mirror of
https://github.com/llvm/llvm-project.git
synced 2025-04-28 10:26:05 +00:00
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
43 lines
1.7 KiB
LLVM
43 lines
1.7 KiB
LLVM
; RUN: opt -S -scalarizer -dxil-op-lower -mtriple=dxil-pc-shadermodel6.3-library %s | FileCheck %s
|
|
|
|
; Make sure dxil operation function calls for round are generated for float and half.
|
|
|
|
; CHECK-LABEL: round_half
|
|
define noundef half @round_half(half noundef %a) {
|
|
entry:
|
|
; CHECK: call half @dx.op.unary.f16(i32 26, half %{{.*}})
|
|
%elt.roundeven = call half @llvm.roundeven.f16(half %a)
|
|
ret half %elt.roundeven
|
|
}
|
|
|
|
; CHECK-LABEL: round_float
|
|
define noundef float @round_float(float noundef %a) {
|
|
entry:
|
|
; CHECK: call float @dx.op.unary.f32(i32 26, float %{{.*}})
|
|
%elt.roundeven = call float @llvm.roundeven.f32(float %a)
|
|
ret float %elt.roundeven
|
|
}
|
|
|
|
define noundef <4 x float> @round_float4(<4 x float> noundef %a) #0 {
|
|
entry:
|
|
; CHECK: [[ee0:%.*]] = extractelement <4 x float> %a, i64 0
|
|
; CHECK: [[ie0:%.*]] = call float @dx.op.unary.f32(i32 26, float [[ee0]])
|
|
; CHECK: [[ee1:%.*]] = extractelement <4 x float> %a, i64 1
|
|
; CHECK: [[ie1:%.*]] = call float @dx.op.unary.f32(i32 26, float [[ee1]])
|
|
; CHECK: [[ee2:%.*]] = extractelement <4 x float> %a, i64 2
|
|
; CHECK: [[ie2:%.*]] = call float @dx.op.unary.f32(i32 26, float [[ee2]])
|
|
; CHECK: [[ee3:%.*]] = extractelement <4 x float> %a, i64 3
|
|
; CHECK: [[ie3:%.*]] = call float @dx.op.unary.f32(i32 26, float [[ee3]])
|
|
; CHECK: insertelement <4 x float> poison, float [[ie0]], i64 0
|
|
; CHECK: insertelement <4 x float> %{{.*}}, float [[ie1]], i64 1
|
|
; CHECK: insertelement <4 x float> %{{.*}}, float [[ie2]], i64 2
|
|
; CHECK: insertelement <4 x float> %{{.*}}, float [[ie3]], i64 3
|
|
%2 = call <4 x float> @llvm.roundeven.v4f32(<4 x float> %a)
|
|
ret <4 x float> %2
|
|
}
|
|
|
|
|
|
declare half @llvm.roundeven.f16(half)
|
|
declare float @llvm.roundeven.f32(float)
|
|
declare <4 x float> @llvm.roundeven.v4f32(<4 x float>)
|