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
43 lines
2.4 KiB
MLIR
43 lines
2.4 KiB
MLIR
// RUN: mlir-opt %s -convert-linalg-to-affine-loops | FileCheck %s
|
|
|
|
// Test that we can lower all the way to LLVM without crashing, don't check results here.
|
|
// RUN: mlir-opt %s -convert-linalg-to-affine-loops -test-lower-to-llvm -o=/dev/null 2>&1
|
|
|
|
func.func @matmul(%arg0: memref<?xi8>, %M: index, %N: index, %K: index) {
|
|
%c0 = arith.constant 0 : index
|
|
%c1 = arith.constant 1 : index
|
|
%A = memref.view %arg0[%c0][%M, %K] : memref<?xi8> to memref<?x?xf32>
|
|
%B = memref.view %arg0[%c0][%K, %N] : memref<?xi8> to memref<?x?xf32>
|
|
%C = memref.view %arg0[%c0][%M, %N] : memref<?xi8> to memref<?x?xf32>
|
|
linalg.matmul ins(%A, %B: memref<?x?xf32>, memref<?x?xf32>)
|
|
outs(%C: memref<?x?xf32>)
|
|
return
|
|
}
|
|
|
|
//----------------------------------------------------------------------------//
|
|
// Named ops to loops.
|
|
//----------------------------------------------------------------------------//
|
|
func.func @named_batch_matmul(%A: memref<?x?x?xf32>, %B: memref<?x?x?xf32>, %C: memref<?x?x?xf32>) {
|
|
linalg.batch_matmul ins(%A, %B: memref<?x?x?xf32>, memref<?x?x?xf32>)
|
|
outs(%C : memref<?x?x?xf32>)
|
|
return
|
|
}
|
|
// CHECK-LABEL: @named_batch_matmul
|
|
// CHECK-SAME: %[[mA:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
|
|
// CHECK-SAME: %[[mB:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
|
|
// CHECK-SAME: %[[mC:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
|
|
// CHECK: %[[B:.*]] = memref.dim %[[mA]], %c0 : memref<?x?x?xf32>
|
|
// CHECK: %[[M:.*]] = memref.dim %[[mA]], %c1 : memref<?x?x?xf32>
|
|
// CHECK: %[[K:.*]] = memref.dim %[[mA]], %c2 : memref<?x?x?xf32>
|
|
// CHECK: %[[N:.*]] = memref.dim %[[mB]], %c2 : memref<?x?x?xf32>
|
|
// CHECK: affine.for %[[b:.*]] = {{.*}}0 to %[[B]] {
|
|
// CHECK: affine.for %[[m:.*]] = {{.*}}0 to %[[M]] {
|
|
// CHECK: affine.for %[[n:.*]] = {{.*}}0 to %[[N]] {
|
|
// CHECK: affine.for %[[k:.*]] = {{.*}}0 to %[[K]] {
|
|
// CHECK: %[[va:.*]] = affine.load %[[mA]][%[[b]], %[[m]], %[[k]]] : memref<?x?x?xf32>
|
|
// CHECK: %[[vb:.*]] = affine.load %[[mB]][%[[b]], %[[k]], %[[n]]] : memref<?x?x?xf32>
|
|
// CHECK: %[[vc:.*]] = affine.load %[[mC]][%[[b]], %[[m]], %[[n]]] : memref<?x?x?xf32>
|
|
// CHECK: %[[inc:.*]] = arith.mulf %[[va]], %[[vb]] : f32
|
|
// CHECK: %[[res:.*]] = arith.addf %[[vc]], %[[inc]] : f32
|
|
// CHECK: affine.store %[[res]], %[[mC]][%[[b]], %[[m]], %[[n]]] : memref<?x?x?xf32>
|