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
79 lines
4.4 KiB
LLVM
79 lines
4.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -passes='lower-matrix-intrinsics' -S < %s | FileCheck %s
|
|
|
|
define <9 x double> @strided_load_3x3(ptr %in, i64 %stride) {
|
|
; CHECK-LABEL: @strided_load_3x3(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[VEC_START:%.*]] = mul i64 0, [[STRIDE:%.*]]
|
|
; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr inbounds double, ptr [[IN:%.*]], i64 [[VEC_START]]
|
|
; CHECK-NEXT: [[COL_LOAD:%.*]] = load <3 x double>, ptr [[VEC_GEP]], align 8
|
|
; CHECK-NEXT: [[VEC_START1:%.*]] = mul i64 1, [[STRIDE]]
|
|
; CHECK-NEXT: [[VEC_GEP2:%.*]] = getelementptr inbounds double, ptr [[IN]], i64 [[VEC_START1]]
|
|
; CHECK-NEXT: [[COL_LOAD4:%.*]] = load <3 x double>, ptr [[VEC_GEP2]], align 8
|
|
; CHECK-NEXT: [[VEC_START5:%.*]] = mul i64 2, [[STRIDE]]
|
|
; CHECK-NEXT: [[VEC_GEP6:%.*]] = getelementptr inbounds double, ptr [[IN]], i64 [[VEC_START5]]
|
|
; CHECK-NEXT: [[COL_LOAD8:%.*]] = load <3 x double>, ptr [[VEC_GEP6]], align 8
|
|
; CHECK-NEXT: [[TMP0:%.*]] = shufflevector <3 x double> [[COL_LOAD]], <3 x double> [[COL_LOAD4]], <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <3 x double> [[COL_LOAD8]], <3 x double> poison, <6 x i32> <i32 0, i32 1, i32 2, i32 poison, i32 poison, i32 poison>
|
|
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <6 x double> [[TMP0]], <6 x double> [[TMP1]], <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>
|
|
; CHECK-NEXT: ret <9 x double> [[TMP2]]
|
|
;
|
|
entry:
|
|
%load = call <9 x double> @llvm.matrix.column.major.load.v9f64.i64(ptr %in, i64 %stride, i1 false, i32 3, i32 3)
|
|
ret <9 x double> %load
|
|
}
|
|
|
|
declare <9 x double> @llvm.matrix.column.major.load.v9f64.i64(ptr, i64, i1, i32, i32)
|
|
|
|
define <9 x double> @strided_load_9x1(ptr %in, i64 %stride) {
|
|
; CHECK-LABEL: @strided_load_9x1(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[VEC_START:%.*]] = mul i64 0, [[STRIDE:%.*]]
|
|
; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr inbounds double, ptr [[IN:%.*]], i64 [[VEC_START]]
|
|
; CHECK-NEXT: [[COL_LOAD:%.*]] = load <9 x double>, ptr [[VEC_GEP]], align 8
|
|
; CHECK-NEXT: ret <9 x double> [[COL_LOAD]]
|
|
;
|
|
entry:
|
|
%load = call <9 x double> @llvm.matrix.column.major.load.v9f64.i64(ptr %in, i64 %stride, i1 false, i32 9, i32 1)
|
|
ret <9 x double> %load
|
|
}
|
|
|
|
declare <8 x double> @llvm.matrix.column.major.load.v8f64.i64(ptr, i64, i1, i32, i32)
|
|
|
|
define <8 x double> @strided_load_4x2(ptr %in, i64 %stride) {
|
|
; CHECK-LABEL: @strided_load_4x2(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[VEC_START:%.*]] = mul i64 0, [[STRIDE:%.*]]
|
|
; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr inbounds double, ptr [[IN:%.*]], i64 [[VEC_START]]
|
|
; CHECK-NEXT: [[COL_LOAD:%.*]] = load <4 x double>, ptr [[VEC_GEP]], align 8
|
|
; CHECK-NEXT: [[VEC_START1:%.*]] = mul i64 1, [[STRIDE]]
|
|
; CHECK-NEXT: [[VEC_GEP2:%.*]] = getelementptr inbounds double, ptr [[IN]], i64 [[VEC_START1]]
|
|
; CHECK-NEXT: [[COL_LOAD4:%.*]] = load <4 x double>, ptr [[VEC_GEP2]], align 8
|
|
; CHECK-NEXT: [[TMP0:%.*]] = shufflevector <4 x double> [[COL_LOAD]], <4 x double> [[COL_LOAD4]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
; CHECK-NEXT: ret <8 x double> [[TMP0]]
|
|
;
|
|
entry:
|
|
%load = call <8 x double> @llvm.matrix.column.major.load.v8f64.i64(ptr %in, i64 %stride, i1 false, i32 4, i32 2)
|
|
ret <8 x double> %load
|
|
}
|
|
|
|
declare <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr, i32, i1, i32, i32)
|
|
|
|
define <8 x double> @strided_load_4x2_stride_i32(ptr %in, i32 %stride) {
|
|
; CHECK-LABEL: @strided_load_4x2_stride_i32(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[STRIDE_CAST:%.*]] = zext i32 [[STRIDE:%.*]] to i64
|
|
; CHECK-NEXT: [[VEC_START:%.*]] = mul i64 0, [[STRIDE_CAST]]
|
|
; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr inbounds double, ptr [[IN:%.*]], i64 [[VEC_START]]
|
|
; CHECK-NEXT: [[COL_LOAD:%.*]] = load <4 x double>, ptr [[VEC_GEP]], align 8
|
|
; CHECK-NEXT: [[VEC_START1:%.*]] = mul i64 1, [[STRIDE_CAST]]
|
|
; CHECK-NEXT: [[VEC_GEP2:%.*]] = getelementptr inbounds double, ptr [[IN]], i64 [[VEC_START1]]
|
|
; CHECK-NEXT: [[COL_LOAD4:%.*]] = load <4 x double>, ptr [[VEC_GEP2]], align 8
|
|
; CHECK-NEXT: [[TMP0:%.*]] = shufflevector <4 x double> [[COL_LOAD]], <4 x double> [[COL_LOAD4]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
; CHECK-NEXT: ret <8 x double> [[TMP0]]
|
|
;
|
|
entry:
|
|
%load = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr %in, i32 %stride, i1 false, i32 4, i32 2)
|
|
ret <8 x double> %load
|
|
}
|