diff options
| -rw-r--r-- | llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp | 14 | ||||
| -rw-r--r-- | llvm/test/Transforms/InstCombine/amdgcn-intrinsics.ll | 34 | ||||
| -rw-r--r-- | llvm/test/Transforms/InstCombine/cos-intrinsic.ll | 55 |
3 files changed, 103 insertions, 0 deletions
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp index f863d192fc2..b29ed3c8745 100644 --- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp +++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp @@ -1637,6 +1637,20 @@ Instruction *InstCombiner::visitCallInst(CallInst &CI) { break; } + case Intrinsic::cos: + case Intrinsic::amdgcn_cos: { + Value *SrcSrc; + Value *Src = II->getArgOperand(0); + if (match(Src, m_FNeg(m_Value(SrcSrc))) || + match(Src, m_Intrinsic<Intrinsic::fabs>(m_Value(SrcSrc)))) { + // cos(-x) -> cos(x) + // cos(fabs(x)) -> cos(x) + II->setArgOperand(0, SrcSrc); + return II; + } + + break; + } case Intrinsic::ppc_altivec_lvx: case Intrinsic::ppc_altivec_lvxl: // Turn PPC lvx -> load if the pointer is known aligned. diff --git a/llvm/test/Transforms/InstCombine/amdgcn-intrinsics.ll b/llvm/test/Transforms/InstCombine/amdgcn-intrinsics.ll index 3c38e789062..a228968f25b 100644 --- a/llvm/test/Transforms/InstCombine/amdgcn-intrinsics.ll +++ b/llvm/test/Transforms/InstCombine/amdgcn-intrinsics.ll @@ -599,3 +599,37 @@ define i1 @test_constant_class_snan_test_pinf_f64() nounwind { %val = call i1 @llvm.amdgcn.class.f64(double 0x7FF0000000000001, i32 512) ret i1 %val } + +; -------------------------------------------------------------------- +; llvm.amdgcn.cos +; -------------------------------------------------------------------- +declare float @llvm.amdgcn.cos.f32(float) nounwind readnone +declare float @llvm.fabs.f32(float) nounwind readnone + +; CHECK-LABEL: @cos_fneg_f32( +; CHECK: %cos = call float @llvm.amdgcn.cos.f32(float %x) +; CHECK-NEXT: ret float %cos +define float @cos_fneg_f32(float %x) { + %x.fneg = fsub float -0.0, %x + %cos = call float @llvm.amdgcn.cos.f32(float %x.fneg) + ret float %cos +} + +; CHECK-LABEL: @cos_fabs_f32( +; CHECK-NEXT: %cos = call float @llvm.amdgcn.cos.f32(float %x) +; CHECK-NEXT: ret float %cos +define float @cos_fabs_f32(float %x) { + %x.fabs = call float @llvm.fabs.f32(float %x) + %cos = call float @llvm.amdgcn.cos.f32(float %x.fabs) + ret float %cos +} + +; CHECK-LABEL: @cos_fabs_fneg_f32( +; CHECK-NEXT: %cos = call float @llvm.amdgcn.cos.f32(float %x) +; CHECK-NEXT: ret float %cos +define float @cos_fabs_fneg_f32(float %x) { + %x.fabs = call float @llvm.fabs.f32(float %x) + %x.fabs.fneg = fsub float -0.0, %x.fabs + %cos = call float @llvm.amdgcn.cos.f32(float %x.fabs.fneg) + ret float %cos +} diff --git a/llvm/test/Transforms/InstCombine/cos-intrinsic.ll b/llvm/test/Transforms/InstCombine/cos-intrinsic.ll index b4d07cf8047..24b605e9c8c 100644 --- a/llvm/test/Transforms/InstCombine/cos-intrinsic.ll +++ b/llvm/test/Transforms/InstCombine/cos-intrinsic.ll @@ -3,6 +3,10 @@ declare double @llvm.cos.f64(double %Val) declare float @llvm.cos.f32(float %Val) +declare <2 x float> @llvm.cos.v2f32(<2 x float> %Val) + +declare float @llvm.fabs.f32(float %Val) +declare <2 x float> @llvm.fabs.v2f32(<2 x float> %Val) ; Function Attrs: nounwind readnone define double @test1() { @@ -24,3 +28,54 @@ define float @test2(float %d) { ; CHECK-NEXT: %fsum ; CHECK: ret float %fsum } + +; CHECK-LABEL: @cos_fneg_f32( +; CHECK: %cos = call float @llvm.cos.f32(float %x) +; CHECK-NEXT: ret float %cos +define float @cos_fneg_f32(float %x) { + %x.fneg = fsub float -0.0, %x + %cos = call float @llvm.cos.f32(float %x.fneg) + ret float %cos +} + +; FIXME: m_FNeg() doesn't handle vectors +; CHECK-LABEL: @cos_fneg_v2f32( +; CHECK: %x.fneg = fsub <2 x float> <float -0.000000e+00, float -0.000000e+00>, %x +; CHECK-NEXT: %cos = call <2 x float> @llvm.cos.v2f32(<2 x float> %x.fneg) +; CHECK-NEXT: ret <2 x float> %cos +define <2 x float> @cos_fneg_v2f32(<2 x float> %x) { + %x.fneg = fsub <2 x float> <float -0.0, float -0.0>, %x + %cos = call <2 x float> @llvm.cos.v2f32(<2 x float> %x.fneg) + ret <2 x float> %cos +} + +; CHECK-LABEL: @cos_fabs_f32( +; CHECK-NEXT: %cos = call float @llvm.cos.f32(float %x) +; CHECK-NEXT: ret float %cos +define float @cos_fabs_f32(float %x) { + %x.fabs = call float @llvm.fabs.f32(float %x) + %cos = call float @llvm.cos.f32(float %x.fabs) + ret float %cos +} + +; CHECK-LABEL: @cos_fabs_fneg_f32( +; CHECK: %cos = call float @llvm.cos.f32(float %x) +; CHECK-NEXT: ret float %cos +define float @cos_fabs_fneg_f32(float %x) { + %x.fabs = call float @llvm.fabs.f32(float %x) + %x.fabs.fneg = fsub float -0.0, %x.fabs + %cos = call float @llvm.cos.f32(float %x.fabs.fneg) + ret float %cos +} + +; CHECK-LABEL: @cos_fabs_fneg_v2f32( +; CHECK: %x.fabs = call <2 x float> @llvm.fabs.v2f32(<2 x float> %x) +; CHECK-NEXT: %x.fabs.fneg = fsub <2 x float> <float -0.000000e+00, float -0.000000e+00>, %x.fabs +; CHECK-NEXT: %cos = call <2 x float> @llvm.cos.v2f32(<2 x float> %x.fabs.fneg) +; CHECK-NEXT: ret <2 x float> %cos +define <2 x float> @cos_fabs_fneg_v2f32(<2 x float> %x) { + %x.fabs = call <2 x float> @llvm.fabs.v2f32(<2 x float> %x) + %x.fabs.fneg = fsub <2 x float> <float -0.0, float -0.0>, %x.fabs + %cos = call <2 x float> @llvm.cos.v2f32(<2 x float> %x.fabs.fneg) + ret <2 x float> %cos +} |
