Skip to content

[CI] Switch SIMT tests to upstream XeGPU master pass #1145

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Garra1980 merged 2 commits into from
Feb 18, 2026
Merged

[CI] Switch SIMT tests to upstream XeGPU master pass #1145

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
addf308
[CI] Switch SIMT tests to upstream XeGPU master pass
Garra1980 Feb 17, 2026
51aef11
Fix conflict
Garra1980 Feb 17, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,10 +41,10 @@ endif()
string(FIND "${LLVM_TARGETS_TO_BUILD}" "SPIRV" SPIRV_FOUND)
if(SPIRV_FOUND GREATER -1)
message(STATUS "SPIRV is part of the LLVM targets")
set(IMEX_SPIRV_BACKEND_ENABLED 1)
set(MLIR_SPIRV_BACKEND_ENABLED 1)
else()
message(STATUS "SPIRV is not part of the LLVM targets")
set(IMEX_SPIRV_BACKEND_ENABLED 0)
set(MLIR_SPIRV_BACKEND_ENABLED 0)
endif()

# option(IMEX_BUILD_SPIRV_BACKEND "Append SPIRV to LLVM_TARGETS_TO_BUILD" ON)
Expand Down
19 changes: 15 additions & 4 deletions test/Integration/Dialect/XeGPU/SG/col_reduce_16x16xf16.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,18 @@
// RUN: %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// RUN: --runner mlir-runner -e main \
// RUN: --entry-point-result=void \
// RUN: --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck

// RUN: imex-opt %s --gpu-lower-to-xevm-pipeline="xegpu-op-level=subgroup" \
// RUN: | mlir-runner \
// RUN: --shared-libs=%mlir_levelzero_runtime \
// RUN: --shared-libs=%mlir_runner_utils \
// RUN: --shared-libs=%mlir_c_runner_utils \
// RUN: --shared-libs=%irunner_utils \
// RUN: --entry-point-result=void \
// RUN: | FileCheck %s

// Example of pass pipeline usage:
// %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// --runner mlir-runner -e main \
// --entry-point-result=void \
// --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck
module @gemm attributes {gpu.container_module} {
gpu.module @kernel {
gpu.func @reduce_broadcast(%in: memref<16x16xf16>, %c: memref<1x16xf16>) kernel attributes {intel_reqd_sub_group_size = 16 : i32} {
Expand Down
18 changes: 14 additions & 4 deletions test/Integration/Dialect/XeGPU/SG/flash_attention_fwd.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,17 @@
// RUN: %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// RUN: --runner mlir-runner -e main \
// RUN: --entry-point-result=void \
// RUN: --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck
// RUN: imex-opt %s --gpu-lower-to-xevm-pipeline="xegpu-op-level=subgroup" \
// RUN: | mlir-runner \
// RUN: --shared-libs=%mlir_levelzero_runtime \
// RUN: --shared-libs=%mlir_runner_utils \
// RUN: --shared-libs=%mlir_c_runner_utils \
// RUN: --shared-libs=%irunner_utils \
// RUN: --entry-point-result=void \
// RUN: | FileCheck %s

// Example of pass pipeline usage:
// %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// --runner mlir-runner -e main \
// --entry-point-result=void \
// --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck
module @flash_attention attributes {gpu.container_module} {
gpu.module @flash_attention_fwd {
gpu.func @flash_attention_fwd(
Expand Down
18 changes: 14 additions & 4 deletions test/Integration/Dialect/XeGPU/SG/gemm_4kx4kx4k_f16_f16_f16.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,17 @@
// RUN: %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// RUN: --runner mlir-runner -e main \
// RUN: --entry-point-result=void \
// RUN: --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck
// RUN: imex-opt %s --gpu-lower-to-xevm-pipeline="xegpu-op-level=subgroup" \
// RUN: | mlir-runner \
// RUN: --shared-libs=%mlir_levelzero_runtime \
// RUN: --shared-libs=%mlir_runner_utils \
// RUN: --shared-libs=%mlir_c_runner_utils \
// RUN: --shared-libs=%irunner_utils \
// RUN: --entry-point-result=void \
// RUN: | FileCheck %s

// Example of pass pipeline usage:
// %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// --runner mlir-runner -e main \
// --entry-point-result=void \
// --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck
module @gemm attributes {gpu.container_module} {
func.func @test(%A: memref<4096x4096xf16>, %B: memref<4096x4096xf16>, %C: memref<4096x4096xf16>) -> memref<4096x4096xf16> attributes {llvm.emit_c_interface} {
%c1 = arith.constant 1 : index
Expand Down
18 changes: 14 additions & 4 deletions test/Integration/Dialect/XeGPU/SG/gemm_4kx4kx4k_transpose_b.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,17 @@
// RUN: %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// RUN: --runner mlir-runner -e main \
// RUN: --entry-point-result=void \
// RUN: --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck
// RUN: imex-opt %s --gpu-lower-to-xevm-pipeline="xegpu-op-level=subgroup" \
// RUN: | mlir-runner \
// RUN: --shared-libs=%mlir_levelzero_runtime \
// RUN: --shared-libs=%mlir_runner_utils \
// RUN: --shared-libs=%mlir_c_runner_utils \
// RUN: --shared-libs=%irunner_utils \
// RUN: --entry-point-result=void \
// RUN: | FileCheck %s

// Example of pass pipeline usage:
// %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// --runner mlir-runner -e main \
// --entry-point-result=void \
// --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck

module @gemm attributes {gpu.container_module} {
func.func @test(%A: memref<4096x4096xf16>, %B: memref<4096x4096xf16>, %C: memref<4096x4096xf16>) -> memref<4096x4096xf16> attributes {llvm.emit_c_interface} {
Expand Down
2 changes: 1 addition & 1 deletion test/Integration/Dialect/XeGPU/SG/lit.local.cfg
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
if(not config.mlir_enable_levelzero_runtime):
if(not config.mlir_enable_levelzero_runtime or not config.mlir_enable_spirv_backend):
config.unsupported = True
18 changes: 14 additions & 4 deletions test/Integration/Dialect/XeGPU/SG/row_reduce_16x16xf16.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,17 @@
// RUN: %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// RUN: --runner mlir-runner -e main \
// RUN: --entry-point-result=void \
// RUN: --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck
// RUN: imex-opt %s --gpu-lower-to-xevm-pipeline="xegpu-op-level=subgroup" \
// RUN: | mlir-runner \
// RUN: --shared-libs=%mlir_levelzero_runtime \
// RUN: --shared-libs=%mlir_runner_utils \
// RUN: --shared-libs=%mlir_c_runner_utils \
// RUN: --shared-libs=%irunner_utils \
// RUN: --entry-point-result=void \
// RUN: | FileCheck %s

// Example of pass pipeline usage:
// %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// --runner mlir-runner -e main \
// --entry-point-result=void \
// --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck
module @gemm attributes {gpu.container_module} {
gpu.module @kernel {
gpu.func @reduce_broadcast(%in: memref<16x16xf16>, %c: memref<16x16xf16>) kernel attributes {intel_reqd_sub_group_size = 16 : i32} {
Expand Down
18 changes: 14 additions & 4 deletions test/Integration/Dialect/XeGPU/SG/simple_gemm.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,17 @@
// RUN: %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// RUN: --runner mlir-runner -e main \
// RUN: --entry-point-result=void \
// RUN: --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck
// RUN: imex-opt %s --gpu-lower-to-xevm-pipeline="xegpu-op-level=subgroup" \
// RUN: | mlir-runner \
// RUN: --shared-libs=%mlir_levelzero_runtime \
// RUN: --shared-libs=%mlir_runner_utils \
// RUN: --shared-libs=%mlir_c_runner_utils \
// RUN: --shared-libs=%irunner_utils \
// RUN: --entry-point-result=void \
// RUN: | FileCheck %s

// Example of pass pipeline usage:
// %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// --runner mlir-runner -e main \
// --entry-point-result=void \
// --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck

module @gemm attributes {gpu.container_module} {
gpu.module @kernel {
Expand Down
18 changes: 14 additions & 4 deletions test/Integration/Dialect/XeGPU/SG/simple_gemm_transpose_b.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,17 @@
// RUN: %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// RUN: --runner mlir-runner -e main \
// RUN: --entry-point-result=void \
// RUN: --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck
// RUN: imex-opt %s --gpu-lower-to-xevm-pipeline="xegpu-op-level=subgroup" \
// RUN: | mlir-runner \
// RUN: --shared-libs=%mlir_levelzero_runtime \
// RUN: --shared-libs=%mlir_runner_utils \
// RUN: --shared-libs=%mlir_c_runner_utils \
// RUN: --shared-libs=%irunner_utils \
// RUN: --entry-point-result=void \
// RUN: | FileCheck %s

// Example of pass pipeline usage:
// %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// --runner mlir-runner -e main \
// --entry-point-result=void \
// --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck


module @gemm attributes {gpu.container_module} {
Expand Down
18 changes: 14 additions & 4 deletions test/Integration/Dialect/XeGPU/SIMT/col_reduce_16x16xf16.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,17 @@
// RUN: %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// RUN: --runner mlir-runner -e main \
// RUN: --entry-point-result=void \
// RUN: --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck
// RUN: imex-opt %s --gpu-lower-to-xevm-pipeline="xegpu-op-level=lane" \
// RUN: | mlir-runner \
// RUN: --shared-libs=%mlir_levelzero_runtime \
// RUN: --shared-libs=%mlir_runner_utils \
// RUN: --shared-libs=%mlir_c_runner_utils \
// RUN: --shared-libs=%irunner_utils \
// RUN: --entry-point-result=void \
// RUN: | FileCheck %s

// Example of pass pipeline usage:
// %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// --runner mlir-runner -e main \
// --entry-point-result=void \
// --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck
module @gemm attributes {gpu.container_module} {
gpu.module @kernel {
gpu.func @col_reduce(%in: memref<16x16xf16>, %c: memref<1x16xf16>) kernel attributes {intel_reqd_sub_group_size = 16 : i32} {
Expand Down
18 changes: 14 additions & 4 deletions test/Integration/Dialect/XeGPU/SIMT/gemm_4kx4kx4k_f16_f16_f16.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,17 @@
// RUN: %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// RUN: --runner mlir-runner -e main \
// RUN: --entry-point-result=void \
// RUN: --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck
// RUN: imex-opt %s --gpu-lower-to-xevm-pipeline="xegpu-op-level=lane" \
// RUN: | mlir-runner \
// RUN: --shared-libs=%mlir_levelzero_runtime \
// RUN: --shared-libs=%mlir_runner_utils \
// RUN: --shared-libs=%mlir_c_runner_utils \
// RUN: --shared-libs=%irunner_utils \
// RUN: --entry-point-result=void \
// RUN: | FileCheck %s

// Example of pass pipeline usage:
// %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// --runner mlir-runner -e main \
// --entry-point-result=void \
// --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck
module @gemm attributes {gpu.container_module} {
func.func @test(%A: memref<4096x4096xf16>, %B: memref<4096x4096xf16>, %C: memref<4096x4096xf16>) -> memref<4096x4096xf16> attributes {llvm.emit_c_interface} {
%c1 = arith.constant 1 : index
Expand Down
18 changes: 14 additions & 4 deletions test/Integration/Dialect/XeGPU/SIMT/gemm_4kx4kx4k_transpose_b.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,17 @@
// RUN: %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// RUN: --runner mlir-runner -e main \
// RUN: --entry-point-result=void \
// RUN: --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck
// RUN: imex-opt %s --gpu-lower-to-xevm-pipeline="xegpu-op-level=lane" \
// RUN: | mlir-runner \
// RUN: --shared-libs=%mlir_levelzero_runtime \
// RUN: --shared-libs=%mlir_runner_utils \
// RUN: --shared-libs=%mlir_c_runner_utils \
// RUN: --shared-libs=%irunner_utils \
// RUN: --entry-point-result=void \
// RUN: | FileCheck %s

// Example of pass pipeline usage:
// %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// --runner mlir-runner -e main \
// --entry-point-result=void \
// --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck
module @gemm attributes {gpu.container_module} {
func.func @test(%A: memref<4096x4096xf16>, %B: memref<4096x4096xf16>, %C: memref<4096x4096xf16>) -> memref<4096x4096xf16> attributes {llvm.emit_c_interface} {
%c1 = arith.constant 1 : index
Expand Down
2 changes: 1 addition & 1 deletion test/Integration/Dialect/XeGPU/SIMT/lit.local.cfg
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
if(not config.mlir_enable_levelzero_runtime):
if(not config.mlir_enable_levelzero_runtime or not config.mlir_enable_spirv_backend):
config.unsupported = True
18 changes: 14 additions & 4 deletions test/Integration/Dialect/XeGPU/SIMT/loadstore_nd.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,17 @@
// RUN: %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// RUN: --runner mlir-runner -e main \
// RUN: --entry-point-result=void \
// RUN: --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck
// RUN: imex-opt %s --gpu-lower-to-xevm-pipeline="xegpu-op-level=lane" \
// RUN: | mlir-runner \
// RUN: --shared-libs=%mlir_levelzero_runtime \
// RUN: --shared-libs=%mlir_runner_utils \
// RUN: --shared-libs=%mlir_c_runner_utils \
// RUN: --shared-libs=%irunner_utils \
// RUN: --entry-point-result=void \
// RUN: | FileCheck %s

// Example of pass pipeline usage:
// %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// --runner mlir-runner -e main \
// --entry-point-result=void \
// --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck

module @gemm attributes {gpu.container_module} {
gpu.module @kernel {
Expand Down
18 changes: 14 additions & 4 deletions test/Integration/Dialect/XeGPU/SIMT/loadstore_nd_dpas.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,17 @@
// RUN: %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// RUN: --runner mlir-runner -e main \
// RUN: --entry-point-result=void \
// RUN: --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck
// RUN: imex-opt %s --gpu-lower-to-xevm-pipeline="xegpu-op-level=lane" \
// RUN: | mlir-runner \
// RUN: --shared-libs=%mlir_levelzero_runtime \
// RUN: --shared-libs=%mlir_runner_utils \
// RUN: --shared-libs=%mlir_c_runner_utils \
// RUN: --shared-libs=%irunner_utils \
// RUN: --entry-point-result=void \
// RUN: | FileCheck %s

// Example of pass pipeline usage:
// %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// --runner mlir-runner -e main \
// --entry-point-result=void \
// --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck

#sg_map_a_f16 = #xegpu.layout<lane_layout = [1, 16], lane_data = [1, 1]>
#sg_map_b_f16 = #xegpu.layout<lane_layout = [1, 16], lane_data = [2, 1]>
Expand Down
18 changes: 14 additions & 4 deletions test/Integration/Dialect/XeGPU/SIMT/loadstore_nd_prefetch.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,17 @@
// RUN: %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// RUN: --runner mlir-runner -e main \
// RUN: --entry-point-result=void \
// RUN: --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck
// RUN: imex-opt %s --gpu-lower-to-xevm-pipeline="xegpu-op-level=lane" \
// RUN: | mlir-runner \
// RUN: --shared-libs=%mlir_levelzero_runtime \
// RUN: --shared-libs=%mlir_runner_utils \
// RUN: --shared-libs=%mlir_c_runner_utils \
// RUN: --shared-libs=%irunner_utils \
// RUN: --entry-point-result=void \
// RUN: | FileCheck %s

// Example of pass pipeline usage:
// %python_executable %imex_runner --requires=mlir-levelzero-runtime,spirv-backend -i %s --pass-pipeline-file=%p/xegpu-to-llvm.pp \
// --runner mlir-runner -e main \
// --entry-point-result=void \
// --shared-libs=%irunner_utils,%mlir_runner_utils,%mlir_c_runner_utils,%mlir_levelzero_runtime --filecheck

module @gemm attributes {gpu.container_module} {
gpu.module @kernel {
Expand Down
Loading
Loading