From 5fa6039a5fc1b6392a3c9a3326a76604e0cb1001 Mon Sep 17 00:00:00 2001 From: Simon Pilgrim Date: Thu, 19 Aug 2021 18:44:26 +0100 Subject: [PATCH] [SLP][X86] Add llvm.isnan intrinsic test coverage We still need to tag the llvm.isnan.? intrinsic as vectorizable --- .../Transforms/SLPVectorizer/X86/intrinsic.ll | 66 +++++++++++++++---- 1 file changed, 54 insertions(+), 12 deletions(-) diff --git a/llvm/test/Transforms/SLPVectorizer/X86/intrinsic.ll b/llvm/test/Transforms/SLPVectorizer/X86/intrinsic.ll index 97197d722823..2f948de7a135 100644 --- a/llvm/test/Transforms/SLPVectorizer/X86/intrinsic.ll +++ b/llvm/test/Transforms/SLPVectorizer/X86/intrinsic.ll @@ -195,25 +195,25 @@ define void @vec_ctlz_i32_neg(i32* %a, i32* %b, i32* %c, i1) { ; CHECK-NEXT: [[I0:%.*]] = load i32, i32* [[A:%.*]], align 4 ; CHECK-NEXT: [[I1:%.*]] = load i32, i32* [[B:%.*]], align 4 ; CHECK-NEXT: [[ADD1:%.*]] = add i32 [[I0]], [[I1]] -; CHECK-NEXT: [[CALL1:%.*]] = tail call i32 @llvm.ctlz.i32(i32 [[ADD1]], i1 true) #[[ATTR3:[0-9]+]] +; CHECK-NEXT: [[CALL1:%.*]] = tail call i32 @llvm.ctlz.i32(i32 [[ADD1]], i1 true) #[[ATTR4:[0-9]+]] ; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 1 ; CHECK-NEXT: [[I2:%.*]] = load i32, i32* [[ARRAYIDX2]], align 4 ; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B]], i32 1 ; CHECK-NEXT: [[I3:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4 ; CHECK-NEXT: [[ADD2:%.*]] = add i32 [[I2]], [[I3]] -; CHECK-NEXT: [[CALL2:%.*]] = tail call i32 @llvm.ctlz.i32(i32 [[ADD2]], i1 false) #[[ATTR3]] +; CHECK-NEXT: [[CALL2:%.*]] = tail call i32 @llvm.ctlz.i32(i32 [[ADD2]], i1 false) #[[ATTR4]] ; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 2 ; CHECK-NEXT: [[I4:%.*]] = load i32, i32* [[ARRAYIDX4]], align 4 ; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, i32* [[B]], i32 2 ; CHECK-NEXT: [[I5:%.*]] = load i32, i32* [[ARRAYIDX5]], align 4 ; CHECK-NEXT: [[ADD3:%.*]] = add i32 [[I4]], [[I5]] -; CHECK-NEXT: [[CALL3:%.*]] = tail call i32 @llvm.ctlz.i32(i32 [[ADD3]], i1 true) #[[ATTR3]] +; CHECK-NEXT: [[CALL3:%.*]] = tail call i32 @llvm.ctlz.i32(i32 [[ADD3]], i1 true) #[[ATTR4]] ; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 3 ; CHECK-NEXT: [[I6:%.*]] = load i32, i32* [[ARRAYIDX6]], align 4 ; CHECK-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds i32, i32* [[B]], i32 3 ; CHECK-NEXT: [[I7:%.*]] = load i32, i32* [[ARRAYIDX7]], align 4 ; CHECK-NEXT: [[ADD4:%.*]] = add i32 [[I6]], [[I7]] -; CHECK-NEXT: [[CALL4:%.*]] = tail call i32 @llvm.ctlz.i32(i32 [[ADD4]], i1 false) #[[ATTR3]] +; CHECK-NEXT: [[CALL4:%.*]] = tail call i32 @llvm.ctlz.i32(i32 [[ADD4]], i1 false) #[[ATTR4]] ; CHECK-NEXT: store i32 [[CALL1]], i32* [[C:%.*]], align 4 ; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds i32, i32* [[C]], i32 1 ; CHECK-NEXT: store i32 [[CALL2]], i32* [[ARRAYIDX8]], align 4 @@ -322,25 +322,25 @@ define void @vec_cttz_i32_neg(i32* %a, i32* %b, i32* %c, i1) { ; CHECK-NEXT: [[I0:%.*]] = load i32, i32* [[A:%.*]], align 4 ; CHECK-NEXT: [[I1:%.*]] = load i32, i32* [[B:%.*]], align 4 ; CHECK-NEXT: [[ADD1:%.*]] = add i32 [[I0]], [[I1]] -; CHECK-NEXT: [[CALL1:%.*]] = tail call i32 @llvm.cttz.i32(i32 [[ADD1]], i1 true) #[[ATTR3]] +; CHECK-NEXT: [[CALL1:%.*]] = tail call i32 @llvm.cttz.i32(i32 [[ADD1]], i1 true) #[[ATTR4]] ; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 1 ; CHECK-NEXT: [[I2:%.*]] = load i32, i32* [[ARRAYIDX2]], align 4 ; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B]], i32 1 ; CHECK-NEXT: [[I3:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4 ; CHECK-NEXT: [[ADD2:%.*]] = add i32 [[I2]], [[I3]] -; CHECK-NEXT: [[CALL2:%.*]] = tail call i32 @llvm.cttz.i32(i32 [[ADD2]], i1 false) #[[ATTR3]] +; CHECK-NEXT: [[CALL2:%.*]] = tail call i32 @llvm.cttz.i32(i32 [[ADD2]], i1 false) #[[ATTR4]] ; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 2 ; CHECK-NEXT: [[I4:%.*]] = load i32, i32* [[ARRAYIDX4]], align 4 ; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, i32* [[B]], i32 2 ; CHECK-NEXT: [[I5:%.*]] = load i32, i32* [[ARRAYIDX5]], align 4 ; CHECK-NEXT: [[ADD3:%.*]] = add i32 [[I4]], [[I5]] -; CHECK-NEXT: [[CALL3:%.*]] = tail call i32 @llvm.cttz.i32(i32 [[ADD3]], i1 true) #[[ATTR3]] +; CHECK-NEXT: [[CALL3:%.*]] = tail call i32 @llvm.cttz.i32(i32 [[ADD3]], i1 true) #[[ATTR4]] ; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 3 ; CHECK-NEXT: [[I6:%.*]] = load i32, i32* [[ARRAYIDX6]], align 4 ; CHECK-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds i32, i32* [[B]], i32 3 ; CHECK-NEXT: [[I7:%.*]] = load i32, i32* [[ARRAYIDX7]], align 4 ; CHECK-NEXT: [[ADD4:%.*]] = add i32 [[I6]], [[I7]] -; CHECK-NEXT: [[CALL4:%.*]] = tail call i32 @llvm.cttz.i32(i32 [[ADD4]], i1 false) #[[ATTR3]] +; CHECK-NEXT: [[CALL4:%.*]] = tail call i32 @llvm.cttz.i32(i32 [[ADD4]], i1 false) #[[ATTR4]] ; CHECK-NEXT: store i32 [[CALL1]], i32* [[C:%.*]], align 4 ; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds i32, i32* [[C]], i32 1 ; CHECK-NEXT: store i32 [[CALL2]], i32* [[ARRAYIDX8]], align 4 @@ -448,25 +448,25 @@ define void @vec_powi_f32_neg(float* %a, float* %b, float* %c, i32 %P, i32 %Q) { ; CHECK-NEXT: [[I0:%.*]] = load float, float* [[A:%.*]], align 4 ; CHECK-NEXT: [[I1:%.*]] = load float, float* [[B:%.*]], align 4 ; CHECK-NEXT: [[ADD1:%.*]] = fadd float [[I0]], [[I1]] -; CHECK-NEXT: [[CALL1:%.*]] = tail call float @llvm.powi.f32.i32(float [[ADD1]], i32 [[P:%.*]]) #[[ATTR3]] +; CHECK-NEXT: [[CALL1:%.*]] = tail call float @llvm.powi.f32.i32(float [[ADD1]], i32 [[P:%.*]]) #[[ATTR4]] ; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds float, float* [[A]], i32 1 ; CHECK-NEXT: [[I2:%.*]] = load float, float* [[ARRAYIDX2]], align 4 ; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds float, float* [[B]], i32 1 ; CHECK-NEXT: [[I3:%.*]] = load float, float* [[ARRAYIDX3]], align 4 ; CHECK-NEXT: [[ADD2:%.*]] = fadd float [[I2]], [[I3]] -; CHECK-NEXT: [[CALL2:%.*]] = tail call float @llvm.powi.f32.i32(float [[ADD2]], i32 [[Q:%.*]]) #[[ATTR3]] +; CHECK-NEXT: [[CALL2:%.*]] = tail call float @llvm.powi.f32.i32(float [[ADD2]], i32 [[Q:%.*]]) #[[ATTR4]] ; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds float, float* [[A]], i32 2 ; CHECK-NEXT: [[I4:%.*]] = load float, float* [[ARRAYIDX4]], align 4 ; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds float, float* [[B]], i32 2 ; CHECK-NEXT: [[I5:%.*]] = load float, float* [[ARRAYIDX5]], align 4 ; CHECK-NEXT: [[ADD3:%.*]] = fadd float [[I4]], [[I5]] -; CHECK-NEXT: [[CALL3:%.*]] = tail call float @llvm.powi.f32.i32(float [[ADD3]], i32 [[P]]) #[[ATTR3]] +; CHECK-NEXT: [[CALL3:%.*]] = tail call float @llvm.powi.f32.i32(float [[ADD3]], i32 [[P]]) #[[ATTR4]] ; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds float, float* [[A]], i32 3 ; CHECK-NEXT: [[I6:%.*]] = load float, float* [[ARRAYIDX6]], align 4 ; CHECK-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds float, float* [[B]], i32 3 ; CHECK-NEXT: [[I7:%.*]] = load float, float* [[ARRAYIDX7]], align 4 ; CHECK-NEXT: [[ADD4:%.*]] = fadd float [[I6]], [[I7]] -; CHECK-NEXT: [[CALL4:%.*]] = tail call float @llvm.powi.f32.i32(float [[ADD4]], i32 [[Q]]) #[[ATTR3]] +; CHECK-NEXT: [[CALL4:%.*]] = tail call float @llvm.powi.f32.i32(float [[ADD4]], i32 [[Q]]) #[[ATTR4]] ; CHECK-NEXT: store float [[CALL1]], float* [[C:%.*]], align 4 ; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds float, float* [[C]], i32 1 ; CHECK-NEXT: store float [[CALL2]], float* [[ARRAYIDX8]], align 4 @@ -513,3 +513,45 @@ entry: ret void } + + +declare i1 @llvm.isnan.f64(double) + +define void @vec_isnan_f64(double* %a, double* %b, double* %c, double* %d) { +; CHECK-LABEL: @vec_isnan_f64( +; CHECK-NEXT: entry: +; CHECK-NEXT: [[AIDX1:%.*]] = getelementptr inbounds double, double* [[A:%.*]], i64 1 +; CHECK-NEXT: [[A0:%.*]] = load double, double* [[A]], align 8 +; CHECK-NEXT: [[A1:%.*]] = load double, double* [[AIDX1]], align 8 +; CHECK-NEXT: [[TMP0:%.*]] = bitcast double* [[B:%.*]] to <2 x double>* +; CHECK-NEXT: [[TMP1:%.*]] = load <2 x double>, <2 x double>* [[TMP0]], align 8 +; CHECK-NEXT: [[TMP2:%.*]] = bitcast double* [[C:%.*]] to <2 x double>* +; CHECK-NEXT: [[TMP3:%.*]] = load <2 x double>, <2 x double>* [[TMP2]], align 8 +; CHECK-NEXT: [[ISNAN0:%.*]] = tail call i1 @llvm.isnan.f64(double [[A0]]) +; CHECK-NEXT: [[ISNAN1:%.*]] = tail call i1 @llvm.isnan.f64(double [[A1]]) +; CHECK-NEXT: [[TMP4:%.*]] = insertelement <2 x i1> poison, i1 [[ISNAN0]], i32 0 +; CHECK-NEXT: [[TMP5:%.*]] = insertelement <2 x i1> [[TMP4]], i1 [[ISNAN1]], i32 1 +; CHECK-NEXT: [[TMP6:%.*]] = select <2 x i1> [[TMP5]], <2 x double> [[TMP1]], <2 x double> [[TMP3]] +; CHECK-NEXT: [[TMP7:%.*]] = bitcast double* [[D:%.*]] to <2 x double>* +; CHECK-NEXT: store <2 x double> [[TMP6]], <2 x double>* [[TMP7]], align 8 +; CHECK-NEXT: ret void +; +entry: + %aidx1 = getelementptr inbounds double, double* %a, i64 1 + %bidx1 = getelementptr inbounds double, double* %b, i64 1 + %cidx1 = getelementptr inbounds double, double* %c, i64 1 + %didx1 = getelementptr inbounds double, double* %d, i64 1 + %a0 = load double, double* %a, align 8 + %b0 = load double, double* %b, align 8 + %c0 = load double, double* %c, align 8 + %a1 = load double, double* %aidx1, align 8 + %b1 = load double, double* %bidx1, align 8 + %c1 = load double, double* %cidx1, align 8 + %isnan0 = tail call i1 @llvm.isnan.f64(double %a0) + %isnan1 = tail call i1 @llvm.isnan.f64(double %a1) + %r0 = select i1 %isnan0, double %b0, double %c0 + %r1 = select i1 %isnan1, double %b1, double %c1 + store double %r0, double* %d, align 8 + store double %r1, double* %didx1, align 8 + ret void +}