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
46 lines
2.6 KiB
LLVM
46 lines
2.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: opt -p lower-matrix-intrinsics -S %s | FileCheck %s
|
|
|
|
define void @redundant_transpose_of_shuffle(<4 x float> %m, ptr %dst) {
|
|
; CHECK-LABEL: define void @redundant_transpose_of_shuffle(
|
|
; CHECK-SAME: <4 x float> [[M:%.*]], ptr [[DST:%.*]]) {
|
|
; CHECK-NEXT: [[ENTRY:.*:]]
|
|
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x float> [[M]], <4 x float> zeroinitializer, <4 x i32> zeroinitializer
|
|
; CHECK-NEXT: [[SPLIT:%.*]] = shufflevector <4 x float> [[SHUFFLE]], <4 x float> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
; CHECK-NEXT: store <4 x float> [[SPLIT]], ptr [[DST]], align 4
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%shuffle = shufflevector <4 x float> %m, <4 x float> zeroinitializer, <4 x i32> zeroinitializer
|
|
%t = tail call <4 x float> @llvm.matrix.transpose.v3f32(<4 x float> %shuffle, i32 1, i32 4)
|
|
store <4 x float> %t, ptr %dst, align 4
|
|
ret void
|
|
}
|
|
|
|
define void @redundant_transpose_of_shuffle_2(<4 x float> %m, ptr %dst) {
|
|
; CHECK-LABEL: define void @redundant_transpose_of_shuffle_2(
|
|
; CHECK-SAME: <4 x float> [[M:%.*]], ptr [[DST:%.*]]) {
|
|
; CHECK-NEXT: [[ENTRY:.*:]]
|
|
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x float> [[M]], <4 x float> zeroinitializer, <4 x i32> zeroinitializer
|
|
; CHECK-NEXT: [[SPLIT:%.*]] = shufflevector <4 x float> [[SHUFFLE]], <4 x float> poison, <1 x i32> zeroinitializer
|
|
; CHECK-NEXT: [[SPLIT1:%.*]] = shufflevector <4 x float> [[SHUFFLE]], <4 x float> poison, <1 x i32> <i32 1>
|
|
; CHECK-NEXT: [[SPLIT2:%.*]] = shufflevector <4 x float> [[SHUFFLE]], <4 x float> poison, <1 x i32> <i32 2>
|
|
; CHECK-NEXT: [[SPLIT3:%.*]] = shufflevector <4 x float> [[SHUFFLE]], <4 x float> poison, <1 x i32> <i32 3>
|
|
; CHECK-NEXT: store <1 x float> [[SPLIT]], ptr [[DST]], align 4
|
|
; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr inbounds float, ptr [[DST]], i64 1
|
|
; CHECK-NEXT: store <1 x float> [[SPLIT1]], ptr [[VEC_GEP]], align 4
|
|
; CHECK-NEXT: [[VEC_GEP4:%.*]] = getelementptr inbounds float, ptr [[DST]], i64 2
|
|
; CHECK-NEXT: store <1 x float> [[SPLIT2]], ptr [[VEC_GEP4]], align 4
|
|
; CHECK-NEXT: [[VEC_GEP5:%.*]] = getelementptr inbounds float, ptr [[DST]], i64 3
|
|
; CHECK-NEXT: store <1 x float> [[SPLIT3]], ptr [[VEC_GEP5]], align 4
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%shuffle = shufflevector <4 x float> %m, <4 x float> zeroinitializer, <4 x i32> zeroinitializer
|
|
%t = tail call <4 x float> @llvm.matrix.transpose.v3f32(<4 x float> %shuffle, i32 4, i32 1)
|
|
store <4 x float> %t, ptr %dst, align 4
|
|
ret void
|
|
}
|
|
|
|
declare <4 x float> @llvm.matrix.transpose.v3f32(<4 x float>, i32, i32)
|