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
48 lines
3.3 KiB
LLVM
48 lines
3.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -passes='lower-matrix-intrinsics' -S < %s | FileCheck %s
|
|
|
|
; Currently we only lower stores with shape information, but need to embed the
|
|
; matrix in a flat vector for function calls and returns.
|
|
define <8 x double> @strided_load_4x4(<8 x double> %in, ptr %Ptr) {
|
|
; CHECK-LABEL: @strided_load_4x4(
|
|
; CHECK-NEXT: [[SPLIT:%.*]] = shufflevector <8 x double> [[IN:%.*]], <8 x double> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
; CHECK-NEXT: [[SPLIT1:%.*]] = shufflevector <8 x double> [[IN]], <8 x double> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
|
|
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <4 x double> [[SPLIT]], i64 0
|
|
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x double> poison, double [[TMP1]], i64 0
|
|
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 0
|
|
; CHECK-NEXT: [[TMP4:%.*]] = insertelement <2 x double> [[TMP2]], double [[TMP3]], i64 1
|
|
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x double> [[SPLIT]], i64 1
|
|
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x double> poison, double [[TMP5]], i64 0
|
|
; CHECK-NEXT: [[TMP7:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 1
|
|
; CHECK-NEXT: [[TMP8:%.*]] = insertelement <2 x double> [[TMP6]], double [[TMP7]], i64 1
|
|
; CHECK-NEXT: [[TMP9:%.*]] = extractelement <4 x double> [[SPLIT]], i64 2
|
|
; CHECK-NEXT: [[TMP10:%.*]] = insertelement <2 x double> poison, double [[TMP9]], i64 0
|
|
; CHECK-NEXT: [[TMP11:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 2
|
|
; CHECK-NEXT: [[TMP12:%.*]] = insertelement <2 x double> [[TMP10]], double [[TMP11]], i64 1
|
|
; CHECK-NEXT: [[TMP13:%.*]] = extractelement <4 x double> [[SPLIT]], i64 3
|
|
; CHECK-NEXT: [[TMP14:%.*]] = insertelement <2 x double> poison, double [[TMP13]], i64 0
|
|
; CHECK-NEXT: [[TMP15:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 3
|
|
; CHECK-NEXT: [[TMP16:%.*]] = insertelement <2 x double> [[TMP14]], double [[TMP15]], i64 1
|
|
; CHECK-NEXT: [[TMP17:%.*]] = shufflevector <2 x double> [[TMP4]], <2 x double> [[TMP8]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
; CHECK-NEXT: [[TMP18:%.*]] = shufflevector <2 x double> [[TMP12]], <2 x double> [[TMP16]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
; CHECK-NEXT: [[TMP19:%.*]] = shufflevector <4 x double> [[TMP17]], <4 x double> [[TMP18]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
; CHECK-NEXT: store <2 x double> [[TMP4]], ptr [[PTR:%.*]], align 8
|
|
; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr inbounds double, ptr [[PTR]], i64 2
|
|
; CHECK-NEXT: store <2 x double> [[TMP8]], ptr [[VEC_GEP]], align 8
|
|
; CHECK-NEXT: [[VEC_GEP2:%.*]] = getelementptr inbounds double, ptr [[PTR]], i64 4
|
|
; CHECK-NEXT: store <2 x double> [[TMP12]], ptr [[VEC_GEP2]], align 8
|
|
; CHECK-NEXT: [[VEC_GEP3:%.*]] = getelementptr inbounds double, ptr [[PTR]], i64 6
|
|
; CHECK-NEXT: store <2 x double> [[TMP16]], ptr [[VEC_GEP3]], align 8
|
|
; CHECK-NEXT: call void @foo(<8 x double> [[TMP19]])
|
|
; CHECK-NEXT: ret <8 x double> [[TMP19]]
|
|
;
|
|
%transposed = call <8 x double> @llvm.matrix.transpose(<8 x double> %in, i32 4, i32 2)
|
|
store <8 x double> %transposed, ptr %Ptr, align 8
|
|
call void @foo(<8 x double> %transposed)
|
|
ret <8 x double> %transposed
|
|
}
|
|
|
|
declare <8 x double> @llvm.matrix.transpose(<8 x double>, i32, i32)
|
|
|
|
declare void @foo(<8 x double>)
|