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
114 lines
8.3 KiB
LLVM
114 lines
8.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -passes='lower-matrix-intrinsics' -S < %s | FileCheck %s
|
|
|
|
|
|
define <8 x float> @transpose(<8 x float> %a) {
|
|
; CHECK-LABEL: @transpose(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[SPLIT:%.*]] = shufflevector <8 x float> [[A:%.*]], <8 x float> poison, <2 x i32> <i32 0, i32 1>
|
|
; CHECK-NEXT: [[SPLIT1:%.*]] = shufflevector <8 x float> [[A]], <8 x float> poison, <2 x i32> <i32 2, i32 3>
|
|
; CHECK-NEXT: [[SPLIT2:%.*]] = shufflevector <8 x float> [[A]], <8 x float> poison, <2 x i32> <i32 4, i32 5>
|
|
; CHECK-NEXT: [[SPLIT3:%.*]] = shufflevector <8 x float> [[A]], <8 x float> poison, <2 x i32> <i32 6, i32 7>
|
|
; CHECK-NEXT: [[TMP0:%.*]] = extractelement <2 x float> [[SPLIT]], i64 0
|
|
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x float> poison, float [[TMP0]], i64 0
|
|
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x float> [[SPLIT1]], i64 0
|
|
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <4 x float> [[TMP1]], float [[TMP2]], i64 1
|
|
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <2 x float> [[SPLIT2]], i64 0
|
|
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <4 x float> [[TMP3]], float [[TMP4]], i64 2
|
|
; CHECK-NEXT: [[TMP6:%.*]] = extractelement <2 x float> [[SPLIT3]], i64 0
|
|
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <4 x float> [[TMP5]], float [[TMP6]], i64 3
|
|
; CHECK-NEXT: [[TMP8:%.*]] = extractelement <2 x float> [[SPLIT]], i64 1
|
|
; CHECK-NEXT: [[TMP9:%.*]] = insertelement <4 x float> poison, float [[TMP8]], i64 0
|
|
; CHECK-NEXT: [[TMP10:%.*]] = extractelement <2 x float> [[SPLIT1]], i64 1
|
|
; CHECK-NEXT: [[TMP11:%.*]] = insertelement <4 x float> [[TMP9]], float [[TMP10]], i64 1
|
|
; CHECK-NEXT: [[TMP12:%.*]] = extractelement <2 x float> [[SPLIT2]], i64 1
|
|
; CHECK-NEXT: [[TMP13:%.*]] = insertelement <4 x float> [[TMP11]], float [[TMP12]], i64 2
|
|
; CHECK-NEXT: [[TMP14:%.*]] = extractelement <2 x float> [[SPLIT3]], i64 1
|
|
; CHECK-NEXT: [[TMP15:%.*]] = insertelement <4 x float> [[TMP13]], float [[TMP14]], i64 3
|
|
; CHECK-NEXT: [[TMP16:%.*]] = shufflevector <4 x float> [[TMP7]], <4 x float> [[TMP15]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
; CHECK-NEXT: ret <8 x float> [[TMP16]]
|
|
;
|
|
entry:
|
|
%c = call <8 x float> @llvm.matrix.transpose(<8 x float> %a, i32 2, i32 4)
|
|
ret <8 x float> %c
|
|
}
|
|
|
|
declare <8 x float> @llvm.matrix.transpose(<8 x float>, i32, i32)
|
|
|
|
define <8 x float> @transpose_single_column(<8 x float> %a) {
|
|
; CHECK-LABEL: @transpose_single_column(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[SPLIT:%.*]] = shufflevector <8 x float> [[A:%.*]], <8 x float> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
; CHECK-NEXT: [[TMP0:%.*]] = extractelement <8 x float> [[SPLIT]], i64 0
|
|
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <1 x float> poison, float [[TMP0]], i64 0
|
|
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <8 x float> [[SPLIT]], i64 1
|
|
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <1 x float> poison, float [[TMP2]], i64 0
|
|
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <8 x float> [[SPLIT]], i64 2
|
|
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <1 x float> poison, float [[TMP4]], i64 0
|
|
; CHECK-NEXT: [[TMP6:%.*]] = extractelement <8 x float> [[SPLIT]], i64 3
|
|
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <1 x float> poison, float [[TMP6]], i64 0
|
|
; CHECK-NEXT: [[TMP8:%.*]] = extractelement <8 x float> [[SPLIT]], i64 4
|
|
; CHECK-NEXT: [[TMP9:%.*]] = insertelement <1 x float> poison, float [[TMP8]], i64 0
|
|
; CHECK-NEXT: [[TMP10:%.*]] = extractelement <8 x float> [[SPLIT]], i64 5
|
|
; CHECK-NEXT: [[TMP11:%.*]] = insertelement <1 x float> poison, float [[TMP10]], i64 0
|
|
; CHECK-NEXT: [[TMP12:%.*]] = extractelement <8 x float> [[SPLIT]], i64 6
|
|
; CHECK-NEXT: [[TMP13:%.*]] = insertelement <1 x float> poison, float [[TMP12]], i64 0
|
|
; CHECK-NEXT: [[TMP14:%.*]] = extractelement <8 x float> [[SPLIT]], i64 7
|
|
; CHECK-NEXT: [[TMP15:%.*]] = insertelement <1 x float> poison, float [[TMP14]], i64 0
|
|
; CHECK-NEXT: [[TMP16:%.*]] = shufflevector <1 x float> [[TMP1]], <1 x float> [[TMP3]], <2 x i32> <i32 0, i32 1>
|
|
; CHECK-NEXT: [[TMP17:%.*]] = shufflevector <1 x float> [[TMP5]], <1 x float> [[TMP7]], <2 x i32> <i32 0, i32 1>
|
|
; CHECK-NEXT: [[TMP18:%.*]] = shufflevector <1 x float> [[TMP9]], <1 x float> [[TMP11]], <2 x i32> <i32 0, i32 1>
|
|
; CHECK-NEXT: [[TMP19:%.*]] = shufflevector <1 x float> [[TMP13]], <1 x float> [[TMP15]], <2 x i32> <i32 0, i32 1>
|
|
; CHECK-NEXT: [[TMP20:%.*]] = shufflevector <2 x float> [[TMP16]], <2 x float> [[TMP17]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
; CHECK-NEXT: [[TMP21:%.*]] = shufflevector <2 x float> [[TMP18]], <2 x float> [[TMP19]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
; CHECK-NEXT: [[TMP22:%.*]] = shufflevector <4 x float> [[TMP20]], <4 x float> [[TMP21]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
; CHECK-NEXT: ret <8 x float> [[TMP22]]
|
|
;
|
|
entry:
|
|
%c = call <8 x float> @llvm.matrix.transpose(<8 x float> %a, i32 8, i32 1)
|
|
ret <8 x float> %c
|
|
}
|
|
|
|
declare <12 x float> @llvm.matrix.transpose.v12f32(<12 x float>, i32, i32)
|
|
|
|
define <12 x float> @transpose_float_3x4(<12 x float> %a) {
|
|
; CHECK-LABEL: @transpose_float_3x4(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[SPLIT:%.*]] = shufflevector <12 x float> [[A:%.*]], <12 x float> poison, <3 x i32> <i32 0, i32 1, i32 2>
|
|
; CHECK-NEXT: [[SPLIT1:%.*]] = shufflevector <12 x float> [[A]], <12 x float> poison, <3 x i32> <i32 3, i32 4, i32 5>
|
|
; CHECK-NEXT: [[SPLIT2:%.*]] = shufflevector <12 x float> [[A]], <12 x float> poison, <3 x i32> <i32 6, i32 7, i32 8>
|
|
; CHECK-NEXT: [[SPLIT3:%.*]] = shufflevector <12 x float> [[A]], <12 x float> poison, <3 x i32> <i32 9, i32 10, i32 11>
|
|
; CHECK-NEXT: [[TMP0:%.*]] = extractelement <3 x float> [[SPLIT]], i64 0
|
|
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x float> poison, float [[TMP0]], i64 0
|
|
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <3 x float> [[SPLIT1]], i64 0
|
|
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <4 x float> [[TMP1]], float [[TMP2]], i64 1
|
|
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <3 x float> [[SPLIT2]], i64 0
|
|
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <4 x float> [[TMP3]], float [[TMP4]], i64 2
|
|
; CHECK-NEXT: [[TMP6:%.*]] = extractelement <3 x float> [[SPLIT3]], i64 0
|
|
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <4 x float> [[TMP5]], float [[TMP6]], i64 3
|
|
; CHECK-NEXT: [[TMP8:%.*]] = extractelement <3 x float> [[SPLIT]], i64 1
|
|
; CHECK-NEXT: [[TMP9:%.*]] = insertelement <4 x float> poison, float [[TMP8]], i64 0
|
|
; CHECK-NEXT: [[TMP10:%.*]] = extractelement <3 x float> [[SPLIT1]], i64 1
|
|
; CHECK-NEXT: [[TMP11:%.*]] = insertelement <4 x float> [[TMP9]], float [[TMP10]], i64 1
|
|
; CHECK-NEXT: [[TMP12:%.*]] = extractelement <3 x float> [[SPLIT2]], i64 1
|
|
; CHECK-NEXT: [[TMP13:%.*]] = insertelement <4 x float> [[TMP11]], float [[TMP12]], i64 2
|
|
; CHECK-NEXT: [[TMP14:%.*]] = extractelement <3 x float> [[SPLIT3]], i64 1
|
|
; CHECK-NEXT: [[TMP15:%.*]] = insertelement <4 x float> [[TMP13]], float [[TMP14]], i64 3
|
|
; CHECK-NEXT: [[TMP16:%.*]] = extractelement <3 x float> [[SPLIT]], i64 2
|
|
; CHECK-NEXT: [[TMP17:%.*]] = insertelement <4 x float> poison, float [[TMP16]], i64 0
|
|
; CHECK-NEXT: [[TMP18:%.*]] = extractelement <3 x float> [[SPLIT1]], i64 2
|
|
; CHECK-NEXT: [[TMP19:%.*]] = insertelement <4 x float> [[TMP17]], float [[TMP18]], i64 1
|
|
; CHECK-NEXT: [[TMP20:%.*]] = extractelement <3 x float> [[SPLIT2]], i64 2
|
|
; CHECK-NEXT: [[TMP21:%.*]] = insertelement <4 x float> [[TMP19]], float [[TMP20]], i64 2
|
|
; CHECK-NEXT: [[TMP22:%.*]] = extractelement <3 x float> [[SPLIT3]], i64 2
|
|
; CHECK-NEXT: [[TMP23:%.*]] = insertelement <4 x float> [[TMP21]], float [[TMP22]], i64 3
|
|
; CHECK-NEXT: [[TMP24:%.*]] = shufflevector <4 x float> [[TMP7]], <4 x float> [[TMP15]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
; CHECK-NEXT: [[TMP25:%.*]] = shufflevector <4 x float> [[TMP23]], <4 x float> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
|
|
; CHECK-NEXT: [[TMP26:%.*]] = shufflevector <8 x float> [[TMP24]], <8 x float> [[TMP25]], <12 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
|
|
; CHECK-NEXT: ret <12 x float> [[TMP26]]
|
|
;
|
|
entry:
|
|
%c = call <12 x float> @llvm.matrix.transpose.v12f32(<12 x float> %a, i32 3, i32 4)
|
|
ret <12 x float> %c
|
|
}
|