This is an archive of the discontinued LLVM Phabricator instance.

Differential D91912

[mlir] Fix async microbench integration test
ClosedPublic

Authored by ezhulenev on Nov 21 2020, 7:01 AM.

Details

Reviewers
aartbik
Commits
rGf2df67e2a69e: [mlir] Fix async microbench integration test

Diff Detail

Event Timeline

ezhulenev created this revision.Nov 21 2020, 7:01 AM
Herald added a reviewer: aartbik. · View Herald TranscriptNov 21 2020, 7:01 AM
Herald added a project: Restricted Project. · View Herald Transcript
Herald added subscribers: teijeong, rdzhabarov, tatianashp and 14 others. · View Herald Transcript
ezhulenev requested review of this revision.Nov 21 2020, 7:01 AM
Herald added subscribers: stephenneuendorffer, nicolasvasilache. · View Herald TranscriptNov 21 2020, 7:01 AM
This revision was not accepted when it landed; it landed in state Needs Review.Nov 21 2020, 7:02 AM
This revision was landed with ongoing or failed builds.
Closed by commit rGf2df67e2a69e: [mlir] Fix async microbench integration test (authored by ezhulenev). · Explain Why
This revision was automatically updated to reflect the committed changes.
ezhulenev added a commit: rGf2df67e2a69e: [mlir] Fix async microbench integration test.
ezhulenev mentioned this in D91896: [mlir] Add microbenchmark for linalg+async-parallel-for.Nov 21 2020, 7:02 AM
Harbormaster completed remote builds in B79688: Diff 306844.Nov 21 2020, 7:21 AM

Revision Contents

PathSize
mlir/
integration_test/
Dialect/
Async/
CPU/
14 lines

Diff 306844

mlir/integration_test/Dialect/Async/CPU/microbench-linalg-async-parallel-for.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -linalg-tile-to-parallel-loops="linalg-tile-sizes=256" \ // RUN: -linalg-tile-to-parallel-loops="linalg-tile-sizes=256" \
// RUN: -async-parallel-for="num-concurrent-async-execute=4" \ // RUN: -async-parallel-for="num-concurrent-async-execute=4" \
// RUN: -async-ref-counting \ // RUN: -async-ref-counting \
// RUN: -convert-async-to-llvm \ // RUN: -convert-async-to-llvm \
// RUN: -lower-affine \ // RUN: -lower-affine \
// RUN: -convert-linalg-to-loops \ // RUN: -convert-linalg-to-loops \
// RUN: -convert-scf-to-std \ // RUN: -convert-scf-to-std \
// RUN: -std-expand \ // RUN: -std-expand \
// RUN: -convert-vector-to-llvm \ // RUN: -convert-vector-to-llvm \
// RUN: -convert-std-to-llvm \ // RUN: -convert-std-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void -O3 \ // RUN: -e entry -entry-point-result=void -O3 \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext\
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_async_runtime%shlibext\ // RUN: -shared-libs=%mlir_integration_test_dir/libmlir_async_runtime%shlibext \
// RUN: | FileCheck %s --dump-input=always // RUN: | FileCheck %s --dump-input=always
// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -convert-linalg-to-loops \ // RUN: -convert-linalg-to-loops \
// RUN: -convert-scf-to-std \ // RUN: -convert-scf-to-std \
// RUN: -convert-vector-to-llvm \ // RUN: -convert-vector-to-llvm \
// RUN: -convert-std-to-llvm \ // RUN: -convert-std-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void -O3 \ // RUN: -e entry -entry-point-result=void -O3 \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext\
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_async_runtime%shlibext\ // RUN: -shared-libs=%mlir_integration_test_dir/libmlir_async_runtime%shlibext \
// RUN: | FileCheck %s --dump-input=always // RUN: | FileCheck %s --dump-input=always
#map0 = affine_map<(d0, d1) -> (d0, d1)> #map0 = affine_map<(d0, d1) -> (d0, d1)>
func @linalg_generic(%lhs: memref<?x?xf32>, func @linalg_generic(%lhs: memref<?x?xf32>,
%rhs: memref<?x?xf32>, %rhs: memref<?x?xf32>,
%sum: memref<?x?xf32>) { %sum: memref<?x?xf32>) {
linalg.generic { linalg.generic {
▲ Show 20 Lines • Show All 93 Lines • Show Last 20 Lines