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
97 lines
4.6 KiB
MLIR
97 lines
4.6 KiB
MLIR
// RUN: mlir-opt --transform-interpreter --split-input-file --verify-diagnostics %s | FileCheck %s
|
|
|
|
#map = affine_map<(d0, d1, d2) -> (d0, d2)>
|
|
#map1 = affine_map<(d0, d1, d2) -> (d2, d1)>
|
|
#map2 = affine_map<(d0, d1, d2) -> (d0, d1)>
|
|
func.func @specialize_matmul(%arg0: tensor<?x?xf32>, %arg1: tensor<?x?xf32>, %arg2: tensor<?x?xf32>) -> tensor<?x?xf32> {
|
|
%0 = linalg.generic
|
|
{indexing_maps = [#map, #map1, #map2], iterator_types = ["parallel", "parallel", "reduction"]}
|
|
ins(%arg0, %arg1 : tensor<?x?xf32>, tensor<?x?xf32>) outs(%arg2 : tensor<?x?xf32>) {
|
|
^bb0(%in: f32, %in_0: f32, %out: f32):
|
|
%0 = arith.mulf %in, %in_0 : f32
|
|
%1 = arith.addf %out, %0 : f32
|
|
linalg.yield %1 : f32
|
|
} -> tensor<?x?xf32>
|
|
return %0 : tensor<?x?xf32>
|
|
}
|
|
|
|
// CHECK-LABEL: @specialize_matmul
|
|
// CHECK-SAME: %[[ARG0:.+]]: tensor<?x?xf32>, %[[ARG1:.+]]: tensor<?x?xf32>, %[[ARG2:.+]]: tensor<?x?xf32>) -> tensor<?x?xf32>
|
|
// CHECK-NOT: linalg.generic
|
|
// CHECK: linalg.matmul ins(%[[ARG0]], %[[ARG1]] : tensor<?x?xf32>, tensor<?x?xf32>) outs(%[[ARG2]] : tensor<?x?xf32>) -> tensor<?x?xf32>
|
|
|
|
module attributes {transform.with_named_sequence} {
|
|
transform.named_sequence @__transform_main(%arg0: !transform.any_op {transform.readonly}) {
|
|
%0 = transform.structured.match interface{LinalgOp} in %arg0 : (!transform.any_op) -> !transform.any_op
|
|
%1 = transform.structured.specialize %0 : (!transform.any_op) -> !transform.any_op
|
|
transform.yield
|
|
}
|
|
}
|
|
|
|
// -----
|
|
|
|
#map = affine_map<(d0, d1, d2, d3) -> (d0, d1, d3)>
|
|
#map1 = affine_map<(d0, d1, d2, d3) -> (d0, d3, d2)>
|
|
#map2 = affine_map<(d0, d1, d2, d3) -> (d0, d1, d2)>
|
|
func.func @batch_matmul(%arg0: tensor<2x16x8xf32>, %arg1: tensor<2x8x16xf32>, %arg2: tensor<2x16x16xf32>) -> tensor<2x16x16xf32> {
|
|
%0 = linalg.generic
|
|
{indexing_maps = [#map, #map1, #map2], iterator_types = ["parallel", "parallel", "parallel", "reduction"]}
|
|
ins(%arg0, %arg1 : tensor<2x16x8xf32>, tensor<2x8x16xf32>) outs(%arg2 : tensor<2x16x16xf32>) {
|
|
^bb0(%in: f32, %in_0: f32, %out: f32):
|
|
%1 = arith.mulf %in, %in_0 : f32
|
|
%2 = arith.addf %out, %1 : f32
|
|
linalg.yield %2 : f32
|
|
} -> tensor<2x16x16xf32>
|
|
return %0 : tensor<2x16x16xf32>
|
|
}
|
|
|
|
// CHECK-LABEL: @batch_matmul
|
|
// CHECK-SAME: %[[ARG0:.+]]: tensor<2x16x8xf32>, %[[ARG1:.+]]: tensor<2x8x16xf32>, %[[ARG2:.+]]: tensor<2x16x16xf32>) -> tensor<2x16x16xf32>
|
|
// CHECK-NOT: linalg.generic
|
|
// CHECK: linalg.batch_matmul ins(%[[ARG0]], %[[ARG1]] : tensor<2x16x8xf32>, tensor<2x8x16xf32>) outs(%[[ARG2]] : tensor<2x16x16xf32>) -> tensor<2x16x16xf32>
|
|
|
|
module attributes {transform.with_named_sequence} {
|
|
transform.named_sequence @__transform_main(%arg0: !transform.any_op {transform.readonly}) {
|
|
%0 = transform.structured.match interface{LinalgOp} in %arg0 : (!transform.any_op) -> !transform.any_op
|
|
%1 = transform.structured.specialize %0 : (!transform.any_op) -> !transform.any_op
|
|
transform.yield
|
|
}
|
|
}
|
|
|
|
// -----
|
|
|
|
#map = affine_map<(d0, d1, d2) -> (d0, d2)>
|
|
#map1 = affine_map<(d0, d1, d2) -> (d2, d1)>
|
|
#map2 = affine_map<(d0, d1, d2) -> (d0, d1)>
|
|
func.func @category_contract(%arg0: tensor<?x?xf32>, %arg1: tensor<?x?xf32>, %arg2: tensor<?x?xf32>) -> tensor<?x?xf32> {
|
|
%0 = linalg.generic
|
|
{indexing_maps = [#map, #map1, #map2], iterator_types = ["parallel", "parallel", "reduction"]}
|
|
ins(%arg0, %arg1 : tensor<?x?xf32>, tensor<?x?xf32>) outs(%arg2 : tensor<?x?xf32>) {
|
|
^bb0(%in: f32, %in_0: f32, %out: f32):
|
|
%0 = arith.mulf %in, %in_0 : f32
|
|
%1 = arith.addf %out, %0 : f32
|
|
linalg.yield %1 : f32
|
|
} -> tensor<?x?xf32>
|
|
return %0 : tensor<?x?xf32>
|
|
}
|
|
|
|
// CHECK-DAG: #[[$MAP_A:.+]] = affine_map<(d0, d1, d2) -> (d0, d2)>
|
|
// CHECK-DAG: #[[$MAP_B:.+]] = affine_map<(d0, d1, d2) -> (d2, d1)>
|
|
// CHECK-DAG: #[[$MAP_C:.+]] = affine_map<(d0, d1, d2) -> (d0, d1)>
|
|
|
|
// CHECK-LABEL: @category_contract
|
|
// CHECK-SAME: %[[ARG0:.+]]: tensor<?x?xf32>, %[[ARG1:.+]]: tensor<?x?xf32>, %[[ARG2:.+]]: tensor<?x?xf32>) -> tensor<?x?xf32>
|
|
// CHECK-NOT: linalg.generic
|
|
// CHECK: linalg.contract
|
|
// CHECK-SAME: indexing_maps = {{\[}}#[[$MAP_A]], #[[$MAP_B]], #[[$MAP_C]]{{\]}}
|
|
// CHECK-SAME: ins(%[[ARG0]], %[[ARG1]] : tensor<?x?xf32>, tensor<?x?xf32>)
|
|
// CHECK-SAME: outs(%[[ARG2]] : tensor<?x?xf32>) -> tensor<?x?xf32>
|
|
|
|
module attributes {transform.with_named_sequence} {
|
|
transform.named_sequence @__transform_main(%arg0: !transform.any_op {transform.readonly}) {
|
|
%0 = transform.structured.match interface{LinalgOp} in %arg0 : (!transform.any_op) -> !transform.any_op
|
|
%1 = transform.structured.specialize %0 {emit_category = true} : (!transform.any_op) -> !transform.any_op
|
|
transform.yield
|
|
}
|
|
}
|