diff options
Diffstat (limited to 'llvm/test/Transforms/SLPVectorizer/X86/cse.ll')
| -rw-r--r-- | llvm/test/Transforms/SLPVectorizer/X86/cse.ll | 25 |
1 files changed, 13 insertions, 12 deletions
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/cse.ll b/llvm/test/Transforms/SLPVectorizer/X86/cse.ll index 5860a24906b..d2512dcd615 100644 --- a/llvm/test/Transforms/SLPVectorizer/X86/cse.ll +++ b/llvm/test/Transforms/SLPVectorizer/X86/cse.ll @@ -18,20 +18,21 @@ define i32 @test(double* nocapture %G) { ; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds double, double* [[G]], i64 6 ; 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> <double 4.000000e+00, double 3.000000e+00>, [[TMP1]] -; CHECK-NEXT: [[TMP3:%.*]] = fadd <2 x double> <double 1.000000e+00, double 6.000000e+00>, [[TMP2]] +; 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: [[ADD8:%.*]] = fadd double [[TMP5]], 7.000000e+00 ; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds double, double* [[G]], i64 2 -; CHECK-NEXT: store double [[ADD8]], double* [[ARRAYIDX9]], align 8 ; CHECK-NEXT: [[TMP6:%.*]] = extractelement <2 x double> [[TMP1]], i32 1 ; CHECK-NEXT: [[MUL11:%.*]] = fmul double [[TMP6]], 4.000000e+00 -; CHECK-NEXT: [[ADD12:%.*]] = fadd double [[MUL11]], 8.000000e+00 +; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x double> undef, 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: store double [[ADD12]], double* [[ARRAYIDX13]], align 8 +; 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 ; entry: @@ -72,13 +73,13 @@ define i32 @foo(double* nocapture %A, i32 %n) { ; CHECK-NEXT: [[ARRAYIDX15:%.*]] = getelementptr inbounds double, double* [[A]], i64 3 ; CHECK-NEXT: [[TMP0:%.*]] = bitcast double* [[A]] to <4 x double>* ; CHECK-NEXT: [[TMP1:%.*]] = load <4 x double>, <4 x double>* [[TMP0]], align 8 -; CHECK-NEXT: [[TMP2:%.*]] = fmul <4 x double> <double 7.900000e+00, double 7.700000e+00, double 7.600000e+00, double 7.400000e+00>, [[TMP1]] +; CHECK-NEXT: [[TMP2:%.*]] = fmul <4 x double> [[TMP1]], <double 7.900000e+00, double 7.700000e+00, double 7.600000e+00, double 7.400000e+00> ; CHECK-NEXT: [[TMP3:%.*]] = insertelement <4 x double> undef, double [[CONV]], i32 0 ; CHECK-NEXT: [[TMP4:%.*]] = insertelement <4 x double> [[TMP3]], double [[CONV]], i32 1 ; CHECK-NEXT: [[TMP5:%.*]] = insertelement <4 x double> [[TMP4]], double [[CONV]], i32 2 ; CHECK-NEXT: [[TMP6:%.*]] = insertelement <4 x double> [[TMP5]], double [[CONV]], i32 3 ; CHECK-NEXT: [[TMP7:%.*]] = fmul <4 x double> [[TMP6]], [[TMP2]] -; CHECK-NEXT: [[TMP8:%.*]] = fadd <4 x double> <double 6.000000e+00, double 2.000000e+00, double 3.000000e+00, double 4.000000e+00>, [[TMP7]] +; CHECK-NEXT: [[TMP8:%.*]] = fadd <4 x double> [[TMP7]], <double 6.000000e+00, double 2.000000e+00, double 3.000000e+00, double 4.000000e+00> ; CHECK-NEXT: [[TMP9:%.*]] = bitcast double* [[A]] to <4 x double>* ; CHECK-NEXT: store <4 x double> [[TMP8]], <4 x double>* [[TMP9]], align 8 ; CHECK-NEXT: ret i32 undef @@ -135,7 +136,7 @@ define i32 @test2(double* nocapture %G, i32 %k) { ; CHECK-NEXT: [[TMP8:%.*]] = fmul double [[TMP7]], 3.000000e+00 ; CHECK-NEXT: [[TMP9:%.*]] = insertelement <2 x double> undef, double [[TMP4]], i32 0 ; CHECK-NEXT: [[TMP10:%.*]] = insertelement <2 x double> [[TMP9]], double [[TMP8]], i32 1 -; CHECK-NEXT: [[TMP11:%.*]] = fadd <2 x double> <double 1.000000e+00, double 6.000000e+00>, [[TMP10]] +; 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: [[TMP13:%.*]] = bitcast double* [[G]] to <2 x double>* ; CHECK-NEXT: store <2 x double> [[TMP11]], <2 x double>* [[TMP13]], align 8 @@ -146,7 +147,7 @@ define i32 @test2(double* nocapture %G, i32 %k) { ; CHECK-NEXT: [[TMP18:%.*]] = fmul double [[TMP17]], 3.000000e+00 ; CHECK-NEXT: [[TMP19:%.*]] = insertelement <2 x double> undef, double [[TMP4]], i32 0 ; CHECK-NEXT: [[TMP20:%.*]] = insertelement <2 x double> [[TMP19]], double [[TMP18]], i32 1 -; CHECK-NEXT: [[TMP21:%.*]] = fadd <2 x double> <double 7.000000e+00, double 8.000000e+00>, [[TMP20]] +; 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: [[TMP23:%.*]] = bitcast double* [[TMP15]] to <2 x double>* ; CHECK-NEXT: store <2 x double> [[TMP21]], <2 x double>* [[TMP23]], align 8 @@ -203,13 +204,13 @@ define i32 @foo4(double* nocapture %A, i32 %n) { ; CHECK-NEXT: [[ARRAYIDX15:%.*]] = getelementptr inbounds double, double* [[A]], i64 3 ; CHECK-NEXT: [[TMP0:%.*]] = bitcast double* [[A]] to <4 x double>* ; CHECK-NEXT: [[TMP1:%.*]] = load <4 x double>, <4 x double>* [[TMP0]], align 8 -; CHECK-NEXT: [[TMP2:%.*]] = fmul <4 x double> <double 7.900000e+00, double 7.900000e+00, double 7.900000e+00, double 7.900000e+00>, [[TMP1]] +; CHECK-NEXT: [[TMP2:%.*]] = fmul <4 x double> [[TMP1]], <double 7.900000e+00, double 7.900000e+00, double 7.900000e+00, double 7.900000e+00> ; CHECK-NEXT: [[TMP3:%.*]] = insertelement <4 x double> undef, double [[CONV]], i32 0 ; CHECK-NEXT: [[TMP4:%.*]] = insertelement <4 x double> [[TMP3]], double [[CONV]], i32 1 ; CHECK-NEXT: [[TMP5:%.*]] = insertelement <4 x double> [[TMP4]], double [[CONV]], i32 2 ; CHECK-NEXT: [[TMP6:%.*]] = insertelement <4 x double> [[TMP5]], double [[CONV]], i32 3 ; CHECK-NEXT: [[TMP7:%.*]] = fmul <4 x double> [[TMP6]], [[TMP2]] -; CHECK-NEXT: [[TMP8:%.*]] = fadd <4 x double> <double 6.000000e+00, double 6.000000e+00, double 6.000000e+00, double 6.000000e+00>, [[TMP7]] +; CHECK-NEXT: [[TMP8:%.*]] = fadd <4 x double> [[TMP7]], <double 6.000000e+00, double 6.000000e+00, double 6.000000e+00, double 6.000000e+00> ; CHECK-NEXT: [[TMP9:%.*]] = bitcast double* [[A]] to <4 x double>* ; CHECK-NEXT: store <4 x double> [[TMP8]], <4 x double>* [[TMP9]], align 8 ; CHECK-NEXT: ret i32 undef |
