c05e29bff0
As discussed in this [proposal](https://github.com/llvm/wg-hlsl/pull/62/files?short_path=ac6e592#diff-ac6e59276afe8016e307eedc5c835f534c0cb353707760b44df0fa9d905a5cf8). We had to bring back the legacy pass manager interface for the scalarizer pass. Two reasons for this: 1. The DirectX backend is still using the legacy pass manager 2. The new PM isn't hooked up in clang yet via `BackendUtil.cpp`'s `AddEmitPasses` That means even if we add a `buildCodeGenPipeline` we won't be able to benefit from the new pass manager's scalarizer pass interface. The remaining changes are hooking up the scalarizer pass to the DirectX backend, updating the DirectX test cases, and allowing the `optdriver` to not block the legacy invocation of the scalarizer pass. Future work still needs to be done to allow the scalarizer pass to handle target specific intrinsics. closes #105178
26 lines
1.5 KiB
LLVM
26 lines
1.5 KiB
LLVM
; RUN: llc %s -mtriple=dxil-pc-shadermodel6.3-library --filetype=asm -o - | FileCheck %s
|
|
|
|
; CHECK: target triple = "dxilv1.3-pc-shadermodel6.3-library"
|
|
; CHECK-LABEL: cos_sin_float_test
|
|
define noundef <4 x float> @cos_sin_float_test(<4 x float> noundef %a) {
|
|
; CHECK: [[ee0:%.*]] = extractelement <4 x float> %a, i64 0
|
|
; CHECK: [[ie0:%.*]] = call float @dx.op.unary.f32(i32 13, float [[ee0]])
|
|
; CHECK: [[ee1:%.*]] = extractelement <4 x float> %a, i64 1
|
|
; CHECK: [[ie1:%.*]] = call float @dx.op.unary.f32(i32 13, float [[ee1]])
|
|
; CHECK: [[ee2:%.*]] = extractelement <4 x float> %a, i64 2
|
|
; CHECK: [[ie2:%.*]] = call float @dx.op.unary.f32(i32 13, float [[ee2]])
|
|
; CHECK: [[ee3:%.*]] = extractelement <4 x float> %a, i64 3
|
|
; CHECK: [[ie3:%.*]] = call float @dx.op.unary.f32(i32 13, float [[ee3]])
|
|
; CHECK: [[ie4:%.*]] = call float @dx.op.unary.f32(i32 12, float [[ie0]])
|
|
; CHECK: [[ie5:%.*]] = call float @dx.op.unary.f32(i32 12, float [[ie1]])
|
|
; CHECK: [[ie6:%.*]] = call float @dx.op.unary.f32(i32 12, float [[ie2]])
|
|
; CHECK: [[ie7:%.*]] = call float @dx.op.unary.f32(i32 12, float [[ie3]])
|
|
; CHECK: insertelement <4 x float> poison, float [[ie4]], i64 0
|
|
; CHECK: insertelement <4 x float> %{{.*}}, float [[ie5]], i64 1
|
|
; CHECK: insertelement <4 x float> %{{.*}}, float [[ie6]], i64 2
|
|
; CHECK: insertelement <4 x float> %{{.*}}, float [[ie7]], i64 3
|
|
%2 = tail call <4 x float> @llvm.sin.v4f32(<4 x float> %a)
|
|
%3 = tail call <4 x float> @llvm.cos.v4f32(<4 x float> %2)
|
|
ret <4 x float> %3
|
|
}
|