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
73 lines
4.1 KiB
MLIR
73 lines
4.1 KiB
MLIR
// RUN: mlir-opt -split-input-file -test-fold-arith-extf-into-vector-contract-patterns %s | FileCheck %s
|
|
|
|
|
|
// CHECK-DAG: #[[$map0:.*]] = affine_map<(d0, d1, d2) -> (d0, d2)>
|
|
// CHECK-DAG: #[[$map1:.*]] = affine_map<(d0, d1, d2) -> (d2, d1)>
|
|
// CHECK-DAG: #[[$map2:.*]] = affine_map<(d0, d1, d2) -> (d0, d1)>
|
|
// CHECK-LABEL: func.func @fold_arith_extf_into_contract
|
|
// CHECK-SAME: (%[[ARG0:.*]]: vector<64x64xf16>, %[[ARG1:.*]]: vector<64x64xf16>, %[[ARG2:.*]]: vector<64x64xf32>)
|
|
// CHECK-NEXT: %[[R:.+]] = vector.contract {indexing_maps = [#[[$map0]], #[[$map1]], #[[$map2]]],
|
|
// CHECK-SAME: iterator_types = ["parallel", "parallel", "reduction"], kind = #vector.kind<add>}
|
|
// CHECK-SAME: %[[ARG0]], %[[ARG1]], %[[ARG2]] : vector<64x64xf16>, vector<64x64xf16> into vector<64x64xf32>
|
|
// CHECK-NEXT: return %[[R]] : vector<64x64xf32>
|
|
func.func @fold_arith_extf_into_contract(
|
|
%arg0: vector<64x64xf16>,
|
|
%arg1: vector<64x64xf16>,
|
|
%arg2: vector<64x64xf32>) -> vector<64x64xf32> {
|
|
%lhs_f32 = arith.extf %arg0 : vector<64x64xf16> to vector<64x64xf32>
|
|
%rhs_f32 = arith.extf %arg1 : vector<64x64xf16> to vector<64x64xf32>
|
|
%result = vector.contract {
|
|
indexing_maps = [affine_map<(d0, d1, d2) -> (d0, d2)>, affine_map<(d0, d1, d2) -> (d2, d1)>, affine_map<(d0, d1, d2) -> (d0, d1)>],
|
|
iterator_types = ["parallel", "parallel", "reduction"],
|
|
kind = #vector.kind<add>}
|
|
%lhs_f32, %rhs_f32, %arg2 : vector<64x64xf32>, vector<64x64xf32> into vector<64x64xf32>
|
|
return %result : vector<64x64xf32>
|
|
}
|
|
|
|
// -----
|
|
|
|
// CHECK-DAG: #[[$map0:.*]] = affine_map<(d0, d1, d2) -> (d0, d2)>
|
|
// CHECK-DAG: #[[$map1:.*]] = affine_map<(d0, d1, d2) -> (d2, d1)>
|
|
// CHECK-DAG: #[[$map2:.*]] = affine_map<(d0, d1, d2) -> (d0, d1)>
|
|
// CHECK-LABEL: func.func @fold_arith_extf_into_contract_scalable
|
|
// CHECK-SAME: (%[[ARG0:.*]]: vector<[64]x64xf16>, %[[ARG1:.*]]: vector<64x64xf16>, %[[ARG2:.*]]: vector<[64]x64xf32>)
|
|
// CHECK-NEXT: %[[R:.+]] = vector.contract {indexing_maps = [#[[$map0]], #[[$map1]], #[[$map2]]],
|
|
// CHECK-SAME: iterator_types = ["parallel", "parallel", "reduction"], kind = #vector.kind<add>}
|
|
// CHECK-SAME: %[[ARG0]], %[[ARG1]], %[[ARG2]] : vector<[64]x64xf16>, vector<64x64xf16> into vector<[64]x64xf32>
|
|
// CHECK-NEXT: return %[[R]] : vector<[64]x64xf32>
|
|
func.func @fold_arith_extf_into_contract_scalable(
|
|
%arg0: vector<[64]x64xf16>,
|
|
%arg1: vector<64x64xf16>,
|
|
%arg2: vector<[64]x64xf32>) -> vector<[64]x64xf32> {
|
|
%lhs_f32 = arith.extf %arg0 : vector<[64]x64xf16> to vector<[64]x64xf32>
|
|
%rhs_f32 = arith.extf %arg1 : vector<64x64xf16> to vector<64x64xf32>
|
|
%result = vector.contract {
|
|
indexing_maps = [affine_map<(d0, d1, d2) -> (d0, d2)>, affine_map<(d0, d1, d2) -> (d2, d1)>, affine_map<(d0, d1, d2) -> (d0, d1)>],
|
|
iterator_types = ["parallel", "parallel", "reduction"],
|
|
kind = #vector.kind<add>}
|
|
%lhs_f32, %rhs_f32, %arg2 : vector<[64]x64xf32>, vector<64x64xf32> into vector<[64]x64xf32>
|
|
return %result : vector<[64]x64xf32>
|
|
}
|
|
|
|
// -----
|
|
|
|
// CHECK-LABEL: func.func @fold_arith_extsi_into_contract
|
|
// CHECK-SAME: (%[[ARG0:.*]]: vector<64x64xi8>, %[[ARG1:.*]]: vector<64x64xi8>, %[[ARG2:.*]]: vector<64x64xi32>)
|
|
// CHECK-NEXT: %[[R:.+]] = vector.contract
|
|
// CHECK-SAME: iterator_types = ["parallel", "parallel", "reduction"], kind = #vector.kind<add>}
|
|
// CHECK-SAME: %[[ARG0]], %[[ARG1]], %[[ARG2]] : vector<64x64xi8>, vector<64x64xi8> into vector<64x64xi32>
|
|
// CHECK-NEXT: return %[[R]] : vector<64x64xi32>
|
|
func.func @fold_arith_extsi_into_contract(
|
|
%arg0: vector<64x64xi8>,
|
|
%arg1: vector<64x64xi8>,
|
|
%arg2: vector<64x64xi32>) -> vector<64x64xi32> {
|
|
%lhs_i32 = arith.extsi %arg0 : vector<64x64xi8> to vector<64x64xi32>
|
|
%rhs_i32 = arith.extsi %arg1 : vector<64x64xi8> to vector<64x64xi32>
|
|
%result = vector.contract {
|
|
indexing_maps = [affine_map<(d0, d1, d2) -> (d0, d2)>, affine_map<(d0, d1, d2) -> (d2, d1)>, affine_map<(d0, d1, d2) -> (d0, d1)>],
|
|
iterator_types = ["parallel", "parallel", "reduction"],
|
|
kind = #vector.kind<add>}
|
|
%lhs_i32, %rhs_i32, %arg2 : vector<64x64xi32>, vector<64x64xi32> into vector<64x64xi32>
|
|
return %result : vector<64x64xi32>
|
|
}
|