32 1, i32 0>
; CHECK-NEXT: [[TMP27:%.*]] = sub <4 x i32> [[TMP22]], <i32 0, i32 0, i32 1, i32 0>
; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 3
; CHECK-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 7
; CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, i32* [[TMP2:%.*]], i64 2
; CHECK-NEXT: [[TMP15:%.*]] = getelementptr inbounds i32, i32* [[TMP2]], i64 1
; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, i32* [[TMP2]], i64 3
; CHECK-NEXT: [[TMP17:%.*]] = bitcast i32* [[TMP1]] to <4 x i32>*
; CHECK-NEXT: [[TMP18:%.*]] = load <4 x i32>, <4 x i32>* [[TMP17]], align 4
; CHECK-NEXT: [[TMP19:%.*]] = bitcast i32* [[TMP0]] to <4 x i32>*
; CHECK-NEXT: [[TMP20:%.*]] = load <4 x i32>, <4 x i32>* [[TMP19]], align 4
; CHECK-NEXT: [[TMP21:%.*]] = bitcast i32* [[TMP4]] to <4 x i32>*
; CHECK-NEXT: [[TMP22:%.*]] = load <4 x i32>, <4 x i32>* [[TMP21]], align 4
; CHECK-NEXT: [[TMP23:%.*]] = sub <4 x i32> <i32 0, i32 0, i32 undef, i32 0>, [[TMP20]]
; CHECK-NEXT: [[TMP24:%.*]] = sub <4 x i32> [[TMP23]], [[TMP22]]
; CHECK-NEXT: [[TMP25:%.*]] = add <4 x i32> [[TMP24]], [[TMP18]]
; CHECK-NEXT: [[TMP26:%.*]] = add <4 x i32> [[TMP25]], <i32 0, i32 0, i32 1, i32 0>
; CHECK-NEXT: [[TMP27:%.*]] = sub <4 x i32> [[TMP25]], <i32 0, i32 0, i32 1, i32 0>
; CHECK-NEXT: [[TMP28:%.*]] = shufflevector <4 x i32> [[TMP26]], <4 x i32> [[TMP27]], <4 x i32> <i32 2, i32 0, i32 1, i32 7>
; CHECK-NEXT: [[TMP29:%.*]] = add <4 x i32> [[TMP28]], zeroinitializer
; CHECK-NEXT: [[TMP30:%.*]] = sub <4 x i32> [[TMP28]], zeroinitializer
Expand Down
18 changes: 9 additions & 9 deletions llvm/test/Transforms/SLPVectorizer/X86/broadcast.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -17,15 +17,15 @@ define void @bcast_vals(i64 *%A, i64 *%B, i64 *%S) {
; CHECK-NEXT: [[B0:%.*]] = load i64, i64* [[B:%.*]], align 8
; CHECK-NEXT: [[V1:%.*]] = sub i64 [[A0]], 1
; CHECK-NEXT: [[V2:%.*]] = sub i64 [[B0]], 1
; CHECK-NEXT: [[IDXS0:%.*]] = getelementptr inbounds i64, i64* [[S:%.*]], i64 0
; CHECK-NEXT: [[IDXS1:%.*]] = getelementptr inbounds i64, i64* [[S]], i64 1
; CHECK-NEXT: [[IDXS2:%.*]] = getelementptr inbounds i64, i64* [[S]], i64 2
; CHECK-NEXT: [[IDXS3:%.*]] = getelementptr inbounds i64, i64* [[S]], i64 3
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i64> poison, i64 [[V1]], i32 0
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x i64> [[TMP0]], <4 x i64> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x i64> poison, i64 [[V2]], i32 0
; CHECK-NEXT: [[SHUFFLE1:%.*]] = shufflevector <4 x i64> [[TMP1]], <4 x i64> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP2:%.*]] = add <4 x i64> [[SHUFFLE]], [[SHUFFLE1]]
; CHECK-NEXT: [[IDXS0:%.*]] = getelementptr inbounds i64, i64* [[S:%.*]], i64 0
; CHECK-NEXT: [[IDXS1:%.*]] = getelementptr inbounds i64, i64* [[S]], i64 1
; CHECK-NEXT: [[IDXS2:%.*]] = getelementptr inbounds i64, i64* [[S]], i64 2
; CHECK-NEXT: [[IDXS3:%.*]] = getelementptr inbounds i64, i64* [[S]], i64 3
; CHECK-NEXT: [[TMP3:%.*]] = bitcast i64* [[IDXS0]] to <4 x i64>*
; CHECK-NEXT: store <4 x i64> [[TMP2]], <4 x i64>* [[TMP3]], align 8
; CHECK-NEXT: ret void
Expand Down Expand Up @@ -66,11 +66,15 @@ define void @bcast_vals2(i16 *%A, i16 *%B, i16 *%C, i16 *%D, i16 *%E, i32 *%S) {
; CHECK-LABEL: @bcast_vals2(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A0:%.*]] = load i16, i16* [[A:%.*]], align 8
; CHECK-NEXT: [[V1:%.*]] = sext i16 [[A0]] to i32
; CHECK-NEXT: [[IDXS0:%.*]] = getelementptr inbounds i32, i32* [[S:%.*]], i64 0
; CHECK-NEXT: [[IDXS1:%.*]] = getelementptr inbounds i32, i32* [[S]], i64 1
; CHECK-NEXT: [[IDXS2:%.*]] = getelementptr inbounds i32, i32* [[S]], i64 2
; CHECK-NEXT: [[IDXS3:%.*]] = getelementptr inbounds i32, i32* [[S]], i64 3
; CHECK-NEXT: [[B0:%.*]] = load i16, i16* [[B:%.*]], align 8
; CHECK-NEXT: [[C0:%.*]] = load i16, i16* [[C:%.*]], align 8
; CHECK-NEXT: [[D0:%.*]] = load i16, i16* [[D:%.*]], align 8
; CHECK-NEXT: [[E0:%.*]] = load i16, i16* [[E:%.*]], align 8
; CHECK-NEXT: [[V1:%.*]] = sext i16 [[A0]] to i32
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i16> poison, i16 [[B0]], i32 0
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x i16> [[TMP0]], i16 [[C0]], i32 1
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <4 x i16> [[TMP1]], i16 [[E0]], i32 2
Expand All @@ -79,10 +83,6 @@ define void @bcast_vals2(i16 *%A, i16 *%B, i16 *%C, i16 *%D, i16 *%E, i32 *%S) {
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <4 x i32> poison, i32 [[V1]], i32 0
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x i32> [[TMP5]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP6:%.*]] = add <4 x i32> [[SHUFFLE]], [[TMP4]]
; CHECK-NEXT: [[IDXS0:%.*]] = getelementptr inbounds i32, i32* [[S:%.*]], i64 0
; CHECK-NEXT: [[IDXS1:%.*]] = getelementptr inbounds i32, i32* [[S]], i64 1
; CHECK-NEXT: [[IDXS2:%.*]] = getelementptr inbounds i32, i32* [[S]], i64 2
; CHECK-NEXT: [[IDXS3:%.*]] = getelementptr inbounds i32, i32* [[S]], i64 3
; CHECK-NEXT: [[TMP7:%.*]] = bitcast i32* [[IDXS0]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP6]], <4 x i32>* [[TMP7]], align 8
; CHECK-NEXT: ret void
Expand Down
16 changes: 8 additions & 8 deletions llvm/test/Transforms/SLPVectorizer/X86/bswap.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -103,10 +103,10 @@ define void @bswap_4i32() #0 {
define void @bswap_8i32() #0 {
; SSE-LABEL: @bswap_8i32(
; SSE-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([8 x i32]* @src32 to <4 x i32>*), align 2
; SSE-NEXT: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @src32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE-NEXT: [[TMP3:%.*]] = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> [[TMP1]])
; SSE-NEXT: [[TMP4:%.*]] = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> [[TMP2]])
; SSE-NEXT: store <4 x i32> [[TMP3]], <4 x i32>* bitcast ([8 x i32]* @dst32 to <4 x i32>*), align 2
; SSE-NEXT: [[TMP2:%.*]] = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> [[TMP1]])
; SSE-NEXT: store <4 x i32> [[TMP2]], <4 x i32>* bitcast ([8 x i32]* @dst32 to <4 x i32>*), align 2
; SSE-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @src32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE-NEXT: [[TMP4:%.*]] = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> [[TMP3]])
; SSE-NEXT: store <4 x i32> [[TMP4]], <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @dst32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE-NEXT: ret void
;
Expand Down Expand Up @@ -180,10 +180,10 @@ define void @bswap_8i16() #0 {
define void @bswap_16i16() #0 {
; SSE-LABEL: @bswap_16i16(
; SSE-NEXT: [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* bitcast ([16 x i16]* @src16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP2:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @src16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: [[TMP3:%.*]] = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> [[TMP1]])
; SSE-NEXT: [[TMP4:%.*]] = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> [[TMP2]])
; SSE-NEXT: store <8 x i16> [[TMP3]], <8 x i16>* bitcast ([16 x i16]* @dst16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> [[TMP1]])
; SSE-NEXT: store <8 x i16> [[TMP2]], <8 x i16>* bitcast ([16 x i16]* @dst16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP3:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @src16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: [[TMP4:%.*]] = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> [[TMP3]])
; SSE-NEXT: store <8 x i16> [[TMP4]], <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @dst16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: ret void
;
Expand Down
24 changes: 12 additions & 12 deletions llvm/test/Transforms/SLPVectorizer/X86/combined-stores-chains.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -23,21 +23,21 @@ define void @foo(i8* %v0, i8* readonly %v1) {
; CHECK-NEXT: [[T252:%.*]] = getelementptr inbounds i64, i64* [[T02]], i64 9
; CHECK-NEXT: [[T292:%.*]] = getelementptr inbounds i64, i64* [[T02]], i64 10
; CHECK-NEXT: [[T322:%.*]] = getelementptr inbounds i64, i64* [[T02]], i64 11
; CHECK-NEXT: [[TMP1:%.*]] = bitcast i32* [[T14]] to <4 x i32>*
; CHECK-NEXT: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP1]], align 4
; CHECK-NEXT: [[TMP3:%.*]] = bitcast i64* [[T142]] to <2 x i64>*
; CHECK-NEXT: [[TMP4:%.*]] = load <2 x i64>, <2 x i64>* [[TMP3]], align 8
; CHECK-NEXT: [[TMP1:%.*]] = bitcast i64* [[T142]] to <2 x i64>*
; CHECK-NEXT: [[TMP2:%.*]] = load <2 x i64>, <2 x i64>* [[TMP1]], align 8
; CHECK-NEXT: [[TMP3:%.*]] = add nsw <2 x i64> [[TMP2]], <i64 4, i64 4>
; CHECK-NEXT: [[TMP4:%.*]] = bitcast i64* [[T212]] to <2 x i64>*
; CHECK-NEXT: [[TMP5:%.*]] = bitcast i64* [[T222]] to <2 x i64>*
; CHECK-NEXT: [[TMP6:%.*]] = load <2 x i64>, <2 x i64>* [[TMP5]], align 8
; CHECK-NEXT: [[TMP7:%.*]] = add nsw <4 x i32> [[TMP2]], <i32 4, i32 4, i32 6, i32 7>
; CHECK-NEXT: [[TMP8:%.*]] = add nsw <2 x i64> [[TMP4]], <i64 4, i64 4>
; CHECK-NEXT: [[TMP9:%.*]] = add nsw <2 x i64> [[TMP6]], <i64 6, i64 7>
; CHECK-NEXT: [[TMP10:%.*]] = bitcast i64* [[T212]] to <2 x i64>*
; CHECK-NEXT: store <2 x i64> [[TMP8]], <2 x i64>* [[TMP10]], align 8
; CHECK-NEXT: [[TMP11:%.*]] = bitcast i64* [[T292]] to <2 x i64>*
; CHECK-NEXT: store <2 x i64> [[TMP9]], <2 x i64>* [[TMP11]], align 8
; CHECK-NEXT: [[TMP7:%.*]] = add nsw <2 x i64> [[TMP6]], <i64 6, i64 7>
; CHECK-NEXT: [[TMP8:%.*]] = bitcast i64* [[T292]] to <2 x i64>*
; CHECK-NEXT: [[TMP9:%.*]] = bitcast i32* [[T14]] to <4 x i32>*
; CHECK-NEXT: [[TMP10:%.*]] = load <4 x i32>, <4 x i32>* [[TMP9]], align 4
; CHECK-NEXT: [[TMP11:%.*]] = add nsw <4 x i32> [[TMP10]], <i32 4, i32 4, i32 6, i32 7>
; CHECK-NEXT: store <2 x i64> [[TMP3]], <2 x i64>* [[TMP4]], align 8
; CHECK-NEXT: store <2 x i64> [[TMP7]], <2 x i64>* [[TMP8]], align 8
; CHECK-NEXT: [[TMP12:%.*]] = bitcast i32* [[T21]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP7]], <4 x i32>* [[TMP12]], align 4
; CHECK-NEXT: store <4 x i32> [[TMP11]], <4 x i32>* [[TMP12]], align 4
; CHECK-NEXT: ret void
;
%t0 = bitcast i8* %v0 to i32*
Expand Down
10 changes: 5 additions & 5 deletions llvm/test/Transforms/SLPVectorizer/X86/consecutive-access.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -21,9 +21,9 @@ define void @foo_3double(i32 %u) #0 {
; CHECK-NEXT: [[ADD11:%.*]] = add nsw i32 [[MUL]], 1
; CHECK-NEXT: [[IDXPROM12:%.*]] = sext i32 [[ADD11]] to i64
; CHECK-NEXT: [[ARRAYIDX13:%.*]] = getelementptr inbounds [2000 x double], [2000 x double]* @A, i32 0, i64 [[IDXPROM12]]
; CHECK-NEXT: [[ARRAYIDX17:%.*]] = getelementptr inbounds [2000 x double], [2000 x double]* @B, i32 0, i64 [[IDXPROM12]]
; CHECK-NEXT: [[TMP0:%.*]] = bitcast double* [[ARRAYIDX]] to <2 x double>*
; CHECK-NEXT: [[TMP1:%.*]] = load <2 x double>, <2 x double>* [[TMP0]], align 8
; CHECK-NEXT: [[ARRAYIDX17:%.*]] = getelementptr inbounds [2000 x double], [2000 x double]* @B, i32 0, i64 [[IDXPROM12]]
; CHECK-NEXT: [[TMP2:%.*]] = bitcast double* [[ARRAYIDX4]] to <2 x double>*
; CHECK-NEXT: [[TMP3:%.*]] = load <2 x double>, <2 x double>* [[TMP2]], align 8
; CHECK-NEXT: [[TMP4:%.*]] = fadd <2 x double> [[TMP1]], [[TMP3]]
Expand Down Expand Up @@ -85,9 +85,9 @@ define void @foo_2double(i32 %u) #0 {
; CHECK-NEXT: [[ADD11:%.*]] = add nsw i32 [[MUL]], 1
; CHECK-NEXT: [[IDXPROM12:%.*]] = sext i32 [[ADD11]] to i64
; CHECK-NEXT: [[ARRAYIDX13:%.*]] = getelementptr inbounds [2000 x double], [2000 x double]* @A, i32 0, i64 [[IDXPROM12]]
; CHECK-NEXT: [[ARRAYIDX17:%.*]] = getelementptr inbounds [2000 x double], [2000 x double]* @B, i32 0, i64 [[IDXPROM12]]
; CHECK-NEXT: [[TMP0:%.*]] = bitcast double* [[ARRAYIDX]] to <2 x double>*
; CHECK-NEXT: [[TMP1:%.*]] = load <2 x double>, <2 x double>* [[TMP0]], align 8
; CHECK-NEXT: [[ARRAYIDX17:%.*]] = getelementptr inbounds [2000 x double], [2000 x double]* @B, i32 0, i64 [[IDXPROM12]]
; CHECK-NEXT: [[TMP2:%.*]] = bitcast double* [[ARRAYIDX4]] to <2 x double>*
; CHECK-NEXT: [[TMP3:%.*]] = load <2 x double>, <2 x double>* [[TMP2]], align 8
; CHECK-NEXT: [[TMP4:%.*]] = fadd <2 x double> [[TMP1]], [[TMP3]]
Expand Down Expand Up @@ -139,9 +139,9 @@ define void @foo_4float(i32 %u) #0 {
; CHECK-NEXT: [[ADD37:%.*]] = add nsw i32 [[MUL]], 3
; CHECK-NEXT: [[IDXPROM38:%.*]] = sext i32 [[ADD37]] to i64
; CHECK-NEXT: [[ARRAYIDX39:%.*]] = getelementptr inbounds [2000 x float], [2000 x float]* @C, i32 0, i64 [[IDXPROM38]]
; CHECK-NEXT: [[ARRAYIDX43:%.*]] = getelementptr inbounds [2000 x float], [2000 x float]* @D, i32 0, i64 [[IDXPROM38]]
; CHECK-NEXT: [[TMP0:%.*]] = bitcast float* [[ARRAYIDX]] to <4 x float>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
; CHECK-NEXT: [[ARRAYIDX43:%.*]] = getelementptr inbounds [2000 x float], [2000 x float]* @D, i32 0, i64 [[IDXPROM38]]
; CHECK-NEXT: [[TMP2:%.*]] = bitcast float* [[ARRAYIDX4]] to <4 x float>*
; CHECK-NEXT: [[TMP3:%.*]] = load <4 x float>, <4 x float>* [[TMP2]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = fadd <4 x float> [[TMP1]], [[TMP3]]
Expand Down Expand Up @@ -295,9 +295,9 @@ define void @foo_2double_non_power_of_2(i32 %u) #0 {
; CHECK-NEXT: [[ADD7:%.*]] = add i32 [[MUL]], 7
; CHECK-NEXT: [[IDXPROM12:%.*]] = sext i32 [[ADD7]] to i64
; CHECK-NEXT: [[ARRAYIDX13:%.*]] = getelementptr inbounds [2000 x double], [2000 x double]* @A, i32 0, i64 [[IDXPROM12]]
; CHECK-NEXT: [[ARRAYIDX17:%.*]] = getelementptr inbounds [2000 x double], [2000 x double]* @B, i32 0, i64 [[IDXPROM12]]
; CHECK-NEXT: [[TMP0:%.*]] = bitcast double* [[ARRAYIDX]] to <2 x double>*
; CHECK-NEXT: [[TMP1:%.*]] = load <2 x double>, <2 x double>* [[TMP0]], align 8
; CHECK-NEXT: [[ARRAYIDX17:%.*]] = getelementptr inbounds [2000 x double], [2000 x double]* @B, i32 0, i64 [[IDXPROM12]]
; CHECK-NEXT: [[TMP2:%.*]] = bitcast double* [[ARRAYIDX4]] to <2 x double>*
; CHECK-NEXT: [[TMP3:%.*]] = load <2 x double>, <2 x double>* [[TMP2]], align 8
; CHECK-NEXT: [[TMP4:%.*]] = fadd <2 x double> [[TMP1]], [[TMP3]]
Expand Down Expand Up @@ -343,9 +343,9 @@ define void @foo_2double_non_power_of_2_zext(i32 %u) #0 {
; CHECK-NEXT: [[ADD7:%.*]] = add i32 [[MUL]], 7
; CHECK-NEXT: [[IDXPROM12:%.*]] = zext i32 [[ADD7]] to i64
; CHECK-NEXT: [[ARRAYIDX13:%.*]] = getelementptr inbounds [2000 x double], [2000 x double]* @A, i32 0, i64 [[IDXPROM12]]
; CHECK-NEXT: [[ARRAYIDX17:%.*]] = getelementptr inbounds [2000 x double], [2000 x double]* @B, i32 0, i64 [[IDXPROM12]]
; CHECK-NEXT: [[TMP0:%.*]] = bitcast double* [[ARRAYIDX]] to <2 x double>*
; CHECK-NEXT: [[TMP1:%.*]] = load <2 x double>, <2 x double>* [[TMP0]], align 8
; CHECK-NEXT: [[ARRAYIDX17:%.*]] = getelementptr inbounds [2000 x double], [2000 x double]* @B, i32 0, i64 [[IDXPROM12]]
; CHECK-NEXT: [[TMP2:%.*]] = bitcast double* [[ARRAYIDX4]] to <2 x double>*
; CHECK-NEXT: [[TMP3:%.*]] = load <2 x double>, <2 x double>* [[TMP2]], align 8
; CHECK-NEXT: [[TMP4:%.*]] = fadd <2 x double> [[TMP1]], [[TMP3]]
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/Transforms/SLPVectorizer/X86/continue_vectorizing.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -9,13 +9,13 @@ define void @test1(double* %a, double* %b, double* %c, double* %d) {
; CHECK-LABEL: @test1(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds double, double* [[A:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds double, double* [[B:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds double, double* [[C:%.*]], i64 1
; CHECK-NEXT: [[TMP0:%.*]] = bitcast double* [[A]] to <2 x double>*
; CHECK-NEXT: [[TMP1:%.*]] = load <2 x double>, <2 x double>* [[TMP0]], align 8
; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds double, double* [[B:%.*]], i64 1
; CHECK-NEXT: [[TMP2:%.*]] = bitcast double* [[B]] to <2 x double>*
; CHECK-NEXT: [[TMP3:%.*]] = load <2 x double>, <2 x double>* [[TMP2]], align 8
; CHECK-NEXT: [[TMP4:%.*]] = fmul <2 x double> [[TMP1]], [[TMP3]]
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds double, double* [[C:%.*]], i64 1
; CHECK-NEXT: [[TMP5:%.*]] = bitcast double* [[C]] to <2 x double>*
; CHECK-NEXT: store <2 x double> [[TMP4]], <2 x double>* [[TMP5]], align 8
; CHECK-NEXT: [[TMP6:%.*]] = bitcast double* [[A]] to <4 x i32>*
Expand Down
18 changes: 9 additions & 9 deletions llvm/test/Transforms/SLPVectorizer/X86/crash_exceed_scheduling.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -4,20 +4,12 @@
define void @exceed(double %0, double %1) {
; CHECK-LABEL: @exceed(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x double> poison, double [[TMP0:%.*]], i32 0
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <2 x double> [[TMP2]], double [[TMP0]], i32 1
; CHECK-NEXT: [[TMP4:%.*]] = insertelement <2 x double> poison, double [[TMP1:%.*]], i32 0
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <2 x double> [[TMP4]], double [[TMP1]], i32 1
; CHECK-NEXT: [[TMP6:%.*]] = fdiv fast <2 x double> [[TMP3]], [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = extractelement <2 x double> [[TMP6]], i32 1
; CHECK-NEXT: [[IX:%.*]] = fmul double [[TMP7]], undef
; CHECK-NEXT: [[IXX0:%.*]] = fsub double undef, undef
; CHECK-NEXT: [[IXX1:%.*]] = fsub double undef, undef
; CHECK-NEXT: [[IXX2:%.*]] = fsub double undef, undef
; CHECK-NEXT: [[IXX3:%.*]] = fsub double undef, undef
; CHECK-NEXT: [[IXX4:%.*]] = fsub double undef, undef
; CHECK-NEXT: [[IXX5:%.*]] = fsub double undef, undef
; CHECK-NEXT: [[IX1:%.*]] = fmul double [[TMP7]], undef
; CHECK-NEXT: [[IXX10:%.*]] = fsub double undef, undef
; CHECK-NEXT: [[IXX11:%.*]] = fsub double undef, undef
; CHECK-NEXT: [[IXX12:%.*]] = fsub double undef, undef
Expand All @@ -27,13 +19,21 @@ define void @exceed(double %0, double %1) {
; CHECK-NEXT: [[IXX20:%.*]] = fsub double undef, undef
; CHECK-NEXT: [[IXX21:%.*]] = fsub double undef, undef
; CHECK-NEXT: [[IXX22:%.*]] = fsub double undef, undef
; CHECK-NEXT: [[IXX101:%.*]] = fsub double undef, undef
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x double> poison, double [[TMP0:%.*]], i32 0
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <2 x double> [[TMP2]], double [[TMP0]], i32 1
; CHECK-NEXT: [[TMP4:%.*]] = insertelement <2 x double> poison, double [[TMP1:%.*]], i32 0
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <2 x double> [[TMP4]], double [[TMP1]], i32 1
; CHECK-NEXT: [[TMP6:%.*]] = fdiv fast <2 x double> [[TMP3]], [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = extractelement <2 x double> [[TMP6]], i32 1
; CHECK-NEXT: [[IX:%.*]] = fmul double [[TMP7]], undef
; CHECK-NEXT: [[IX1:%.*]] = fmul double [[TMP7]], undef
; CHECK-NEXT: [[TMP8:%.*]] = extractelement <2 x double> [[TMP6]], i32 0
; CHECK-NEXT: [[IX2:%.*]] = fmul double [[TMP8]], [[TMP8]]
; CHECK-NEXT: [[TMP9:%.*]] = insertelement <2 x double> [[TMP2]], double [[TMP1]], i32 1
; CHECK-NEXT: [[TMP10:%.*]] = fadd fast <2 x double> [[TMP6]], [[TMP9]]
; CHECK-NEXT: [[TMP11:%.*]] = fadd fast <2 x double> [[TMP3]], [[TMP5]]
; CHECK-NEXT: [[TMP12:%.*]] = fmul fast <2 x double> [[TMP10]], [[TMP11]]
; CHECK-NEXT: [[IXX101:%.*]] = fsub double undef, undef
; CHECK-NEXT: [[TMP13:%.*]] = insertelement <2 x double> poison, double [[TMP1]], i32 1
; CHECK-NEXT: [[TMP14:%.*]] = insertelement <2 x double> [[TMP13]], double [[TMP7]], i32 0
; CHECK-NEXT: [[TMP15:%.*]] = fmul fast <2 x double> [[TMP14]], undef
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/Transforms/SLPVectorizer/X86/crash_mandeltext.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -93,12 +93,12 @@ for.end48: ; preds = %for.end44
define void @zot(%struct.hoge* %arg) {
; CHECK-LABEL: @zot(
; CHECK-NEXT: bb:
; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds [[STRUCT_HOGE:%.*]], %struct.hoge* [[ARG:%.*]], i64 0, i32 1
; CHECK-NEXT: [[TMP:%.*]] = load double, double* undef, align 8
; CHECK-NEXT: [[TMP2:%.*]] = load double, double* undef, align 8
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <2 x double> poison, double [[TMP2]], i32 0
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x double> [[TMP0]], double [[TMP]], i32 1
; CHECK-NEXT: [[TMP2:%.*]] = fsub <2 x double> [[TMP1]], undef
; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds [[STRUCT_HOGE:%.*]], %struct.hoge* [[ARG:%.*]], i64 0, i32 1
; CHECK-NEXT: [[TMP3:%.*]] = fmul <2 x double> [[TMP2]], undef
; CHECK-NEXT: [[TMP4:%.*]] = fsub <2 x double> [[TMP3]], undef
; CHECK-NEXT: [[TMP5:%.*]] = bitcast double* [[TMP7]] to <2 x double>*
Expand Down
14 changes: 7 additions & 7 deletions llvm/test/Transforms/SLPVectorizer/X86/crash_smallpt.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -36,13 +36,13 @@ define void @main() #0 {
; CHECK-NEXT: [[TMP3:%.*]] = fadd <2 x double> [[TMP2]], <double 5.000000e+01, double 5.200000e+01>
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <2 x double> [[TMP1]], i32 0
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <2 x double> [[TMP1]], i32 1
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x double> <double poison, double undef>, double [[TMP4]], i32 0
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x double> <double undef, double poison>, double [[TMP5]], i32 1
; CHECK-NEXT: [[TMP8:%.*]] = fmul <2 x double> [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP9:%.*]] = bitcast double* [[AGG_TMP99208_SROA_0_0_IDX]] to <2 x double>*
; CHECK-NEXT: store <2 x double> [[TMP3]], <2 x double>* [[TMP9]], align 8
; CHECK-NEXT: [[TMP6:%.*]] = bitcast double* [[AGG_TMP99208_SROA_0_0_IDX]] to <2 x double>*
; CHECK-NEXT: store <2 x double> [[TMP3]], <2 x double>* [[TMP6]], align 8
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x double> <double poison, double undef>, double [[TMP4]], i32 0
; CHECK-NEXT: [[TMP8:%.*]] = insertelement <2 x double> <double undef, double poison>, double [[TMP5]], i32 1
; CHECK-NEXT: [[TMP9:%.*]] = fmul <2 x double> [[TMP7]], [[TMP8]]
; CHECK-NEXT: [[TMP10:%.*]] = bitcast double* [[AGG_TMP101211_SROA_0_0_IDX]] to <2 x double>*
; CHECK-NEXT: store <2 x double> [[TMP8]], <2 x double>* [[TMP10]], align 8
; CHECK-NEXT: store <2 x double> [[TMP9]], <2 x double>* [[TMP10]], align 8
; CHECK-NEXT: unreachable
; CHECK: cond.true63.us:
; CHECK-NEXT: unreachable
Expand Down Expand Up @@ -114,6 +114,7 @@ define void @_Z8radianceRK3RayiPt() #0 {
; CHECK-NEXT: entry:
; CHECK-NEXT: br i1 undef, label [[IF_THEN78:%.*]], label [[IF_THEN38:%.*]]
; CHECK: if.then38:
; CHECK-NEXT: [[AGG_TMP74663_SROA_0_0_IDX:%.*]] = getelementptr inbounds [[STRUCT_RAY_5_11_53_95_137_191_197_203_239_257_263_269_275_281_287_293_383_437_443_455_461_599_601:%.*]], %struct.Ray.5.11.53.95.137.191.197.203.239.257.263.269.275.281.287.293.383.437.443.455.461.599.601* undef, i64 0, i32 1, i32 0
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <2 x double> <double undef, double poison>, double undef, i32 1
; CHECK-NEXT: [[TMP1:%.*]] = fmul <2 x double> undef, [[TMP0]]
; CHECK-NEXT: [[TMP2:%.*]] = fsub <2 x double> undef, [[TMP1]]
Expand All @@ -122,7 +123,6 @@ define void @_Z8radianceRK3RayiPt() #0 {
; CHECK-NEXT: [[TMP5:%.*]] = fadd <2 x double> undef, [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = fadd <2 x double> undef, [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = fmul <2 x double> undef, [[TMP6]]
; CHECK-NEXT: [[AGG_TMP74663_SROA_0_0_IDX:%.*]] = getelementptr inbounds [[STRUCT_RAY_5_11_53_95_137_191_197_203_239_257_263_269_275_281_287_293_383_437_443_455_461_599_601:%.*]], %struct.Ray.5.11.53.95.137.191.197.203.239.257.263.269.275.281.287.293.383.437.443.455.461.599.601* undef, i64 0, i32 1, i32 0
; CHECK-NEXT: [[TMP8:%.*]] = bitcast double* [[AGG_TMP74663_SROA_0_0_IDX]] to <2 x double>*
; CHECK-NEXT: store <2 x double> [[TMP7]], <2 x double>* [[TMP8]], align 8
; CHECK-NEXT: br label [[RETURN:%.*]]
Expand Down
28 changes: 14 additions & 14 deletions llvm/test/Transforms/SLPVectorizer/X86/cse.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -16,21 +16,21 @@ define i32 @test(double* nocapture %G) {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds double, double* [[G:%.*]], i64 5
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds double, double* [[G]], i64 6
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds double, double* [[G]], i64 1
; CHECK-NEXT: [[TMP0:%.*]] = bitcast double* [[ARRAYIDX]] to <2 x double>*
; CHECK-NEXT: [[TMP1:%.*]] = load <2 x double>, <2 x double>* [[TMP0]], align 8
; CHECK-NEXT: [[TMP2:%.*]] = fmul <2 x double> [[TMP1]], <double 4.000000e+00, double 3.000000e+00>
; CHECK-NEXT: [[TMP3:%.*]] = fadd <2 x double> [[TMP2]], <double 1.000000e+00, double 6.000000e+00>
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds double, double* [[G]], i64 1
; CHECK-NEXT: [[TMP4:%.*]] = bitcast double* [[G]] to <2 x double>*
; CHECK-NEXT: store <2 x double> [[TMP3]], <2 x double>* [[TMP4]], align 8
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <2 x double> [[TMP2]], i32 0
; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds double, double* [[G]], i64 2
; CHECK-NEXT: [[TMP6:%.*]] = extractelement <2 x double> [[TMP1]], i32 1
; CHECK-NEXT: [[MUL11:%.*]] = fmul double [[TMP6]], 4.000000e+00
; CHECK-NEXT: [[ARRAYIDX13:%.*]] = getelementptr inbounds double, double* [[G]], i64 3
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x double> poison, double [[TMP5]], i32 0
; CHECK-NEXT: [[TMP8:%.*]] = insertelement <2 x double> [[TMP7]], double [[MUL11]], i32 1
; CHECK-NEXT: [[TMP9:%.*]] = fadd <2 x double> [[TMP8]], <double 7.000000e+00, double 8.000000e+00>
; CHECK-NEXT: [[ARRAYIDX13:%.*]] = getelementptr inbounds double, double* [[G]], i64 3
; CHECK-NEXT: [[TMP10:%.*]] = bitcast double* [[ARRAYIDX9]] to <2 x double>*
; CHECK-NEXT: store <2 x double> [[TMP9]], <2 x double>* [[TMP10]], align 8
; CHECK-NEXT: ret i32 undef
Expand Down Expand Up @@ -133,24 +133,24 @@ define i32 @test2(double* nocapture %G, i32 %k) {
; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds double, double* [[G]], i64 6
; CHECK-NEXT: [[TMP7:%.*]] = load double, double* [[TMP6]], align 8
; CHECK-NEXT: [[TMP8:%.*]] = fmul double [[TMP7]], 3.000000e+00
; CHECK-NEXT: [[TMP9:%.*]] = insertelement <2 x double> poison, double [[TMP4]], i32 0
; CHECK-NEXT: [[TMP10:%.*]] = insertelement <2 x double> [[TMP9]], double [[TMP8]], i32 1
; CHECK-NEXT: [[TMP11:%.*]] = fadd <2 x double> [[TMP10]], <double 1.000000e+00, double 6.000000e+00>
; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds double, double* [[G]], i64 1
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds double, double* [[G]], i64 1
; CHECK-NEXT: [[TMP10:%.*]] = insertelement <2 x double> poison, double [[TMP4]], i32 0
; CHECK-NEXT: [[TMP11:%.*]] = insertelement <2 x double> [[TMP10]], double [[TMP8]], i32 1
; CHECK-NEXT: [[TMP12:%.*]] = fadd <2 x double> [[TMP11]], <double 1.000000e+00, double 6.000000e+00>
; CHECK-NEXT: [[TMP13:%.*]] = bitcast double* [[G]] to <2 x double>*
; CHECK-NEXT: store <2 x double> [[TMP11]], <2 x double>* [[TMP13]], align 8
; CHECK-NEXT: store <2 x double> [[TMP12]], <2 x double>* [[TMP13]], align 8
; CHECK-NEXT: br label [[TMP24:%.*]]
; CHECK: 14:
; CHECK-NEXT: [[TMP15:%.*]] = getelementptr inbounds double, double* [[G]], i64 2
; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds double, double* [[G]], i64 6
; CHECK-NEXT: [[TMP17:%.*]] = load double, double* [[TMP16]], align 8
; CHECK-NEXT: [[TMP18:%.*]] = fmul double [[TMP17]], 3.000000e+00
; CHECK-NEXT: [[TMP19:%.*]] = insertelement <2 x double> poison, double [[TMP4]], i32 0
; CHECK-NEXT: [[TMP20:%.*]] = insertelement <2 x double> [[TMP19]], double [[TMP18]], i32 1
; CHECK-NEXT: [[TMP21:%.*]] = fadd <2 x double> [[TMP20]], <double 7.000000e+00, double 8.000000e+00>
; CHECK-NEXT: [[TMP22:%.*]] = getelementptr inbounds double, double* [[G]], i64 3
; CHECK-NEXT: [[TMP19:%.*]] = getelementptr inbounds double, double* [[G]], i64 3
; CHECK-NEXT: [[TMP20:%.*]] = insertelement <2 x double> poison, double [[TMP4]], i32 0
; CHECK-NEXT: [[TMP21:%.*]] = insertelement <2 x double> [[TMP20]], double [[TMP18]], i32 1
; CHECK-NEXT: [[TMP22:%.*]] = fadd <2 x double> [[TMP21]], <double 7.000000e+00, double 8.000000e+00>
; CHECK-NEXT: [[TMP23:%.*]] = bitcast double* [[TMP15]] to <2 x double>*
; CHECK-NEXT: store <2 x double> [[TMP21]], <2 x double>* [[TMP23]], align 8
; CHECK-NEXT: store <2 x double> [[TMP22]], <2 x double>* [[TMP23]], align 8
; CHECK-NEXT: br label [[TMP24]]
; CHECK: 24:
; CHECK-NEXT: ret i32 undef
Expand Down Expand Up @@ -267,10 +267,10 @@ define i32 @partial_mrg(double* nocapture %A, i32 %n) {
; CHECK: if.end:
; CHECK-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds double, double* [[A]], i64 2
; CHECK-NEXT: [[ARRAYIDX11:%.*]] = getelementptr inbounds double, double* [[A]], i64 3
; CHECK-NEXT: [[TMP6:%.*]] = bitcast double* [[ARRAYIDX7]] to <2 x double>*
; CHECK-NEXT: [[TMP7:%.*]] = load <2 x double>, <2 x double>* [[TMP6]], align 8
; CHECK-NEXT: [[ADD:%.*]] = add nsw i32 [[N]], 4
; CHECK-NEXT: [[CONV12:%.*]] = sitofp i32 [[ADD]] to double
; CHECK-NEXT: [[TMP6:%.*]] = bitcast double* [[ARRAYIDX7]] to <2 x double>*
; CHECK-NEXT: [[TMP7:%.*]] = load <2 x double>, <2 x double>* [[TMP6]], align 8
; CHECK-NEXT: [[TMP8:%.*]] = insertelement <2 x double> [[TMP2]], double [[CONV12]], i32 1
; CHECK-NEXT: [[TMP9:%.*]] = fmul <2 x double> [[TMP8]], [[TMP7]]
; CHECK-NEXT: [[TMP10:%.*]] = bitcast double* [[ARRAYIDX7]] to <2 x double>*
Expand Down
48 changes: 24 additions & 24 deletions llvm/test/Transforms/SLPVectorizer/X86/ctlz.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -168,10 +168,10 @@ define void @ctlz_8i32() #0 {
;
; SSE42-LABEL: @ctlz_8i32(
; SSE42-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([8 x i32]* @src32 to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @src32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP3:%.*]] = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> [[TMP1]], i1 false)
; SSE42-NEXT: [[TMP4:%.*]] = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> [[TMP2]], i1 false)
; SSE42-NEXT: store <4 x i32> [[TMP3]], <4 x i32>* bitcast ([8 x i32]* @dst32 to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP2:%.*]] = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> [[TMP1]], i1 false)
; SSE42-NEXT: store <4 x i32> [[TMP2]], <4 x i32>* bitcast ([8 x i32]* @dst32 to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @src32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP4:%.*]] = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> [[TMP3]], i1 false)
; SSE42-NEXT: store <4 x i32> [[TMP4]], <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @dst32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE42-NEXT: ret void
;
Expand Down Expand Up @@ -245,10 +245,10 @@ define void @ctlz_8i16() #0 {
define void @ctlz_16i16() #0 {
; SSE-LABEL: @ctlz_16i16(
; SSE-NEXT: [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* bitcast ([16 x i16]* @src16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP2:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @src16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: [[TMP3:%.*]] = call <8 x i16> @llvm.ctlz.v8i16(<8 x i16> [[TMP1]], i1 false)
; SSE-NEXT: [[TMP4:%.*]] = call <8 x i16> @llvm.ctlz.v8i16(<8 x i16> [[TMP2]], i1 false)
; SSE-NEXT: store <8 x i16> [[TMP3]], <8 x i16>* bitcast ([16 x i16]* @dst16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.ctlz.v8i16(<8 x i16> [[TMP1]], i1 false)
; SSE-NEXT: store <8 x i16> [[TMP2]], <8 x i16>* bitcast ([16 x i16]* @dst16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP3:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @src16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: [[TMP4:%.*]] = call <8 x i16> @llvm.ctlz.v8i16(<8 x i16> [[TMP3]], i1 false)
; SSE-NEXT: store <8 x i16> [[TMP4]], <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @dst16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: ret void
;
Expand Down Expand Up @@ -370,10 +370,10 @@ define void @ctlz_16i8() #0 {
define void @ctlz_32i8() #0 {
; SSE-LABEL: @ctlz_32i8(
; SSE-NEXT: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([32 x i8]* @src8 to <16 x i8>*), align 1
; SSE-NEXT: [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT: [[TMP3:%.*]] = call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> [[TMP1]], i1 false)
; SSE-NEXT: [[TMP4:%.*]] = call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> [[TMP2]], i1 false)
; SSE-NEXT: store <16 x i8> [[TMP3]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
; SSE-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> [[TMP1]], i1 false)
; SSE-NEXT: store <16 x i8> [[TMP2]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
; SSE-NEXT: [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT: [[TMP4:%.*]] = call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> [[TMP3]], i1 false)
; SSE-NEXT: store <16 x i8> [[TMP4]], <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @dst8, i8 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT: ret void
;
Expand Down Expand Up @@ -630,10 +630,10 @@ define void @ctlz_undef_8i32() #0 {
;
; SSE42-LABEL: @ctlz_undef_8i32(
; SSE42-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([8 x i32]* @src32 to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @src32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP3:%.*]] = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> [[TMP1]], i1 true)
; SSE42-NEXT: [[TMP4:%.*]] = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> [[TMP2]], i1 true)
; SSE42-NEXT: store <4 x i32> [[TMP3]], <4 x i32>* bitcast ([8 x i32]* @dst32 to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP2:%.*]] = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> [[TMP1]], i1 true)
; SSE42-NEXT: store <4 x i32> [[TMP2]], <4 x i32>* bitcast ([8 x i32]* @dst32 to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @src32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP4:%.*]] = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> [[TMP3]], i1 true)
; SSE42-NEXT: store <4 x i32> [[TMP4]], <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @dst32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE42-NEXT: ret void
;
Expand Down Expand Up @@ -707,10 +707,10 @@ define void @ctlz_undef_8i16() #0 {
define void @ctlz_undef_16i16() #0 {
; SSE-LABEL: @ctlz_undef_16i16(
; SSE-NEXT: [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* bitcast ([16 x i16]* @src16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP2:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @src16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: [[TMP3:%.*]] = call <8 x i16> @llvm.ctlz.v8i16(<8 x i16> [[TMP1]], i1 true)
; SSE-NEXT: [[TMP4:%.*]] = call <8 x i16> @llvm.ctlz.v8i16(<8 x i16> [[TMP2]], i1 true)
; SSE-NEXT: store <8 x i16> [[TMP3]], <8 x i16>* bitcast ([16 x i16]* @dst16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.ctlz.v8i16(<8 x i16> [[TMP1]], i1 true)
; SSE-NEXT: store <8 x i16> [[TMP2]], <8 x i16>* bitcast ([16 x i16]* @dst16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP3:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @src16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: [[TMP4:%.*]] = call <8 x i16> @llvm.ctlz.v8i16(<8 x i16> [[TMP3]], i1 true)
; SSE-NEXT: store <8 x i16> [[TMP4]], <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @dst16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: ret void
;
Expand Down Expand Up @@ -832,10 +832,10 @@ define void @ctlz_undef_16i8() #0 {
define void @ctlz_undef_32i8() #0 {
; SSE-LABEL: @ctlz_undef_32i8(
; SSE-NEXT: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([32 x i8]* @src8 to <16 x i8>*), align 1
; SSE-NEXT: [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT: [[TMP3:%.*]] = call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> [[TMP1]], i1 true)
; SSE-NEXT: [[TMP4:%.*]] = call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> [[TMP2]], i1 true)
; SSE-NEXT: store <16 x i8> [[TMP3]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
; SSE-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> [[TMP1]], i1 true)
; SSE-NEXT: store <16 x i8> [[TMP2]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
; SSE-NEXT: [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT: [[TMP4:%.*]] = call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> [[TMP3]], i1 true)
; SSE-NEXT: store <16 x i8> [[TMP4]], <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @dst8, i8 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT: ret void
;
Expand Down
32 changes: 16 additions & 16 deletions llvm/test/Transforms/SLPVectorizer/X86/ctpop.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -63,10 +63,10 @@ define void @ctpop_2i64() #0 {
define void @ctpop_4i64() #0 {
; SSE2-LABEL: @ctpop_4i64(
; SSE2-NEXT: [[TMP1:%.*]] = load <2 x i64>, <2 x i64>* bitcast ([4 x i64]* @src64 to <2 x i64>*), align 4
; SSE2-NEXT: [[TMP2:%.*]] = load <2 x i64>, <2 x i64>* bitcast (i64* getelementptr inbounds ([4 x i64], [4 x i64]* @src64, i64 0, i64 2) to <2 x i64>*), align 4
; SSE2-NEXT: [[TMP3:%.*]] = call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> [[TMP1]])
; SSE2-NEXT: [[TMP4:%.*]] = call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> [[TMP2]])
; SSE2-NEXT: store <2 x i64> [[TMP3]], <2 x i64>* bitcast ([4 x i64]* @dst64 to <2 x i64>*), align 4
; SSE2-NEXT: [[TMP2:%.*]] = call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> [[TMP1]])
; SSE2-NEXT: store <2 x i64> [[TMP2]], <2 x i64>* bitcast ([4 x i64]* @dst64 to <2 x i64>*), align 4
; SSE2-NEXT: [[TMP3:%.*]] = load <2 x i64>, <2 x i64>* bitcast (i64* getelementptr inbounds ([4 x i64], [4 x i64]* @src64, i64 0, i64 2) to <2 x i64>*), align 4
; SSE2-NEXT: [[TMP4:%.*]] = call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> [[TMP3]])
; SSE2-NEXT: store <2 x i64> [[TMP4]], <2 x i64>* bitcast (i64* getelementptr inbounds ([4 x i64], [4 x i64]* @dst64, i64 0, i64 2) to <2 x i64>*), align 4
; SSE2-NEXT: ret void
;
Expand Down Expand Up @@ -182,10 +182,10 @@ define void @ctpop_4i32() #0 {
define void @ctpop_8i32() #0 {
; SSE2-LABEL: @ctpop_8i32(
; SSE2-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([8 x i32]* @src32 to <4 x i32>*), align 2
; SSE2-NEXT: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @src32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE2-NEXT: [[TMP3:%.*]] = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> [[TMP1]])
; SSE2-NEXT: [[TMP4:%.*]] = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> [[TMP2]])
; SSE2-NEXT: store <4 x i32> [[TMP3]], <4 x i32>* bitcast ([8 x i32]* @dst32 to <4 x i32>*), align 2
; SSE2-NEXT: [[TMP2:%.*]] = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> [[TMP1]])
; SSE2-NEXT: store <4 x i32> [[TMP2]], <4 x i32>* bitcast ([8 x i32]* @dst32 to <4 x i32>*), align 2
; SSE2-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @src32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE2-NEXT: [[TMP4:%.*]] = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> [[TMP3]])
; SSE2-NEXT: store <4 x i32> [[TMP4]], <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @dst32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE2-NEXT: ret void
;
Expand Down Expand Up @@ -313,10 +313,10 @@ define void @ctpop_8i16() #0 {
define void @ctpop_16i16() #0 {
; SSE-LABEL: @ctpop_16i16(
; SSE-NEXT: [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* bitcast ([16 x i16]* @src16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP2:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @src16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: [[TMP3:%.*]] = call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> [[TMP1]])
; SSE-NEXT: [[TMP4:%.*]] = call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> [[TMP2]])
; SSE-NEXT: store <8 x i16> [[TMP3]], <8 x i16>* bitcast ([16 x i16]* @dst16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> [[TMP1]])
; SSE-NEXT: store <8 x i16> [[TMP2]], <8 x i16>* bitcast ([16 x i16]* @dst16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP3:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @src16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: [[TMP4:%.*]] = call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> [[TMP3]])
; SSE-NEXT: store <8 x i16> [[TMP4]], <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @dst16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: ret void
;
Expand Down Expand Up @@ -438,10 +438,10 @@ define void @ctpop_16i8() #0 {
define void @ctpop_32i8() #0 {
; SSE-LABEL: @ctpop_32i8(
; SSE-NEXT: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([32 x i8]* @src8 to <16 x i8>*), align 1
; SSE-NEXT: [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT: [[TMP3:%.*]] = call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> [[TMP1]])
; SSE-NEXT: [[TMP4:%.*]] = call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> [[TMP2]])
; SSE-NEXT: store <16 x i8> [[TMP3]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
; SSE-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> [[TMP1]])
; SSE-NEXT: store <16 x i8> [[TMP2]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
; SSE-NEXT: [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT: [[TMP4:%.*]] = call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> [[TMP3]])
; SSE-NEXT: store <16 x i8> [[TMP4]], <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @dst8, i8 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT: ret void
;
Expand Down
48 changes: 24 additions & 24 deletions llvm/test/Transforms/SLPVectorizer/X86/cttz.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -168,10 +168,10 @@ define void @cttz_8i32() #0 {
;
; SSE42-LABEL: @cttz_8i32(
; SSE42-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([8 x i32]* @src32 to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @src32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP3:%.*]] = call <4 x i32> @llvm.cttz.v4i32(<4 x i32> [[TMP1]], i1 false)
; SSE42-NEXT: [[TMP4:%.*]] = call <4 x i32> @llvm.cttz.v4i32(<4 x i32> [[TMP2]], i1 false)
; SSE42-NEXT: store <4 x i32> [[TMP3]], <4 x i32>* bitcast ([8 x i32]* @dst32 to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP2:%.*]] = call <4 x i32> @llvm.cttz.v4i32(<4 x i32> [[TMP1]], i1 false)
; SSE42-NEXT: store <4 x i32> [[TMP2]], <4 x i32>* bitcast ([8 x i32]* @dst32 to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @src32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP4:%.*]] = call <4 x i32> @llvm.cttz.v4i32(<4 x i32> [[TMP3]], i1 false)
; SSE42-NEXT: store <4 x i32> [[TMP4]], <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @dst32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE42-NEXT: ret void
;
Expand Down Expand Up @@ -245,10 +245,10 @@ define void @cttz_8i16() #0 {
define void @cttz_16i16() #0 {
; SSE-LABEL: @cttz_16i16(
; SSE-NEXT: [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* bitcast ([16 x i16]* @src16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP2:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @src16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: [[TMP3:%.*]] = call <8 x i16> @llvm.cttz.v8i16(<8 x i16> [[TMP1]], i1 false)
; SSE-NEXT: [[TMP4:%.*]] = call <8 x i16> @llvm.cttz.v8i16(<8 x i16> [[TMP2]], i1 false)
; SSE-NEXT: store <8 x i16> [[TMP3]], <8 x i16>* bitcast ([16 x i16]* @dst16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.cttz.v8i16(<8 x i16> [[TMP1]], i1 false)
; SSE-NEXT: store <8 x i16> [[TMP2]], <8 x i16>* bitcast ([16 x i16]* @dst16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP3:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @src16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: [[TMP4:%.*]] = call <8 x i16> @llvm.cttz.v8i16(<8 x i16> [[TMP3]], i1 false)
; SSE-NEXT: store <8 x i16> [[TMP4]], <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @dst16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: ret void
;
Expand Down Expand Up @@ -370,10 +370,10 @@ define void @cttz_16i8() #0 {
define void @cttz_32i8() #0 {
; SSE-LABEL: @cttz_32i8(
; SSE-NEXT: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([32 x i8]* @src8 to <16 x i8>*), align 1
; SSE-NEXT: [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT: [[TMP3:%.*]] = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> [[TMP1]], i1 false)
; SSE-NEXT: [[TMP4:%.*]] = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> [[TMP2]], i1 false)
; SSE-NEXT: store <16 x i8> [[TMP3]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
; SSE-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> [[TMP1]], i1 false)
; SSE-NEXT: store <16 x i8> [[TMP2]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
; SSE-NEXT: [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT: [[TMP4:%.*]] = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> [[TMP3]], i1 false)
; SSE-NEXT: store <16 x i8> [[TMP4]], <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @dst8, i8 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT: ret void
;
Expand Down Expand Up @@ -630,10 +630,10 @@ define void @cttz_undef_8i32() #0 {
;
; SSE42-LABEL: @cttz_undef_8i32(
; SSE42-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([8 x i32]* @src32 to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @src32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP3:%.*]] = call <4 x i32> @llvm.cttz.v4i32(<4 x i32> [[TMP1]], i1 true)
; SSE42-NEXT: [[TMP4:%.*]] = call <4 x i32> @llvm.cttz.v4i32(<4 x i32> [[TMP2]], i1 true)
; SSE42-NEXT: store <4 x i32> [[TMP3]], <4 x i32>* bitcast ([8 x i32]* @dst32 to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP2:%.*]] = call <4 x i32> @llvm.cttz.v4i32(<4 x i32> [[TMP1]], i1 true)
; SSE42-NEXT: store <4 x i32> [[TMP2]], <4 x i32>* bitcast ([8 x i32]* @dst32 to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @src32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE42-NEXT: [[TMP4:%.*]] = call <4 x i32> @llvm.cttz.v4i32(<4 x i32> [[TMP3]], i1 true)
; SSE42-NEXT: store <4 x i32> [[TMP4]], <4 x i32>* bitcast (i32* getelementptr inbounds ([8 x i32], [8 x i32]* @dst32, i32 0, i64 4) to <4 x i32>*), align 2
; SSE42-NEXT: ret void
;
Expand Down Expand Up @@ -707,10 +707,10 @@ define void @cttz_undef_8i16() #0 {
define void @cttz_undef_16i16() #0 {
; SSE-LABEL: @cttz_undef_16i16(
; SSE-NEXT: [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* bitcast ([16 x i16]* @src16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP2:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @src16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: [[TMP3:%.*]] = call <8 x i16> @llvm.cttz.v8i16(<8 x i16> [[TMP1]], i1 true)
; SSE-NEXT: [[TMP4:%.*]] = call <8 x i16> @llvm.cttz.v8i16(<8 x i16> [[TMP2]], i1 true)
; SSE-NEXT: store <8 x i16> [[TMP3]], <8 x i16>* bitcast ([16 x i16]* @dst16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.cttz.v8i16(<8 x i16> [[TMP1]], i1 true)
; SSE-NEXT: store <8 x i16> [[TMP2]], <8 x i16>* bitcast ([16 x i16]* @dst16 to <8 x i16>*), align 2
; SSE-NEXT: [[TMP3:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @src16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: [[TMP4:%.*]] = call <8 x i16> @llvm.cttz.v8i16(<8 x i16> [[TMP3]], i1 true)
; SSE-NEXT: store <8 x i16> [[TMP4]], <8 x i16>* bitcast (i16* getelementptr inbounds ([16 x i16], [16 x i16]* @dst16, i16 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT: ret void
;
Expand Down Expand Up @@ -832,10 +832,10 @@ define void @cttz_undef_16i8() #0 {
define void @cttz_undef_32i8() #0 {
; SSE-LABEL: @cttz_undef_32i8(
; SSE-NEXT: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([32 x i8]* @src8 to <16 x i8>*), align 1
; SSE-NEXT: [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT: [[TMP3:%.*]] = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> [[TMP1]], i1 true)
; SSE-NEXT: [[TMP4:%.*]] = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> [[TMP2]], i1 true)
; SSE-NEXT: store <16 x i8> [[TMP3]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
; SSE-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> [[TMP1]], i1 true)
; SSE-NEXT: store <16 x i8> [[TMP2]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
; SSE-NEXT: [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT: [[TMP4:%.*]] = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> [[TMP3]], i1 true)
; SSE-NEXT: store <16 x i8> [[TMP4]], <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @dst8, i8 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT: ret void
;
Expand Down
Loading