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
58 lines
2.7 KiB
MLIR
58 lines
2.7 KiB
MLIR
// RUN: mlir-opt %s --sparse-reinterpret-map -sparsification | FileCheck %s
|
|
|
|
//
|
|
// A contrived example where the sparse tensor B is only
|
|
// used in the linalg op to determine the number of iterations
|
|
// for the k-loop. This is included to make sure the sparse
|
|
// compiler still generates the correct loop nest for this case.
|
|
//
|
|
|
|
#SM = #sparse_tensor.encoding<{ map = (d0, d1) -> (d0 : dense, d1 : compressed) }>
|
|
|
|
#trait = {
|
|
indexing_maps = [
|
|
affine_map<(i,j,k) -> (i,j)>, // A
|
|
affine_map<(i,j,k) -> (k,j)>, // B
|
|
affine_map<(i,j,k) -> (i,j)> // S_out
|
|
],
|
|
iterator_types = ["parallel", "parallel", "reduction"],
|
|
doc = "C(i,j) = SUM_k A(i,j)"
|
|
}
|
|
|
|
// CHECK-LABEL: func.func @b_ununsed(
|
|
// CHECK-SAME: %[[VAL_0:.*]]: tensor<2x4xf64>,
|
|
// CHECK-SAME: %[[VAL_1:.*]]: tensor<8x4xf64, #sparse{{[0-9]*}}>,
|
|
// CHECK-SAME: %[[VAL_2:.*]]: tensor<2x4xf64>) -> tensor<2x4xf64> {
|
|
// CHECK-DAG: %[[VAL_3:.*]] = arith.constant 8 : index
|
|
// CHECK-DAG: %[[VAL_4:.*]] = arith.constant 2 : index
|
|
// CHECK-DAG: %[[VAL_5:.*]] = arith.constant 4 : index
|
|
// CHECK-DAG: %[[VAL_6:.*]] = arith.constant 0 : index
|
|
// CHECK-DAG: %[[VAL_7:.*]] = arith.constant 1 : index
|
|
// CHECK-DAG: %[[VAL_8:.*]] = bufferization.to_buffer %[[VAL_0]] : tensor<2x4xf64>
|
|
// CHECK-DAG: %[[VAL_9:.*]] = bufferization.to_buffer %[[VAL_2]] : tensor<2x4xf64>
|
|
// CHECK: scf.for %[[VAL_10:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
|
|
// CHECK: scf.for %[[VAL_11:.*]] = %[[VAL_6]] to %[[VAL_3]] step %[[VAL_7]] {
|
|
// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_6]] to %[[VAL_5]] step %[[VAL_7]] {
|
|
// CHECK: %[[VAL_13:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_10]], %[[VAL_12]]] : memref<2x4xf64>
|
|
// CHECK: %[[VAL_14:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_10]], %[[VAL_12]]] : memref<2x4xf64>
|
|
// CHECK: %[[VAL_15:.*]] = arith.addf %[[VAL_13]], %[[VAL_14]] : f64
|
|
// CHECK: memref.store %[[VAL_15]], %[[VAL_9]]{{\[}}%[[VAL_10]], %[[VAL_12]]] : memref<2x4xf64>
|
|
// CHECK: }
|
|
// CHECK: }
|
|
// CHECK: }
|
|
// CHECK: %[[VAL_16:.*]] = bufferization.to_tensor %[[VAL_9]] : memref<2x4xf64>
|
|
// CHECK: return %[[VAL_16]] : tensor<2x4xf64>
|
|
// CHECK: }
|
|
func.func @b_ununsed(%argA: tensor<2x4xf64>,
|
|
%argB: tensor<8x4xf64, #SM>,
|
|
%argC: tensor<2x4xf64>) -> tensor<2x4xf64> {
|
|
%result = linalg.generic #trait
|
|
ins(%argA, %argB: tensor<2x4xf64>, tensor<8x4xf64, #SM>)
|
|
outs(%argC: tensor<2x4xf64>) {
|
|
^bb(%a: f64, %b: f64, %c: f64):
|
|
%0 = arith.addf %c, %a : f64
|
|
linalg.yield %0 : f64
|
|
} -> tensor<2x4xf64>
|
|
return %result : tensor<2x4xf64>
|
|
}
|