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
36 lines
1.7 KiB
LLVM
36 lines
1.7 KiB
LLVM
; RUN: opt -S -scalarizer -dxil-op-lower -mtriple=dxil-pc-shadermodel6.3-compute %s | FileCheck %s
|
|
|
|
; Test that for vector values, WaveReadLaneAt scalarizes and maps down to the
|
|
; DirectX op
|
|
|
|
define noundef <2 x half> @wave_read_lane_v2half(<2 x half> noundef %expr, i32 %idx) {
|
|
entry:
|
|
; CHECK: call half @dx.op.waveReadLaneAt.f16(i32 117, half %expr.i0, i32 %idx)
|
|
; CHECK: call half @dx.op.waveReadLaneAt.f16(i32 117, half %expr.i1, i32 %idx)
|
|
%ret = call <2 x half> @llvm.dx.wave.readlane.f16(<2 x half> %expr, i32 %idx)
|
|
ret <2 x half> %ret
|
|
}
|
|
|
|
define noundef <3 x i32> @wave_read_lane_v3i32(<3 x i32> noundef %expr, i32 %idx) {
|
|
entry:
|
|
; CHECK: call i32 @dx.op.waveReadLaneAt.i32(i32 117, i32 %expr.i0, i32 %idx)
|
|
; CHECK: call i32 @dx.op.waveReadLaneAt.i32(i32 117, i32 %expr.i1, i32 %idx)
|
|
; CHECK: call i32 @dx.op.waveReadLaneAt.i32(i32 117, i32 %expr.i2, i32 %idx)
|
|
%ret = call <3 x i32> @llvm.dx.wave.readlane(<3 x i32> %expr, i32 %idx)
|
|
ret <3 x i32> %ret
|
|
}
|
|
|
|
define noundef <4 x double> @wave_read_lane_v4f64(<4 x double> noundef %expr, i32 %idx) {
|
|
entry:
|
|
; CHECK: call double @dx.op.waveReadLaneAt.f64(i32 117, double %expr.i0, i32 %idx)
|
|
; CHECK: call double @dx.op.waveReadLaneAt.f64(i32 117, double %expr.i1, i32 %idx)
|
|
; CHECK: call double @dx.op.waveReadLaneAt.f64(i32 117, double %expr.i2, i32 %idx)
|
|
; CHECK: call double @dx.op.waveReadLaneAt.f64(i32 117, double %expr.i3, i32 %idx)
|
|
%ret = call <4 x double> @llvm.dx.wave.readlane(<4 x double> %expr, i32 %idx)
|
|
ret <4 x double> %ret
|
|
}
|
|
|
|
declare <2 x half> @llvm.dx.wave.readlane.v2f16(<2 x half>, i32)
|
|
declare <3 x i32> @llvm.dx.wave.readlane.v3i32(<3 x i32>, i32)
|
|
declare <4 x double> @llvm.dx.wave.readlane.v4f64(<4 x double>, i32)
|