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
59 lines
3.5 KiB
LLVM
59 lines
3.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -passes='lower-matrix-intrinsics' -S < %s | FileCheck %s
|
|
|
|
define void @strided_store_3x2(<6 x float> %in, ptr %out) {
|
|
; CHECK-LABEL: @strided_store_3x2(
|
|
; CHECK-NEXT: [[SPLIT:%.*]] = shufflevector <6 x float> [[IN:%.*]], <6 x float> poison, <3 x i32> <i32 0, i32 1, i32 2>
|
|
; CHECK-NEXT: [[SPLIT1:%.*]] = shufflevector <6 x float> [[IN]], <6 x float> poison, <3 x i32> <i32 3, i32 4, i32 5>
|
|
; CHECK-NEXT: store <3 x float> [[SPLIT]], ptr [[OUT:%.*]], align 4
|
|
; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr inbounds float, ptr [[OUT]], i64 5
|
|
; CHECK-NEXT: store <3 x float> [[SPLIT1]], ptr [[VEC_GEP]], align 4
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @llvm.matrix.column.major.store(<6 x float> %in, ptr %out, i64 5, i1 false, i32 3, i32 2)
|
|
ret void
|
|
}
|
|
|
|
define void @strided_store_3x2_nonconst_stride(<6 x float> %in, i64 %stride, ptr %out) {
|
|
; CHECK-LABEL: @strided_store_3x2_nonconst_stride(
|
|
; CHECK-NEXT: [[SPLIT:%.*]] = shufflevector <6 x float> [[IN:%.*]], <6 x float> poison, <3 x i32> <i32 0, i32 1, i32 2>
|
|
; CHECK-NEXT: [[SPLIT1:%.*]] = shufflevector <6 x float> [[IN]], <6 x float> poison, <3 x i32> <i32 3, i32 4, i32 5>
|
|
; CHECK-NEXT: [[VEC_START:%.*]] = mul i64 0, [[STRIDE:%.*]]
|
|
; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr inbounds float, ptr [[OUT:%.*]], i64 [[VEC_START]]
|
|
; CHECK-NEXT: store <3 x float> [[SPLIT]], ptr [[VEC_GEP]], align 4
|
|
; CHECK-NEXT: [[VEC_START2:%.*]] = mul i64 1, [[STRIDE]]
|
|
; CHECK-NEXT: [[VEC_GEP3:%.*]] = getelementptr inbounds float, ptr [[OUT]], i64 [[VEC_START2]]
|
|
; CHECK-NEXT: store <3 x float> [[SPLIT1]], ptr [[VEC_GEP3]], align 4
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @llvm.matrix.column.major.store(<6 x float> %in, ptr %out, i64 %stride, i1 false, i32 3, i32 2)
|
|
ret void
|
|
}
|
|
|
|
|
|
declare void @llvm.matrix.column.major.store(<6 x float>, ptr, i64, i1, i32, i32)
|
|
|
|
define void @strided_store_2x3(<10 x float> %in, ptr %out) {
|
|
; CHECK-LABEL: @strided_store_2x3(
|
|
; CHECK-NEXT: [[SPLIT:%.*]] = shufflevector <10 x float> [[IN:%.*]], <10 x float> poison, <2 x i32> <i32 0, i32 1>
|
|
; CHECK-NEXT: [[SPLIT1:%.*]] = shufflevector <10 x float> [[IN]], <10 x float> poison, <2 x i32> <i32 2, i32 3>
|
|
; CHECK-NEXT: [[SPLIT2:%.*]] = shufflevector <10 x float> [[IN]], <10 x float> poison, <2 x i32> <i32 4, i32 5>
|
|
; CHECK-NEXT: [[SPLIT3:%.*]] = shufflevector <10 x float> [[IN]], <10 x float> poison, <2 x i32> <i32 6, i32 7>
|
|
; CHECK-NEXT: [[SPLIT4:%.*]] = shufflevector <10 x float> [[IN]], <10 x float> poison, <2 x i32> <i32 8, i32 9>
|
|
; CHECK-NEXT: store <2 x float> [[SPLIT]], ptr [[OUT:%.*]], align 4
|
|
; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr inbounds float, ptr [[OUT]], i64 4
|
|
; CHECK-NEXT: store <2 x float> [[SPLIT1]], ptr [[VEC_GEP]], align 4
|
|
; CHECK-NEXT: [[VEC_GEP6:%.*]] = getelementptr inbounds float, ptr [[OUT]], i64 8
|
|
; CHECK-NEXT: store <2 x float> [[SPLIT2]], ptr [[VEC_GEP6]], align 4
|
|
; CHECK-NEXT: [[VEC_GEP8:%.*]] = getelementptr inbounds float, ptr [[OUT]], i64 12
|
|
; CHECK-NEXT: store <2 x float> [[SPLIT3]], ptr [[VEC_GEP8]], align 4
|
|
; CHECK-NEXT: [[VEC_GEP10:%.*]] = getelementptr inbounds float, ptr [[OUT]], i64 16
|
|
; CHECK-NEXT: store <2 x float> [[SPLIT4]], ptr [[VEC_GEP10]], align 4
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @llvm.matrix.column.major.store.v10f32(<10 x float> %in, ptr %out, i64 4, i1 false, i32 2, i32 5)
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.matrix.column.major.store.v10f32(<10 x float>, ptr, i64, i1, i32, i32)
|