derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
41 lines
1.8 KiB
LLVM
41 lines
1.8 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 ddx_coarse are generated for half/float and matching vectors
|
|
|
|
define noundef half @deriv_coarse_x_half(half noundef %a) {
|
|
; CHECK: call half @dx.op.unary.f16(i32 83, half %{{.*}})
|
|
entry:
|
|
%dx.ddx.coarse = call half @llvm.dx.ddx.coarse.f16(half %a)
|
|
ret half %dx.ddx.coarse
|
|
}
|
|
|
|
define noundef float @deriv_coarse_x_float(float noundef %a) {
|
|
; CHECK: call float @dx.op.unary.f32(i32 83, float %{{.*}})
|
|
entry:
|
|
%dx.ddx.coarse = call float @llvm.dx.ddx.coarse.f32(float %a)
|
|
ret float %dx.ddx.coarse
|
|
}
|
|
|
|
define noundef <4 x float> @deriv_coarse_x_float4(<4 x float> noundef %a) {
|
|
; CHECK: [[ee0:%.*]] = extractelement <4 x float> %a, i64 0
|
|
; CHECK: [[ie0:%.*]] = call float @dx.op.unary.f32(i32 83, float [[ee0]])
|
|
; CHECK: [[ee1:%.*]] = extractelement <4 x float> %a, i64 1
|
|
; CHECK: [[ie1:%.*]] = call float @dx.op.unary.f32(i32 83, float [[ee1]])
|
|
; CHECK: [[ee2:%.*]] = extractelement <4 x float> %a, i64 2
|
|
; CHECK: [[ie2:%.*]] = call float @dx.op.unary.f32(i32 83, float [[ee2]])
|
|
; CHECK: [[ee3:%.*]] = extractelement <4 x float> %a, i64 3
|
|
; CHECK: [[ie3:%.*]] = call float @dx.op.unary.f32(i32 83, 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
|
|
; CHECK: ret <4 x float> %{{.*}}
|
|
entry:
|
|
%dx.ddx.coarse = call <4 x float> @llvm.dx.ddx.coarse.v4f32(<4 x float> %a)
|
|
ret <4 x float> %dx.ddx.coarse
|
|
}
|
|
|
|
declare half @llvm.dx.ddx.coarse.f16(half)
|
|
declare float @llvm.dx.ddx.coarse.f32(float)
|
|
declare <4 x float> @llvm.dx.ddx.coarse.v4f32(<4 x float>)
|