This is an archive of the discontinued LLVM Phabricator instance.

Differential D133270

[MLIR] Switch lit tests to %mlir_lib_dir and %mlir_src_dir replacements.
ClosedPublic

Authored by csigg on Sep 4 2022, 1:48 AM.

Details

Reviewers
mehdi_amini
antiagainst
aartbik
ftynse
nicolasvasilache
herhut
dcaballe
Commits
rG0f2ec35691cd: [MLIR] Switch lit tests to %mlir_lib_dir and %mlir_src_dir replacements.
Summary

The old replacements will be removed soon:

  • %linalg_test_lib_dir
  • %cuda_wrapper_library_dir
  • %spirv_wrapper_library_dir
  • %vulkan_wrapper_library_dir
  • %mlir_runner_utils_dir
  • %mlir_integration_test_dir

Diff Detail

Event Timeline

csigg created this revision.Sep 4 2022, 1:48 AM
Herald added a reviewer: antiagainst. · View Herald TranscriptSep 4 2022, 1:48 AM
Herald added a reviewer: aartbik. · View Herald Transcript
Herald added a reviewer: ftynse. · View Herald Transcript
Herald added a reviewer: aartbik. · View Herald Transcript
Herald added a reviewer: aartbik. · View Herald Transcript
Herald added a project: Restricted Project. · View Herald Transcript
Herald added subscribers: anlunx, bzcheeseman, ThomasRaoux and 25 others. · View Herald Transcript
csigg requested review of this revision.Sep 4 2022, 1:48 AM
Herald added a reviewer: nicolasvasilache. · View Herald TranscriptSep 4 2022, 1:48 AM
Herald added a reviewer: herhut. · View Herald Transcript
Herald added a reviewer: dcaballe. · View Herald Transcript
Herald added a project: Restricted Project. · View Herald Transcript
Herald added subscribers: limo1996, stephenneuendorffer, nicolasvasilache. · View Herald Transcript
csigg mentioned this in D133190: [MLIR] Fix runner library paths for integration tests.Sep 4 2022, 2:11 AM
Harbormaster completed remote builds in B185000: Diff 457845.Sep 4 2022, 2:39 AM
csigg updated this revision to Diff 457847.Sep 4 2022, 2:56 AM

Remove libmlir_test_spirv_cpu_runner_c_wrappers.so bazel target for now.

The corresponding test package will be added later.

Harbormaster completed remote builds in B185002: Diff 457847.Sep 4 2022, 3:11 AM
csigg updated this revision to Diff 457848.Sep 4 2022, 4:03 AM

Tag cuda-dependent targets with 'manual'.

Harbormaster completed remote builds in B185003: Diff 457848.Sep 4 2022, 4:21 AM
herhut added a comment.Sep 5 2022, 1:38 AM

+1 for the direction. Just a bazil question.

utils/bazel/llvm-project-overlay/mlir/BUILD.bazel
6489

Why are these aliases needed?

csigg added inline comments.Sep 5 2022, 3:36 AM
utils/bazel/llvm-project-overlay/mlir/BUILD.bazel
6489

They are needed because the shared library name (lib<name>.so) of the cc_library target would otherwise clash with the cc_binary target below.

I will add a comment explaining this.

csigg updated this revision to Diff 457998.Sep 5 2022, 7:43 AM

Add comments why alias are needed.

Harbormaster completed remote builds in B185095: Diff 457998.Sep 5 2022, 8:01 AM
herhut accepted this revision.Sep 6 2022, 1:02 AM

Thanks for the explanation. My bazil-foo is not as strong as yours.

This revision is now accepted and ready to land.Sep 6 2022, 1:02 AM
Closed by commit rG0f2ec35691cd: [MLIR] Switch lit tests to %mlir_lib_dir and %mlir_src_dir replacements. (authored by csigg). · Explain WhySep 6 2022, 3:34 AM
This revision was automatically updated to reflect the committed changes.
csigg added a commit: rG0f2ec35691cd: [MLIR] Switch lit tests to %mlir_lib_dir and %mlir_src_dir replacements..

Revision Contents

PathSize
mlir/
test/
9 lines
Integration/
Dialect/
Async/
CPU/
12 lines
18 lines
12 lines
12 lines
Complex/
CPU/
2 lines
LLVMIR/
CPU/
X86/
2 lines
2 lines
2 lines
2 lines
Linalg/
CPU/
2 lines
2 lines
2 lines
4 lines
4 lines
4 lines
4 lines
4 lines
4 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
4 lines
SparseTensor/
CPU/
2 lines
4 lines
2 lines
2 lines
2 lines
2 lines
4 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
4 lines
8 lines
2 lines
4 lines
2 lines
2 lines
8 lines
8 lines
2 lines
2 lines
8 lines
4 lines
2 lines
2 lines
4 lines
2 lines
8 lines
4 lines
4 lines
2 lines
2 lines
8 lines
2 lines
8 lines
2 lines
4 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
python/
211 lines
181 lines
2 lines
94 lines
2 lines
taco/
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
Standard/
CPU/
2 lines
2 lines
Vector/
CPU/
AMX/
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
X86Vector/
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
8 lines
8 lines
8 lines
4 lines
4 lines
2 lines
2 lines
4 lines
GPU/
CUDA/
6 lines
18 lines
GPU/
CUDA/
TensorCore/
4 lines
4 lines
4 lines
4 lines
4 lines
4 lines
4 lines
4 lines
4 lines
6 lines
6 lines
4 lines
4 lines
4 lines
ROCM/
4 lines
4 lines
4 lines
4 lines
4 lines
39 lines
mlir-cpu-runner/
X86Vector/
4 lines
6 lines
6 lines
6 lines
6 lines
2 lines
2 lines
2 lines
4 lines
2 lines
2 lines
2 lines
2 lines
2 lines
8 lines
mlir-spirv-cpu-runner/
2 lines
2 lines
mlir-vulkan-runner/
2 lines
2 lines
2 lines
2 lines
2 lines
2 lines
utils/
bazel/
llvm-project-overlay/
mlir/
92 lines

Diff 458132

mlir/test/CMakeLists.txt

Show All 29 Linesif (MLIR_INCLUDE_INTEGRATION_TESTS)
option(MLIR_RUN_ARM_SVE_TESTS "Run Arm SVE tests.") option(MLIR_RUN_ARM_SVE_TESTS "Run Arm SVE tests.")
# The native target may not be enabled when cross compiling, raise an error. # The native target may not be enabled when cross compiling, raise an error.
if(NOT MLIR_ENABLE_EXECUTION_ENGINE) if(NOT MLIR_ENABLE_EXECUTION_ENGINE)
message(FATAL_ERROR "MLIR_INCLUDE_INTEGRATION_TESTS requires a native target") message(FATAL_ERROR "MLIR_INCLUDE_INTEGRATION_TESTS requires a native target")
endif() endif()
# Copy test data over.
# TODO: drop copy and load files relative to MLIR_SOURCE_DIR / %mlir_src_root.
file(COPY ${CMAKE_CURRENT_SOURCE_DIR}/Integration/data/mttkrp_b.tns
${CMAKE_CURRENT_SOURCE_DIR}/Integration/data/test.mtx
${CMAKE_CURRENT_SOURCE_DIR}/Integration/data/test_symmetric.mtx
${CMAKE_CURRENT_SOURCE_DIR}/Integration/data/test_symmetric_complex.mtx
${CMAKE_CURRENT_SOURCE_DIR}/Integration/data/test.tns
${CMAKE_CURRENT_SOURCE_DIR}/Integration/data/wide.mtx
DESTINATION ${MLIR_LIB_DIR}/data/)
endif() endif()
llvm_canonicalize_cmake_booleans( llvm_canonicalize_cmake_booleans(
LLVM_BUILD_EXAMPLES LLVM_BUILD_EXAMPLES
MLIR_ENABLE_BINDINGS_PYTHON MLIR_ENABLE_BINDINGS_PYTHON
MLIR_ENABLE_CUDA_CONVERSIONS MLIR_ENABLE_CUDA_CONVERSIONS
MLIR_ENABLE_CUDA_RUNNER MLIR_ENABLE_CUDA_RUNNER
MLIR_ENABLE_ROCM_CONVERSIONS MLIR_ENABLE_ROCM_CONVERSIONS
▲ Show 20 Lines • Show All 118 Lines • Show Last 20 Lines

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

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -convert-linalg-to-parallel-loops \ // RUN: -convert-linalg-to-parallel-loops \
// RUN: -async-parallel-for \ // RUN: -async-parallel-for \
// RUN: -async-to-async-runtime \ // RUN: -async-to-async-runtime \
// RUN: -async-runtime-ref-counting \ // RUN: -async-runtime-ref-counting \
// RUN: -async-runtime-ref-counting-opt \ // RUN: -async-runtime-ref-counting-opt \
// RUN: -convert-async-to-llvm \ // RUN: -convert-async-to-llvm \
// RUN: -convert-scf-to-cf \ // RUN: -convert-scf-to-cf \
// RUN: -arith-expand \ // RUN: -arith-expand \
// RUN: -memref-expand \ // RUN: -memref-expand \
// RUN: -convert-vector-to-llvm \ // RUN: -convert-vector-to-llvm \
// RUN: -convert-memref-to-llvm \ // RUN: -convert-memref-to-llvm \
// RUN: -convert-func-to-llvm \ // RUN: -convert-func-to-llvm \
// RUN: -reconcile-unrealized-casts \ // RUN: -reconcile-unrealized-casts \
// 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_lib_dir/libmlir_runner_utils%shlibext \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext\ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext\
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_async_runtime%shlibext \ // RUN: -shared-libs=%mlir_lib_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-cf \ // RUN: -convert-scf-to-cf \
// RUN: -convert-vector-to-llvm \ // RUN: -convert-vector-to-llvm \
// RUN: -convert-memref-to-llvm \ // RUN: -convert-memref-to-llvm \
// RUN: -convert-func-to-llvm \ // RUN: -convert-func-to-llvm \
// RUN: -reconcile-unrealized-casts \ // RUN: -reconcile-unrealized-casts \
// 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_lib_dir/libmlir_runner_utils%shlibext \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext\ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext\
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_async_runtime%shlibext \ // RUN: -shared-libs=%mlir_lib_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.func @linalg_generic(%lhs: memref<?x?xf32>, func.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

mlir/test/Integration/Dialect/Async/CPU/microbench-scf-async-parallel-for.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -async-parallel-for \ // RUN: -async-parallel-for \
// RUN: -async-to-async-runtime \ // RUN: -async-to-async-runtime \
// RUN: -async-runtime-ref-counting \ // RUN: -async-runtime-ref-counting \
// RUN: -async-runtime-ref-counting-opt \ // RUN: -async-runtime-ref-counting-opt \
// RUN: -convert-async-to-llvm \ // RUN: -convert-async-to-llvm \
// RUN: -convert-linalg-to-loops \ // RUN: -convert-linalg-to-loops \
// RUN: -convert-scf-to-cf \ // RUN: -convert-scf-to-cf \
// RUN: -arith-expand \ // RUN: -arith-expand \
// RUN: -memref-expand \ // RUN: -memref-expand \
// RUN: -convert-vector-to-llvm \ // RUN: -convert-vector-to-llvm \
// RUN: -convert-memref-to-llvm \ // RUN: -convert-memref-to-llvm \
// RUN: -convert-func-to-llvm \ // RUN: -convert-func-to-llvm \
// RUN: -reconcile-unrealized-casts \ // RUN: -reconcile-unrealized-casts \
// 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_lib_dir/libmlir_runner_utils%shlibext \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext\ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext\
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_async_runtime%shlibext \ // RUN: -shared-libs=%mlir_lib_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: -async-parallel-for=async-dispatch=false \ // RUN: -async-parallel-for=async-dispatch=false \
// RUN: -async-to-async-runtime \ // RUN: -async-to-async-runtime \
// RUN: -async-runtime-ref-counting \ // RUN: -async-runtime-ref-counting \
// RUN: -async-runtime-ref-counting-opt \ // RUN: -async-runtime-ref-counting-opt \
// RUN: -convert-async-to-llvm \ // RUN: -convert-async-to-llvm \
// RUN: -convert-linalg-to-loops \ // RUN: -convert-linalg-to-loops \
// RUN: -convert-scf-to-cf \ // RUN: -convert-scf-to-cf \
// RUN: -arith-expand \ // RUN: -arith-expand \
// RUN: -memref-expand \ // RUN: -memref-expand \
// RUN: -convert-vector-to-llvm \ // RUN: -convert-vector-to-llvm \
// RUN: -convert-memref-to-llvm \ // RUN: -convert-memref-to-llvm \
// RUN: -convert-func-to-llvm \ // RUN: -convert-func-to-llvm \
// RUN: -reconcile-unrealized-casts \ // RUN: -reconcile-unrealized-casts \
// 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_lib_dir/libmlir_runner_utils%shlibext \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext\ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext\
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_async_runtime%shlibext \ // RUN: -shared-libs=%mlir_lib_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-cf \ // RUN: -convert-scf-to-cf \
// RUN: -convert-vector-to-llvm \ // RUN: -convert-vector-to-llvm \
// RUN: -convert-memref-to-llvm \ // RUN: -convert-memref-to-llvm \
// RUN: -convert-func-to-llvm \ // RUN: -convert-func-to-llvm \
// RUN: -reconcile-unrealized-casts \ // RUN: -reconcile-unrealized-casts \
// 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_lib_dir/libmlir_runner_utils%shlibext \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext\ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext\
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_async_runtime%shlibext \ // RUN: -shared-libs=%mlir_lib_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.func @scf_parallel(%lhs: memref<?x?xf32>, func.func @scf_parallel(%lhs: memref<?x?xf32>,
%rhs: memref<?x?xf32>, %rhs: memref<?x?xf32>,
%sum: memref<?x?xf32>) { %sum: memref<?x?xf32>) {
%c0 = arith.constant 0 : index %c0 = arith.constant 0 : index
▲ Show 20 Lines • Show All 94 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Async/CPU/test-async-parallel-for-1d.mlir

// RUN: mlir-opt %s -async-parallel-for \ // RUN: mlir-opt %s -async-parallel-for \
// RUN: -async-to-async-runtime \ // RUN: -async-to-async-runtime \
// RUN: -async-runtime-ref-counting \ // RUN: -async-runtime-ref-counting \
// RUN: -async-runtime-ref-counting-opt \ // RUN: -async-runtime-ref-counting-opt \
// RUN: -convert-async-to-llvm \ // RUN: -convert-async-to-llvm \
// RUN: -convert-scf-to-cf \ // RUN: -convert-scf-to-cf \
// RUN: -convert-memref-to-llvm \ // RUN: -convert-memref-to-llvm \
// RUN: -arith-expand \ // RUN: -arith-expand \
// RUN: -memref-expand \ // RUN: -memref-expand \
// RUN: -convert-func-to-llvm \ // RUN: -convert-func-to-llvm \
// RUN: -reconcile-unrealized-casts \ // RUN: -reconcile-unrealized-casts \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void -O0 \ // RUN: -e entry -entry-point-result=void -O0 \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_async_runtime%shlibext\ // RUN: -shared-libs=%mlir_lib_dir/libmlir_async_runtime%shlibext\
// RUN: | FileCheck %s --dump-input=always // RUN: | FileCheck %s --dump-input=always
// RUN: mlir-opt %s -async-parallel-for \ // RUN: mlir-opt %s -async-parallel-for \
// RUN: -async-to-async-runtime \ // RUN: -async-to-async-runtime \
// RUN: -async-runtime-policy-based-ref-counting \ // RUN: -async-runtime-policy-based-ref-counting \
// RUN: -convert-async-to-llvm \ // RUN: -convert-async-to-llvm \
// RUN: -convert-scf-to-cf \ // RUN: -convert-scf-to-cf \
// RUN: -convert-memref-to-llvm \ // RUN: -convert-memref-to-llvm \
// RUN: -arith-expand \ // RUN: -arith-expand \
// RUN: -memref-expand \ // RUN: -memref-expand \
// RUN: -convert-func-to-llvm \ // RUN: -convert-func-to-llvm \
// RUN: -reconcile-unrealized-casts \ // RUN: -reconcile-unrealized-casts \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void -O0 \ // RUN: -e entry -entry-point-result=void -O0 \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_async_runtime%shlibext\ // RUN: -shared-libs=%mlir_lib_dir/libmlir_async_runtime%shlibext\
// RUN: | FileCheck %s --dump-input=always // RUN: | FileCheck %s --dump-input=always
// RUN: mlir-opt %s -async-parallel-for="async-dispatch=false \ // RUN: mlir-opt %s -async-parallel-for="async-dispatch=false \
// RUN: num-workers=20 \ // RUN: num-workers=20 \
// RUN: min-task-size=1" \ // RUN: min-task-size=1" \
// RUN: -async-to-async-runtime \ // RUN: -async-to-async-runtime \
// RUN: -async-runtime-ref-counting \ // RUN: -async-runtime-ref-counting \
// RUN: -async-runtime-ref-counting-opt \ // RUN: -async-runtime-ref-counting-opt \
// RUN: -convert-async-to-llvm \ // RUN: -convert-async-to-llvm \
// RUN: -convert-scf-to-cf \ // RUN: -convert-scf-to-cf \
// RUN: -convert-memref-to-llvm \ // RUN: -convert-memref-to-llvm \
// RUN: -arith-expand \ // RUN: -arith-expand \
// RUN: -memref-expand \ // RUN: -memref-expand \
// RUN: -convert-func-to-llvm \ // RUN: -convert-func-to-llvm \
// RUN: -reconcile-unrealized-casts \ // RUN: -reconcile-unrealized-casts \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void -O0 \ // RUN: -e entry -entry-point-result=void -O0 \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_async_runtime%shlibext\ // RUN: -shared-libs=%mlir_lib_dir/libmlir_async_runtime%shlibext\
// RUN: | FileCheck %s --dump-input=always // RUN: | FileCheck %s --dump-input=always
// Suppress constant folding by introducing "dynamic" zero value at runtime. // Suppress constant folding by introducing "dynamic" zero value at runtime.
func.func private @zero() -> index { func.func private @zero() -> index {
%0 = arith.constant 0 : index %0 = arith.constant 0 : index
return %0 : index return %0 : index
} }
▲ Show 20 Lines • Show All 77 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Async/CPU/test-async-parallel-for-2d.mlir

// RUN: mlir-opt %s -async-parallel-for \ // RUN: mlir-opt %s -async-parallel-for \
// RUN: -async-to-async-runtime \ // RUN: -async-to-async-runtime \
// RUN: -async-runtime-ref-counting \ // RUN: -async-runtime-ref-counting \
// RUN: -async-runtime-ref-counting-opt \ // RUN: -async-runtime-ref-counting-opt \
// RUN: -arith-expand \ // RUN: -arith-expand \
// RUN: -convert-async-to-llvm \ // RUN: -convert-async-to-llvm \
// RUN: -convert-scf-to-cf \ // RUN: -convert-scf-to-cf \
// RUN: -convert-memref-to-llvm \ // RUN: -convert-memref-to-llvm \
// RUN: -convert-func-to-llvm \ // RUN: -convert-func-to-llvm \
// RUN: -reconcile-unrealized-casts \ // RUN: -reconcile-unrealized-casts \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void -O0 \ // RUN: -e entry -entry-point-result=void -O0 \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_async_runtime%shlibext\ // RUN: -shared-libs=%mlir_lib_dir/libmlir_async_runtime%shlibext\
// RUN: | FileCheck %s --dump-input=always // RUN: | FileCheck %s --dump-input=always
// RUN: mlir-opt %s -async-parallel-for \ // RUN: mlir-opt %s -async-parallel-for \
// RUN: -async-to-async-runtime \ // RUN: -async-to-async-runtime \
// RUN: -async-runtime-policy-based-ref-counting \ // RUN: -async-runtime-policy-based-ref-counting \
// RUN: -arith-expand \ // RUN: -arith-expand \
// RUN: -convert-async-to-llvm \ // RUN: -convert-async-to-llvm \
// RUN: -convert-scf-to-cf \ // RUN: -convert-scf-to-cf \
// RUN: -convert-memref-to-llvm \ // RUN: -convert-memref-to-llvm \
// RUN: -convert-func-to-llvm \ // RUN: -convert-func-to-llvm \
// RUN: -reconcile-unrealized-casts \ // RUN: -reconcile-unrealized-casts \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void -O0 \ // RUN: -e entry -entry-point-result=void -O0 \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_async_runtime%shlibext\ // RUN: -shared-libs=%mlir_lib_dir/libmlir_async_runtime%shlibext\
// RUN: | FileCheck %s --dump-input=always // RUN: | FileCheck %s --dump-input=always
// RUN: mlir-opt %s -async-parallel-for="async-dispatch=false \ // RUN: mlir-opt %s -async-parallel-for="async-dispatch=false \
// RUN: num-workers=20 \ // RUN: num-workers=20 \
// RUN: min-task-size=1" \ // RUN: min-task-size=1" \
// RUN: -async-to-async-runtime \ // RUN: -async-to-async-runtime \
// RUN: -async-runtime-ref-counting \ // RUN: -async-runtime-ref-counting \
// RUN: -async-runtime-ref-counting-opt \ // RUN: -async-runtime-ref-counting-opt \
// RUN: -arith-expand \ // RUN: -arith-expand \
// RUN: -convert-async-to-llvm \ // RUN: -convert-async-to-llvm \
// RUN: -convert-scf-to-cf \ // RUN: -convert-scf-to-cf \
// RUN: -convert-memref-to-llvm \ // RUN: -convert-memref-to-llvm \
// RUN: -convert-func-to-llvm \ // RUN: -convert-func-to-llvm \
// RUN: -reconcile-unrealized-casts \ // RUN: -reconcile-unrealized-casts \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void -O0 \ // RUN: -e entry -entry-point-result=void -O0 \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_async_runtime%shlibext\ // RUN: -shared-libs=%mlir_lib_dir/libmlir_async_runtime%shlibext\
// RUN: | FileCheck %s --dump-input=always // RUN: | FileCheck %s --dump-input=always
func.func @entry() { func.func @entry() {
%c0 = arith.constant 0.0 : f32 %c0 = arith.constant 0.0 : f32
%c1 = arith.constant 1 : index %c1 = arith.constant 1 : index
%c2 = arith.constant 2 : index %c2 = arith.constant 2 : index
%c8 = arith.constant 8 : index %c8 = arith.constant 8 : index
▲ Show 20 Lines • Show All 89 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Complex/CPU/correctness.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -func-bufferize -tensor-bufferize -arith-bufferize --canonicalize \ // RUN: -func-bufferize -tensor-bufferize -arith-bufferize --canonicalize \
// RUN: -convert-scf-to-cf --convert-complex-to-standard \ // RUN: -convert-scf-to-cf --convert-complex-to-standard \
// RUN: -convert-memref-to-llvm -convert-math-to-llvm -convert-math-to-libm \ // RUN: -convert-memref-to-llvm -convert-math-to-llvm -convert-math-to-libm \
// RUN: -convert-vector-to-llvm -convert-complex-to-llvm \ // RUN: -convert-vector-to-llvm -convert-complex-to-llvm \
// RUN: -convert-func-to-llvm -reconcile-unrealized-casts |\ // RUN: -convert-func-to-llvm -reconcile-unrealized-casts |\
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext |\ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext |\
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @test_unary(%input: tensor<?xcomplex<f32>>, func.func @test_unary(%input: tensor<?xcomplex<f32>>,
%func: (complex<f32>) -> complex<f32>) { %func: (complex<f32>) -> complex<f32>) {
%c0 = arith.constant 0 : index %c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index %c1 = arith.constant 1 : index
%size = tensor.dim %input, %c0: tensor<?xcomplex<f32>> %size = tensor.dim %input, %c0: tensor<?xcomplex<f32>>
▲ Show 20 Lines • Show All 284 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/LLVMIR/CPU/X86/test-inline-asm-vector.mlir

// RUN: mlir-opt %s -convert-vector-to-llvm | \ // RUN: mlir-opt %s -convert-vector-to-llvm | \
// RUN: mlir-cpu-runner -e entry_point_with_all_constants -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry_point_with_all_constants -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext
module { module {
llvm.func @function_to_run(%a: vector<8xf32>, %b: vector<8xf32>) { llvm.func @function_to_run(%a: vector<8xf32>, %b: vector<8xf32>) {
// CHECK: ( 8, 10, 12, 14, 16, 18, 20, 22 ) // CHECK: ( 8, 10, 12, 14, 16, 18, 20, 22 )
%r0 = llvm.inline_asm asm_dialect = intel %r0 = llvm.inline_asm asm_dialect = intel
"vaddps $0, $1, $2", "=x,x,x" %a, %b: "vaddps $0, $1, $2", "=x,x,x" %a, %b:
(vector<8xf32>, vector<8xf32>) -> vector<8xf32> (vector<8xf32>, vector<8xf32>) -> vector<8xf32>
vector.print %r0: vector<8xf32> vector.print %r0: vector<8xf32>
▲ Show 20 Lines • Show All 45 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/LLVMIR/CPU/X86/test-inline-asm.mlir

// RUN: mlir-cpu-runner %s -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner %s -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
module { module {
llvm.func @printI64(i64) llvm.func @printI64(i64)
llvm.func @entry() { llvm.func @entry() {
%c2 = llvm.mlir.constant(-42: i64) :i64 %c2 = llvm.mlir.constant(-42: i64) :i64
%val = llvm.inline_asm "xor $0, $0", "=r,r" %c2 : %val = llvm.inline_asm "xor $0, $0", "=r,r" %c2 :
(i64) -> i64 (i64) -> i64
// CHECK: 0 // CHECK: 0
llvm.call @printI64(%val) : (i64) -> () llvm.call @printI64(%val) : (i64) -> ()
llvm.return llvm.return
} }
} }

mlir/test/Integration/Dialect/LLVMIR/CPU/test-vector-reductions-fp.mlir

// RUN: mlir-cpu-runner %s -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner %s -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// End-to-end test of all fp reduction intrinsics (not exhaustive unit tests). // End-to-end test of all fp reduction intrinsics (not exhaustive unit tests).
module { module {
llvm.func @printNewline() llvm.func @printNewline()
llvm.func @printF32(f32) llvm.func @printF32(f32)
llvm.func @entry() { llvm.func @entry() {
// Setup (1,2,3,4). // Setup (1,2,3,4).
▲ Show 20 Lines • Show All 78 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/LLVMIR/CPU/test-vector-reductions-int.mlir

// RUN: mlir-cpu-runner %s -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner %s -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// End-to-end test of all int reduction intrinsics (not exhaustive unit tests). // End-to-end test of all int reduction intrinsics (not exhaustive unit tests).
module { module {
llvm.func @printNewline() llvm.func @printNewline()
llvm.func @printI64(i64) llvm.func @printI64(i64)
llvm.func @entry() { llvm.func @entry() {
// Setup (1,2,3,4). // Setup (1,2,3,4).
▲ Show 20 Lines • Show All 72 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Linalg/CPU/matmul-vs-matvec.mlir

// RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -O3 -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -O3 -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func private @printMemrefF32(memref<*xf32>) func.func private @printMemrefF32(memref<*xf32>)
func.func @matmul(%A: memref<?x?xf32>, %B: memref<?x?xf32>) -> (memref<?x?xf32>) { func.func @matmul(%A: memref<?x?xf32>, %B: memref<?x?xf32>) -> (memref<?x?xf32>) {
%c0 = arith.constant 0 : index %c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index %c1 = arith.constant 1 : index
%f0 = arith.constant 0.0 : f32 %f0 = arith.constant 0.0 : f32
▲ Show 20 Lines • Show All 65 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Linalg/CPU/rank-reducing-subview.mlir

// RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -O3 -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -O3 -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func private @printMemrefF32(memref<*xf32>) func.func private @printMemrefF32(memref<*xf32>)
func.func @main() { func.func @main() {
%c0 = arith.constant 0 : index %c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index %c1 = arith.constant 1 : index
%c2 = arith.constant 2 : index %c2 = arith.constant 2 : index
Show All 28 Lines

mlir/test/Integration/Dialect/Linalg/CPU/test-collapse-tensor.mlir

// RUN: mlir-opt %s -linalg-bufferize \ // RUN: mlir-opt %s -linalg-bufferize \
// RUN: -arith-bufferize -tensor-bufferize -func-bufferize \ // RUN: -arith-bufferize -tensor-bufferize -func-bufferize \
// RUN: -finalizing-bufferize -buffer-deallocation -convert-linalg-to-llvm \ // RUN: -finalizing-bufferize -buffer-deallocation -convert-linalg-to-llvm \
// RUN: -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func @main() { func.func @main() {
%const = arith.constant dense<[[[[-3.9058,0.9072],[-2.9470,-2.2055],[18.3946,8.2997]],[[3.4700,5.9006],[-17.2267,4.9777],[1.0450,-0.8201]]],[[[17.6996,-11.1763],[26.7775,-3.8823],[-4.2492,-5.8966]],[[2.1259,13.1794],[-10.7136,0.8428],[16.4233,9.4589]]]]> : tensor<2x2x3x2xf32> %const = arith.constant dense<[[[[-3.9058,0.9072],[-2.9470,-2.2055],[18.3946,8.2997]],[[3.4700,5.9006],[-17.2267,4.9777],[1.0450,-0.8201]]],[[[17.6996,-11.1763],[26.7775,-3.8823],[-4.2492,-5.8966]],[[2.1259,13.1794],[-10.7136,0.8428],[16.4233,9.4589]]]]> : tensor<2x2x3x2xf32>
%dynamic = tensor.cast %const: tensor<2x2x3x2xf32> to tensor<2x?x?x?xf32> %dynamic = tensor.cast %const: tensor<2x2x3x2xf32> to tensor<2x?x?x?xf32>
%collapsed = call @collapse_dynamic_shape(%dynamic) : (tensor<2x?x?x?xf32>) -> (tensor<2x?x?xf32>) %collapsed = call @collapse_dynamic_shape(%dynamic) : (tensor<2x?x?x?xf32>) -> (tensor<2x?x?xf32>)
%unranked = tensor.cast %collapsed: tensor<2x?x?xf32> to tensor<*xf32> %unranked = tensor.cast %collapsed: tensor<2x?x?xf32> to tensor<*xf32>
Show All 24 Lines

mlir/test/Integration/Dialect/Linalg/CPU/test-conv-1d-call.mlir

// RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
// RUN: mlir-opt %s -linalg-tile="tile-sizes=4" -convert-linalg-to-loops -convert-scf-to-cf \ // RUN: mlir-opt %s -linalg-tile="tile-sizes=4" -convert-linalg-to-loops -convert-scf-to-cf \
// RUN: -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func private @printMemrefF32(memref<*xf32>) func.func private @printMemrefF32(memref<*xf32>)
// Creates and returns a 1-D buffer of size %s1 filled with the value %f // Creates and returns a 1-D buffer of size %s1 filled with the value %f
func.func @alloc_1d_filled_f32(%s1 : index, %f : f32) -> memref<?xf32> { func.func @alloc_1d_filled_f32(%s1 : index, %f : f32) -> memref<?xf32> {
%buf = memref.alloc(%s1) : memref<?xf32> %buf = memref.alloc(%s1) : memref<?xf32>
linalg.fill ins(%f : f32) outs(%buf : memref<?xf32>) linalg.fill ins(%f : f32) outs(%buf : memref<?xf32>)
Show All 34 Lines

mlir/test/Integration/Dialect/Linalg/CPU/test-conv-1d-nwc-wcf-call.mlir

// RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,4" -convert-linalg-to-loops -convert-scf-to-cf \ // RUN: mlir-opt %s -linalg-tile="tile-sizes=2,4" -convert-linalg-to-loops -convert-scf-to-cf \
// RUN: -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func private @printMemrefF32(memref<*xf32>) func.func private @printMemrefF32(memref<*xf32>)
// Creates and returns 3-D buffer of size (%s1, %s2, %s3) filled with the value %f // Creates and returns 3-D buffer of size (%s1, %s2, %s3) filled with the value %f
func.func @alloc_3d_filled_f32(%s1 : index, %s2 : index, %s3 : index, %f : f32) -> memref<?x?x?xf32> { func.func @alloc_3d_filled_f32(%s1 : index, %s2 : index, %s3 : index, %f : f32) -> memref<?x?x?xf32> {
%buf = memref.alloc(%s1, %s2, %s3) : memref<?x?x?xf32> %buf = memref.alloc(%s1, %s2, %s3) : memref<?x?x?xf32>
linalg.fill ins(%f : f32) outs(%buf : memref<?x?x?xf32>) linalg.fill ins(%f : f32) outs(%buf : memref<?x?x?xf32>)
▲ Show 20 Lines • Show All 53 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Linalg/CPU/test-conv-2d-call.mlir

// RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,2" -convert-linalg-to-loops -convert-scf-to-cf \ // RUN: mlir-opt %s -linalg-tile="tile-sizes=2,2" -convert-linalg-to-loops -convert-scf-to-cf \
// RUN: -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func private @printMemrefF32(memref<*xf32>) func.func private @printMemrefF32(memref<*xf32>)
// Creates and returns a 2-D buffer of size (%s1, %s2) filled with the value %f // Creates and returns a 2-D buffer of size (%s1, %s2) filled with the value %f
func.func @alloc_2d_filled_f32(%s1 : index, %s2 : index, %f : f32) -> memref<?x?xf32> { func.func @alloc_2d_filled_f32(%s1 : index, %s2 : index, %f : f32) -> memref<?x?xf32> {
%buf = memref.alloc(%s1, %s2) : memref<?x?xf32> %buf = memref.alloc(%s1, %s2) : memref<?x?xf32>
linalg.fill ins(%f : f32) outs(%buf : memref<?x?xf32>) linalg.fill ins(%f : f32) outs(%buf : memref<?x?xf32>)
Show All 39 Lines

mlir/test/Integration/Dialect/Linalg/CPU/test-conv-2d-nhwc-hwcf-call.mlir

// RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,3,3,2" -convert-linalg-to-loops -convert-scf-to-cf \ // RUN: mlir-opt %s -linalg-tile="tile-sizes=2,3,3,2" -convert-linalg-to-loops -convert-scf-to-cf \
// RUN: -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func private @printMemrefF32(memref<*xf32>) func.func private @printMemrefF32(memref<*xf32>)
// Creates and returns 4-D buffer of size (%s1, %s2, %s3, %s4) filled with the value %f // Creates and returns 4-D buffer of size (%s1, %s2, %s3, %s4) filled with the value %f
func.func @alloc_4d_filled_f32(%s1 : index, %s2 : index, %s3 : index, %s4 : index, %f : f32) -> memref<?x?x?x?xf32> { func.func @alloc_4d_filled_f32(%s1 : index, %s2 : index, %s3 : index, %s4 : index, %f : f32) -> memref<?x?x?x?xf32> {
%buf = memref.alloc(%s1, %s2, %s3, %s4) : memref<?x?x?x?xf32> %buf = memref.alloc(%s1, %s2, %s3, %s4) : memref<?x?x?x?xf32>
linalg.fill ins(%f : f32) outs(%buf : memref<?x?x?x?xf32>) linalg.fill ins(%f : f32) outs(%buf : memref<?x?x?x?xf32>)
▲ Show 20 Lines • Show All 101 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Linalg/CPU/test-conv-3d-call.mlir

// RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,2,2" -convert-linalg-to-loops -convert-scf-to-cf \ // RUN: mlir-opt %s -linalg-tile="tile-sizes=2,2,2" -convert-linalg-to-loops -convert-scf-to-cf \
// RUN: -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func private @printMemrefF32(memref<*xf32>) func.func private @printMemrefF32(memref<*xf32>)
// Creates and returns 3-D buffer of size (%s1, %s2, %s3) filled with the value %f // Creates and returns 3-D buffer of size (%s1, %s2, %s3) filled with the value %f
func.func @alloc_3d_filled_f32(%s1 : index, %s2 : index, %s3 : index, %f : f32) -> memref<?x?x?xf32> { func.func @alloc_3d_filled_f32(%s1 : index, %s2 : index, %s3 : index, %f : f32) -> memref<?x?x?xf32> {
%buf = memref.alloc(%s1, %s2, %s3) : memref<?x?x?xf32> %buf = memref.alloc(%s1, %s2, %s3) : memref<?x?x?xf32>
linalg.fill ins(%f : f32) outs(%buf : memref<?x?x?xf32>) linalg.fill ins(%f : f32) outs(%buf : memref<?x?x?xf32>)
▲ Show 20 Lines • Show All 56 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Linalg/CPU/test-conv-3d-ndhwc-dhwcf-call.mlir

// RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
// RUN: mlir-opt %s -linalg-tile="tile-sizes=0,5,5,5" -convert-linalg-to-loops -convert-scf-to-cf \ // RUN: mlir-opt %s -linalg-tile="tile-sizes=0,5,5,5" -convert-linalg-to-loops -convert-scf-to-cf \
// RUN: -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func private @printMemrefF32(memref<*xf32>) func.func private @printMemrefF32(memref<*xf32>)
// Creates and returns 5-D buffer of size (%s1, %s2, %s3, %s4, %s5) filled with the value %f // Creates and returns 5-D buffer of size (%s1, %s2, %s3, %s4, %s5) filled with the value %f
func.func @alloc_5d_filled_f32(%s1 : index, %s2 : index, %s3 : index, %s4 : index, %s5 : index, %f : f32) -> memref<?x?x?x?x?xf32> { func.func @alloc_5d_filled_f32(%s1 : index, %s2 : index, %s3 : index, %s4 : index, %s5 : index, %f : f32) -> memref<?x?x?x?x?xf32> {
%buf = memref.alloc(%s1, %s2, %s3, %s4, %s5) : memref<?x?x?x?x?xf32> %buf = memref.alloc(%s1, %s2, %s3, %s4, %s5) : memref<?x?x?x?x?xf32>
linalg.fill ins(%f : f32) outs(%buf : memref<?x?x?x?x?xf32>) linalg.fill ins(%f : f32) outs(%buf : memref<?x?x?x?x?xf32>)
▲ Show 20 Lines • Show All 164 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Linalg/CPU/test-elementwise.mlir

// RUN: mlir-opt %s -convert-elementwise-to-linalg \ // RUN: mlir-opt %s -convert-elementwise-to-linalg \
// RUN: -arith-bufferize -linalg-bufferize -tensor-bufferize \ // RUN: -arith-bufferize -linalg-bufferize -tensor-bufferize \
// RUN: -func-bufferize -buffer-deallocation -convert-linalg-to-loops \ // RUN: -func-bufferize -buffer-deallocation -convert-linalg-to-loops \
// RUN: -convert-linalg-to-llvm --convert-memref-to-llvm -convert-func-to-llvm \ // RUN: -convert-linalg-to-llvm --convert-memref-to-llvm -convert-func-to-llvm \
// RUN: -reconcile-unrealized-casts | \ // RUN: -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func @main() { func.func @main() {
%a = arith.constant dense<[1.0, 2.0, 3.0]> : tensor<3xf32> %a = arith.constant dense<[1.0, 2.0, 3.0]> : tensor<3xf32>
%b = arith.constant dense<[10.0, 20.0, 30.0]> : tensor<3xf32> %b = arith.constant dense<[10.0, 20.0, 30.0]> : tensor<3xf32>
%addf = arith.addf %a, %b : tensor<3xf32> %addf = arith.addf %a, %b : tensor<3xf32>
%addf_unranked = tensor.cast %addf : tensor<3xf32> to tensor<*xf32> %addf_unranked = tensor.cast %addf : tensor<3xf32> to tensor<*xf32>
call @printMemrefF32(%addf_unranked) : (tensor<*xf32>) -> () call @printMemrefF32(%addf_unranked) : (tensor<*xf32>) -> ()
// CHECK: Unranked Memref base@ = {{.*}} rank = 1 offset = 0 sizes = [3] strides = [1] data = // CHECK: Unranked Memref base@ = {{.*}} rank = 1 offset = 0 sizes = [3] strides = [1] data =
// CHECK-NEXT: [11, 22, 33] // CHECK-NEXT: [11, 22, 33]
return return
} }
func.func private @printMemrefF32(%ptr : tensor<*xf32>) func.func private @printMemrefF32(%ptr : tensor<*xf32>)

mlir/test/Integration/Dialect/Linalg/CPU/test-expand-tensor.mlir

// RUN: mlir-opt %s -linalg-bufferize \ // RUN: mlir-opt %s -linalg-bufferize \
// RUN: -arith-bufferize -tensor-bufferize -func-bufferize \ // RUN: -arith-bufferize -tensor-bufferize -func-bufferize \
// RUN: -finalizing-bufferize -buffer-deallocation -convert-linalg-to-llvm \ // RUN: -finalizing-bufferize -buffer-deallocation -convert-linalg-to-llvm \
// RUN: -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func @main() { func.func @main() {
%const = arith.constant dense<[[[-3.9058,0.9072],[-2.9470,-2.2055],[18.3946,8.2997],[3.4700,5.9006],[-17.2267,4.9777],[1.0450,-0.8201]],[[17.6996,-11.1763],[26.7775,-3.8823],[-4.2492,-5.8966],[2.1259,13.1794],[-10.7136,0.8428],[16.4233,9.4589]]]> : tensor<2x6x2xf32> %const = arith.constant dense<[[[-3.9058,0.9072],[-2.9470,-2.2055],[18.3946,8.2997],[3.4700,5.9006],[-17.2267,4.9777],[1.0450,-0.8201]],[[17.6996,-11.1763],[26.7775,-3.8823],[-4.2492,-5.8966],[2.1259,13.1794],[-10.7136,0.8428],[16.4233,9.4589]]]> : tensor<2x6x2xf32>
%dynamic = tensor.cast %const: tensor<2x6x2xf32> to tensor<2x?x?xf32> %dynamic = tensor.cast %const: tensor<2x6x2xf32> to tensor<2x?x?xf32>
%expanded = call @expand_dynamic_shape(%dynamic) : (tensor<2x?x?xf32>) -> (tensor<2x2x?x1x?xf32>) %expanded = call @expand_dynamic_shape(%dynamic) : (tensor<2x?x?xf32>) -> (tensor<2x2x?x1x?xf32>)
%unranked = tensor.cast %expanded: tensor<2x2x?x1x?xf32> to tensor<*xf32> %unranked = tensor.cast %expanded: tensor<2x2x?x1x?xf32> to tensor<*xf32>
Show All 25 Lines

mlir/test/Integration/Dialect/Linalg/CPU/test-one-shot-bufferize.mlir

// RUN: mlir-opt %s -pass-pipeline="func.func(canonicalize,cse),one-shot-bufferize{bufferize-function-boundaries}" |\ // RUN: mlir-opt %s -pass-pipeline="func.func(canonicalize,cse),one-shot-bufferize{bufferize-function-boundaries}" |\
// RUN: mlir-opt -pass-pipeline="func.func(buffer-deallocation,convert-vector-to-scf,lower-affine,convert-linalg-to-loops)" |\ // RUN: mlir-opt -pass-pipeline="func.func(buffer-deallocation,convert-vector-to-scf,lower-affine,convert-linalg-to-loops)" |\
// RUN: mlir-opt -pass-pipeline="func.func(canonicalize,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt -pass-pipeline="func.func(canonicalize,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -O3 -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -O3 -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext,%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext |\ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext,%mlir_lib_dir/libmlir_c_runner_utils%shlibext |\
// RUN: FileCheck %s // RUN: FileCheck %s
#map0 = affine_map<(d0, d1)[s0] -> ((d1 - d0) ceildiv s0)> #map0 = affine_map<(d0, d1)[s0] -> ((d1 - d0) ceildiv s0)>
#map1 = affine_map<(d0, d1)[s0] -> ((d0 - d1) ceildiv s0)> #map1 = affine_map<(d0, d1)[s0] -> ((d0 - d1) ceildiv s0)>
func.func @init_and_dot(%arg0: tensor<64xf32>, %arg1: tensor<64xf32>, %arg2: tensor<f32>) -> tensor<f32> { func.func @init_and_dot(%arg0: tensor<64xf32>, %arg1: tensor<64xf32>, %arg2: tensor<f32>) -> tensor<f32> {
%c64 = arith.constant 64 : index %c64 = arith.constant 64 : index
%cst = arith.constant 0.000000e+00 : f32 %cst = arith.constant 0.000000e+00 : f32
▲ Show 20 Lines • Show All 88 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Linalg/CPU/test-padtensor.mlir

// RUN: mlir-opt %s -test-linalg-transform-patterns=test-linalg-to-vector-patterns \ // RUN: mlir-opt %s -test-linalg-transform-patterns=test-linalg-to-vector-patterns \
// RUN: -linalg-init-tensor-to-alloc-tensor -linalg-bufferize -arith-bufferize \ // RUN: -linalg-init-tensor-to-alloc-tensor -linalg-bufferize -arith-bufferize \
// RUN: -bufferization-bufferize -tensor-bufferize -func-bufferize \ // RUN: -bufferization-bufferize -tensor-bufferize -func-bufferize \
// RUN: -finalizing-bufferize -buffer-deallocation \ // RUN: -finalizing-bufferize -buffer-deallocation \
// RUN: -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext,%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext,%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func @main() { func.func @main() {
%const = arith.constant dense<[[[1.0, 2.0, 3.0], [2.0, 3.0, 4.0]]]> : tensor<1x2x3xf32> %const = arith.constant dense<[[[1.0, 2.0, 3.0], [2.0, 3.0, 4.0]]]> : tensor<1x2x3xf32>
%dynamic = tensor.cast %const: tensor<1x2x3xf32> to tensor<1x?x3xf32> %dynamic = tensor.cast %const: tensor<1x2x3xf32> to tensor<1x?x3xf32>
%offset = arith.constant 2 : index %offset = arith.constant 2 : index
%cst = arith.constant 2.3 : f32 %cst = arith.constant 2.3 : f32
Show All 19 Lines

mlir/test/Integration/Dialect/Linalg/CPU/test-subtensor-insert-multiple-uses.mlir

// RUN: mlir-opt %s -linalg-bufferize \ // RUN: mlir-opt %s -linalg-bufferize \
// RUN: -arith-bufferize -tensor-bufferize -func-bufferize \ // RUN: -arith-bufferize -tensor-bufferize -func-bufferize \
// RUN: -finalizing-bufferize -buffer-deallocation \ // RUN: -finalizing-bufferize -buffer-deallocation \
// RUN: -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext,%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext,%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func @main() { func.func @main() {
%const = arith.constant dense<10.0> : tensor<2xf32> %const = arith.constant dense<10.0> : tensor<2xf32>
%insert_val = arith.constant dense<20.0> : tensor<1xf32> %insert_val = arith.constant dense<20.0> : tensor<1xf32>
// Both of these insert_slice ops insert into the same original tensor // Both of these insert_slice ops insert into the same original tensor
// value `%const`. This can easily cause bugs if at the memref level // value `%const`. This can easily cause bugs if at the memref level
Show All 23 Lines

mlir/test/Integration/Dialect/Linalg/CPU/test-subtensor-insert.mlir

// RUN: mlir-opt %s -linalg-bufferize \ // RUN: mlir-opt %s -linalg-bufferize \
// RUN: -arith-bufferize -tensor-bufferize -func-bufferize \ // RUN: -arith-bufferize -tensor-bufferize -func-bufferize \
// RUN: -finalizing-bufferize -buffer-deallocation \ // RUN: -finalizing-bufferize -buffer-deallocation \
// RUN: -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: -convert-linalg-to-loops -convert-scf-to-cf -convert-linalg-to-llvm --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func @main() { func.func @main() {
%const = arith.constant dense<10.0> : tensor<2xf32> %const = arith.constant dense<10.0> : tensor<2xf32>
%insert_val = arith.constant dense<20.0> : tensor<1xf32> %insert_val = arith.constant dense<20.0> : tensor<1xf32>
%inserted = tensor.insert_slice %insert_val into %const[0][1][1] : tensor<1xf32> into tensor<2xf32> %inserted = tensor.insert_slice %insert_val into %const[0][1][1] : tensor<1xf32> into tensor<2xf32>
%unranked = tensor.cast %inserted : tensor<2xf32> to tensor<*xf32> %unranked = tensor.cast %inserted : tensor<2xf32> to tensor<*xf32>
Show All 10 Lines

mlir/test/Integration/Dialect/Linalg/CPU/test-tensor-e2e.mlir

// RUN: mlir-opt %s -arith-bufferize -linalg-bufferize \ // RUN: mlir-opt %s -arith-bufferize -linalg-bufferize \
// RUN: -tensor-bufferize -func-bufferize -finalizing-bufferize -buffer-deallocation -convert-linalg-to-loops \ // RUN: -tensor-bufferize -func-bufferize -finalizing-bufferize -buffer-deallocation -convert-linalg-to-loops \
// RUN: -convert-linalg-to-llvm --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: -convert-linalg-to-llvm --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func @foo() -> tensor<4xf32> { func.func @foo() -> tensor<4xf32> {
%0 = arith.constant dense<[1.0, 2.0, 3.0, 4.0]> : tensor<4xf32> %0 = arith.constant dense<[1.0, 2.0, 3.0, 4.0]> : tensor<4xf32>
return %0 : tensor<4xf32> return %0 : tensor<4xf32>
} }
func.func @main() { func.func @main() {
Show All 23 Lines

mlir/test/Integration/Dialect/Linalg/CPU/test-tensor-matmul.mlir

// UNSUPPORTED: asan // UNSUPPORTED: asan
// RUN: mlir-opt %s -linalg-bufferize -arith-bufferize \ // RUN: mlir-opt %s -linalg-bufferize -arith-bufferize \
// RUN: -tensor-bufferize -func-bufferize -finalizing-bufferize -buffer-deallocation -convert-linalg-to-loops -convert-scf-to-cf \ // RUN: -tensor-bufferize -func-bufferize -finalizing-bufferize -buffer-deallocation -convert-linalg-to-loops -convert-scf-to-cf \
// RUN: -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext,%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext,%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
// RUN: mlir-opt %s -linalg-tile="tile-sizes=1,2,3" -linalg-bufferize \ // RUN: mlir-opt %s -linalg-tile="tile-sizes=1,2,3" -linalg-bufferize \
// RUN: -scf-bufferize -arith-bufferize -tensor-bufferize \ // RUN: -scf-bufferize -arith-bufferize -tensor-bufferize \
// RUN: -func-bufferize \ // RUN: -func-bufferize \
// RUN: -finalizing-bufferize -convert-linalg-to-loops -convert-scf-to-cf -convert-scf-to-cf \ // RUN: -finalizing-bufferize -convert-linalg-to-loops -convert-scf-to-cf -convert-scf-to-cf \
// RUN: -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: -convert-linalg-to-llvm -lower-affine -convert-scf-to-cf --convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext,%mlir_integration_test_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext,%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func @main() { func.func @main() {
%A = arith.constant dense<[[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]]> : tensor<2x3xf32> %A = arith.constant dense<[[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]]> : tensor<2x3xf32>
%B = arith.constant dense<[[1.0, 2.0, 3.0, 4.0], %B = arith.constant dense<[[1.0, 2.0, 3.0, 4.0],
[5.0, 6.0, 7.0, 8.0], [5.0, 6.0, 7.0, 8.0],
[9.0, 10.0, 11.0, 12.0]]> : tensor<3x4xf32> [9.0, 10.0, 11.0, 12.0]]> : tensor<3x4xf32>
%C = arith.constant dense<1000.0> : tensor<2x4xf32> %C = arith.constant dense<1000.0> : tensor<2x4xf32>
Show All 16 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/concatenate.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#MAT_C_C = #sparse_tensor.encoding<{dimLevelType = ["compressed", "compressed"]}> #MAT_C_C = #sparse_tensor.encoding<{dimLevelType = ["compressed", "compressed"]}>
#MAT_D_C = #sparse_tensor.encoding<{dimLevelType = ["dense", "compressed"]}> #MAT_D_C = #sparse_tensor.encoding<{dimLevelType = ["dense", "compressed"]}>
#MAT_C_D = #sparse_tensor.encoding<{dimLevelType = ["compressed", "dense"]}> #MAT_C_D = #sparse_tensor.encoding<{dimLevelType = ["compressed", "dense"]}>
#MAT_C_C_P = #sparse_tensor.encoding<{ #MAT_C_C_P = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed" ], dimLevelType = [ "compressed", "compressed" ],
▲ Show 20 Lines • Show All 411 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: TENSOR0="%mlir_integration_test_dir/data/test.mtx" \ // RUN: TENSOR0="%mlir_src_dir/test/Integration/data/test.mtx" \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
!Filename = !llvm.ptr<i8> !Filename = !llvm.ptr<i8>
#DenseMatrix = #sparse_tensor.encoding<{ #DenseMatrix = #sparse_tensor.encoding<{
dimLevelType = [ "dense", "dense" ], dimLevelType = [ "dense", "dense" ],
dimOrdering = affine_map<(i,j) -> (i,j)> dimOrdering = affine_map<(i,j) -> (i,j)>
}> }>
▲ Show 20 Lines • Show All 83 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output_bf16.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}> #SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}>
#DenseVector = #sparse_tensor.encoding<{dimLevelType = ["dense"]}> #DenseVector = #sparse_tensor.encoding<{dimLevelType = ["dense"]}>
#trait_vec_op = { #trait_vec_op = {
indexing_maps = [ indexing_maps = [
affine_map<(i) -> (i)>, // a (in) affine_map<(i) -> (i)>, // a (in)
▲ Show 20 Lines • Show All 78 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output_f16.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}> #SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}>
#DenseVector = #sparse_tensor.encoding<{dimLevelType = ["dense"]}> #DenseVector = #sparse_tensor.encoding<{dimLevelType = ["dense"]}>
#trait_vec_op = { #trait_vec_op = {
indexing_maps = [ indexing_maps = [
affine_map<(i) -> (i)>, // a (in) affine_map<(i) -> (i)>, // a (in)
▲ Show 20 Lines • Show All 78 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_abs.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SparseVector = #sparse_tensor.encoding<{ dimLevelType = [ "compressed" ] }> #SparseVector = #sparse_tensor.encoding<{ dimLevelType = [ "compressed" ] }>
#trait_op = { #trait_op = {
indexing_maps = [ indexing_maps = [
affine_map<(i) -> (i)>, // a affine_map<(i) -> (i)>, // a
affine_map<(i) -> (i)> // x (out) affine_map<(i) -> (i)> // x (out)
▲ Show 20 Lines • Show All 98 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_binary.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}> #SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}>
#DCSR = #sparse_tensor.encoding<{dimLevelType = ["compressed", "compressed"]}> #DCSR = #sparse_tensor.encoding<{dimLevelType = ["compressed", "compressed"]}>
// //
// Traits for tensor operations. // Traits for tensor operations.
// //
▲ Show 20 Lines • Show All 547 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_cast.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// //
// Do the same run, but now with SIMDization as well. This should not change the outcome. // Do the same run, but now with SIMDization as well. This should not change the outcome.
// //
// RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=2" | \ // RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=2" | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SV = #sparse_tensor.encoding<{ dimLevelType = [ "compressed" ] }> #SV = #sparse_tensor.encoding<{ dimLevelType = [ "compressed" ] }>
#trait_cast = { #trait_cast = {
indexing_maps = [ indexing_maps = [
affine_map<(i) -> (i)>, // A (in) affine_map<(i) -> (i)>, // A (in)
affine_map<(i) -> (i)> // X (out) affine_map<(i) -> (i)> // X (out)
▲ Show 20 Lines • Show All 247 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_complex32.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}> #SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}>
#trait_op = { #trait_op = {
indexing_maps = [ indexing_maps = [
affine_map<(i) -> (i)>, // a (in) affine_map<(i) -> (i)>, // a (in)
affine_map<(i) -> (i)>, // b (in) affine_map<(i) -> (i)>, // b (in)
▲ Show 20 Lines • Show All 104 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_complex64.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}> #SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}>
#trait_op = { #trait_op = {
indexing_maps = [ indexing_maps = [
affine_map<(i) -> (i)>, // a (in) affine_map<(i) -> (i)>, // a (in)
affine_map<(i) -> (i)>, // b (in) affine_map<(i) -> (i)>, // b (in)
▲ Show 20 Lines • Show All 104 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_complex_ops.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}> #SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}>
#trait_op1 = { #trait_op1 = {
indexing_maps = [ indexing_maps = [
affine_map<(i) -> (i)>, // a (in) affine_map<(i) -> (i)>, // a (in)
affine_map<(i) -> (i)> // x (out) affine_map<(i) -> (i)> // x (out)
▲ Show 20 Lines • Show All 243 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_constant_to_sparse_tensor.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#Tensor1 = #sparse_tensor.encoding<{ #Tensor1 = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed"] dimLevelType = [ "compressed", "compressed"]
}> }>
// //
// Integration tests for conversions from sparse constants to sparse tensors. // Integration tests for conversions from sparse constants to sparse tensors.
Show All 37 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_conversion.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#Tensor1 = #sparse_tensor.encoding<{ #Tensor1 = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed", "compressed" ], dimLevelType = [ "compressed", "compressed", "compressed" ],
dimOrdering = affine_map<(i,j,k) -> (i,j,k)> dimOrdering = affine_map<(i,j,k) -> (i,j,k)>
}> }>
#Tensor2 = #sparse_tensor.encoding<{ #Tensor2 = #sparse_tensor.encoding<{
▲ Show 20 Lines • Show All 252 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_conversion_dyn.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#DCSR = #sparse_tensor.encoding<{ #DCSR = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed" ] dimLevelType = [ "compressed", "compressed" ]
}> }>
#DCSC = #sparse_tensor.encoding<{ #DCSC = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed" ], dimLevelType = [ "compressed", "compressed" ],
▲ Show 20 Lines • Show All 72 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_conversion_ptr.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#DCSR = #sparse_tensor.encoding<{ #DCSR = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed" ], dimLevelType = [ "compressed", "compressed" ],
pointerBitWidth = 8, pointerBitWidth = 8,
indexBitWidth = 8 indexBitWidth = 8
}> }>
▲ Show 20 Lines • Show All 128 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_conversion_sparse2dense.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
// RUN: | \ // RUN: | \
// RUN: FileCheck %s // RUN: FileCheck %s
#Tensor1 = #sparse_tensor.encoding<{ #Tensor1 = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed", "compressed" ], dimLevelType = [ "compressed", "compressed", "compressed" ],
dimOrdering = affine_map<(i,j,k) -> (i,j,k)> dimOrdering = affine_map<(i,j,k) -> (i,j,k)>
}> }>
▲ Show 20 Lines • Show All 209 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_conversion_sparse2sparse.mlir

// Force this file to use the kDirect method for sparse2sparse. // Force this file to use the kDirect method for sparse2sparse.
// RUN: mlir-opt %s --sparse-compiler="s2s-strategy=2" | \ // RUN: mlir-opt %s --sparse-compiler="s2s-strategy=2" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#Tensor1 = #sparse_tensor.encoding<{ #Tensor1 = #sparse_tensor.encoding<{
dimLevelType = [ "dense", "dense", "compressed" ] dimLevelType = [ "dense", "dense", "compressed" ]
}> }>
// NOTE: dense after compressed is not currently supported for the target // NOTE: dense after compressed is not currently supported for the target
// of direct-sparse2sparse conversion. (It's fine for the source though.) // of direct-sparse2sparse conversion. (It's fine for the source though.)
▲ Show 20 Lines • Show All 88 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_dot.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SparseVector = #sparse_tensor.encoding<{ dimLevelType = [ "compressed" ] }> #SparseVector = #sparse_tensor.encoding<{ dimLevelType = [ "compressed" ] }>
module { module {
// //
// Sparse kernel. // Sparse kernel.
▲ Show 20 Lines • Show All 44 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_filter_conv2d.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// //
// Do the same run, but now with SIMDization as well. This should not change the outcome. // Do the same run, but now with SIMDization as well. This should not change the outcome.
// //
// RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=2" | \ // RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=2" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#DCSR = #sparse_tensor.encoding<{ dimLevelType = [ "compressed", "compressed" ] }> #DCSR = #sparse_tensor.encoding<{ dimLevelType = [ "compressed", "compressed" ] }>
// An example of a 2D convolution with a sparse filter. // An example of a 2D convolution with a sparse filter.
module { module {
func.func @conv2d(%input: tensor<8x8xi32>, func.func @conv2d(%input: tensor<8x8xi32>,
▲ Show 20 Lines • Show All 57 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_flatten.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: TENSOR0="%mlir_integration_test_dir/data/test.tns" \ // RUN: TENSOR0="%mlir_src_dir/test/Integration/data/test.tns" \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// //
// Do the same run, but now with SIMDization as well. This should not change the outcome. // Do the same run, but now with SIMDization as well. This should not change the outcome.
// //
// RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=4" | \ // RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=4" | \
// RUN: TENSOR0="%mlir_integration_test_dir/data/test.tns" \ // RUN: TENSOR0="%mlir_src_dir/test/Integration/data/test.tns" \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
!Filename = !llvm.ptr<i8> !Filename = !llvm.ptr<i8>
#SparseTensor = #sparse_tensor.encoding<{ #SparseTensor = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed", "compressed", "compressed", dimLevelType = [ "compressed", "compressed", "compressed", "compressed",
"compressed", "compressed", "compressed", "compressed" ], "compressed", "compressed", "compressed", "compressed" ],
// Note that any dimOrdering permutation should give the same results // Note that any dimOrdering permutation should give the same results
▲ Show 20 Lines • Show All 81 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_index.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SparseVector = #sparse_tensor.encoding<{ #SparseVector = #sparse_tensor.encoding<{
dimLevelType = ["compressed"] dimLevelType = ["compressed"]
}> }>
#SparseMatrix = #sparse_tensor.encoding<{ #SparseMatrix = #sparse_tensor.encoding<{
dimLevelType = ["compressed", "compressed"] dimLevelType = ["compressed", "compressed"]
▲ Show 20 Lines • Show All 235 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_index_dense.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// //
// Do the same run, but now with SIMDization as well. This should not change the outcome. // Do the same run, but now with SIMDization as well. This should not change the outcome.
// //
// RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=4" | \ // RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=4" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SparseVector = #sparse_tensor.encoding<{ #SparseVector = #sparse_tensor.encoding<{
dimLevelType = ["compressed"] dimLevelType = ["compressed"]
}> }>
#SparseMatrix = #sparse_tensor.encoding<{ #SparseMatrix = #sparse_tensor.encoding<{
dimLevelType = ["compressed", "compressed"] dimLevelType = ["compressed", "compressed"]
▲ Show 20 Lines • Show All 176 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_matmul.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#CSR = #sparse_tensor.encoding<{ #CSR = #sparse_tensor.encoding<{
dimLevelType = [ "dense", "compressed" ], dimLevelType = [ "dense", "compressed" ],
dimOrdering = affine_map<(i,j) -> (i,j)> dimOrdering = affine_map<(i,j) -> (i,j)>
}> }>
#DCSR = #sparse_tensor.encoding<{ #DCSR = #sparse_tensor.encoding<{
▲ Show 20 Lines • Show All 233 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_matrix_ops.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#DCSR = #sparse_tensor.encoding<{dimLevelType = ["compressed", "compressed"]}> #DCSR = #sparse_tensor.encoding<{dimLevelType = ["compressed", "compressed"]}>
// //
// Traits for 2-d tensor (aka matrix) operations. // Traits for 2-d tensor (aka matrix) operations.
// //
#trait_scale = { #trait_scale = {
▲ Show 20 Lines • Show All 157 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_matvec.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: TENSOR0="%mlir_integration_test_dir/data/wide.mtx" \ // RUN: TENSOR0="%mlir_src_dir/test/Integration/data/wide.mtx" \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// //
// Do the same run, but now with SIMDization as well. This should not change the outcome. // Do the same run, but now with SIMDization as well. This should not change the outcome.
// //
// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=16 enable-simd-index32" | \ // RUN: --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=16 enable-simd-index32" | \
// RUN: TENSOR0="%mlir_integration_test_dir/data/wide.mtx" \ // RUN: TENSOR0="%mlir_src_dir/test/Integration/data/wide.mtx" \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
!Filename = !llvm.ptr<i8> !Filename = !llvm.ptr<i8>
#SparseMatrix = #sparse_tensor.encoding<{ #SparseMatrix = #sparse_tensor.encoding<{
dimLevelType = [ "dense", "compressed" ], dimLevelType = [ "dense", "compressed" ],
pointerBitWidth = 8, pointerBitWidth = 8,
indexBitWidth = 8 indexBitWidth = 8
▲ Show 20 Lines • Show All 83 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_mttkrp.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: TENSOR0="%mlir_integration_test_dir/data/mttkrp_b.tns" \ // RUN: TENSOR0="%mlir_src_dir/test/Integration/data/mttkrp_b.tns" \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// //
// Do the same run, but now with SIMDization as well. This should not change the outcome. // Do the same run, but now with SIMDization as well. This should not change the outcome.
// //
// RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=4" | \ // RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=4" | \
// RUN: TENSOR0="%mlir_integration_test_dir/data/mttkrp_b.tns" \ // RUN: TENSOR0="%mlir_src_dir/test/Integration/data/mttkrp_b.tns" \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
!Filename = !llvm.ptr<i8> !Filename = !llvm.ptr<i8>
#SparseTensor = #sparse_tensor.encoding<{ #SparseTensor = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed", "compressed" ] dimLevelType = [ "compressed", "compressed", "compressed" ]
}> }>
▲ Show 20 Lines • Show All 107 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_out_mult_elt.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#DCSR = #sparse_tensor.encoding<{ #DCSR = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed" ] dimLevelType = [ "compressed", "compressed" ]
}> }>
#trait_mult_elt = { #trait_mult_elt = {
indexing_maps = [ indexing_maps = [
▲ Show 20 Lines • Show All 61 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_out_reduction.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SparseMatrix = #sparse_tensor.encoding<{ #SparseMatrix = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed" ] dimLevelType = [ "compressed", "compressed" ]
}> }>
#SparseTensor = #sparse_tensor.encoding<{ #SparseTensor = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed", "compressed" ] dimLevelType = [ "compressed", "compressed", "compressed" ]
▲ Show 20 Lines • Show All 77 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_out_simple.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: TENSOR0="%mlir_integration_test_dir/data/test.mtx" \ // RUN: TENSOR0="%mlir_src_dir/test/Integration/data/test.mtx" \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// //
// Do the same run, but now with SIMDization as well. This should not change the outcome. // Do the same run, but now with SIMDization as well. This should not change the outcome.
// //
// RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=4" | \ // RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=4" | \
// RUN: TENSOR0="%mlir_integration_test_dir/data/test.mtx" \ // RUN: TENSOR0="%mlir_src_dir/test/Integration/data/test.mtx" \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
!Filename = !llvm.ptr<i8> !Filename = !llvm.ptr<i8>
#DCSR = #sparse_tensor.encoding<{ #DCSR = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed" ], dimLevelType = [ "compressed", "compressed" ],
dimOrdering = affine_map<(i,j) -> (i,j)> dimOrdering = affine_map<(i,j) -> (i,j)>
}> }>
▲ Show 20 Lines • Show All 62 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_quantized_matmul.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// //
// Do the same run, but now with SIMDization as well. This should not change the outcome. // Do the same run, but now with SIMDization as well. This should not change the outcome.
// //
// RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=2" | \ // RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=2" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#DCSR = #sparse_tensor.encoding<{ dimLevelType = [ "compressed", "compressed" ] }> #DCSR = #sparse_tensor.encoding<{ dimLevelType = [ "compressed", "compressed" ] }>
// An example of a quantized sparse matmul. With the zero offset for the // An example of a quantized sparse matmul. With the zero offset for the
// sparse input, the sparse compiler generates very efficient code for the // sparse input, the sparse compiler generates very efficient code for the
// x(i,j) += (ext(a(i,k)) - 2) * ext(b(k,j)) // x(i,j) += (ext(a(i,k)) - 2) * ext(b(k,j))
// operation. // operation.
▲ Show 20 Lines • Show All 59 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_re_im.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}> #SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}>
#trait_op = { #trait_op = {
indexing_maps = [ indexing_maps = [
affine_map<(i) -> (i)>, // a (in) affine_map<(i) -> (i)>, // a (in)
affine_map<(i) -> (i)> // x (out) affine_map<(i) -> (i)> // x (out)
▲ Show 20 Lines • Show All 81 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_reduce_custom.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}> #SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}>
#CSR = #sparse_tensor.encoding<{dimLevelType = ["dense", "compressed"]}> #CSR = #sparse_tensor.encoding<{dimLevelType = ["dense", "compressed"]}>
#CSC = #sparse_tensor.encoding<{ #CSC = #sparse_tensor.encoding<{
dimLevelType = [ "dense", "compressed" ], dimLevelType = [ "dense", "compressed" ],
dimOrdering = affine_map<(i,j) -> (j,i)> dimOrdering = affine_map<(i,j) -> (j,i)>
}> }>
▲ Show 20 Lines • Show All 222 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_reductions.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// //
// Do the same run, but now with SIMDization as well. This should not change the outcome. // Do the same run, but now with SIMDization as well. This should not change the outcome.
// //
// RUN: mlir-opt %s -sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=8" | \ // RUN: mlir-opt %s -sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=8" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SV = #sparse_tensor.encoding<{ dimLevelType = [ "compressed" ] }> #SV = #sparse_tensor.encoding<{ dimLevelType = [ "compressed" ] }>
#DV = #sparse_tensor.encoding<{ dimLevelType = [ "dense" ] }> #DV = #sparse_tensor.encoding<{ dimLevelType = [ "dense" ] }>
#trait_reduction = { #trait_reduction = {
indexing_maps = [ indexing_maps = [
affine_map<(i) -> (i)>, // a affine_map<(i) -> (i)>, // a
▲ Show 20 Lines • Show All 186 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_reshape.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SparseVector = #sparse_tensor.encoding<{ #SparseVector = #sparse_tensor.encoding<{
dimLevelType = ["compressed"] dimLevelType = ["compressed"]
}> }>
#SparseMatrix = #sparse_tensor.encoding<{ #SparseMatrix = #sparse_tensor.encoding<{
dimLevelType = ["compressed", "compressed"] dimLevelType = ["compressed", "compressed"]
▲ Show 20 Lines • Show All 301 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sampled_matmul.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: TENSOR0="%mlir_integration_test_dir/data/test.mtx" \ // RUN: TENSOR0="%mlir_src_dir/test/Integration/data/test.mtx" \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// //
// Do the same run, but now with SIMDization as well. This should not change the outcome. // Do the same run, but now with SIMDization as well. This should not change the outcome.
// //
// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=4 enable-simd-index32" | \ // RUN: --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=4 enable-simd-index32" | \
// RUN: TENSOR0="%mlir_integration_test_dir/data/test.mtx" \ // RUN: TENSOR0="%mlir_src_dir/test/Integration/data/test.mtx" \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// //
!Filename = !llvm.ptr<i8> !Filename = !llvm.ptr<i8>
#SparseMatrix = #sparse_tensor.encoding<{ #SparseMatrix = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed" ], dimLevelType = [ "compressed", "compressed" ],
pointerBitWidth = 32, pointerBitWidth = 32,
▲ Show 20 Lines • Show All 101 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sampled_mm_fusion.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// //
// Do the same run, but now with SIMDization as well. This should not change the outcome. // Do the same run, but now with SIMDization as well. This should not change the outcome.
// //
// RUN: mlir-opt %s -sparse-compiler="vl=8" | \ // RUN: mlir-opt %s -sparse-compiler="vl=8" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SM = #sparse_tensor.encoding<{ dimLevelType = [ "compressed", "compressed" ] }> #SM = #sparse_tensor.encoding<{ dimLevelType = [ "compressed", "compressed" ] }>
#trait_sampled_dense_dense = { #trait_sampled_dense_dense = {
indexing_maps = [ indexing_maps = [
affine_map<(i,j,k) -> (i,j)>, // S affine_map<(i,j,k) -> (i,j)>, // S
affine_map<(i,j,k) -> (i,k)>, // A affine_map<(i,j,k) -> (i,k)>, // A
▲ Show 20 Lines • Show All 197 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_scale.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// //
// Do the same run, but now with SIMDization as well. This should not change the outcome. // Do the same run, but now with SIMDization as well. This should not change the outcome.
// //
// RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=4" | \ // RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=4" | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#CSR = #sparse_tensor.encoding<{ dimLevelType = [ "dense", "compressed" ] }> #CSR = #sparse_tensor.encoding<{ dimLevelType = [ "dense", "compressed" ] }>
#trait_scale = { #trait_scale = {
indexing_maps = [ indexing_maps = [
affine_map<(i,j) -> (i,j)> // X (out) affine_map<(i,j) -> (i,j)> // X (out)
], ],
▲ Show 20 Lines • Show All 64 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_scf_nested.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#map = affine_map<(d0, d1, d2) -> (d0, d1, d2)> #map = affine_map<(d0, d1, d2) -> (d0, d1, d2)>
#SparseMatrix = #sparse_tensor.encoding<{ dimLevelType = [ "compressed", "compressed", "compressed" ] }> #SparseMatrix = #sparse_tensor.encoding<{ dimLevelType = [ "compressed", "compressed", "compressed" ] }>
module @func_sparse.2 { module @func_sparse.2 {
// Do elementwise x+1 when true, x-1 when false // Do elementwise x+1 when true, x-1 when false
func.func public @condition(%cond: i1, %arg0: tensor<2x3x4xf64, #SparseMatrix>) -> tensor<2x3x4xf64, #SparseMatrix> { func.func public @condition(%cond: i1, %arg0: tensor<2x3x4xf64, #SparseMatrix>) -> tensor<2x3x4xf64, #SparseMatrix> {
▲ Show 20 Lines • Show All 62 Lines • ▼ Show 20 Lines func.func public @entry() {
call @dump(%sm_f) : (tensor<2x3x4xf64, #SparseMatrix>) -> () call @dump(%sm_f) : (tensor<2x3x4xf64, #SparseMatrix>) -> ()
bufferization.dealloc_tensor %sm : tensor<2x3x4xf64, #SparseMatrix> bufferization.dealloc_tensor %sm : tensor<2x3x4xf64, #SparseMatrix>
bufferization.dealloc_tensor %sm_t : tensor<2x3x4xf64, #SparseMatrix> bufferization.dealloc_tensor %sm_t : tensor<2x3x4xf64, #SparseMatrix>
bufferization.dealloc_tensor %sm_f : tensor<2x3x4xf64, #SparseMatrix> bufferization.dealloc_tensor %sm_f : tensor<2x3x4xf64, #SparseMatrix>
return return
} }
} }
No newline at end of file No newline at end of file

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sign.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SparseVector = #sparse_tensor.encoding<{ dimLevelType = [ "compressed" ] }> #SparseVector = #sparse_tensor.encoding<{ dimLevelType = [ "compressed" ] }>
#trait_op = { #trait_op = {
indexing_maps = [ indexing_maps = [
affine_map<(i) -> (i)>, // a affine_map<(i) -> (i)>, // a
affine_map<(i) -> (i)> // x (out) affine_map<(i) -> (i)> // x (out)
▲ Show 20 Lines • Show All 88 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_spmm.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: TENSOR0="%mlir_integration_test_dir/data/wide.mtx" \ // RUN: TENSOR0="%mlir_src_dir/test/Integration/data/wide.mtx" \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// //
// Do the same run, but now with SIMDization as well. This should not change the outcome. // Do the same run, but now with SIMDization as well. This should not change the outcome.
// //
// RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=2" | \ // RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=2" | \
// RUN: TENSOR0="%mlir_integration_test_dir/data/wide.mtx" \ // RUN: TENSOR0="%mlir_src_dir/test/Integration/data/wide.mtx" \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
!Filename = !llvm.ptr<i8> !Filename = !llvm.ptr<i8>
#SparseMatrix = #sparse_tensor.encoding<{ #SparseMatrix = #sparse_tensor.encoding<{
dimLevelType = [ "dense", "compressed" ] dimLevelType = [ "dense", "compressed" ]
}> }>
▲ Show 20 Lines • Show All 82 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_storage.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// //
// Several common sparse storage schemes. // Several common sparse storage schemes.
// //
#Dense = #sparse_tensor.encoding<{ #Dense = #sparse_tensor.encoding<{
dimLevelType = [ "dense", "dense" ] dimLevelType = [ "dense", "dense" ]
▲ Show 20 Lines • Show All 247 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sum.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: TENSOR0="%mlir_integration_test_dir/data/test_symmetric.mtx" \ // RUN: TENSOR0="%mlir_src_dir/test/Integration/data/test_symmetric.mtx" \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// //
// Do the same run, but now with SIMDization as well. This should not change the outcome. // Do the same run, but now with SIMDization as well. This should not change the outcome.
// //
// RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=2" | \ // RUN: mlir-opt %s --sparse-compiler="vectorization-strategy=any-storage-inner-loop vl=2" | \
// RUN: TENSOR0="%mlir_integration_test_dir/data/test_symmetric.mtx" \ // RUN: TENSOR0="%mlir_src_dir/test/Integration/data/test_symmetric.mtx" \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
!Filename = !llvm.ptr<i8> !Filename = !llvm.ptr<i8>
#SparseMatrix = #sparse_tensor.encoding<{ #SparseMatrix = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed" ] dimLevelType = [ "compressed", "compressed" ]
}> }>
▲ Show 20 Lines • Show All 64 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sum_bf16.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
!Filename = !llvm.ptr<i8> !Filename = !llvm.ptr<i8>
#SparseMatrix = #sparse_tensor.encoding<{ #SparseMatrix = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed" ] dimLevelType = [ "compressed", "compressed" ]
}> }>
▲ Show 20 Lines • Show All 62 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sum_c32.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: TENSOR0="%mlir_integration_test_dir/data/test_symmetric_complex.mtx" \ // RUN: TENSOR0="%mlir_src_dir/test/Integration/data/test_symmetric_complex.mtx" \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
!Filename = !llvm.ptr<i8> !Filename = !llvm.ptr<i8>
#SparseMatrix = #sparse_tensor.encoding<{ #SparseMatrix = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed" ] dimLevelType = [ "compressed", "compressed" ]
}> }>
▲ Show 20 Lines • Show All 71 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sum_f16.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
!Filename = !llvm.ptr<i8> !Filename = !llvm.ptr<i8>
#SparseMatrix = #sparse_tensor.encoding<{ #SparseMatrix = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed" ] dimLevelType = [ "compressed", "compressed" ]
}> }>
▲ Show 20 Lines • Show All 62 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_tanh.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SparseVector = #sparse_tensor.encoding<{ dimLevelType = [ "compressed" ] }> #SparseVector = #sparse_tensor.encoding<{ dimLevelType = [ "compressed" ] }>
#trait_op = { #trait_op = {
indexing_maps = [ indexing_maps = [
affine_map<(i) -> (i)> // X (out) affine_map<(i) -> (i)> // X (out)
], ],
▲ Show 20 Lines • Show All 61 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_tensor_mul.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#ST = #sparse_tensor.encoding<{dimLevelType = ["compressed", "compressed", "compressed"]}> #ST = #sparse_tensor.encoding<{dimLevelType = ["compressed", "compressed", "compressed"]}>
// //
// Trait for 3-d tensor element wise multiplication. // Trait for 3-d tensor element wise multiplication.
// //
#trait_mul = { #trait_mul = {
▲ Show 20 Lines • Show All 90 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_tensor_ops.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#ST1 = #sparse_tensor.encoding<{dimLevelType = ["compressed", "compressed", "compressed"]}> #ST1 = #sparse_tensor.encoding<{dimLevelType = ["compressed", "compressed", "compressed"]}>
#ST2 = #sparse_tensor.encoding<{dimLevelType = ["compressed", "compressed", "dense"]}> #ST2 = #sparse_tensor.encoding<{dimLevelType = ["compressed", "compressed", "dense"]}>
// //
// Trait for 3-d tensor operation. // Trait for 3-d tensor operation.
// //
▲ Show 20 Lines • Show All 71 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_transpose.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#DCSR = #sparse_tensor.encoding<{ #DCSR = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed" ] dimLevelType = [ "compressed", "compressed" ]
}> }>
#DCSC = #sparse_tensor.encoding<{ #DCSC = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed" ], dimLevelType = [ "compressed", "compressed" ],
▲ Show 20 Lines • Show All 109 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_unary.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}> #SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}>
#DCSR = #sparse_tensor.encoding<{dimLevelType = ["compressed", "compressed"]}> #DCSR = #sparse_tensor.encoding<{dimLevelType = ["compressed", "compressed"]}>
// //
// Traits for tensor operations. // Traits for tensor operations.
// //
▲ Show 20 Lines • Show All 255 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_vector_ops.mlir

// RUN: mlir-opt %s --sparse-compiler | \ // RUN: mlir-opt %s --sparse-compiler | \
// RUN: mlir-cpu-runner \ // RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \ // RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}> #SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}>
#DenseVector = #sparse_tensor.encoding<{dimLevelType = ["dense"]}> #DenseVector = #sparse_tensor.encoding<{dimLevelType = ["dense"]}>
// //
// Traits for 1-d tensor (aka vector) operations. // Traits for 1-d tensor (aka vector) operations.
// //
▲ Show 20 Lines • Show All 223 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/python/test_SDDMM.py

# RUN: SUPPORT_LIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext \ # RUN: SUPPORT_LIB=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
# RUN: %PYTHON %s | FileCheck %s # RUN: %PYTHON %s | FileCheck %s
import ctypes import ctypes
import numpy as np import numpy as np
import os import os
import sys import sys
from mlir import ir from mlir import ir
Show All 9 Lines
from tools import sparse_compiler from tools import sparse_compiler
@dsl.linalg_structured_op @dsl.linalg_structured_op
def sddmm_dsl( def sddmm_dsl(
A=dsl.TensorDef(dsl.T, dsl.S.M, dsl.S.K), A=dsl.TensorDef(dsl.T, dsl.S.M, dsl.S.K),
B=dsl.TensorDef(dsl.T, dsl.S.K, dsl.S.N), B=dsl.TensorDef(dsl.T, dsl.S.K, dsl.S.N),
S=dsl.TensorDef(dsl.T, dsl.S.M, dsl.S.N), S=dsl.TensorDef(dsl.T, dsl.S.M, dsl.S.N),
C=dsl.TensorDef(dsl.T, dsl.S.M, dsl.S.N, output=True)): C=dsl.TensorDef(dsl.T, dsl.S.M, dsl.S.N, output=True)):
C[dsl.D.m, C[dsl.D.m,
dsl.D.n] += S[dsl.D.m, dsl.D.n] * A[dsl.D.m, dsl.D.k] * B[dsl.D.k, dsl.D.n] dsl.D.n] += S[dsl.D.m, dsl.D.n] * A[dsl.D.m, dsl.D.k] * B[dsl.D.k, dsl.D.n]
def build_SDDMM(attr: st.EncodingAttr): def build_SDDMM(attr: st.EncodingAttr):
"""Build SDDMM kernel. """Build SDDMM kernel.
This method generates a linalg op with for matrix multiplication using This method generates a linalg op with for matrix multiplication using
just the Python API. Effectively, a generic linalg op is constructed just the Python API. Effectively, a generic linalg op is constructed
that computes C(i,j) += S(i,j) SUM_k A(i,k) B(k,j) for sparse S. that computes C(i,j) += S(i,j) SUM_k A(i,k) B(k,j) for sparse S.
""" """
module = ir.Module.create() module = ir.Module.create()
f64 = ir.F64Type.get() f64 = ir.F64Type.get()
a = ir.RankedTensorType.get([8, 8], f64) a = ir.RankedTensorType.get([8, 8], f64)
b = ir.RankedTensorType.get([8, 8], f64) b = ir.RankedTensorType.get([8, 8], f64)
c = ir.RankedTensorType.get([8, 8], f64) c = ir.RankedTensorType.get([8, 8], f64)
s = ir.RankedTensorType.get([8, 8], f64, attr) s = ir.RankedTensorType.get([8, 8], f64, attr)
arguments = [a, b, s, c] arguments = [a, b, s, c]
with ir.InsertionPoint(module.body): with ir.InsertionPoint(module.body):
@func.FuncOp.from_py_func(*arguments) @func.FuncOp.from_py_func(*arguments)
def sddmm(*args): def sddmm(*args):
return sddmm_dsl(args[0], args[1], args[2], outs=[args[3]]) return sddmm_dsl(args[0], args[1], args[2], outs=[args[3]])
return module return module
def boilerplate(attr: st.EncodingAttr): def boilerplate(attr: st.EncodingAttr):
"""Returns boilerplate code for main driver.""" """Returns boilerplate code for main driver."""
return f""" return f"""
func.func @main(%a: tensor<8x8xf64>, func.func @main(%a: tensor<8x8xf64>,
%b: tensor<8x8xf64>, %b: tensor<8x8xf64>,
%c: tensor<8x8xf64>) -> tensor<8x8xf64> attributes {{ llvm.emit_c_interface }} {{ %c: tensor<8x8xf64>) -> tensor<8x8xf64> attributes {{ llvm.emit_c_interface }} {{
%t = arith.constant sparse<[[0,0], [0,2], [4,1]], [1.0, 2.0, 3.0]> : tensor<8x8xf64> %t = arith.constant sparse<[[0,0], [0,2], [4,1]], [1.0, 2.0, 3.0]> : tensor<8x8xf64>
%s = sparse_tensor.convert %t : tensor<8x8xf64> to tensor<8x8xf64, {attr}> %s = sparse_tensor.convert %t : tensor<8x8xf64> to tensor<8x8xf64, {attr}>
%0 = call @sddmm(%a, %b, %s, %c) : (tensor<8x8xf64>, %0 = call @sddmm(%a, %b, %s, %c) : (tensor<8x8xf64>,
tensor<8x8xf64>, tensor<8x8xf64>,
tensor<8x8xf64, {attr}>, tensor<8x8xf64, {attr}>,
tensor<8x8xf64>) -> tensor<8x8xf64> tensor<8x8xf64>) -> tensor<8x8xf64>
return %0 : tensor<8x8xf64> return %0 : tensor<8x8xf64>
}} }}
""" """
def build_compile_and_run_SDDMMM(attr: st.EncodingAttr, compiler): def build_compile_and_run_SDDMMM(attr: st.EncodingAttr, compiler):
# Build. # Build.
module = build_SDDMM(attr) module = build_SDDMM(attr)
func = str(module.operation.regions[0].blocks[0].operations[0].operation) func = str(module.operation.regions[0].blocks[0].operations[0].operation)
module = ir.Module.parse(func + boilerplate(attr)) module = ir.Module.parse(func + boilerplate(attr))
# Compile. # Compile.
engine = compiler.compile_and_jit(module) engine = compiler.compile_and_jit(module)
# Set up numpy input and buffer for output. # Set up numpy input and buffer for output.
a = np.array([[1.1, 2.1, 3.1, 4.1, 5.1, 6.1, 7.1, 8.1], a = np.array([[1.1, 2.1, 3.1, 4.1, 5.1, 6.1, 7.1, 8.1],
[1.2, 2.2, 3.2, 4.2, 5.2, 6.2, 7.2, 8.2], [1.2, 2.2, 3.2, 4.2, 5.2, 6.2, 7.2, 8.2],
[1.3, 2.3, 3.3, 4.3, 5.3, 6.3, 7.3, 8.3], [1.3, 2.3, 3.3, 4.3, 5.3, 6.3, 7.3, 8.3],
[1.4, 2.4, 3.4, 4.4, 5.4, 6.4, 7.4, 8.4], [1.4, 2.4, 3.4, 4.4, 5.4, 6.4, 7.4, 8.4],
[1.5, 2.5, 3.5, 4.5, 5.5, 6.5, 7.5, 8.5], [1.5, 2.5, 3.5, 4.5, 5.5, 6.5, 7.5, 8.5],
[1.6, 2.6, 3.6, 4.6, 5.6, 6.6, 7.6, 8.6], [1.6, 2.6, 3.6, 4.6, 5.6, 6.6, 7.6, 8.6],
[1.7, 2.7, 3.7, 4.7, 5.7, 6.7, 7.7, 8.7], [1.7, 2.7, 3.7, 4.7, 5.7, 6.7, 7.7, 8.7],
[1.8, 2.8, 3.8, 4.8, 5.8, 6.8, 7.8, 8.8]], np.float64) [1.8, 2.8, 3.8, 4.8, 5.8, 6.8, 7.8, 8.8]], np.float64)
b = np.ones((8, 8), np.float64) b = np.ones((8, 8), np.float64)
c = np.zeros((8, 8), np.float64) c = np.zeros((8, 8), np.float64)
mem_a = ctypes.pointer(ctypes.pointer(rt.get_ranked_memref_descriptor(a))) mem_a = ctypes.pointer(ctypes.pointer(rt.get_ranked_memref_descriptor(a)))
mem_b = ctypes.pointer(ctypes.pointer(rt.get_ranked_memref_descriptor(b))) mem_b = ctypes.pointer(ctypes.pointer(rt.get_ranked_memref_descriptor(b)))
mem_c = ctypes.pointer(ctypes.pointer(rt.get_ranked_memref_descriptor(c))) mem_c = ctypes.pointer(ctypes.pointer(rt.get_ranked_memref_descriptor(c)))
# Allocate a MemRefDescriptor to receive the output tensor. # Allocate a MemRefDescriptor to receive the output tensor.
# The buffer itself is allocated inside the MLIR code generation. # The buffer itself is allocated inside the MLIR code generation.
ref_out = rt.make_nd_memref_descriptor(2, ctypes.c_double)() ref_out = rt.make_nd_memref_descriptor(2, ctypes.c_double)()
mem_out = ctypes.pointer(ctypes.pointer(ref_out)) mem_out = ctypes.pointer(ctypes.pointer(ref_out))
# Invoke the kernel and get numpy output. # Invoke the kernel and get numpy output.
# Built-in bufferization uses in-out buffers. # Built-in bufferization uses in-out buffers.
# TODO: replace with inplace comprehensive bufferization. # TODO: replace with inplace comprehensive bufferization.
engine.invoke('main', mem_out, mem_a, mem_b, mem_c) engine.invoke('main', mem_out, mem_a, mem_b, mem_c)
# Sanity check on computed result. Only a few elements # Sanity check on computed result. Only a few elements
# are sampled from the full dense matrix multiplication. # are sampled from the full dense matrix multiplication.
full_matmul = np.matmul(a, b) full_matmul = np.matmul(a, b)
expected = np.zeros((8, 8), np.float64) expected = np.zeros((8, 8), np.float64)
expected[0, 0] = 1.0 * full_matmul[0, 0] expected[0, 0] = 1.0 * full_matmul[0, 0]
expected[0, 2] = 2.0 * full_matmul[0, 2] expected[0, 2] = 2.0 * full_matmul[0, 2]
expected[4, 1] = 3.0 * full_matmul[4, 1] expected[4, 1] = 3.0 * full_matmul[4, 1]
c = rt.ranked_memref_to_numpy(mem_out[0]) c = rt.ranked_memref_to_numpy(mem_out[0])
if np.allclose(c, expected): if np.allclose(c, expected):
pass pass
else: else:
quit(f'FAILURE') quit(f'FAILURE')
def main(): def main():
support_lib = os.getenv('SUPPORT_LIB') support_lib = os.getenv('SUPPORT_LIB')
assert support_lib is not None, 'SUPPORT_LIB is undefined' assert support_lib is not None, 'SUPPORT_LIB is undefined'
if not os.path.exists(support_lib): if not os.path.exists(support_lib):
raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT), raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT),
support_lib) support_lib)
# CHECK-LABEL: TEST: testSDDMMM # CHECK-LABEL: TEST: testSDDMMM
print('\nTEST: testSDDMMM') print('\nTEST: testSDDMMM')
with ir.Context() as ctx, ir.Location.unknown(): with ir.Context() as ctx, ir.Location.unknown():
count = 0 count = 0
# Loop over various ways to compile and annotate the SDDMM kernel with # Loop over various ways to compile and annotate the SDDMM kernel with
# a *single* sparse tensor. Note that we deliberate do not exhaustively # a *single* sparse tensor. Note that we deliberate do not exhaustively
# search the full state space to reduce runtime of the test. It is # search the full state space to reduce runtime of the test. It is
# straightforward to adapt the code below to explore more combinations. # straightforward to adapt the code below to explore more combinations.
levels = [[st.DimLevelType.dense, st.DimLevelType.dense], levels = [[st.DimLevelType.dense, st.DimLevelType.dense],
[st.DimLevelType.dense, st.DimLevelType.compressed], [st.DimLevelType.dense, st.DimLevelType.compressed],
[st.DimLevelType.compressed, st.DimLevelType.dense], [st.DimLevelType.compressed, st.DimLevelType.dense],
[st.DimLevelType.compressed, st.DimLevelType.compressed]] [st.DimLevelType.compressed, st.DimLevelType.compressed]]
orderings = [ orderings = [
ir.AffineMap.get_permutation([0, 1]), ir.AffineMap.get_permutation([0, 1]),
ir.AffineMap.get_permutation([1, 0]) ir.AffineMap.get_permutation([1, 0])
] ]
vec_strategy = [ vec_strategy = [
'none', 'dense-inner-loop' 'none', 'dense-inner-loop'
] ]for level in levels:
for level in levels:
for ordering in orderings: for ordering in orderings:
for pwidth in [32]: for pwidth in [32]:
for iwidth in [32]: for iwidth in [32]:
for vec in vec_strategy: for vec in vec_strategy:
for e in [True]: for e in [True]:
vl = 1 if vec == 0 else 16 vl = 1 if vec == 0 else 16
attr = st.EncodingAttr.get(level, ordering, pwidth, iwidth) attr = st.EncodingAttr.get(level, ordering, pwidth, iwidth)
opt = (f'parallelization-strategy=none ' opt = (f'parallelization-strategy=none '
f'vectorization-strategy={vec} ' f'vectorization-strategy={vec} '
f'vl={vl} enable-simd-index32={e}') f'vl={vl} enable-simd-index32={e}')
compiler = sparse_compiler.SparseCompiler( compiler = sparse_compiler.SparseCompiler(
options=opt, opt_level=0, shared_libs=[support_lib]) options=opt, opt_level=0, shared_libs=[support_lib])
build_compile_and_run_SDDMMM(attr, compiler) build_compile_and_run_SDDMMM(attr, compiler)
count = count + 1 count = count + 1
# CHECK: Passed 16 tests # CHECK: Passed 16 tests
print('Passed ', count, 'tests') print('Passed ', count, 'tests')
if __name__ == '__main__': if __name__ == '__main__':
main() main()

mlir/test/Integration/Dialect/SparseTensor/python/test_SpMM.py

# RUN: SUPPORT_LIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext \ # RUN: SUPPORT_LIB=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
# RUN: %PYTHON %s | FileCheck %s # RUN: %PYTHON %s | FileCheck %s
import ctypes import ctypes
import numpy as np import numpy as np
import os import os
import sys import sys
from mlir import ir from mlir import ir
from mlir import runtime as rt from mlir import runtime as rt
from mlir.dialects import sparse_tensor as st from mlir.dialects import sparse_tensor as st
from mlir.dialects import builtin from mlir.dialects import builtin
from mlir.dialects import func from mlir.dialects import func
from mlir.dialects.linalg.opdsl import lang as dsl from mlir.dialects.linalg.opdsl import lang as dsl
_SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__)) _SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__))
sys.path.append(_SCRIPT_PATH) sys.path.append(_SCRIPT_PATH)
from tools import sparse_compiler from tools import sparse_compiler
@dsl.linalg_structured_op @dsl.linalg_structured_op
def matmul_dsl( def matmul_dsl(
A=dsl.TensorDef(dsl.T, dsl.S.M, dsl.S.K), A=dsl.TensorDef(dsl.T, dsl.S.M, dsl.S.K),
B=dsl.TensorDef(dsl.T, dsl.S.K, dsl.S.N), B=dsl.TensorDef(dsl.T, dsl.S.K, dsl.S.N),
C=dsl.TensorDef(dsl.T, dsl.S.M, dsl.S.N, output=True)): C=dsl.TensorDef(dsl.T, dsl.S.M, dsl.S.N, output=True)):
C[dsl.D.m, dsl.D.n] += A[dsl.D.m, dsl.D.k] * B[dsl.D.k, dsl.D.n] C[dsl.D.m, dsl.D.n] += A[dsl.D.m, dsl.D.k] * B[dsl.D.k, dsl.D.n]
def build_SpMM(attr: st.EncodingAttr): def build_SpMM(attr: st.EncodingAttr):
"""Build SpMM kernel. """Build SpMM kernel.
This method generates a linalg op with for matrix multiplication using This method generates a linalg op with for matrix multiplication using
just the Python API. Effectively, a generic linalg op is constructed just the Python API. Effectively, a generic linalg op is constructed
that computes C(i,j) += A(i,k) * B(k,j) for annotated matrix A. that computes C(i,j) += A(i,k) * B(k,j) for annotated matrix A.
""" """
module = ir.Module.create() module = ir.Module.create()
f64 = ir.F64Type.get() f64 = ir.F64Type.get()
a = ir.RankedTensorType.get([3, 4], f64, attr) a = ir.RankedTensorType.get([3, 4], f64, attr)
b = ir.RankedTensorType.get([4, 2], f64) b = ir.RankedTensorType.get([4, 2], f64)
c = ir.RankedTensorType.get([3, 2], f64) c = ir.RankedTensorType.get([3, 2], f64)
arguments = [a, b, c] arguments = [a, b, c]
with ir.InsertionPoint(module.body): with ir.InsertionPoint(module.body):
@func.FuncOp.from_py_func(*arguments) @func.FuncOp.from_py_func(*arguments)
def spMxM(*args): def spMxM(*args):
return matmul_dsl(args[0], args[1], outs=[args[2]]) return matmul_dsl(args[0], args[1], outs=[args[2]])
return module return module
def boilerplate(attr: st.EncodingAttr): def boilerplate(attr: st.EncodingAttr):
"""Returns boilerplate main method. """Returns boilerplate main method.
This method sets up a boilerplate main method that takes three tensors This method sets up a boilerplate main method that takes three tensors
(a, b, c), converts the first tensor a into s sparse tensor, and then (a, b, c), converts the first tensor a into s sparse tensor, and then
calls the sparse kernel for matrix multiplication. For convenience, calls the sparse kernel for matrix multiplication. For convenience,
this part is purely done as string input. this part is purely done as string input.
""" """
return f""" return f"""
func.func @main(%ad: tensor<3x4xf64>, %b: tensor<4x2xf64>, %c: tensor<3x2xf64>) -> tensor<3x2xf64> func.func @main(%ad: tensor<3x4xf64>, %b: tensor<4x2xf64>, %c: tensor<3x2xf64>) -> tensor<3x2xf64>
attributes {{ llvm.emit_c_interface }} {{ attributes {{ llvm.emit_c_interface }} {{
%a = sparse_tensor.convert %ad : tensor<3x4xf64> to tensor<3x4xf64, {attr}> %a = sparse_tensor.convert %ad : tensor<3x4xf64> to tensor<3x4xf64, {attr}>
%0 = call @spMxM(%a, %b, %c) : (tensor<3x4xf64, {attr}>, %0 = call @spMxM(%a, %b, %c) : (tensor<3x4xf64, {attr}>,
tensor<4x2xf64>, tensor<4x2xf64>,
tensor<3x2xf64>) -> tensor<3x2xf64> tensor<3x2xf64>) -> tensor<3x2xf64>
return %0 : tensor<3x2xf64> return %0 : tensor<3x2xf64>
}} }}
""" """
def build_compile_and_run_SpMM(attr: st.EncodingAttr, compiler): def build_compile_and_run_SpMM(attr: st.EncodingAttr, compiler):
# Build. # Build.
module = build_SpMM(attr) module = build_SpMM(attr)
func = str(module.operation.regions[0].blocks[0].operations[0].operation) func = str(module.operation.regions[0].blocks[0].operations[0].operation)
module = ir.Module.parse(func + boilerplate(attr)) module = ir.Module.parse(func + boilerplate(attr))
# Compile. # Compile.
engine = compiler.compile_and_jit(module) engine = compiler.compile_and_jit(module)
# Set up numpy input and buffer for output. # Set up numpy input and buffer for output.
a = np.array( a = np.array(
[[1.1, 0.0, 0.0, 1.4], [0.0, 0.0, 0.0, 0.0], [0.0, 0.0, 3.3, 0.0]], [[1.1, 0.0, 0.0, 1.4], [0.0, 0.0, 0.0, 0.0], [0.0, 0.0, 3.3, 0.0]],
np.float64) np.float64)
b = np.array([[1.0, 2.0], [4.0, 3.0], [5.0, 6.0], [8.0, 7.0]], np.float64) b = np.array([[1.0, 2.0], [4.0, 3.0], [5.0, 6.0], [8.0, 7.0]], np.float64)
c = np.zeros((3, 2), np.float64) c = np.zeros((3, 2), np.float64)
mem_a = ctypes.pointer(ctypes.pointer(rt.get_ranked_memref_descriptor(a))) mem_a = ctypes.pointer(ctypes.pointer(rt.get_ranked_memref_descriptor(a)))
mem_b = ctypes.pointer(ctypes.pointer(rt.get_ranked_memref_descriptor(b))) mem_b = ctypes.pointer(ctypes.pointer(rt.get_ranked_memref_descriptor(b)))
mem_c = ctypes.pointer(ctypes.pointer(rt.get_ranked_memref_descriptor(c))) mem_c = ctypes.pointer(ctypes.pointer(rt.get_ranked_memref_descriptor(c)))
# Allocate a MemRefDescriptor to receive the output tensor. # Allocate a MemRefDescriptor to receive the output tensor.
# The buffer itself is allocated inside the MLIR code generation. # The buffer itself is allocated inside the MLIR code generation.
ref_out = rt.make_nd_memref_descriptor(2, ctypes.c_double)() ref_out = rt.make_nd_memref_descriptor(2, ctypes.c_double)()
mem_out = ctypes.pointer(ctypes.pointer(ref_out)) mem_out = ctypes.pointer(ctypes.pointer(ref_out))
# Invoke the kernel and get numpy output. # Invoke the kernel and get numpy output.
# Built-in bufferization uses in-out buffers. # Built-in bufferization uses in-out buffers.
# TODO: replace with inplace comprehensive bufferization. # TODO: replace with inplace comprehensive bufferization.
engine.invoke('main', mem_out, mem_a, mem_b, mem_c) engine.invoke('main', mem_out, mem_a, mem_b, mem_c)
# Sanity check on computed result. # Sanity check on computed result.
expected = np.matmul(a, b); expected = np.matmul(a, b);
c = rt.ranked_memref_to_numpy(mem_out[0]) c = rt.ranked_memref_to_numpy(mem_out[0])
if np.allclose(c, expected): if np.allclose(c, expected):
pass pass
else: else:
quit(f'FAILURE') quit(f'FAILURE')
def main(): def main():
support_lib = os.getenv('SUPPORT_LIB') support_lib = os.getenv('SUPPORT_LIB')
assert support_lib is not None, 'SUPPORT_LIB is undefined' assert support_lib is not None, 'SUPPORT_LIB is undefined'
if not os.path.exists(support_lib): if not os.path.exists(support_lib):
raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT), support_lib) raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT), support_lib)
# CHECK-LABEL: TEST: testSpMM # CHECK-LABEL: TEST: testSpMM
print('\nTEST: testSpMM') print('\nTEST: testSpMM')
with ir.Context() as ctx, ir.Location.unknown(): with ir.Context() as ctx, ir.Location.unknown():
count = 0 count = 0
# Loop over various ways to compile and annotate the SpMM kernel with # Loop over various ways to compile and annotate the SpMM kernel with
# a *single* sparse tensor. Note that we deliberate do not exhaustively # a *single* sparse tensor. Note that we deliberate do not exhaustively
# search the full state space to reduce runtime of the test. It is # search the full state space to reduce runtime of the test. It is
# straightforward to adapt the code below to explore more combinations. # straightforward to adapt the code below to explore more combinations.
vl = 1 vl = 1
e = False e = False
opt = (f'parallelization-strategy=none ' opt = (f'parallelization-strategy=none '
f'vectorization-strategy=none ' f'vectorization-strategy=none '
f'vl={vl} enable-simd-index32={e}') f'vl={vl} enable-simd-index32={e}')
levels = [[st.DimLevelType.dense, st.DimLevelType.dense], levels = [[st.DimLevelType.dense, st.DimLevelType.dense],
[st.DimLevelType.dense, st.DimLevelType.compressed], [st.DimLevelType.dense, st.DimLevelType.compressed],
[st.DimLevelType.compressed, st.DimLevelType.dense], [st.DimLevelType.compressed, st.DimLevelType.dense],
[st.DimLevelType.compressed, st.DimLevelType.compressed]] [st.DimLevelType.compressed, st.DimLevelType.compressed]]
orderings = [ orderings = [
ir.AffineMap.get_permutation([0, 1]), ir.AffineMap.get_permutation([0, 1]),
ir.AffineMap.get_permutation([1, 0]) ir.AffineMap.get_permutation([1, 0])
] ]
bitwidths = [0] bitwidths = [0]
compiler = sparse_compiler.SparseCompiler( compiler = sparse_compiler.SparseCompiler(
options=opt, opt_level=0, shared_libs=[support_lib]) options=opt, opt_level=0, shared_libs=[support_lib])
for level in levels: for level in levels:
for ordering in orderings: for ordering in orderings:
for pwidth in bitwidths: for pwidth in bitwidths:
for iwidth in bitwidths: for iwidth in bitwidths:
attr = st.EncodingAttr.get(level, ordering, pwidth, iwidth) attr = st.EncodingAttr.get(level, ordering, pwidth, iwidth)
build_compile_and_run_SpMM(attr, compiler) build_compile_and_run_SpMM(attr, compiler)
count = count + 1 count = count + 1
# CHECK: Passed 8 tests # CHECK: Passed 8 tests
print('Passed ', count, 'tests') print('Passed ', count, 'tests')
if __name__ == '__main__': if __name__ == '__main__':
main() main()

mlir/test/Integration/Dialect/SparseTensor/python/test_elementwise_add_sparse_output.py

# RUN: SUPPORT_LIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s # RUN: SUPPORT_LIB=%mlir_lib_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s
import ctypes import ctypes
import numpy as np import numpy as np
import os import os
import sys import sys
from mlir import ir from mlir import ir
from mlir import runtime as rt from mlir import runtime as rt
▲ Show 20 Lines • Show All 96 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/python/test_output.py

# RUN: SUPPORT_LIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext \ # RUN: SUPPORT_LIB=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
# RUN: %PYTHON %s | FileCheck %s # RUN: %PYTHON %s | FileCheck %s
import ctypes import ctypes
import os import os
import sys import sys
import tempfile import tempfile
from mlir import ir from mlir import ir
from mlir import runtime as rt from mlir import runtime as rt
from mlir.dialects import builtin from mlir.dialects import builtin
from mlir.dialects import sparse_tensor as st from mlir.dialects import sparse_tensor as st
_SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__)) _SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__))
sys.path.append(_SCRIPT_PATH) sys.path.append(_SCRIPT_PATH)
from tools import sparse_compiler from tools import sparse_compiler
# TODO: move more into actual IR building. # TODO: move more into actual IR building.
def boilerplate(attr: st.EncodingAttr): def boilerplate(attr: st.EncodingAttr):
"""Returns boilerplate main method.""" """Returns boilerplate main method."""
return f""" return f"""
func.func @main(%p : !llvm.ptr<i8>) -> () attributes {{ llvm.emit_c_interface }} {{ func.func @main(%p : !llvm.ptr<i8>) -> () attributes {{ llvm.emit_c_interface }} {{
%d = arith.constant sparse<[[0, 0], [1, 1], [0, 9], [9, 0], [4, 4]], %d = arith.constant sparse<[[0, 0], [1, 1], [0, 9], [9, 0], [4, 4]],
[1.0, 2.0, 3.0, 4.0, 5.0]> : tensor<10x10xf64> [1.0, 2.0, 3.0, 4.0, 5.0]> : tensor<10x10xf64>
%a = sparse_tensor.convert %d : tensor<10x10xf64> to tensor<10x10xf64, {attr}> %a = sparse_tensor.convert %d : tensor<10x10xf64> to tensor<10x10xf64, {attr}>
sparse_tensor.out %a, %p : tensor<10x10xf64, {attr}>, !llvm.ptr<i8> sparse_tensor.out %a, %p : tensor<10x10xf64, {attr}>, !llvm.ptr<i8>
return return
}} }}
""" """
def expected(): def expected():
"""Returns expected contents of output. """Returns expected contents of output.
Regardless of the dimension ordering, compression, and bitwidths that are Regardless of the dimension ordering, compression, and bitwidths that are
used in the sparse tensor, the output is always lexicographically sorted used in the sparse tensor, the output is always lexicographically sorted
by natural index order. by natural index order.
""" """
return f"""; extended FROSTT format return f"""; extended FROSTT format
2 5 2 5
10 10 10 10
1 1 1 1 1 1
1 10 3 1 10 3
2 2 2 2 2 2
5 5 5 5 5 5
10 1 4 10 1 4
""" """
def build_compile_and_run_output(attr: st.EncodingAttr, compiler): def build_compile_and_run_output(attr: st.EncodingAttr, compiler):
# Build and Compile. # Build and Compile.
module = ir.Module.parse(boilerplate(attr)) module = ir.Module.parse(boilerplate(attr))
engine = compiler.compile_and_jit(module) engine = compiler.compile_and_jit(module)
# Invoke the kernel and compare output. # Invoke the kernel and compare output.
with tempfile.TemporaryDirectory() as test_dir: with tempfile.TemporaryDirectory() as test_dir:
out = os.path.join(test_dir, 'out.tns') out = os.path.join(test_dir, 'out.tns')
buf = out.encode('utf-8') buf = out.encode('utf-8')
mem_a = ctypes.pointer(ctypes.pointer(ctypes.create_string_buffer(buf))) mem_a = ctypes.pointer(ctypes.pointer(ctypes.create_string_buffer(buf)))
engine.invoke('main', mem_a) engine.invoke('main', mem_a)
actual = open(out).read() actual = open(out).read()
if actual != expected(): if actual != expected():
quit('FAILURE') quit('FAILURE')
def main(): def main():
support_lib = os.getenv('SUPPORT_LIB') support_lib = os.getenv('SUPPORT_LIB')
assert support_lib is not None, 'SUPPORT_LIB is undefined' assert support_lib is not None, 'SUPPORT_LIB is undefined'
if not os.path.exists(support_lib): if not os.path.exists(support_lib):
raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT), raise FileNotFoundError(errno.ENOENT, os.strerror(errno.ENOENT),
support_lib) support_lib)
# CHECK-LABEL: TEST: test_output # CHECK-LABEL: TEST: test_output
print('\nTEST: test_output') print('\nTEST: test_output')
count = 0 count = 0
with ir.Context() as ctx, ir.Location.unknown(): with ir.Context() as ctx, ir.Location.unknown():
# Loop over various sparse types: CSR, DCSR, CSC, DCSC. # Loop over various sparse types: CSR, DCSR, CSC, DCSC.
levels = [[st.DimLevelType.dense, st.DimLevelType.compressed], levels = [[st.DimLevelType.dense, st.DimLevelType.compressed],
[st.DimLevelType.compressed, st.DimLevelType.compressed]] [st.DimLevelType.compressed, st.DimLevelType.compressed]]
orderings = [ orderings = [
ir.AffineMap.get_permutation([0, 1]), ir.AffineMap.get_permutation([0, 1]),
ir.AffineMap.get_permutation([1, 0]) ir.AffineMap.get_permutation([1, 0])
] ]
bitwidths = [8, 16, 32, 64] bitwidths = [8, 16, 32, 64]
compiler = sparse_compiler.SparseCompiler( compiler = sparse_compiler.SparseCompiler(
options='', opt_level=2, shared_libs=[support_lib]) options='', opt_level=2, shared_libs=[support_lib])
for level in levels: for level in levels:
for ordering in orderings: for ordering in orderings:
for bwidth in bitwidths: for bwidth in bitwidths:
attr = st.EncodingAttr.get(level, ordering, bwidth, bwidth) attr = st.EncodingAttr.get(level, ordering, bwidth, bwidth)
build_compile_and_run_output(attr, compiler) build_compile_and_run_output(attr, compiler)
count = count + 1 count = count + 1
# CHECK: Passed 16 tests # CHECK: Passed 16 tests
print('Passed', count, 'tests') print('Passed', count, 'tests')
if __name__ == '__main__': if __name__ == '__main__':
main() main()

mlir/test/Integration/Dialect/SparseTensor/python/test_stress.py

# RUN: SUPPORT_LIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext \ # RUN: SUPPORT_LIB=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
# RUN: %PYTHON %s | FileCheck %s # RUN: %PYTHON %s | FileCheck %s
import ctypes import ctypes
import errno import errno
import itertools import itertools
import os import os
import sys import sys
▲ Show 20 Lines • Show All 236 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/taco/test_MTTKRP.py

# RUN: SUPPORTLIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s # RUN: SUPPORTLIB=%mlir_lib_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s
import numpy as np import numpy as np
import os import os
import sys import sys
import tempfile import tempfile
_SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__)) _SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__))
sys.path.append(_SCRIPT_PATH) sys.path.append(_SCRIPT_PATH)
▲ Show 20 Lines • Show All 46 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/taco/test_SDDMM.py

# RUN: SUPPORTLIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s # RUN: SUPPORTLIB=%mlir_lib_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s
import filecmp import filecmp
import numpy as np import numpy as np
import os import os
import sys import sys
import tempfile import tempfile
_SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__)) _SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__))
▲ Show 20 Lines • Show All 49 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/taco/test_SpMM.py

# RUN: SUPPORTLIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s # RUN: SUPPORTLIB=%mlir_lib_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s
import filecmp import filecmp
import numpy as np import numpy as np
import os import os
import sys import sys
import tempfile import tempfile
_SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__)) _SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__))
Show All 26 Lines

mlir/test/Integration/Dialect/SparseTensor/taco/test_SpMV.py

# RUN: SUPPORTLIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s # RUN: SUPPORTLIB=%mlir_lib_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s
import numpy as np import numpy as np
import os import os
import sys import sys
import tempfile import tempfile
_SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__)) _SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__))
sys.path.append(_SCRIPT_PATH) sys.path.append(_SCRIPT_PATH)
▲ Show 20 Lines • Show All 47 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/taco/test_Tensor.py

# RUN: SUPPORTLIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s # RUN: SUPPORTLIB=%mlir_lib_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s
import filecmp import filecmp
import numpy as np import numpy as np
import os import os
import sys import sys
import tempfile import tempfile
_SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__)) _SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__))
▲ Show 20 Lines • Show All 93 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/taco/test_scalar_tensor_algebra.py

# RUN: SUPPORTLIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s # RUN: SUPPORTLIB=%mlir_lib_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s
import numpy as np import numpy as np
import os import os
import sys import sys
_SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__)) _SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__))
sys.path.append(_SCRIPT_PATH) sys.path.append(_SCRIPT_PATH)
from tools import mlir_pytaco_api as pt from tools import mlir_pytaco_api as pt
Show All 27 Lines

mlir/test/Integration/Dialect/SparseTensor/taco/test_simple_tensor_algebra.py

# RUN: SUPPORTLIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s # RUN: SUPPORTLIB=%mlir_lib_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s
import numpy as np import numpy as np
import os import os
import sys import sys
_SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__)) _SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__))
sys.path.append(_SCRIPT_PATH) sys.path.append(_SCRIPT_PATH)
from tools import mlir_pytaco_api as pt from tools import mlir_pytaco_api as pt
▲ Show 20 Lines • Show All 52 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/taco/test_tensor_complex.py

# RUN: SUPPORTLIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s # RUN: SUPPORTLIB=%mlir_lib_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s
import numpy as np import numpy as np
import os import os
import sys import sys
_SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__)) _SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__))
sys.path.append(_SCRIPT_PATH) sys.path.append(_SCRIPT_PATH)
from tools import mlir_pytaco_api as pt from tools import mlir_pytaco_api as pt
Show All 22 Lines

mlir/test/Integration/Dialect/SparseTensor/taco/test_tensor_types.py

# RUN: SUPPORTLIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s # RUN: SUPPORTLIB=%mlir_lib_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s
import numpy as np import numpy as np
import os import os
import sys import sys
_SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__)) _SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__))
sys.path.append(_SCRIPT_PATH) sys.path.append(_SCRIPT_PATH)
from tools import mlir_pytaco_api as pt from tools import mlir_pytaco_api as pt
Show All 26 Lines

mlir/test/Integration/Dialect/SparseTensor/taco/test_tensor_unary_ops.py

# RUN: SUPPORTLIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s # RUN: SUPPORTLIB=%mlir_lib_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s
import numpy as np import numpy as np
import os import os
import sys import sys
_SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__)) _SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__))
sys.path.append(_SCRIPT_PATH) sys.path.append(_SCRIPT_PATH)
from tools import mlir_pytaco_api as pt from tools import mlir_pytaco_api as pt
Show All 31 Lines

mlir/test/Integration/Dialect/SparseTensor/taco/test_true_dense_tensor_algebra.py

# RUN: SUPPORTLIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s # RUN: SUPPORTLIB=%mlir_lib_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s
import numpy as np import numpy as np
import os import os
import sys import sys
_SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__)) _SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__))
sys.path.append(_SCRIPT_PATH) sys.path.append(_SCRIPT_PATH)
from tools import mlir_pytaco_api as pt from tools import mlir_pytaco_api as pt
Show All 13 Lines

mlir/test/Integration/Dialect/SparseTensor/taco/unit_test_tensor_core.py

# RUN: SUPPORTLIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s # RUN: SUPPORTLIB=%mlir_lib_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s
from string import Template from string import Template
import numpy as np import numpy as np
import os import os
import sys import sys
import tempfile import tempfile
▲ Show 20 Lines • Show All 517 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/taco/unit_test_tensor_io.py

# RUN: SUPPORTLIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s # RUN: SUPPORTLIB=%mlir_lib_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s
from string import Template from string import Template
import numpy as np import numpy as np
import os import os
import sys import sys
import tempfile import tempfile
▲ Show 20 Lines • Show All 136 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/SparseTensor/taco/unit_test_tensor_utils.py

# RUN: SUPPORTLIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s # RUN: SUPPORTLIB=%mlir_lib_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s
from typing import Sequence from typing import Sequence
import dataclasses import dataclasses
import numpy as np import numpy as np
import os import os
import sys import sys
import tempfile import tempfile
▲ Show 20 Lines • Show All 112 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Standard/CPU/test-ceil-floor-pos-neg.mlir

// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf,lower-affine,convert-scf-to-cf,memref-expand,arith-expand),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf,lower-affine,convert-scf-to-cf,memref-expand,arith-expand),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @transfer_read_2d(%A : memref<40xi32>, %base1: index) { func.func @transfer_read_2d(%A : memref<40xi32>, %base1: index) {
%i42 = arith.constant -42: i32 %i42 = arith.constant -42: i32
%f = vector.transfer_read %A[%base1], %i42 %f = vector.transfer_read %A[%base1], %i42
{permutation_map = affine_map<(d0) -> (d0)>} : {permutation_map = affine_map<(d0) -> (d0)>} :
memref<40xi32>, vector<40xi32> memref<40xi32>, vector<40xi32>
vector.print %f: vector<40xi32> vector.print %f: vector<40xi32>
▲ Show 20 Lines • Show All 92 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Standard/CPU/test_subview.mlir

// RUN: mlir-opt %s -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext | FileCheck %s // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext | FileCheck %s
memref.global "private" constant @__constant_5x3xf32 : memref<5x3xf32> = memref.global "private" constant @__constant_5x3xf32 : memref<5x3xf32> =
dense<[[0.0, 1.0, 2.0], dense<[[0.0, 1.0, 2.0],
[3.0, 4.0, 5.0], [3.0, 4.0, 5.0],
[6.0, 7.0, 8.0], [6.0, 7.0, 8.0],
[9.0, 10.0, 11.0], [9.0, 10.0, 11.0],
[12.0, 13.0, 14.0]]> [12.0, 13.0, 14.0]]>
▲ Show 20 Lines • Show All 52 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/AMX/test-mulf-full.mlir

// RUN: mlir-opt %s -convert-vector-to-scf -lower-affine -convert-scf-to-cf \ // RUN: mlir-opt %s -convert-vector-to-scf -lower-affine -convert-scf-to-cf \
// RUN: -arith-bufferize -convert-vector-to-llvm="enable-amx" \ // RUN: -arith-bufferize -convert-vector-to-llvm="enable-amx" \
// RUN: -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-translate -mlir-to-llvmir | \ // RUN: mlir-translate -mlir-to-llvmir | \
// RUN: %lli --entry-function=entry --mattr="+amx-tile,+amx-int8,+amx-bf16" \ // RUN: %lli --entry-function=entry --mattr="+amx-tile,+amx-int8,+amx-bf16" \
// RUN: --dlopen=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: --dlopen=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// Note: To run this test, your CPU must support AMX. // Note: To run this test, your CPU must support AMX.
// Multiply full size tiles into zero destination. // Multiply full size tiles into zero destination.
func.func @kernel(%arg0: memref<16x32xbf16>, func.func @kernel(%arg0: memref<16x32xbf16>,
%arg1: memref<16x32xbf16>, %arg1: memref<16x32xbf16>,
%arg2: memref<16x16xf32>) { %arg2: memref<16x16xf32>) {
▲ Show 20 Lines • Show All 124 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/AMX/test-mulf.mlir

// RUN: mlir-opt %s -convert-vector-to-scf -lower-affine -convert-scf-to-cf -convert-vector-to-llvm="enable-amx" -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-vector-to-scf -lower-affine -convert-scf-to-cf -convert-vector-to-llvm="enable-amx" -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-translate -mlir-to-llvmir | \ // RUN: mlir-translate -mlir-to-llvmir | \
// RUN: %lli --entry-function=entry --mattr="+amx-tile,+amx-int8,+amx-bf16" --dlopen=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: %lli --entry-function=entry --mattr="+amx-tile,+amx-int8,+amx-bf16" --dlopen=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// Note: To run this test, your CPU must support AMX. // Note: To run this test, your CPU must support AMX.
// Multiply into zeroed destination. // Multiply into zeroed destination.
func.func @kernel1(%arg0: memref<2x4xbf16>, func.func @kernel1(%arg0: memref<2x4xbf16>,
%arg1: memref<2x4xbf16>, %arg1: memref<2x4xbf16>,
%arg2: memref<2x2xf32>) { %arg2: memref<2x2xf32>) {
▲ Show 20 Lines • Show All 73 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/AMX/test-muli-ext.mlir

// RUN: mlir-opt %s -convert-vector-to-scf -lower-affine -convert-scf-to-cf -convert-vector-to-llvm="enable-amx" -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-vector-to-scf -lower-affine -convert-scf-to-cf -convert-vector-to-llvm="enable-amx" -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-translate -mlir-to-llvmir | \ // RUN: mlir-translate -mlir-to-llvmir | \
// RUN: %lli --entry-function=entry --mattr="+amx-tile,+amx-int8,+amx-bf16" --dlopen=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: %lli --entry-function=entry --mattr="+amx-tile,+amx-int8,+amx-bf16" --dlopen=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// Note: To run this test, your CPU must support AMX. // Note: To run this test, your CPU must support AMX.
func.func @print(%arg0: memref<16x4xi32>) { func.func @print(%arg0: memref<16x4xi32>) {
%iu = arith.constant -1: i32 %iu = arith.constant -1: i32
%c0 = arith.constant 0: index %c0 = arith.constant 0: index
%c1 = arith.constant 1: index %c1 = arith.constant 1: index
▲ Show 20 Lines • Show All 187 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/AMX/test-muli-full.mlir

// RUN: mlir-opt %s -convert-vector-to-scf -lower-affine -convert-scf-to-cf \ // RUN: mlir-opt %s -convert-vector-to-scf -lower-affine -convert-scf-to-cf \
// RUN: -arith-bufferize -convert-vector-to-llvm="enable-amx" \ // RUN: -arith-bufferize -convert-vector-to-llvm="enable-amx" \
// RUN: -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-translate -mlir-to-llvmir | \ // RUN: mlir-translate -mlir-to-llvmir | \
// RUN: %lli --entry-function=entry --mattr="+amx-tile,+amx-int8,+amx-bf16" \ // RUN: %lli --entry-function=entry --mattr="+amx-tile,+amx-int8,+amx-bf16" \
// RUN: --dlopen=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: --dlopen=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// Note: To run this test, your CPU must support AMX. // Note: To run this test, your CPU must support AMX.
// Multiply full size tiles into zero destination. // Multiply full size tiles into zero destination.
func.func @kernel(%arg0: memref<16x64xi8>, func.func @kernel(%arg0: memref<16x64xi8>,
%arg1: memref<16x64xi8>, %arg1: memref<16x64xi8>,
%arg2: memref<16x16xi32>) { %arg2: memref<16x16xi32>) {
▲ Show 20 Lines • Show All 123 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/AMX/test-muli.mlir

// RUN: mlir-opt %s -convert-vector-to-scf -lower-affine -convert-scf-to-cf -convert-vector-to-llvm="enable-amx" -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-vector-to-scf -lower-affine -convert-scf-to-cf -convert-vector-to-llvm="enable-amx" -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-translate -mlir-to-llvmir | \ // RUN: mlir-translate -mlir-to-llvmir | \
// RUN: %lli --entry-function=entry --mattr="+amx-tile,+amx-int8,+amx-bf16" --dlopen=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: %lli --entry-function=entry --mattr="+amx-tile,+amx-int8,+amx-bf16" --dlopen=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// Note: To run this test, your CPU must support AMX. // Note: To run this test, your CPU must support AMX.
// Multiply into zeroed destination. // Multiply into zeroed destination.
func.func @kernel1(%arg0: memref<2x8xi8>, func.func @kernel1(%arg0: memref<2x8xi8>,
%arg1: memref<2x8xi8>, %arg1: memref<2x8xi8>,
%arg2: memref<2x2xi32>) { %arg2: memref<2x2xi32>) {
▲ Show 20 Lines • Show All 72 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/AMX/test-tilezero-block.mlir

// RUN: mlir-opt %s -convert-vector-to-scf -lower-affine -convert-scf-to-cf -convert-vector-to-llvm="enable-amx" -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-vector-to-scf -lower-affine -convert-scf-to-cf -convert-vector-to-llvm="enable-amx" -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-translate -mlir-to-llvmir | \ // RUN: mlir-translate -mlir-to-llvmir | \
// RUN: %lli --entry-function=entry --mattr="+amx-tile,+amx-int8,+amx-bf16" --dlopen=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: %lli --entry-function=entry --mattr="+amx-tile,+amx-int8,+amx-bf16" --dlopen=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// Note: To run this test, your CPU must support AMX. // Note: To run this test, your CPU must support AMX.
func.func @print(%arg0: memref<4x32xf32>) { func.func @print(%arg0: memref<4x32xf32>) {
%fu = arith.constant -1.0: f32 %fu = arith.constant -1.0: f32
%c0 = arith.constant 0: index %c0 = arith.constant 0: index
%c1 = arith.constant 1: index %c1 = arith.constant 1: index
▲ Show 20 Lines • Show All 71 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/AMX/test-tilezero.mlir

// RUN: mlir-opt %s -convert-vector-to-scf -lower-affine -convert-scf-to-cf -convert-vector-to-llvm="enable-amx" -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-vector-to-scf -lower-affine -convert-scf-to-cf -convert-vector-to-llvm="enable-amx" -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-translate -mlir-to-llvmir | \ // RUN: mlir-translate -mlir-to-llvmir | \
// RUN: %lli --entry-function=entry --mattr="+amx-tile,+amx-int8,+amx-bf16" --dlopen=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: %lli --entry-function=entry --mattr="+amx-tile,+amx-int8,+amx-bf16" --dlopen=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// Note: To run this test, your CPU must support AMX. // Note: To run this test, your CPU must support AMX.
func.func @tilezero(%arg0: memref<?x?xi32>, %i: index, %j: index) { func.func @tilezero(%arg0: memref<?x?xi32>, %i: index, %j: index) {
%1 = amx.tile_zero : vector<16x16xi32> %1 = amx.tile_zero : vector<16x16xi32>
amx.tile_store %arg0[%i, %j], %1 : memref<?x?xi32>, vector<16x16xi32> amx.tile_store %arg0[%i, %j], %1 : memref<?x?xi32>, vector<16x16xi32>
return return
▲ Show 20 Lines • Show All 85 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/X86Vector/test-dot.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm="enable-x86vector" -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm="enable-x86vector" -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-translate --mlir-to-llvmir | \ // RUN: mlir-translate --mlir-to-llvmir | \
// RUN: %lli --entry-function=entry --mattr="avx" --dlopen=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: %lli --entry-function=entry --mattr="avx" --dlopen=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() -> i32 { func.func @entry() -> i32 {
%i0 = arith.constant 0 : i32 %i0 = arith.constant 0 : i32
%i4 = arith.constant 4 : i32 %i4 = arith.constant 4 : i32
%a = arith.constant dense<[1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0]> : vector<8xf32> %a = arith.constant dense<[1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0]> : vector<8xf32>
%b = arith.constant dense<[9.0, 10.0, 11.0, 12.0, 13.0, 14.0, 15.0, 16.0]> : vector<8xf32> %b = arith.constant dense<[9.0, 10.0, 11.0, 12.0, 13.0, 14.0, 15.0, 16.0]> : vector<8xf32>
Show All 13 Lines

mlir/test/Integration/Dialect/Vector/CPU/X86Vector/test-inline-asm-vector-avx512.mlir

// RUN: mlir-opt %s -convert-linalg-to-loops -convert-vector-to-scf='full-unroll=true' -lower-affine -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm='use-bare-ptr-memref-call-conv=1' -convert-arith-to-llvm -reconcile-unrealized-casts |\ // RUN: mlir-opt %s -convert-linalg-to-loops -convert-vector-to-scf='full-unroll=true' -lower-affine -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm='use-bare-ptr-memref-call-conv=1' -convert-arith-to-llvm -reconcile-unrealized-casts |\
// RUN: mlir-translate --mlir-to-llvmir |\ // RUN: mlir-translate --mlir-to-llvmir |\
// RUN: %lli --entry-function=entry --mattr="avx512f" --dlopen=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext |\ // RUN: %lli --entry-function=entry --mattr="avx512f" --dlopen=%mlir_lib_dir/libmlir_c_runner_utils%shlibext |\
// RUN: FileCheck %s // RUN: FileCheck %s
module { module {
// an array of 16 i32 of values [0..15] // an array of 16 i32 of values [0..15]
llvm.mlir.global private @const16( llvm.mlir.global private @const16(
dense<[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15]> : tensor<16 x i32>) dense<[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15]> : tensor<16 x i32>)
: !llvm.array<16 x i32> : !llvm.array<16 x i32>
Show All 30 Lines

mlir/test/Integration/Dialect/Vector/CPU/X86Vector/test-mask-compress.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm="enable-x86vector" -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm="enable-x86vector" -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-translate --mlir-to-llvmir | \ // RUN: mlir-translate --mlir-to-llvmir | \
// RUN: %lli --entry-function=entry --mattr="avx512bw" --dlopen=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: %lli --entry-function=entry --mattr="avx512bw" --dlopen=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() -> i32 { func.func @entry() -> i32 {
%i0 = arith.constant 0 : i32 %i0 = arith.constant 0 : i32
%a = arith.constant dense<[1., 0., 0., 2., 4., 3., 5., 7., 8., 1., 5., 5., 3., 1., 0., 7.]> : vector<16xf32> %a = arith.constant dense<[1., 0., 0., 2., 4., 3., 5., 7., 8., 1., 5., 5., 3., 1., 0., 7.]> : vector<16xf32>
%k = arith.constant dense<[1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0]> : vector<16xi1> %k = arith.constant dense<[1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0]> : vector<16xi1>
%r1 = x86vector.avx512.mask.compress %k, %a : vector<16xf32> %r1 = x86vector.avx512.mask.compress %k, %a : vector<16xf32>
Show All 16 Lines

mlir/test/Integration/Dialect/Vector/CPU/X86Vector/test-rsqrt.mlir

// RUN: mlir-opt %s -convert-vector-to-llvm="enable-x86vector" -convert-func-to-llvm | \ // RUN: mlir-opt %s -convert-vector-to-llvm="enable-x86vector" -convert-func-to-llvm | \
// RUN: mlir-translate --mlir-to-llvmir | \ // RUN: mlir-translate --mlir-to-llvmir | \
// RUN: %lli --entry-function=entry --mattr="avx" --dlopen=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: %lli --entry-function=entry --mattr="avx" --dlopen=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() -> i32 { func.func @entry() -> i32 {
%i0 = arith.constant 0 : i32 %i0 = arith.constant 0 : i32
%v = arith.constant dense<[0.125, 0.25, 0.5, 1.0, 2.0, 4.0, 8.0, 16.0]> : vector<8xf32> %v = arith.constant dense<[0.125, 0.25, 0.5, 1.0, 2.0, 4.0, 8.0, 16.0]> : vector<8xf32>
%r = x86vector.avx.rsqrt %v : vector<8xf32> %r = x86vector.avx.rsqrt %v : vector<8xf32>
// `rsqrt` may produce slightly different results on Intel and AMD machines: accept both results here. // `rsqrt` may produce slightly different results on Intel and AMD machines: accept both results here.
// CHECK: {{( 2.82[0-9]*, 1.99[0-9]*, 1.41[0-9]*, 0.99[0-9]*, 0.70[0-9]*, 0.49[0-9]*, 0.35[0-9]*, 0.24[0-9]* )}} // CHECK: {{( 2.82[0-9]*, 1.99[0-9]*, 1.41[0-9]*, 0.99[0-9]*, 0.70[0-9]*, 0.49[0-9]*, 0.35[0-9]*, 0.24[0-9]* )}}
vector.print %r : vector<8xf32> vector.print %r : vector<8xf32>
return %i0 : i32 return %i0 : i32
} }

mlir/test/Integration/Dialect/Vector/CPU/X86Vector/test-sparse-dot-product.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm="enable-x86vector" -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm="enable-x86vector" -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-translate --mlir-to-llvmir | \ // RUN: mlir-translate --mlir-to-llvmir | \
// RUN: %lli --entry-function=entry --mattr="avx512bw,avx512vp2intersect" --dlopen=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: %lli --entry-function=entry --mattr="avx512bw,avx512vp2intersect" --dlopen=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// This test shows how to implement a sparse vector-vector dot product with // This test shows how to implement a sparse vector-vector dot product with
// AVX512. It uses vp2intersect, mask.compress and vector.contract to compute // AVX512. It uses vp2intersect, mask.compress and vector.contract to compute
// the dot product of two sparse HW vectors of 8 float64 elements ("segment"). // the dot product of two sparse HW vectors of 8 float64 elements ("segment").
// Each sparse vector is represented by an index memref (A or C) and by a data // Each sparse vector is represented by an index memref (A or C) and by a data
// memref (B or D), containing M or N elements. // memref (B or D), containing M or N elements.
// //
▲ Show 20 Lines • Show All 466 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/X86Vector/test-vp2intersect-i32.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm="enable-x86vector" -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm="enable-x86vector" -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-translate --mlir-to-llvmir | \ // RUN: mlir-translate --mlir-to-llvmir | \
// RUN: %lli --entry-function=entry --mattr="avx512bw,avx512vp2intersect" --dlopen=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: %lli --entry-function=entry --mattr="avx512bw,avx512vp2intersect" --dlopen=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// Note: To run this test, your CPU must support AVX512 vp2intersect. // Note: To run this test, your CPU must support AVX512 vp2intersect.
func.func @entry() -> i32 { func.func @entry() -> i32 {
%i0 = arith.constant 0 : i32 %i0 = arith.constant 0 : i32
%i1 = arith.constant 1: i32 %i1 = arith.constant 1: i32
%i2 = arith.constant 2: i32 %i2 = arith.constant 2: i32
▲ Show 20 Lines • Show All 41 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-0-d-vectors.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @extract_element_0d(%a: vector<f32>) { func.func @extract_element_0d(%a: vector<f32>) {
%1 = vector.extractelement %a[] : vector<f32> %1 = vector.extractelement %a[] : vector<f32>
// CHECK: 42 // CHECK: 42
vector.print %1: f32 vector.print %1: f32
return return
} }
▲ Show 20 Lines • Show All 163 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-broadcast.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
%i = arith.constant 2147483647: i32 %i = arith.constant 2147483647: i32
%l = arith.constant 9223372036854775807 : i64 %l = arith.constant 9223372036854775807 : i64
%f0 = arith.constant 0.0: f32 %f0 = arith.constant 0.0: f32
%f1 = arith.constant 1.0: f32 %f1 = arith.constant 1.0: f32
▲ Show 20 Lines • Show All 71 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-compress.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @compress16(%base: memref<?xf32>, func.func @compress16(%base: memref<?xf32>,
%mask: vector<16xi1>, %value: vector<16xf32>) { %mask: vector<16xi1>, %value: vector<16xf32>) {
%c0 = arith.constant 0: index %c0 = arith.constant 0: index
vector.compressstore %base[%c0], %mask, %value vector.compressstore %base[%c0], %mask, %value
: memref<?xf32>, vector<16xi1>, vector<16xf32> : memref<?xf32>, vector<16xi1>, vector<16xf32>
return return
▲ Show 20 Lines • Show All 94 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-constant-mask.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
%0 = vector.constant_mask [4] : vector<8xi1> %0 = vector.constant_mask [4] : vector<8xi1>
vector.print %0 : vector<8xi1> vector.print %0 : vector<8xi1>
// CHECK: ( 1, 1, 1, 1, 0, 0, 0, 0 ) // CHECK: ( 1, 1, 1, 1, 0, 0, 0, 0 )
%1 = vector.constant_mask [1, 3] : vector<4x4xi1> %1 = vector.constant_mask [1, 3] : vector<4x4xi1>
Show All 38 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-contraction.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#dotp_accesses = [ #dotp_accesses = [
affine_map<(i) -> (i)>, affine_map<(i) -> (i)>,
affine_map<(i) -> (i)>, affine_map<(i) -> (i)>,
affine_map<(i) -> ()> affine_map<(i) -> ()>
] ]
#dotp_trait = { #dotp_trait = {
▲ Show 20 Lines • Show All 372 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-create-mask-v4i1.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// NOTE: This is similar to test-create-mask.mlir, but with a different length, // NOTE: This is similar to test-create-mask.mlir, but with a different length,
// because the v4i1 vector specifically exposed bugs in the LLVM backend. // because the v4i1 vector specifically exposed bugs in the LLVM backend.
func.func @entry() { func.func @entry() {
%c0 = arith.constant 0 : index %c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index %c1 = arith.constant 1 : index
▲ Show 20 Lines • Show All 88 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-create-mask.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
%cneg1 = arith.constant -1 : index %cneg1 = arith.constant -1 : index
%c0 = arith.constant 0 : index %c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index %c1 = arith.constant 1 : index
%c2 = arith.constant 2 : index %c2 = arith.constant 2 : index
%c3 = arith.constant 3 : index %c3 = arith.constant 3 : index
▲ Show 20 Lines • Show All 103 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-expand.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @expand16(%base: memref<?xf32>, func.func @expand16(%base: memref<?xf32>,
%mask: vector<16xi1>, %mask: vector<16xi1>,
%pass_thru: vector<16xf32>) -> vector<16xf32> { %pass_thru: vector<16xf32>) -> vector<16xf32> {
%c0 = arith.constant 0: index %c0 = arith.constant 0: index
%e = vector.expandload %base[%c0], %mask, %pass_thru %e = vector.expandload %base[%c0], %mask, %pass_thru
: memref<?xf32>, vector<16xi1>, vector<16xf32> into vector<16xf32> : memref<?xf32>, vector<16xi1>, vector<16xf32> into vector<16xf32>
▲ Show 20 Lines • Show All 87 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-extract-strided-slice.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
%f0 = arith.constant 0.0: f32 %f0 = arith.constant 0.0: f32
%f1 = arith.constant 1.0: f32 %f1 = arith.constant 1.0: f32
%f2 = arith.constant 2.0: f32 %f2 = arith.constant 2.0: f32
%f3 = arith.constant 3.0: f32 %f3 = arith.constant 3.0: f32
%f4 = arith.constant 4.0: f32 %f4 = arith.constant 4.0: f32
Show All 21 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-flat-transpose-col.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -O0 -enable-matrix -matrix-allow-contract -matrix-default-layout=column-major \ // RUN: -O0 -enable-matrix -matrix-allow-contract -matrix-default-layout=column-major \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
%f0 = arith.constant 0.0: f64 %f0 = arith.constant 0.0: f64
%f1 = arith.constant 1.0: f64 %f1 = arith.constant 1.0: f64
%f2 = arith.constant 2.0: f64 %f2 = arith.constant 2.0: f64
%f3 = arith.constant 3.0: f64 %f3 = arith.constant 3.0: f64
%f4 = arith.constant 4.0: f64 %f4 = arith.constant 4.0: f64
▲ Show 20 Lines • Show All 66 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-flat-transpose-row.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -O0 -enable-matrix -matrix-allow-contract -matrix-default-layout=row-major \ // RUN: -O0 -enable-matrix -matrix-allow-contract -matrix-default-layout=row-major \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
%f0 = arith.constant 0.0: f64 %f0 = arith.constant 0.0: f64
%f1 = arith.constant 1.0: f64 %f1 = arith.constant 1.0: f64
%f2 = arith.constant 2.0: f64 %f2 = arith.constant 2.0: f64
%f3 = arith.constant 3.0: f64 %f3 = arith.constant 3.0: f64
%f4 = arith.constant 4.0: f64 %f4 = arith.constant 4.0: f64
▲ Show 20 Lines • Show All 66 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-fma.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
%f1 = arith.constant 1.0: f32 %f1 = arith.constant 1.0: f32
%f3 = arith.constant 3.0: f32 %f3 = arith.constant 3.0: f32
%f7 = arith.constant 7.0: f32 %f7 = arith.constant 7.0: f32
%v1 = vector.broadcast %f1 : f32 to vector<8xf32> %v1 = vector.broadcast %f1 : f32 to vector<8xf32>
%v3 = vector.broadcast %f3 : f32 to vector<8xf32> %v3 = vector.broadcast %f3 : f32 to vector<8xf32>
Show All 17 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-gather.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @gather8(%base: memref<?xf32>, %indices: vector<8xi32>, func.func @gather8(%base: memref<?xf32>, %indices: vector<8xi32>,
%mask: vector<8xi1>, %pass_thru: vector<8xf32>) -> vector<8xf32> { %mask: vector<8xi1>, %pass_thru: vector<8xf32>) -> vector<8xf32> {
%c0 = arith.constant 0: index %c0 = arith.constant 0: index
%g = vector.gather %base[%c0][%indices], %mask, %pass_thru %g = vector.gather %base[%c0][%indices], %mask, %pass_thru
: memref<?xf32>, vector<8xi32>, vector<8xi1>, vector<8xf32> into vector<8xf32> : memref<?xf32>, vector<8xi32>, vector<8xi1>, vector<8xf32> into vector<8xf32>
return %g : vector<8xf32> return %g : vector<8xf32>
▲ Show 20 Lines • Show All 80 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-index-vectors.mlir

// RUN: mlir-opt %s -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
%c0 = arith.constant dense<[0, 1, 2, 3]>: vector<4xindex> %c0 = arith.constant dense<[0, 1, 2, 3]>: vector<4xindex>
%c1 = arith.constant dense<[0, 1]>: vector<2xindex> %c1 = arith.constant dense<[0, 1]>: vector<2xindex>
%c2 = arith.constant 2 : index %c2 = arith.constant 2 : index
%v1 = vector.broadcast %c0 : vector<4xindex> to vector<2x4xindex> %v1 = vector.broadcast %c0 : vector<4xindex> to vector<2x4xindex>
Show All 21 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-insert-strided-slice.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
%f1 = arith.constant 1.0: f32 %f1 = arith.constant 1.0: f32
%f2 = arith.constant 2.0: f32 %f2 = arith.constant 2.0: f32
%f3 = arith.constant 3.0: f32 %f3 = arith.constant 3.0: f32
%f4 = arith.constant 4.0: f32 %f4 = arith.constant 4.0: f32
%v1 = vector.broadcast %f1 : f32 to vector<4xf32> %v1 = vector.broadcast %f1 : f32 to vector<4xf32>
Show All 25 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-maskedload.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @maskedload16(%base: memref<?xf32>, %mask: vector<16xi1>, func.func @maskedload16(%base: memref<?xf32>, %mask: vector<16xi1>,
%pass_thru: vector<16xf32>) -> vector<16xf32> { %pass_thru: vector<16xf32>) -> vector<16xf32> {
%c0 = arith.constant 0: index %c0 = arith.constant 0: index
%ld = vector.maskedload %base[%c0], %mask, %pass_thru %ld = vector.maskedload %base[%c0], %mask, %pass_thru
: memref<?xf32>, vector<16xi1>, vector<16xf32> into vector<16xf32> : memref<?xf32>, vector<16xi1>, vector<16xf32> into vector<16xf32>
return %ld : vector<16xf32> return %ld : vector<16xf32>
▲ Show 20 Lines • Show All 70 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-maskedstore.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @maskedstore16(%base: memref<?xf32>, func.func @maskedstore16(%base: memref<?xf32>,
%mask: vector<16xi1>, %value: vector<16xf32>) { %mask: vector<16xi1>, %value: vector<16xf32>) {
%c0 = arith.constant 0: index %c0 = arith.constant 0: index
vector.maskedstore %base[%c0], %mask, %value vector.maskedstore %base[%c0], %mask, %value
: memref<?xf32>, vector<16xi1>, vector<16xf32> : memref<?xf32>, vector<16xi1>, vector<16xf32>
return return
▲ Show 20 Lines • Show All 93 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-matrix-multiply-col.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -O0 -enable-matrix -matrix-allow-contract -matrix-default-layout=column-major \ // RUN: -O0 -enable-matrix -matrix-allow-contract -matrix-default-layout=column-major \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
%f0 = arith.constant 0.0: f64 %f0 = arith.constant 0.0: f64
%f1 = arith.constant 1.0: f64 %f1 = arith.constant 1.0: f64
%f2 = arith.constant 2.0: f64 %f2 = arith.constant 2.0: f64
%f3 = arith.constant 3.0: f64 %f3 = arith.constant 3.0: f64
%f4 = arith.constant 4.0: f64 %f4 = arith.constant 4.0: f64
▲ Show 20 Lines • Show All 41 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-matrix-multiply-row.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -O0 -enable-matrix -matrix-allow-contract -matrix-default-layout=row-major \ // RUN: -O0 -enable-matrix -matrix-allow-contract -matrix-default-layout=row-major \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
%f0 = arith.constant 0.0: f64 %f0 = arith.constant 0.0: f64
%f1 = arith.constant 1.0: f64 %f1 = arith.constant 1.0: f64
%f2 = arith.constant 2.0: f64 %f2 = arith.constant 2.0: f64
%f3 = arith.constant 3.0: f64 %f3 = arith.constant 3.0: f64
%f4 = arith.constant 4.0: f64 %f4 = arith.constant 4.0: f64
▲ Show 20 Lines • Show All 41 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-outerproduct-f32.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
!vector_type_A = vector<8xf32> !vector_type_A = vector<8xf32>
!vector_type_B = vector<8xf32> !vector_type_B = vector<8xf32>
!vector_type_C = vector<8x8xf32> !vector_type_C = vector<8x8xf32>
!vector_type_X = vector<2xf32> !vector_type_X = vector<2xf32>
!vector_type_Y = vector<3xf32> !vector_type_Y = vector<3xf32>
▲ Show 20 Lines • Show All 89 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-outerproduct-i64.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
!vector_type_A = vector<8xi64> !vector_type_A = vector<8xi64>
!vector_type_B = vector<8xi64> !vector_type_B = vector<8xi64>
!vector_type_C = vector<8x8xi64> !vector_type_C = vector<8x8xi64>
!vector_type_X = vector<2xi64> !vector_type_X = vector<2xi64>
!vector_type_Y = vector<3xi64> !vector_type_Y = vector<3xi64>
▲ Show 20 Lines • Show All 89 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-print-int.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// //
// Test various signless, signed, unsigned integer types. // Test various signless, signed, unsigned integer types.
// //
func.func @entry() { func.func @entry() {
%0 = arith.constant dense<[true, false, -1, 0, 1]> : vector<5xi1> %0 = arith.constant dense<[true, false, -1, 0, 1]> : vector<5xi1>
vector.print %0 : vector<5xi1> vector.print %0 : vector<5xi1>
▲ Show 20 Lines • Show All 75 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-reductions-f32-reassoc.mlir

// RUN: mlir-opt %s -convert-scf-to-cf \ // RUN: mlir-opt %s -convert-scf-to-cf \
// RUN: -convert-vector-to-llvm='reassociate-fp-reductions' \ // RUN: -convert-vector-to-llvm='reassociate-fp-reductions' \
// RUN: -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
// Construct test vector, numerically very stable. // Construct test vector, numerically very stable.
%f1 = arith.constant 1.0: f32 %f1 = arith.constant 1.0: f32
%f2 = arith.constant 2.0: f32 %f2 = arith.constant 2.0: f32
%f3 = arith.constant 3.0: f32 %f3 = arith.constant 3.0: f32
%v0 = vector.broadcast %f1 : f32 to vector<64xf32> %v0 = vector.broadcast %f1 : f32 to vector<64xf32>
Show All 25 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-reductions-f32.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
// Construct test vector. // Construct test vector.
%f1 = arith.constant 1.5: f32 %f1 = arith.constant 1.5: f32
%f2 = arith.constant 2.0: f32 %f2 = arith.constant 2.0: f32
%f3 = arith.constant 3.0: f32 %f3 = arith.constant 3.0: f32
%f4 = arith.constant 4.0: f32 %f4 = arith.constant 4.0: f32
Show All 39 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-reductions-f64-reassoc.mlir

// RUN: mlir-opt %s -convert-scf-to-cf \ // RUN: mlir-opt %s -convert-scf-to-cf \
// RUN: -convert-vector-to-llvm='reassociate-fp-reductions' \ // RUN: -convert-vector-to-llvm='reassociate-fp-reductions' \
// RUN: -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
// Construct test vector, numerically very stable. // Construct test vector, numerically very stable.
%f1 = arith.constant 1.0: f64 %f1 = arith.constant 1.0: f64
%f2 = arith.constant 2.0: f64 %f2 = arith.constant 2.0: f64
%f3 = arith.constant 3.0: f64 %f3 = arith.constant 3.0: f64
%v0 = vector.broadcast %f1 : f64 to vector<64xf64> %v0 = vector.broadcast %f1 : f64 to vector<64xf64>
Show All 25 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-reductions-f64.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
// Construct test vector. // Construct test vector.
%f1 = arith.constant 1.5: f64 %f1 = arith.constant 1.5: f64
%f2 = arith.constant 2.0: f64 %f2 = arith.constant 2.0: f64
%f3 = arith.constant 3.0: f64 %f3 = arith.constant 3.0: f64
%f4 = arith.constant 4.0: f64 %f4 = arith.constant 4.0: f64
Show All 39 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-reductions-i32.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
// Construct test vector. // Construct test vector.
%i1 = arith.constant 1: i32 %i1 = arith.constant 1: i32
%i2 = arith.constant 2: i32 %i2 = arith.constant 2: i32
%i3 = arith.constant 3: i32 %i3 = arith.constant 3: i32
%i4 = arith.constant 4: i32 %i4 = arith.constant 4: i32
▲ Show 20 Lines • Show All 48 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-reductions-i4.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
%v = arith.constant dense<[-8, -7, -6, -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15]> : vector<24xi4> %v = arith.constant dense<[-8, -7, -6, -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15]> : vector<24xi4>
vector.print %v : vector<24xi4> vector.print %v : vector<24xi4>
// //
// Test vector: // Test vector:
// //
Show All 33 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-reductions-i64.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
// Construct test vector. // Construct test vector.
%i1 = arith.constant 1: i64 %i1 = arith.constant 1: i64
%i2 = arith.constant 2: i64 %i2 = arith.constant 2: i64
%i3 = arith.constant 3: i64 %i3 = arith.constant 3: i64
%i4 = arith.constant 4: i64 %i4 = arith.constant 4: i64
▲ Show 20 Lines • Show All 48 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-reductions-si4.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
%v0 = arith.constant dense<[-8, -7, -6, -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7]> : vector<16xi4> %v0 = arith.constant dense<[-8, -7, -6, -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7]> : vector<16xi4>
%v = vector.bitcast %v0 : vector<16xi4> to vector<16xsi4> %v = vector.bitcast %v0 : vector<16xi4> to vector<16xsi4>
vector.print %v : vector<16xsi4> vector.print %v : vector<16xsi4>
// //
// Test vector: // Test vector:
Show All 33 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-reductions-ui4.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
%v0 = arith.constant dense<[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15]> : vector<16xi4> %v0 = arith.constant dense<[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15]> : vector<16xi4>
%v = vector.bitcast %v0 : vector<16xi4> to vector<16xui4> %v = vector.bitcast %v0 : vector<16xi4> to vector<16xui4>
vector.print %v : vector<16xui4> vector.print %v : vector<16xui4>
// //
// Test vector: // Test vector:
Show All 33 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-scan.mlir

// RUN: mlir-opt %s -test-vector-scan-lowering -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -test-vector-scan-lowering -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
%f1 = arith.constant 1.0: f32 %f1 = arith.constant 1.0: f32
%f2 = arith.constant 2.0: f32 %f2 = arith.constant 2.0: f32
%f3 = arith.constant 3.0: f32 %f3 = arith.constant 3.0: f32
%f4 = arith.constant 4.0: f32 %f4 = arith.constant 4.0: f32
%f5 = arith.constant 5.0: f32 %f5 = arith.constant 5.0: f32
▲ Show 20 Lines • Show All 43 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-scatter.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @scatter8(%base: memref<?xf32>, func.func @scatter8(%base: memref<?xf32>,
%indices: vector<8xi32>, %indices: vector<8xi32>,
%mask: vector<8xi1>, %value: vector<8xf32>) { %mask: vector<8xi1>, %value: vector<8xf32>) {
%c0 = arith.constant 0: index %c0 = arith.constant 0: index
vector.scatter %base[%c0][%indices], %mask, %value vector.scatter %base[%c0][%indices], %mask, %value
: memref<?xf32>, vector<8xi32>, vector<8xi1>, vector<8xf32> : memref<?xf32>, vector<8xi32>, vector<8xi1>, vector<8xf32>
▲ Show 20 Lines • Show All 108 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-shape-cast.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
%f1 = arith.constant 1.0: f32 %f1 = arith.constant 1.0: f32
%f2 = arith.constant 2.0: f32 %f2 = arith.constant 2.0: f32
%f3 = arith.constant 3.0: f32 %f3 = arith.constant 3.0: f32
%f4 = arith.constant 4.0: f32 %f4 = arith.constant 4.0: f32
%f5 = arith.constant 5.0: f32 %f5 = arith.constant 5.0: f32
Show All 33 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-shuffle.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
%f1 = arith.constant 1.0: f32 %f1 = arith.constant 1.0: f32
%f2 = arith.constant 2.0: f32 %f2 = arith.constant 2.0: f32
%v1 = vector.broadcast %f1 : f32 to vector<2x4xf32> %v1 = vector.broadcast %f1 : f32 to vector<2x4xf32>
%v2 = vector.broadcast %f2 : f32 to vector<2x4xf32> %v2 = vector.broadcast %f2 : f32 to vector<2x4xf32>
vector.print %v1 : vector<2x4xf32> vector.print %v1 : vector<2x4xf32>
Show All 13 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-sparse-dot-matvec.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// Illustrates an 8x8 Sparse Matrix x Vector implemented with only operations // Illustrates an 8x8 Sparse Matrix x Vector implemented with only operations
// of the vector dialect (and some std/scf). Essentially, this example performs // of the vector dialect (and some std/scf). Essentially, this example performs
// the following multiplication: // the following multiplication:
// //
// 0 1 2 3 4 5 6 7 // 0 1 2 3 4 5 6 7
// +------------------------+ // +------------------------+
▲ Show 20 Lines • Show All 260 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-sparse-saxpy-jagged-matvec.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// Illustrates an 8x8 Sparse Matrix x Vector implemented with only operations // Illustrates an 8x8 Sparse Matrix x Vector implemented with only operations
// of the vector dialect (and some std/scf). Essentially, this example performs // of the vector dialect (and some std/scf). Essentially, this example performs
// the following multiplication: // the following multiplication:
// //
// 0 1 2 3 4 5 6 7 // 0 1 2 3 4 5 6 7
// +------------------------+ // +------------------------+
▲ Show 20 Lines • Show All 224 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-transfer-read-1d.mlir

// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf,lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf,lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{lower-permutation-maps=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{lower-permutation-maps=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{full-unroll=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{full-unroll=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{full-unroll=true lower-permutation-maps=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{full-unroll=true lower-permutation-maps=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// Test for special cases of 1D vector transfer ops. // Test for special cases of 1D vector transfer ops.
memref.global "private" @gv : memref<5x6xf32> = memref.global "private" @gv : memref<5x6xf32> =
dense<[[0. , 1. , 2. , 3. , 4. , 5. ], dense<[[0. , 1. , 2. , 3. , 4. , 5. ],
[10., 11., 12., 13., 14., 15.], [10., 11., 12., 13., 14., 15.],
[20., 21., 22., 23., 24., 25.], [20., 21., 22., 23., 24., 25.],
▲ Show 20 Lines • Show All 202 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-transfer-read-2d.mlir

// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf,lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf,lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{lower-permutation-maps=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{lower-permutation-maps=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{full-unroll=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{full-unroll=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{full-unroll=true lower-permutation-maps=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{full-unroll=true lower-permutation-maps=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
memref.global "private" @gv : memref<3x4xf32> = dense<[[0. , 1. , 2. , 3. ], memref.global "private" @gv : memref<3x4xf32> = dense<[[0. , 1. , 2. , 3. ],
[10., 11., 12., 13.], [10., 11., 12., 13.],
[20., 21., 22., 23.]]> [20., 21., 22., 23.]]>
// Vector load. // Vector load.
func.func @transfer_read_2d(%A : memref<?x?xf32>, %base1: index, %base2: index) { func.func @transfer_read_2d(%A : memref<?x?xf32>, %base1: index, %base2: index) {
▲ Show 20 Lines • Show All 170 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-transfer-read-3d.mlir

// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf,lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf,lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{lower-permutation-maps=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{lower-permutation-maps=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{full-unroll=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{full-unroll=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{full-unroll=true lower-permutation-maps=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{full-unroll=true lower-permutation-maps=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @transfer_read_3d(%A : memref<?x?x?x?xf32>, func.func @transfer_read_3d(%A : memref<?x?x?x?xf32>,
%o: index, %a: index, %b: index, %c: index) { %o: index, %a: index, %b: index, %c: index) {
%fm42 = arith.constant -42.0: f32 %fm42 = arith.constant -42.0: f32
%f = vector.transfer_read %A[%o, %a, %b, %c], %fm42 %f = vector.transfer_read %A[%o, %a, %b, %c], %fm42
: memref<?x?x?x?xf32>, vector<2x5x3xf32> : memref<?x?x?x?xf32>, vector<2x5x3xf32>
vector.print %f: vector<2x5x3xf32> vector.print %f: vector<2x5x3xf32>
▲ Show 20 Lines • Show All 123 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-transfer-read.mlir

// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf,lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf,lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{full-unroll=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{full-unroll=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @transfer_read_1d(%A : memref<?xf32>, %base: index) { func.func @transfer_read_1d(%A : memref<?xf32>, %base: index) {
%fm42 = arith.constant -42.0: f32 %fm42 = arith.constant -42.0: f32
%f = vector.transfer_read %A[%base], %fm42 %f = vector.transfer_read %A[%base], %fm42
{permutation_map = affine_map<(d0) -> (d0)>} : {permutation_map = affine_map<(d0) -> (d0)>} :
memref<?xf32>, vector<13xf32> memref<?xf32>, vector<13xf32>
vector.print %f: vector<13xf32> vector.print %f: vector<13xf32>
▲ Show 20 Lines • Show All 79 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-transfer-to-loops.mlir

// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf,lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf,lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext,%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext,%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{full-unroll=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf{full-unroll=true},lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext,%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext,%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
#map0 = affine_map<(d0, d1) -> (d1, d0)> #map0 = affine_map<(d0, d1) -> (d1, d0)>
#map1 = affine_map<(d0, d1) -> (d1)> #map1 = affine_map<(d0, d1) -> (d1)>
func.func private @printMemrefF32(memref<*xf32>) func.func private @printMemrefF32(memref<*xf32>)
func.func @alloc_2d_filled_f32(%arg0: index, %arg1: index) -> memref<?x?xf32> { func.func @alloc_2d_filled_f32(%arg0: index, %arg1: index) -> memref<?x?xf32> {
▲ Show 20 Lines • Show All 94 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-transfer-write.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @transfer_write16_inbounds_1d(%A : memref<?xf32>, %base: index) { func.func @transfer_write16_inbounds_1d(%A : memref<?xf32>, %base: index) {
%f = arith.constant 16.0 : f32 %f = arith.constant 16.0 : f32
%v = vector.splat %f : vector<16xf32> %v = vector.splat %f : vector<16xf32>
vector.transfer_write %v, %A[%base] vector.transfer_write %v, %A[%base]
{permutation_map = affine_map<(d0) -> (d0)>, in_bounds = [true]} {permutation_map = affine_map<(d0) -> (d0)>, in_bounds = [true]}
: vector<16xf32>, memref<?xf32> : vector<16xf32>, memref<?xf32>
▲ Show 20 Lines • Show All 91 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-transpose.mlir

// RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \ // RUN: mlir-opt %s -convert-scf-to-cf -convert-vector-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
// RUN: mlir-cpu-runner -e entry -entry-point-result=void \ // RUN: mlir-cpu-runner -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @entry() { func.func @entry() {
%f0 = arith.constant 0.0: f32 %f0 = arith.constant 0.0: f32
%f1 = arith.constant 1.0: f32 %f1 = arith.constant 1.0: f32
%f2 = arith.constant 2.0: f32 %f2 = arith.constant 2.0: f32
%f3 = arith.constant 3.0: f32 %f3 = arith.constant 3.0: f32
%f4 = arith.constant 4.0: f32 %f4 = arith.constant 4.0: f32
▲ Show 20 Lines • Show All 109 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/CPU/test-vector-distribute.mlir

// RUN: mlir-opt %s -pass-pipeline="func.func(test-vector-to-forloop,convert-vector-to-scf,lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt %s -pass-pipeline="func.func(test-vector-to-forloop,convert-vector-to-scf,lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf,lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e main \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-vector-to-scf,lower-affine,convert-scf-to-cf),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e main \
// RUN: -entry-point-result=void \ // RUN: -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// RUN: mlir-opt %s -pass-pipeline="func.func(test-vector-to-forloop)" | FileCheck %s -check-prefix=TRANSFORM // RUN: mlir-opt %s -pass-pipeline="func.func(test-vector-to-forloop)" | FileCheck %s -check-prefix=TRANSFORM
func.func private @printMemrefF32(memref<*xf32>) func.func private @printMemrefF32(memref<*xf32>)
func.func @alloc_1d_filled_inc_f32(%arg0: index, %arg1: f32) -> memref<?xf32> { func.func @alloc_1d_filled_inc_f32(%arg0: index, %arg1: f32) -> memref<?xf32> {
▲ Show 20 Lines • Show All 50 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/GPU/CUDA/test-reduction-distribute.mlir

// RUN: mlir-opt %s -test-vector-warp-distribute="hoist-uniform distribute-transfer-write propagate-distribution" -canonicalize |\ // RUN: mlir-opt %s -test-vector-warp-distribute="hoist-uniform distribute-transfer-write propagate-distribution" -canonicalize |\
// RUN: mlir-opt -test-vector-warp-distribute=rewrite-warp-ops-to-scf-if |\ // RUN: mlir-opt -test-vector-warp-distribute=rewrite-warp-ops-to-scf-if |\
// RUN: mlir-opt -lower-affine -convert-scf-to-cf -convert-vector-to-llvm \ // RUN: mlir-opt -lower-affine -convert-scf-to-cf -convert-vector-to-llvm \
// RUN: -convert-arith-to-llvm -gpu-kernel-outlining \ // RUN: -convert-arith-to-llvm -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,reconcile-unrealized-casts,gpu-to-cubin)' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,reconcile-unrealized-casts,gpu-to-cubin)' \
// RUN: -gpu-to-llvm -reconcile-unrealized-casts |\ // RUN: -gpu-to-llvm -reconcile-unrealized-casts |\
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_cuda_runtime%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// Run a tiled reduction fused with an elementwise op. // Run a tiled reduction fused with an elementwise op.
func.func @gpu_func(%in: memref<1024xf32>, %out: memref<1xf32>) { func.func @gpu_func(%in: memref<1024xf32>, %out: memref<1xf32>) {
%c1 = arith.constant 1 : index %c1 = arith.constant 1 : index
%cst = arith.constant dense<100.0000> : vector<1xf32> %cst = arith.constant dense<100.0000> : vector<1xf32>
%cst_0 = arith.constant 0.000000e+00 : f32 %cst_0 = arith.constant 0.000000e+00 : f32
▲ Show 20 Lines • Show All 51 Lines • Show Last 20 Lines

mlir/test/Integration/Dialect/Vector/GPU/CUDA/test-warp-distribute.mlir

// Run the test cases without distributing ops to test default lowering. Run // Run the test cases without distributing ops to test default lowering. Run
// everything on the same thread. // everything on the same thread.
// RUN: mlir-opt %s -test-vector-warp-distribute=rewrite-warp-ops-to-scf-if -canonicalize | \ // RUN: mlir-opt %s -test-vector-warp-distribute=rewrite-warp-ops-to-scf-if -canonicalize | \
// RUN: mlir-opt -convert-scf-to-cf -convert-cf-to-llvm -convert-vector-to-llvm -convert-arith-to-llvm \ // RUN: mlir-opt -convert-scf-to-cf -convert-cf-to-llvm -convert-vector-to-llvm -convert-arith-to-llvm \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,reconcile-unrealized-casts,gpu-to-cubin)' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,reconcile-unrealized-casts,gpu-to-cubin)' \
// RUN: -gpu-to-llvm -reconcile-unrealized-casts |\ // RUN: -gpu-to-llvm -reconcile-unrealized-casts |\
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_cuda_runtime%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// Run the same test cases with distribution and propagation. // Run the same test cases with distribution and propagation.
// RUN: mlir-opt %s -test-vector-warp-distribute="hoist-uniform distribute-transfer-write" \ // RUN: mlir-opt %s -test-vector-warp-distribute="hoist-uniform distribute-transfer-write" \
// RUN: -test-vector-warp-distribute=rewrite-warp-ops-to-scf-if -canonicalize | \ // RUN: -test-vector-warp-distribute=rewrite-warp-ops-to-scf-if -canonicalize | \
// RUN: mlir-opt -convert-scf-to-cf -convert-cf-to-llvm -convert-vector-to-llvm -convert-arith-to-llvm \ // RUN: mlir-opt -convert-scf-to-cf -convert-cf-to-llvm -convert-vector-to-llvm -convert-arith-to-llvm \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,reconcile-unrealized-casts,gpu-to-cubin)' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,reconcile-unrealized-casts,gpu-to-cubin)' \
// RUN: -gpu-to-llvm -reconcile-unrealized-casts |\ // RUN: -gpu-to-llvm -reconcile-unrealized-casts |\
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_cuda_runtime%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
// RUN: mlir-opt %s -test-vector-warp-distribute="hoist-uniform distribute-transfer-write propagate-distribution" \ // RUN: mlir-opt %s -test-vector-warp-distribute="hoist-uniform distribute-transfer-write propagate-distribution" \
// RUN: -test-vector-warp-distribute=rewrite-warp-ops-to-scf-if -canonicalize | \ // RUN: -test-vector-warp-distribute=rewrite-warp-ops-to-scf-if -canonicalize | \
// RUN: mlir-opt -convert-scf-to-cf -convert-cf-to-llvm -convert-vector-to-llvm -convert-arith-to-llvm \ // RUN: mlir-opt -convert-scf-to-cf -convert-cf-to-llvm -convert-vector-to-llvm -convert-arith-to-llvm \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,reconcile-unrealized-casts,gpu-to-cubin)' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,reconcile-unrealized-casts,gpu-to-cubin)' \
// RUN: -gpu-to-llvm -reconcile-unrealized-casts |\ // RUN: -gpu-to-llvm -reconcile-unrealized-casts |\
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_cuda_runtime%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext | \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext | \
// RUN: FileCheck %s // RUN: FileCheck %s
func.func @gpu_func(%arg1: memref<32xf32>, %arg2: memref<32xf32>) { func.func @gpu_func(%arg1: memref<32xf32>, %arg2: memref<32xf32>) {
%c1 = arith.constant 1 : index %c1 = arith.constant 1 : index
%c0 = arith.constant 0 : index %c0 = arith.constant 0 : index
%c32 = arith.constant 32 : index %c32 = arith.constant 32 : index
%cst = arith.constant 0.000000e+00 : f32 %cst = arith.constant 0.000000e+00 : f32
gpu.launch blocks(%arg3, %arg4, %arg5) gpu.launch blocks(%arg3, %arg4, %arg5)
Show All 37 Lines

mlir/test/Integration/GPU/CUDA/TensorCore/wmma-matmul-f16.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin{chip=sm_70})' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin{chip=sm_70})' \
// RUN: --convert-scf-to-cf -gpu-to-llvm \ // RUN: --convert-scf-to-cf -gpu-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_cuda_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --entry-point-result=void \ // RUN: --entry-point-result=void \
// RUN: | FileCheck %s // RUN: | FileCheck %s
// Test case to check the working of Tensor cores on Nvidia GPUs. The kernel has already // Test case to check the working of Tensor cores on Nvidia GPUs. The kernel has already
// been outlined to prevent crashing due to introduction of an empty basic block by --gpu- // been outlined to prevent crashing due to introduction of an empty basic block by --gpu-
// kernel-outling. // kernel-outling.
func.func @main() { func.func @main() {
%0 = memref.alloc() : memref<16x16xf16> %0 = memref.alloc() : memref<16x16xf16>
%22 = memref.alloc() : memref<16x16xf16> %22 = memref.alloc() : memref<16x16xf16>
▲ Show 20 Lines • Show All 71 Lines • Show Last 20 Lines

mlir/test/Integration/GPU/CUDA/TensorCore/wmma-matmul-f32.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin{chip=sm_70})' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin{chip=sm_70})' \
// RUN: --convert-scf-to-cf -gpu-to-llvm \ // RUN: --convert-scf-to-cf -gpu-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_cuda_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --entry-point-result=void \ // RUN: --entry-point-result=void \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func @main() { func.func @main() {
%0 = memref.alloc() : memref<16x16xf16> %0 = memref.alloc() : memref<16x16xf16>
%22 = memref.alloc() : memref<16x16xf32> %22 = memref.alloc() : memref<16x16xf32>
%1 = memref.alloc() : memref<16x16xf32> %1 = memref.alloc() : memref<16x16xf32>
▲ Show 20 Lines • Show All 59 Lines • Show Last 20 Lines

mlir/test/Integration/GPU/CUDA/all-reduce-and.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
// RUN: -gpu-to-llvm \ // RUN: -gpu-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_cuda_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --entry-point-result=void \ // RUN: --entry-point-result=void \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func @main() { func.func @main() {
%data = memref.alloc() : memref<2x6xi32> %data = memref.alloc() : memref<2x6xi32>
%sum = memref.alloc() : memref<2xi32> %sum = memref.alloc() : memref<2xi32>
%cst0 = arith.constant 0 : i32 %cst0 = arith.constant 0 : i32
%cst1 = arith.constant 1 : i32 %cst1 = arith.constant 1 : i32
▲ Show 20 Lines • Show All 55 Lines • Show Last 20 Lines

mlir/test/Integration/GPU/CUDA/all-reduce-max.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
// RUN: -gpu-to-llvm \ // RUN: -gpu-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_cuda_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --entry-point-result=void \ // RUN: --entry-point-result=void \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func @main() { func.func @main() {
%data = memref.alloc() : memref<2x6xi32> %data = memref.alloc() : memref<2x6xi32>
%sum = memref.alloc() : memref<2xi32> %sum = memref.alloc() : memref<2xi32>
%cst0 = arith.constant 0 : i32 %cst0 = arith.constant 0 : i32
%cst1 = arith.constant 1 : i32 %cst1 = arith.constant 1 : i32
▲ Show 20 Lines • Show All 55 Lines • Show Last 20 Lines

mlir/test/Integration/GPU/CUDA/all-reduce-min.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
// RUN: -gpu-to-llvm \ // RUN: -gpu-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_cuda_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --entry-point-result=void \ // RUN: --entry-point-result=void \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func @main() { func.func @main() {
%data = memref.alloc() : memref<2x6xi32> %data = memref.alloc() : memref<2x6xi32>
%sum = memref.alloc() : memref<2xi32> %sum = memref.alloc() : memref<2xi32>
%cst0 = arith.constant 0 : i32 %cst0 = arith.constant 0 : i32
%cst1 = arith.constant 1 : i32 %cst1 = arith.constant 1 : i32
▲ Show 20 Lines • Show All 55 Lines • Show Last 20 Lines

mlir/test/Integration/GPU/CUDA/all-reduce-op.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
// RUN: -gpu-to-llvm \ // RUN: -gpu-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_cuda_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --entry-point-result=void \ // RUN: --entry-point-result=void \
// RUN: | FileCheck %s // RUN: | FileCheck %s
// CHECK-COUNT-8: [{{(5356, ){12}5356}}] // CHECK-COUNT-8: [{{(5356, ){12}5356}}]
func.func @main() { func.func @main() {
%arg = memref.alloc() : memref<2x4x13xf32> %arg = memref.alloc() : memref<2x4x13xf32>
%dst = memref.cast %arg : memref<2x4x13xf32> to memref<?x?x?xf32> %dst = memref.cast %arg : memref<2x4x13xf32> to memref<?x?x?xf32>
%c0 = arith.constant 0 : index %c0 = arith.constant 0 : index
Show All 24 Lines

mlir/test/Integration/GPU/CUDA/all-reduce-or.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
// RUN: -gpu-to-llvm \ // RUN: -gpu-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_cuda_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --entry-point-result=void \ // RUN: --entry-point-result=void \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func @main() { func.func @main() {
%data = memref.alloc() : memref<2x6xi32> %data = memref.alloc() : memref<2x6xi32>
%sum = memref.alloc() : memref<2xi32> %sum = memref.alloc() : memref<2xi32>
%cst0 = arith.constant 0 : i32 %cst0 = arith.constant 0 : i32
%cst1 = arith.constant 1 : i32 %cst1 = arith.constant 1 : i32
▲ Show 20 Lines • Show All 55 Lines • Show Last 20 Lines

mlir/test/Integration/GPU/CUDA/all-reduce-region.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
// RUN: -gpu-to-llvm \ // RUN: -gpu-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_cuda_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --entry-point-result=void \ // RUN: --entry-point-result=void \
// RUN: | FileCheck %s // RUN: | FileCheck %s
// CHECK: [{{(35, ){34}35}}] // CHECK: [{{(35, ){34}35}}]
func.func @main() { func.func @main() {
%arg = memref.alloc() : memref<35xf32> %arg = memref.alloc() : memref<35xf32>
%dst = memref.cast %arg : memref<35xf32> to memref<?xf32> %dst = memref.cast %arg : memref<35xf32> to memref<?xf32>
%one = arith.constant 1 : index %one = arith.constant 1 : index
Show All 21 Lines

mlir/test/Integration/GPU/CUDA/all-reduce-xor.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
// RUN: -gpu-to-llvm \ // RUN: -gpu-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_cuda_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --entry-point-result=void \ // RUN: --entry-point-result=void \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func @main() { func.func @main() {
%data = memref.alloc() : memref<2x6xi32> %data = memref.alloc() : memref<2x6xi32>
%sum = memref.alloc() : memref<2xi32> %sum = memref.alloc() : memref<2xi32>
%cst0 = arith.constant 0 : i32 %cst0 = arith.constant 0 : i32
%cst1 = arith.constant 1 : i32 %cst1 = arith.constant 1 : i32
▲ Show 20 Lines • Show All 55 Lines • Show Last 20 Lines

mlir/test/Integration/GPU/CUDA/async.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
// RUN: -gpu-async-region -gpu-to-llvm \ // RUN: -gpu-async-region -gpu-to-llvm \
// RUN: -async-to-async-runtime -async-runtime-ref-counting \ // RUN: -async-to-async-runtime -async-runtime-ref-counting \
// RUN: -convert-async-to-llvm -convert-func-to-llvm \ // RUN: -convert-async-to-llvm -convert-func-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_cuda_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_async_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_async_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --entry-point-result=void -O0 \ // RUN: --entry-point-result=void -O0 \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func @main() { func.func @main() {
%c0 = arith.constant 0 : index %c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index %c1 = arith.constant 1 : index
%count = arith.constant 2 : index %count = arith.constant 2 : index
▲ Show 20 Lines • Show All 55 Lines • Show Last 20 Lines

mlir/test/Integration/GPU/CUDA/gpu-to-cubin.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
// RUN: -gpu-to-llvm \ // RUN: -gpu-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_cuda_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
// RUN: --entry-point-result=void \ // RUN: --entry-point-result=void \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func @other_func(%arg0 : f32, %arg1 : memref<?xf32>) { func.func @other_func(%arg0 : f32, %arg1 : memref<?xf32>) {
%cst = arith.constant 1 : index %cst = arith.constant 1 : index
%c0 = arith.constant 0 : index %c0 = arith.constant 0 : index
%cst2 = memref.dim %arg1, %c0 : memref<?xf32> %cst2 = memref.dim %arg1, %c0 : memref<?xf32>
gpu.launch blocks(%bx, %by, %bz) in (%grid_x = %cst, %grid_y = %cst, %grid_z = %cst) gpu.launch blocks(%bx, %by, %bz) in (%grid_x = %cst, %grid_y = %cst, %grid_z = %cst)
Show All 27 Lines

mlir/test/Integration/GPU/CUDA/multiple-all-reduce.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
// RUN: -gpu-to-llvm \ // RUN: -gpu-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_cuda_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --entry-point-result=void \ // RUN: --entry-point-result=void \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func @main() { func.func @main() {
%data = memref.alloc() : memref<2x6xf32> %data = memref.alloc() : memref<2x6xf32>
%sum = memref.alloc() : memref<2xf32> %sum = memref.alloc() : memref<2xf32>
%mul = memref.alloc() : memref<2xf32> %mul = memref.alloc() : memref<2xf32>
%cst0 = arith.constant 0.0 : f32 %cst0 = arith.constant 0.0 : f32
▲ Show 20 Lines • Show All 62 Lines • Show Last 20 Lines

mlir/test/Integration/GPU/CUDA/shuffle.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
// RUN: -gpu-to-llvm \ // RUN: -gpu-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_cuda_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --entry-point-result=void \ // RUN: --entry-point-result=void \
// RUN: | FileCheck %s // RUN: | FileCheck %s
// CHECK: [4, 5, 6, 7, 0, 1, 2, 3, 12, -1, -1, -1, 8] // CHECK: [4, 5, 6, 7, 0, 1, 2, 3, 12, -1, -1, -1, 8]
func.func @main() { func.func @main() {
%arg = memref.alloc() : memref<13xf32> %arg = memref.alloc() : memref<13xf32>
%dst = memref.cast %arg : memref<13xf32> to memref<?xf32> %dst = memref.cast %arg : memref<13xf32> to memref<?xf32>
%one = arith.constant 1 : index %one = arith.constant 1 : index
Show All 24 Lines

mlir/test/Integration/GPU/CUDA/two-modules.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin)' \
// RUN: -gpu-to-llvm \ // RUN: -gpu-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_cuda_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --entry-point-result=void \ // RUN: --entry-point-result=void \
// RUN: | FileCheck %s // RUN: | FileCheck %s
// CHECK: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12] // CHECK: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
func.func @main() { func.func @main() {
%arg = memref.alloc() : memref<13xi32> %arg = memref.alloc() : memref<13xi32>
%dst = memref.cast %arg : memref<13xi32> to memref<?xi32> %dst = memref.cast %arg : memref<13xi32> to memref<?xi32>
%one = arith.constant 1 : index %one = arith.constant 1 : index
Show All 21 Lines

mlir/test/Integration/GPU/ROCM/gpu-to-hsaco.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl,gpu-to-hsaco{chip=%chip})' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl,gpu-to-hsaco{chip=%chip})' \
// RUN: -gpu-to-llvm \ // RUN: -gpu-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_rocm_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_rocm_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --entry-point-result=void \ // RUN: --entry-point-result=void \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func @other_func(%arg0 : f32, %arg1 : memref<?xf32>) { func.func @other_func(%arg0 : f32, %arg1 : memref<?xf32>) {
%c0 = arith.constant 0 : index %c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index %c1 = arith.constant 1 : index
%block_dim = memref.dim %arg1, %c0 : memref<?xf32> %block_dim = memref.dim %arg1, %c0 : memref<?xf32>
gpu.launch blocks(%bx, %by, %bz) in (%grid_x = %c1, %grid_y = %c1, %grid_z = %c1) gpu.launch blocks(%bx, %by, %bz) in (%grid_x = %c1, %grid_y = %c1, %grid_z = %c1)
Show All 25 Lines

mlir/test/Integration/GPU/ROCM/printf.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl{index-bitwidth=32 runtime=HIP},gpu-to-hsaco{chip=%chip})' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl{index-bitwidth=32 runtime=HIP},gpu-to-hsaco{chip=%chip})' \
// RUN: -gpu-to-llvm \ // RUN: -gpu-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_rocm_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_rocm_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --entry-point-result=void \ // RUN: --entry-point-result=void \
// RUN: | FileCheck %s // RUN: | FileCheck %s
// CHECK: Hello from 0 // CHECK: Hello from 0
// CHECK: Hello from 1 // CHECK: Hello from 1
module attributes {gpu.container_module} { module attributes {gpu.container_module} {
gpu.module @kernels { gpu.module @kernels {
gpu.func @hello() kernel { gpu.func @hello() kernel {
Show All 15 Lines

mlir/test/Integration/GPU/ROCM/two-modules.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl,gpu-to-hsaco{chip=%chip})' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl,gpu-to-hsaco{chip=%chip})' \
// RUN: -gpu-to-llvm \ // RUN: -gpu-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_rocm_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_rocm_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --entry-point-result=void \ // RUN: --entry-point-result=void \
// RUN: | FileCheck %s // RUN: | FileCheck %s
// CHECK: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12] // CHECK: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
func.func @main() { func.func @main() {
%arg = memref.alloc() : memref<13xi32> %arg = memref.alloc() : memref<13xi32>
%dst = memref.cast %arg : memref<13xi32> to memref<?xi32> %dst = memref.cast %arg : memref<13xi32> to memref<?xi32>
%c0 = arith.constant 0 : index %c0 = arith.constant 0 : index
Show All 23 Lines

mlir/test/Integration/GPU/ROCM/vecadd.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -convert-scf-to-cf \ // RUN: -convert-scf-to-cf \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl{use-bare-ptr-memref-call-conv=true},gpu-to-hsaco{chip=%chip})' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl{use-bare-ptr-memref-call-conv=true},gpu-to-hsaco{chip=%chip})' \
// RUN: -gpu-to-llvm=use-bare-pointers-for-kernels=true \ // RUN: -gpu-to-llvm=use-bare-pointers-for-kernels=true \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_rocm_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_rocm_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --entry-point-result=void \ // RUN: --entry-point-result=void \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func @vecadd(%arg0 : memref<5xf32>, %arg1 : memref<5xf32>, %arg2 : memref<5xf32>) { func.func @vecadd(%arg0 : memref<5xf32>, %arg1 : memref<5xf32>, %arg2 : memref<5xf32>) {
%c0 = arith.constant 0 : index %c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index %c1 = arith.constant 1 : index
%block_dim = arith.constant 5 : index %block_dim = arith.constant 5 : index
gpu.launch blocks(%bx, %by, %bz) in (%grid_x = %c1, %grid_y = %c1, %grid_z = %c1) gpu.launch blocks(%bx, %by, %bz) in (%grid_x = %c1, %grid_y = %c1, %grid_z = %c1)
▲ Show 20 Lines • Show All 46 Lines • Show Last 20 Lines

mlir/test/Integration/GPU/ROCM/vector-transferops.mlir

// RUN: mlir-opt %s \ // RUN: mlir-opt %s \
// RUN: -convert-scf-to-cf \ // RUN: -convert-scf-to-cf \
// RUN: -gpu-kernel-outlining \ // RUN: -gpu-kernel-outlining \
// RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl{chipset=%chip index-bitwidth=32},gpu-to-hsaco{chip=%chip})' \ // RUN: -pass-pipeline='gpu.module(strip-debuginfo,convert-gpu-to-rocdl{chipset=%chip index-bitwidth=32},gpu-to-hsaco{chip=%chip})' \
// RUN: -gpu-to-llvm \ // RUN: -gpu-to-llvm \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_rocm_runtime%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_rocm_runtime%shlibext \
// RUN: --shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --entry-point-result=void \ // RUN: --entry-point-result=void \
// RUN: | FileCheck %s // RUN: | FileCheck %s
// TODO: swap for vector transfer reads if we ever create a --vector-to-amdgpu // TODO: swap for vector transfer reads if we ever create a --vector-to-amdgpu
func.func @vectransferx2(%arg0 : memref<?xf32>, %arg1 : memref<?xf32>) { func.func @vectransferx2(%arg0 : memref<?xf32>, %arg1 : memref<?xf32>) {
%cst = arith.constant 1 : index %cst = arith.constant 1 : index
gpu.launch blocks(%bx, %by, %bz) in (%grid_x = %cst, %grid_y = %cst, %grid_z = %cst) gpu.launch blocks(%bx, %by, %bz) in (%grid_x = %cst, %grid_y = %cst, %grid_z = %cst)
threads(%tx, %ty, %tz) in (%block_x = %cst, %block_y = %cst, %block_z = %cst) { threads(%tx, %ty, %tz) in (%block_x = %cst, %block_y = %cst, %block_z = %cst) {
▲ Show 20 Lines • Show All 74 Lines • Show Last 20 Lines

mlir/test/lit.cfg.py

Show First 20 Lines • Show All 71 Lines • ▼ Show 20 Lines
# The following tools are optional # The following tools are optional
tools.extend([ tools.extend([
ToolSubst('toy-ch1', unresolved='ignore'), ToolSubst('toy-ch1', unresolved='ignore'),
ToolSubst('toy-ch2', unresolved='ignore'), ToolSubst('toy-ch2', unresolved='ignore'),
ToolSubst('toy-ch3', unresolved='ignore'), ToolSubst('toy-ch3', unresolved='ignore'),
ToolSubst('toy-ch4', unresolved='ignore'), ToolSubst('toy-ch4', unresolved='ignore'),
ToolSubst('toy-ch5', unresolved='ignore'), ToolSubst('toy-ch5', unresolved='ignore'),
ToolSubst('%mlir_lib_dir', config.mlir_lib_dir, unresolved='ignore'), ToolSubst('%mlir_lib_dir', config.mlir_lib_dir, unresolved='ignore'),
ToolSubst('%mlir_src_dir', config.mlir_src_root, unresolved='ignore'),
# The substitutions below will be replaced by '%mlir_lib_dir' shortly. # The substitutions below will be replaced by '%mlir_lib_dir' shortly.
ToolSubst('%linalg_test_lib_dir', config.mlir_lib_dir, unresolved='ignore'), ToolSubst('%linalg_test_lib_dir', config.mlir_lib_dir, unresolved='ignore'),
ToolSubst('%mlir_runner_utils_dir', config.mlir_lib_dir, unresolved='ignore'), ToolSubst('%mlir_runner_utils_dir', config.mlir_lib_dir, unresolved='ignore'),
ToolSubst('%spirv_wrapper_library_dir', config.mlir_lib_dir, unresolved='ignore'), ToolSubst('%spirv_wrapper_library_dir', config.mlir_lib_dir, unresolved='ignore'),
ToolSubst('%vulkan_wrapper_library_dir', config.mlir_lib_dir, unresolved='ignore'), ToolSubst('%vulkan_wrapper_library_dir', config.mlir_lib_dir, unresolved='ignore'),
ToolSubst('%mlir_integration_test_dir', config.mlir_lib_dir, unresolved='ignore'), ToolSubst('%mlir_integration_test_dir', config.mlir_lib_dir, unresolved='ignore'),
]) ])
Show All 18 Lines
# it can be explicitly opted-in by prefixing the variable name with $ # it can be explicitly opted-in by prefixing the variable name with $
config.environment['FILECHECK_OPTS'] = "-enable-var-scope --allow-unused-prefixes=false" config.environment['FILECHECK_OPTS'] = "-enable-var-scope --allow-unused-prefixes=false"
# Add the python path for both the source and binary tree. # Add the python path for both the source and binary tree.
# Note that presently, the python sources come from the source tree and the # Note that presently, the python sources come from the source tree and the
# binaries come from the build tree. This should be unified to the build tree # binaries come from the build tree. This should be unified to the build tree
# by copying/linking sources to build. # by copying/linking sources to build.
if config.enable_bindings_python: if config.enable_bindings_python:
llvm_config.with_environment('PYTHONPATH', [ llvm_config.with_environment('PYTHONPATH', [
os.path.join(config.mlir_obj_root, 'python_packages', 'mlir_core'), os.path.join(config.mlir_obj_root, 'python_packages', 'mlir_core'),
os.path.join(config.mlir_obj_root, 'python_packages', 'mlir_test'), os.path.join(config.mlir_obj_root, 'python_packages', 'mlir_test'),
], append_path=True) ], append_path=True)
if config.enable_assertions: if config.enable_assertions:
config.available_features.add('asserts') config.available_features.add('asserts')
else: else:
config.available_features.add('noasserts') config.available_features.add('noasserts')
def have_host_jit_feature_support(feature_name): def have_host_jit_feature_support(feature_name):
mlir_cpu_runner_exe = lit.util.which('mlir-cpu-runner', config.mlir_tools_dir) mlir_cpu_runner_exe = lit.util.which('mlir-cpu-runner', config.mlir_tools_dir)
if not mlir_cpu_runner_exe: if not mlir_cpu_runner_exe:
return False return False
try: try:
mlir_cpu_runner_cmd = subprocess.Popen( mlir_cpu_runner_cmd = subprocess.Popen(
[mlir_cpu_runner_exe, '--host-supports-' + feature_name], stdout=subprocess.PIPE) [mlir_cpu_runner_exe, '--host-supports-' + feature_name], stdout=subprocess.PIPE)
except OSError: except OSError:
print('could not exec mlir-cpu-runner') print('could not exec mlir-cpu-runner')
return False return False
mlir_cpu_runner_out = mlir_cpu_runner_cmd.stdout.read().decode('ascii') mlir_cpu_runner_out = mlir_cpu_runner_cmd.stdout.read().decode('ascii')
mlir_cpu_runner_cmd.wait() mlir_cpu_runner_cmd.wait()
return 'true' in mlir_cpu_runner_out return 'true' in mlir_cpu_runner_out
if have_host_jit_feature_support('jit'): if have_host_jit_feature_support('jit'):
config.available_features.add('host-supports-jit') config.available_features.add('host-supports-jit')

mlir/test/mlir-cpu-runner/X86Vector/math-polynomial-approx-avx2.mlir

// RUN: mlir-opt %s -test-math-polynomial-approximation="enable-avx2" \ // RUN: mlir-opt %s -test-math-polynomial-approximation="enable-avx2" \
// RUN: -convert-arith-to-llvm \ // RUN: -convert-arith-to-llvm \
// RUN: -convert-vector-to-llvm="enable-x86vector" \ // RUN: -convert-vector-to-llvm="enable-x86vector" \
// RUN: -convert-math-to-llvm \ // RUN: -convert-math-to-llvm \
// RUN: -convert-func-to-llvm \ // RUN: -convert-func-to-llvm \
// RUN: -reconcile-unrealized-casts \ // RUN: -reconcile-unrealized-casts \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: -e main -entry-point-result=void -O0 \ // RUN: -e main -entry-point-result=void -O0 \
// RUN: -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
// RUN: -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
// -------------------------------------------------------------------------- // // -------------------------------------------------------------------------- //
// rsqrt. // rsqrt.
// -------------------------------------------------------------------------- // // -------------------------------------------------------------------------- //
func.func @rsqrt() { func.func @rsqrt() {
// Sanity-check that the scalar rsqrt still works OK. // Sanity-check that the scalar rsqrt still works OK.
Show All 22 Lines

mlir/test/mlir-cpu-runner/async-error.mlir

// RUN: mlir-opt %s -pass-pipeline="async-to-async-runtime,func.func(async-runtime-ref-counting,async-runtime-ref-counting-opt),convert-async-to-llvm,func.func(convert-linalg-to-loops,convert-scf-to-cf),convert-linalg-to-llvm,convert-vector-to-llvm,func.func(convert-arith-to-llvm),convert-func-to-llvm,reconcile-unrealized-casts" \ // RUN: mlir-opt %s -pass-pipeline="async-to-async-runtime,func.func(async-runtime-ref-counting,async-runtime-ref-counting-opt),convert-async-to-llvm,func.func(convert-linalg-to-loops,convert-scf-to-cf),convert-linalg-to-llvm,convert-vector-to-llvm,func.func(convert-arith-to-llvm),convert-func-to-llvm,reconcile-unrealized-casts" \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: -e main -entry-point-result=void -O0 \ // RUN: -e main -entry-point-result=void -O0 \
// RUN: -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
// RUN: -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: -shared-libs=%linalg_test_lib_dir/libmlir_async_runtime%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_async_runtime%shlibext \
// RUN: | FileCheck %s --dump-input=always // RUN: | FileCheck %s --dump-input=always
// FIXME: https://github.com/llvm/llvm-project/issues/57231 // FIXME: https://github.com/llvm/llvm-project/issues/57231
// UNSUPPORTED: hwasan // UNSUPPORTED: hwasan
func.func @main() { func.func @main() {
%false = arith.constant 0 : i1 %false = arith.constant 0 : i1
▲ Show 20 Lines • Show All 91 Lines • Show Last 20 Lines

mlir/test/mlir-cpu-runner/async-group.mlir

// RUN: mlir-opt %s -pass-pipeline="async-to-async-runtime,func.func(async-runtime-ref-counting,async-runtime-ref-counting-opt),convert-async-to-llvm,func.func(convert-arith-to-llvm),convert-func-to-llvm,reconcile-unrealized-casts" \ // RUN: mlir-opt %s -pass-pipeline="async-to-async-runtime,func.func(async-runtime-ref-counting,async-runtime-ref-counting-opt),convert-async-to-llvm,func.func(convert-arith-to-llvm),convert-func-to-llvm,reconcile-unrealized-casts" \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: -e main -entry-point-result=void -O0 \ // RUN: -e main -entry-point-result=void -O0 \
// RUN: -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
// RUN: -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: -shared-libs=%linalg_test_lib_dir/libmlir_async_runtime%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_async_runtime%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
// This is crashing in CI "most of the time" on a AMD Rome CPU VM on GCP with: // This is crashing in CI "most of the time" on a AMD Rome CPU VM on GCP with:
// Tracer caught signal 11: addr=0x7a800028 pc=0x2e81ba sp=0x7efd2a7ffd50 // Tracer caught signal 11: addr=0x7a800028 pc=0x2e81ba sp=0x7efd2a7ffd50
// LeakSanitizer has encountered a fatal error. // LeakSanitizer has encountered a fatal error.
// This is hard to reproduce locally unfortunately. Disable it with ASAN/LSAN // This is hard to reproduce locally unfortunately. Disable it with ASAN/LSAN
// to keep the bot green for now. // to keep the bot green for now.
// UNSUPPORTED: asan // UNSUPPORTED: asan
Show All 38 Lines

mlir/test/mlir-cpu-runner/async-value.mlir

// RUN: mlir-opt %s -pass-pipeline="async-to-async-runtime,func.func(async-runtime-ref-counting,async-runtime-ref-counting-opt),convert-async-to-llvm,func.func(convert-arith-to-llvm),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" \ // RUN: mlir-opt %s -pass-pipeline="async-to-async-runtime,func.func(async-runtime-ref-counting,async-runtime-ref-counting-opt),convert-async-to-llvm,func.func(convert-arith-to-llvm),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: -e main -entry-point-result=void -O0 \ // RUN: -e main -entry-point-result=void -O0 \
// RUN: -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
// RUN: -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: -shared-libs=%linalg_test_lib_dir/libmlir_async_runtime%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_async_runtime%shlibext \
// RUN: | FileCheck %s --dump-input=always // RUN: | FileCheck %s --dump-input=always
// FIXME: https://github.com/llvm/llvm-project/issues/57231 // FIXME: https://github.com/llvm/llvm-project/issues/57231
// UNSUPPORTED: hwasan // UNSUPPORTED: hwasan
func.func @main() { func.func @main() {
// ------------------------------------------------------------------------ // // ------------------------------------------------------------------------ //
▲ Show 20 Lines • Show All 67 Lines • Show Last 20 Lines

mlir/test/mlir-cpu-runner/async.mlir

// RUN: mlir-opt %s -pass-pipeline="async-to-async-runtime,func.func(async-runtime-ref-counting,async-runtime-ref-counting-opt),convert-async-to-llvm,func.func(convert-linalg-to-loops,convert-scf-to-cf),convert-linalg-to-llvm,convert-memref-to-llvm,func.func(convert-arith-to-llvm),convert-func-to-llvm,reconcile-unrealized-casts" \ // RUN: mlir-opt %s -pass-pipeline="async-to-async-runtime,func.func(async-runtime-ref-counting,async-runtime-ref-counting-opt),convert-async-to-llvm,func.func(convert-linalg-to-loops,convert-scf-to-cf),convert-linalg-to-llvm,convert-memref-to-llvm,func.func(convert-arith-to-llvm),convert-func-to-llvm,reconcile-unrealized-casts" \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: -e main -entry-point-result=void -O0 \ // RUN: -e main -entry-point-result=void -O0 \
// RUN: -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
// RUN: -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: -shared-libs=%linalg_test_lib_dir/libmlir_async_runtime%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_async_runtime%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
// FIXME: https://github.com/llvm/llvm-project/issues/57231 // FIXME: https://github.com/llvm/llvm-project/issues/57231
// UNSUPPORTED: hwasan // UNSUPPORTED: hwasan
func.func @main() { func.func @main() {
%i0 = arith.constant 0 : index %i0 = arith.constant 0 : index
%i1 = arith.constant 1 : index %i1 = arith.constant 1 : index
▲ Show 20 Lines • Show All 70 Lines • Show Last 20 Lines

mlir/test/mlir-cpu-runner/bare-ptr-call-conv.mlir

// RUN: mlir-opt %s -pass-pipeline="func.func(convert-scf-to-cf,convert-arith-to-llvm),convert-memref-to-llvm,convert-func-to-llvm{use-bare-ptr-memref-call-conv=1}" -reconcile-unrealized-casts | mlir-cpu-runner -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext -entry-point-result=void | FileCheck %s // RUN: mlir-opt %s -pass-pipeline="func.func(convert-scf-to-cf,convert-arith-to-llvm),convert-memref-to-llvm,convert-func-to-llvm{use-bare-ptr-memref-call-conv=1}" -reconcile-unrealized-casts | mlir-cpu-runner -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext -entry-point-result=void | FileCheck %s
// Verify bare pointer memref calling convention. `simple_add1_add2_test` // Verify bare pointer memref calling convention. `simple_add1_add2_test`
// gets two 2xf32 memrefs, adds 1.0f to the first one and 2.0f to the second // gets two 2xf32 memrefs, adds 1.0f to the first one and 2.0f to the second
// one. 'main' calls 'simple_add1_add2_test' with {1, 1} and {2, 2} so {2, 2} // one. 'main' calls 'simple_add1_add2_test' with {1, 1} and {2, 2} so {2, 2}
// and {4, 4} are the expected outputs. // and {4, 4} are the expected outputs.
func.func @simple_add1_add2_test(%arg0: memref<2xf32>, %arg1: memref<2xf32>) { func.func @simple_add1_add2_test(%arg0: memref<2xf32>, %arg1: memref<2xf32>) {
%c2 = arith.constant 2 : index %c2 = arith.constant 2 : index
▲ Show 20 Lines • Show All 59 Lines • Show Last 20 Lines

mlir/test/mlir-cpu-runner/copy.mlir

// RUN: mlir-opt %s -pass-pipeline="func.func(convert-scf-to-cf,convert-arith-to-llvm),convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-scf-to-cf,convert-arith-to-llvm),convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" \
// RUN: | mlir-cpu-runner -e main -entry-point-result=void \ // RUN: | mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext,%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext,%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func private @printMemrefF32(memref<*xf32>) attributes { llvm.emit_c_interface } func.func private @printMemrefF32(memref<*xf32>) attributes { llvm.emit_c_interface }
func.func @main() -> () { func.func @main() -> () {
%c0 = arith.constant 0 : index %c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index %c1 = arith.constant 1 : index
%c42 = arith.constant 42.0 : f32 %c42 = arith.constant 42.0 : f32
▲ Show 20 Lines • Show All 67 Lines • Show Last 20 Lines

mlir/test/mlir-cpu-runner/global-memref.mlir

// RUN: mlir-opt %s -pass-pipeline="func.func(convert-arith-to-llvm),convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e main -entry-point-result=void -shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext,%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext | FileCheck %s // RUN: mlir-opt %s -pass-pipeline="func.func(convert-arith-to-llvm),convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e main -entry-point-result=void -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext,%mlir_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s
func.func private @printMemrefF32(memref<*xf32>) attributes { llvm.emit_c_interface } func.func private @printMemrefF32(memref<*xf32>) attributes { llvm.emit_c_interface }
func.func private @printMemrefI32(memref<*xi32>) attributes { llvm.emit_c_interface } func.func private @printMemrefI32(memref<*xi32>) attributes { llvm.emit_c_interface }
func.func private @printNewline() -> () func.func private @printNewline() -> ()
memref.global "private" @gv0 : memref<4xf32> = dense<[0.0, 1.0, 2.0, 3.0]> memref.global "private" @gv0 : memref<4xf32> = dense<[0.0, 1.0, 2.0, 3.0]>
func.func @test1DMemref() { func.func @test1DMemref() {
%0 = memref.get_global @gv0 : memref<4xf32> %0 = memref.get_global @gv0 : memref<4xf32>
▲ Show 20 Lines • Show All 98 Lines • Show Last 20 Lines

mlir/test/mlir-cpu-runner/math-polynomial-approx.mlir

// RUN: mlir-opt %s -pass-pipeline="func.func(test-math-polynomial-approximation,convert-arith-to-llvm),convert-vector-to-llvm,func.func(convert-math-to-llvm),convert-func-to-llvm,reconcile-unrealized-casts" \ // RUN: mlir-opt %s -pass-pipeline="func.func(test-math-polynomial-approximation,convert-arith-to-llvm),convert-vector-to-llvm,func.func(convert-math-to-llvm),convert-func-to-llvm,reconcile-unrealized-casts" \
// RUN: | mlir-cpu-runner \ // RUN: | mlir-cpu-runner \
// RUN: -e main -entry-point-result=void -O0 \ // RUN: -e main -entry-point-result=void -O0 \
// RUN: -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
// RUN: -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
// -------------------------------------------------------------------------- // // -------------------------------------------------------------------------- //
// Tanh. // Tanh.
// -------------------------------------------------------------------------- // // -------------------------------------------------------------------------- //
func.func @tanh() { func.func @tanh() {
// CHECK: 0.848284 // CHECK: 0.848284
%0 = arith.constant 1.25 : f32 %0 = arith.constant 1.25 : f32
▲ Show 20 Lines • Show All 501 Lines • Show Last 20 Lines

mlir/test/mlir-cpu-runner/memref-reinterpret-cast.mlir

// RUN: mlir-opt %s -pass-pipeline="func.func(convert-scf-to-cf),convert-memref-to-llvm,func.func(convert-arith-to-llvm),convert-func-to-llvm,reconcile-unrealized-casts" \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-scf-to-cf),convert-memref-to-llvm,func.func(convert-arith-to-llvm),convert-func-to-llvm,reconcile-unrealized-casts" \
// RUN: | mlir-cpu-runner -e main -entry-point-result=void \ // RUN: | mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext,%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext,%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func private @printMemrefF32(memref<*xf32>) attributes { llvm.emit_c_interface } func.func private @printMemrefF32(memref<*xf32>) attributes { llvm.emit_c_interface }
func.func @main() -> () { func.func @main() -> () {
%c0 = arith.constant 0 : index %c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index %c1 = arith.constant 1 : index
▲ Show 20 Lines • Show All 95 Lines • Show Last 20 Lines

mlir/test/mlir-cpu-runner/memref-reshape.mlir

// RUN: mlir-opt %s -pass-pipeline="func.func(convert-scf-to-cf,memref-expand,convert-arith-to-llvm),convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-scf-to-cf,memref-expand,convert-arith-to-llvm),convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" \
// RUN: | mlir-cpu-runner -e main -entry-point-result=void \ // RUN: | mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext,%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext,%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
func.func private @printMemrefF32(memref<*xf32>) attributes { llvm.emit_c_interface } func.func private @printMemrefF32(memref<*xf32>) attributes { llvm.emit_c_interface }
func.func @main() -> () { func.func @main() -> () {
%c0 = arith.constant 0 : index %c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index %c1 = arith.constant 1 : index
▲ Show 20 Lines • Show All 96 Lines • Show Last 20 Lines

mlir/test/mlir-cpu-runner/print.mlir

// RUN: mlir-opt %s -pass-pipeline="convert-func-to-llvm,reconcile-unrealized-casts" \ // RUN: mlir-opt %s -pass-pipeline="convert-func-to-llvm,reconcile-unrealized-casts" \
// RUN: | mlir-cpu-runner -e main -entry-point-result=void \ // RUN: | mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext,%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext \ // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext,%mlir_lib_dir/libmlir_c_runner_utils%shlibext \
// RUN: | FileCheck %s // RUN: | FileCheck %s
llvm.mlir.global internal constant @str_global("String to print\0A") llvm.mlir.global internal constant @str_global("String to print\0A")
llvm.func @printCString(!llvm.ptr<i8>) llvm.func @printCString(!llvm.ptr<i8>)
func.func @main() { func.func @main() {
%0 = llvm.mlir.addressof @str_global : !llvm.ptr<array<16 x i8>> %0 = llvm.mlir.addressof @str_global : !llvm.ptr<array<16 x i8>>
%1 = llvm.mlir.constant(0 : index) : i64 %1 = llvm.mlir.constant(0 : index) : i64
%2 = llvm.getelementptr %0[%1, %1] %2 = llvm.getelementptr %0[%1, %1]
: (!llvm.ptr<array<16 x i8>>, i64, i64) -> !llvm.ptr<i8> : (!llvm.ptr<array<16 x i8>>, i64, i64) -> !llvm.ptr<i8>
llvm.call @printCString(%2) : (!llvm.ptr<i8>) -> () llvm.call @printCString(%2) : (!llvm.ptr<i8>) -> ()
return return
} }
// CHECK: String to print // CHECK: String to print

mlir/test/mlir-cpu-runner/sgemm-naive-codegen.mlir

// RUN: mlir-opt -pass-pipeline="func.func(convert-linalg-to-loops,lower-affine,convert-scf-to-cf,convert-arith-to-llvm),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" %s | mlir-cpu-runner -O3 -e main -entry-point-result=void -shared-libs=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext | FileCheck %s // RUN: mlir-opt -pass-pipeline="func.func(convert-linalg-to-loops,lower-affine,convert-scf-to-cf,convert-arith-to-llvm),convert-vector-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" %s | mlir-cpu-runner -O3 -e main -entry-point-result=void -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s
func.func @main() { func.func @main() {
%A = memref.alloc() : memref<16x16xf32> %A = memref.alloc() : memref<16x16xf32>
%B = memref.alloc() : memref<16x16xf32> %B = memref.alloc() : memref<16x16xf32>
%C = memref.alloc() : memref<16x16xf32> %C = memref.alloc() : memref<16x16xf32>
%cf1 = arith.constant 1.00000e+00 : f32 %cf1 = arith.constant 1.00000e+00 : f32
▲ Show 20 Lines • Show All 67 Lines • Show Last 20 Lines

mlir/test/mlir-cpu-runner/unranked-memref.mlir

// RUN: mlir-opt %s -pass-pipeline="func.func(convert-linalg-to-loops,convert-scf-to-cf,convert-arith-to-llvm),convert-linalg-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \ // RUN: mlir-opt %s -pass-pipeline="func.func(convert-linalg-to-loops,convert-scf-to-cf,convert-arith-to-llvm),convert-linalg-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | \
// RUN: mlir-cpu-runner -e main -entry-point-result=void \ // RUN: mlir-cpu-runner -e main -entry-point-result=void \
// RUN: -shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext,%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext | FileCheck %s // RUN: -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext,%mlir_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s
// CHECK: rank = 2 // CHECK: rank = 2
// CHECK-SAME: sizes = [10, 3] // CHECK-SAME: sizes = [10, 3]
// CHECK-SAME: strides = [3, 1] // CHECK-SAME: strides = [3, 1]
// CHECK-COUNT-10: [10, 10, 10] // CHECK-COUNT-10: [10, 10, 10]
// //
// CHECK: rank = 2 // CHECK: rank = 2
// CHECK-SAME: sizes = [10, 3] // CHECK-SAME: sizes = [10, 3]
▲ Show 20 Lines • Show All 117 Lines • Show Last 20 Lines

mlir/test/mlir-cpu-runner/utils.mlir

// RUN: mlir-opt %s -pass-pipeline="func.func(convert-linalg-to-loops,convert-scf-to-cf,convert-arith-to-llvm),convert-linalg-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e print_0d -entry-point-result=void -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s --check-prefix=PRINT-0D // RUN: mlir-opt %s -pass-pipeline="func.func(convert-linalg-to-loops,convert-scf-to-cf,convert-arith-to-llvm),convert-linalg-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e print_0d -entry-point-result=void -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s --check-prefix=PRINT-0D
// RUN: mlir-opt %s -pass-pipeline="func.func(convert-linalg-to-loops,convert-scf-to-cf,convert-arith-to-llvm),convert-linalg-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e print_1d -entry-point-result=void -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s --check-prefix=PRINT-1D // RUN: mlir-opt %s -pass-pipeline="func.func(convert-linalg-to-loops,convert-scf-to-cf,convert-arith-to-llvm),convert-linalg-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e print_1d -entry-point-result=void -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s --check-prefix=PRINT-1D
// RUN: mlir-opt %s -pass-pipeline="func.func(convert-linalg-to-loops,convert-scf-to-cf,convert-arith-to-llvm),convert-linalg-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e print_3d -entry-point-result=void -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s --check-prefix=PRINT-3D // RUN: mlir-opt %s -pass-pipeline="func.func(convert-linalg-to-loops,convert-scf-to-cf,convert-arith-to-llvm),convert-linalg-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e print_3d -entry-point-result=void -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s --check-prefix=PRINT-3D
// RUN: mlir-opt %s -pass-pipeline="func.func(convert-linalg-to-loops,convert-scf-to-cf,convert-arith-to-llvm),convert-linalg-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e vector_splat_2d -entry-point-result=void -shared-libs=%linalg_test_lib_dir/libmlir_runner_utils%shlibext -shared-libs=%linalg_test_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s --check-prefix=PRINT-VECTOR-SPLAT-2D // RUN: mlir-opt %s -pass-pipeline="func.func(convert-linalg-to-loops,convert-scf-to-cf,convert-arith-to-llvm),convert-linalg-to-llvm,convert-memref-to-llvm,convert-func-to-llvm,reconcile-unrealized-casts" | mlir-cpu-runner -e vector_splat_2d -entry-point-result=void -shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | FileCheck %s --check-prefix=PRINT-VECTOR-SPLAT-2D
func.func @print_0d() { func.func @print_0d() {
%f = arith.constant 2.00000e+00 : f32 %f = arith.constant 2.00000e+00 : f32
%A = memref.alloc() : memref<f32> %A = memref.alloc() : memref<f32>
memref.store %f, %A[]: memref<f32> memref.store %f, %A[]: memref<f32>
%U = memref.cast %A : memref<f32> to memref<*xf32> %U = memref.cast %A : memref<f32> to memref<*xf32>
call @printMemrefF32(%U): (memref<*xf32>) -> () call @printMemrefF32(%U): (memref<*xf32>) -> ()
memref.dealloc %A : memref<f32> memref.dealloc %A : memref<f32>
▲ Show 20 Lines • Show All 61 Lines • Show Last 20 Lines

mlir/test/mlir-spirv-cpu-runner/double.mlir

// RUN: mlir-spirv-cpu-runner %s -e main --entry-point-result=void --shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext,%spirv_wrapper_library_dir/libmlir_test_spirv_cpu_runner_c_wrappers%shlibext // RUN: mlir-spirv-cpu-runner %s -e main --entry-point-result=void --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext,%mlir_lib_dir/libmlir_test_spirv_cpu_runner_c_wrappers%shlibext
// CHECK: [8, 8, 8, 8, 8, 8] // CHECK: [8, 8, 8, 8, 8, 8]
module attributes { module attributes {
gpu.container_module, gpu.container_module,
spv.target_env = #spv.target_env< spv.target_env = #spv.target_env<
#spv.vce<v1.0, [Shader], [SPV_KHR_variable_pointers]>, #spv.vce<v1.0, [Shader], [SPV_KHR_variable_pointers]>,
#spv.resource_limits< #spv.resource_limits<
max_compute_workgroup_invocations = 128, max_compute_workgroup_invocations = 128,
▲ Show 20 Lines • Show All 59 Lines • Show Last 20 Lines

mlir/test/mlir-spirv-cpu-runner/simple_add.mlir

// RUN: mlir-spirv-cpu-runner %s -e main --entry-point-result=void --shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext,%spirv_wrapper_library_dir/libmlir_test_spirv_cpu_runner_c_wrappers%shlibext // RUN: mlir-spirv-cpu-runner %s -e main --entry-point-result=void --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext,%mlir_lib_dir/libmlir_test_spirv_cpu_runner_c_wrappers%shlibext
// CHECK: [[[7.7, 0, 0], [7.7, 0, 0], [7.7, 0, 0]], [[0, 7.7, 0], [0, 7.7, 0], [0, 7.7, 0]], [[0, 0, 7.7], [0, 0, 7.7], [0, 0, 7.7]]] // CHECK: [[[7.7, 0, 0], [7.7, 0, 0], [7.7, 0, 0]], [[0, 7.7, 0], [0, 7.7, 0], [0, 7.7, 0]], [[0, 0, 7.7], [0, 0, 7.7], [0, 0, 7.7]]]
module attributes { module attributes {
gpu.container_module, gpu.container_module,
spv.target_env = #spv.target_env< spv.target_env = #spv.target_env<
#spv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class, SPV_KHR_8bit_storage]>, #spv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class, SPV_KHR_8bit_storage]>,
#spv.resource_limits< #spv.resource_limits<
max_compute_workgroup_invocations = 128, max_compute_workgroup_invocations = 128,
▲ Show 20 Lines • Show All 53 Lines • Show Last 20 Lines

mlir/test/mlir-vulkan-runner/addf.mlir

// RUN: mlir-vulkan-runner %s --shared-libs=%vulkan_wrapper_library_dir/libvulkan-runtime-wrappers%shlibext,%linalg_test_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s // RUN: mlir-vulkan-runner %s --shared-libs=%mlir_lib_dir/libvulkan-runtime-wrappers%shlibext,%mlir_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s
// CHECK: [3.3, 3.3, 3.3, 3.3, 3.3, 3.3, 3.3, 3.3] // CHECK: [3.3, 3.3, 3.3, 3.3, 3.3, 3.3, 3.3, 3.3]
module attributes { module attributes {
gpu.container_module, gpu.container_module,
spv.target_env = #spv.target_env< spv.target_env = #spv.target_env<
#spv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class]>, #spv.resource_limits<>> #spv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class]>, #spv.resource_limits<>>
} { } {
gpu.module @kernels { gpu.module @kernels {
▲ Show 20 Lines • Show All 41 Lines • Show Last 20 Lines

mlir/test/mlir-vulkan-runner/addi.mlir

// RUN: mlir-vulkan-runner %s --shared-libs=%vulkan_wrapper_library_dir/libvulkan-runtime-wrappers%shlibext,%linalg_test_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s // RUN: mlir-vulkan-runner %s --shared-libs=%mlir_lib_dir/libvulkan-runtime-wrappers%shlibext,%mlir_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s
// CHECK-COUNT-64: [3, 3, 3, 3, 3, 3, 3, 3] // CHECK-COUNT-64: [3, 3, 3, 3, 3, 3, 3, 3]
module attributes { module attributes {
gpu.container_module, gpu.container_module,
spv.target_env = #spv.target_env< spv.target_env = #spv.target_env<
#spv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class]>, #spv.resource_limits<>> #spv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class]>, #spv.resource_limits<>>
} { } {
gpu.module @kernels { gpu.module @kernels {
▲ Show 20 Lines • Show All 42 Lines • Show Last 20 Lines

mlir/test/mlir-vulkan-runner/addi8.mlir

// RUN: mlir-vulkan-runner %s --shared-libs=%vulkan_wrapper_library_dir/libvulkan-runtime-wrappers%shlibext,%linalg_test_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s // RUN: mlir-vulkan-runner %s --shared-libs=%mlir_lib_dir/libvulkan-runtime-wrappers%shlibext,%mlir_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s
// CHECK-COUNT-64: [3, 3, 3, 3, 3, 3, 3, 3] // CHECK-COUNT-64: [3, 3, 3, 3, 3, 3, 3, 3]
module attributes { module attributes {
gpu.container_module, gpu.container_module,
spv.target_env = #spv.target_env< spv.target_env = #spv.target_env<
#spv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class, SPV_KHR_8bit_storage]>, #spv.resource_limits<>> #spv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class, SPV_KHR_8bit_storage]>, #spv.resource_limits<>>
} { } {
gpu.module @kernels { gpu.module @kernels {
▲ Show 20 Lines • Show All 42 Lines • Show Last 20 Lines

mlir/test/mlir-vulkan-runner/mulf.mlir

// RUN: mlir-vulkan-runner %s --shared-libs=%vulkan_wrapper_library_dir/libvulkan-runtime-wrappers%shlibext,%linalg_test_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s // RUN: mlir-vulkan-runner %s --shared-libs=%mlir_lib_dir/libvulkan-runtime-wrappers%shlibext,%mlir_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s
// CHECK-COUNT-4: [6, 6, 6, 6] // CHECK-COUNT-4: [6, 6, 6, 6]
module attributes { module attributes {
gpu.container_module, gpu.container_module,
spv.target_env = #spv.target_env< spv.target_env = #spv.target_env<
#spv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class]>, #spv.resource_limits<>> #spv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class]>, #spv.resource_limits<>>
} { } {
gpu.module @kernels { gpu.module @kernels {
▲ Show 20 Lines • Show All 42 Lines • Show Last 20 Lines

mlir/test/mlir-vulkan-runner/subf.mlir

// RUN: mlir-vulkan-runner %s --shared-libs=%vulkan_wrapper_library_dir/libvulkan-runtime-wrappers%shlibext,%linalg_test_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s // RUN: mlir-vulkan-runner %s --shared-libs=%mlir_lib_dir/libvulkan-runtime-wrappers%shlibext,%mlir_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s
// CHECK-COUNT-32: [2.2, 2.2, 2.2, 2.2] // CHECK-COUNT-32: [2.2, 2.2, 2.2, 2.2]
module attributes { module attributes {
gpu.container_module, gpu.container_module,
spv.target_env = #spv.target_env< spv.target_env = #spv.target_env<
#spv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class]>, #spv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class]>,
#spv.resource_limits<>> #spv.resource_limits<>>
} { } {
▲ Show 20 Lines • Show All 45 Lines • Show Last 20 Lines

mlir/test/mlir-vulkan-runner/time.mlir

// RUN: mlir-vulkan-runner %s --shared-libs=%vulkan_wrapper_library_dir/libvulkan-runtime-wrappers%shlibext,%linalg_test_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s // RUN: mlir-vulkan-runner %s --shared-libs=%mlir_lib_dir/libvulkan-runtime-wrappers%shlibext,%mlir_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s
// CHECK: Compute shader execution time // CHECK: Compute shader execution time
// CHECK: Command buffer submit time // CHECK: Command buffer submit time
// CHECK: Wait idle time // CHECK: Wait idle time
module attributes { module attributes {
gpu.container_module, gpu.container_module,
spv.target_env = #spv.target_env< spv.target_env = #spv.target_env<
▲ Show 20 Lines • Show All 47 Lines • Show Last 20 Lines

utils/bazel/llvm-project-overlay/mlir/BUILD.bazel

Show First 20 Lines • Show All 6,465 Lines • ▼ Show 20 Lines deps = [
":Support", ":Support",
"//llvm:Core", "//llvm:Core",
"//llvm:OrcJIT", "//llvm:OrcJIT",
"//llvm:Support", "//llvm:Support",
], ],
) )
cc_library( cc_library(
name = "mlir_c_runner_utils", name = "mlir_async_runtime_api",
hdrs = ["include/mlir/ExecutionEngine/AsyncRuntime.h"],
includes = ["include"],
)
cc_library(
name = "_mlir_async_runtime",
srcs = ["lib/ExecutionEngine/AsyncRuntime.cpp"],
copts = ["-Dmlir_async_runtime_EXPORTS"],
deps = [
":mlir_async_runtime_api",
"//llvm:Support",
],
)
# Indirection to avoid output filename clash between cc_library and cc_binary.
herhutUnsubmitted
Not Done
ReplyInline Actions

Why are these aliases needed?

herhut: Why are these aliases needed?
csiggAuthorUnsubmitted
Done
ReplyInline Actions

They are needed because the shared library name (lib<name>.so) of the cc_library target would otherwise clash with the cc_binary target below.

I will add a comment explaining this.

csigg: They are needed because the shared library name (`lib<name>.so`) of the `cc_library` target…
alias(
name = "mlir_async_runtime",
actual = "_mlir_async_runtime",
)
cc_binary(
name = "libmlir_async_runtime.so",
linkshared = True,
linkstatic = False,
deps = [":mlir_async_runtime"],
)
cc_library(
name = "_mlir_c_runner_utils",
srcs = [ srcs = [
"lib/ExecutionEngine/CRunnerUtils.cpp", "lib/ExecutionEngine/CRunnerUtils.cpp",
"lib/ExecutionEngine/Float16bits.cpp", "lib/ExecutionEngine/Float16bits.cpp",
"lib/ExecutionEngine/SparseTensorUtils.cpp", "lib/ExecutionEngine/SparseTensorUtils.cpp",
], ],
hdrs = [ hdrs = [
"include/mlir/ExecutionEngine/CRunnerUtils.h", "include/mlir/ExecutionEngine/CRunnerUtils.h",
"include/mlir/ExecutionEngine/Float16bits.h", "include/mlir/ExecutionEngine/Float16bits.h",
"include/mlir/ExecutionEngine/Msan.h", "include/mlir/ExecutionEngine/Msan.h",
"include/mlir/ExecutionEngine/SparseTensorUtils.h", "include/mlir/ExecutionEngine/SparseTensorUtils.h",
], ],
includes = ["include"], includes = ["include"],
) )
cc_library( # Indirection to avoid output filename clash between cc_library and cc_binary.
name = "mlir_async_runtime_api", alias(
hdrs = ["include/mlir/ExecutionEngine/AsyncRuntime.h"], name = "mlir_c_runner_utils",
includes = ["include"], actual = "_mlir_c_runner_utils",
) )
cc_library( cc_binary(
name = "mlir_async_runtime", name = "libmlir_c_runner_utils.so",
srcs = ["lib/ExecutionEngine/AsyncRuntime.cpp"], linkshared = True,
copts = ["-Dmlir_async_runtime_EXPORTS"], linkstatic = False,
deps = [ deps = [":mlir_c_runner_utils"],
":mlir_async_runtime_api",
"//llvm:Support",
],
) )
cc_library( cc_library(
name = "mlir_runner_utils", name = "_mlir_runner_utils",
srcs = ["lib/ExecutionEngine/RunnerUtils.cpp"], srcs = ["lib/ExecutionEngine/RunnerUtils.cpp"],
hdrs = ["include/mlir/ExecutionEngine/RunnerUtils.h"], hdrs = ["include/mlir/ExecutionEngine/RunnerUtils.h"],
includes = ["include"], includes = ["include"],
deps = [":mlir_c_runner_utils"], deps = [":mlir_c_runner_utils"],
) )
# Indirection to avoid output filename clash between cc_library and cc_binary.
alias(
name = "mlir_runner_utils",
actual = "_mlir_runner_utils",
)
cc_binary(
name = "libmlir_runner_utils.so",
linkshared = True,
linkstatic = False,
deps = [":mlir_runner_utils"],
)
cc_binary( cc_binary(
name = "mlir-cpu-runner", name = "mlir-cpu-runner",
srcs = ["tools/mlir-cpu-runner/mlir-cpu-runner.cpp"], srcs = ["tools/mlir-cpu-runner/mlir-cpu-runner.cpp"],
deps = [ deps = [
":AllToLLVMIRTranslations", ":AllToLLVMIRTranslations",
":ExecutionEngineUtils", ":ExecutionEngineUtils",
":IR", ":IR",
":LLVMDialect", ":LLVMDialect",
Show All 20 Lines
# BUILD_SHARED_LIBS), skipping them if none of the symbols are used. # BUILD_SHARED_LIBS), skipping them if none of the symbols are used.
# See also https://reviews.llvm.org/D95613. # See also https://reviews.llvm.org/D95613.
cc_headers_only( cc_headers_only(
name = "LLVMSupportHeaders", name = "LLVMSupportHeaders",
src = "//llvm:Support", src = "//llvm:Support",
) )
cc_library( cc_library(
name = "mlir_cuda_runtime", name = "_mlir_cuda_runtime",
srcs = ["lib/ExecutionEngine/CudaRuntimeWrappers.cpp"], srcs = ["lib/ExecutionEngine/CudaRuntimeWrappers.cpp"],
# Prevent needing EnableABIBreakingChecks symbol from LLVMSupport. # Prevent needing EnableABIBreakingChecks symbol from LLVMSupport.
copts = ["-DLLVM_DISABLE_ABI_BREAKING_CHECKS_ENFORCING=1"], copts = ["-DLLVM_DISABLE_ABI_BREAKING_CHECKS_ENFORCING=1"],
tags = [ tags = [
"manual", # External dependency "manual", # External dependency
"nobuildkite", # TODO(gcmn): Add support for this target "nobuildkite", # TODO(gcmn): Add support for this target
], ],
deps = [ deps = [
":LLVMSupportHeaders", ":LLVMSupportHeaders",
":mlir_c_runner_utils", ":mlir_c_runner_utils",
"@cuda//:cuda_headers", "@cuda//:cuda_headers",
"@cuda//:libcuda", "@cuda//:libcuda",
], ],
) )
# Indirection to avoid output filename clash between cc_library and cc_binary.
alias(
name = "mlir_cuda_runtime",
actual = "_mlir_cuda_runtime",
tags = [
"manual", # External dependency
"nobuildkite", # TODO(gcmn): Add support for this target
],
)
cc_binary(
name = "libmlir_cuda_runtime.so",
linkshared = True,
linkstatic = False,
tags = [
"manual", # External dependency
"nobuildkite", # TODO(gcmn): Add support for this target
],
deps = [":mlir_cuda_runtime"],
)
cc_library( cc_library(
name = "VulkanRuntime", name = "VulkanRuntime",
srcs = ["tools/mlir-vulkan-runner/VulkanRuntime.cpp"], srcs = ["tools/mlir-vulkan-runner/VulkanRuntime.cpp"],
hdrs = ["tools/mlir-vulkan-runner/VulkanRuntime.h"], hdrs = ["tools/mlir-vulkan-runner/VulkanRuntime.h"],
tags = [ tags = [
"manual", # External dependency "manual", # External dependency
], ],
deps = [ deps = [
":FuncDialect", ":FuncDialect",
":IR", ":IR",
":Pass", ":Pass",
":SPIRVDialect", ":SPIRVDialect",
":SideEffectInterfaces", ":SideEffectInterfaces",
":Support", ":Support",
"//llvm:Support", "//llvm:Support",
"@vulkan_headers", "@vulkan_headers",
"@vulkan_sdk//:sdk", "@vulkan_sdk//:sdk",
], ],
) )
cc_binary( cc_binary(
name = "tools/libvulkan-runtime-wrappers.so", name = "libvulkan-runtime-wrappers.so",
srcs = ["tools/mlir-vulkan-runner/vulkan-runtime-wrappers.cpp"], srcs = ["tools/mlir-vulkan-runner/vulkan-runtime-wrappers.cpp"],
linkshared = True, linkshared = True,
tags = [ tags = [
"manual", # External dependency "manual", # External dependency
], ],
deps = [ deps = [
":VulkanRuntime", ":VulkanRuntime",
"//llvm:Support", "//llvm:Support",
▲ Show 20 Lines • Show All 2,796 Lines • Show Last 20 Lines