Skip to content

[CI][L0 v2] Add to CI options for L0v2 adapter #20890

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

Open
luszczewskakasia1 wants to merge 4 commits into
base: sycl
Choose a base branch
from
Open

[CI][L0 v2] Add to CI options for L0v2 adapter #20890

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
55b2227
[CI][L0 v2] Add to CI options for L0v2 adapter
luszczewskakasia1 Dec 15, 2025
87d4732
disable AddressSanitizer tests
mateuszpn Dec 15, 2025
9568cd0
disable failing tests
mateuszpn Dec 15, 2025
378a189
fix of bindless_images/read_sampled.cpp test to be run on proper device
mateuszpn Dec 18, 2025
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: 4 additions & 0 deletions .github/workflows/sycl-linux-precommit.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -189,6 +189,10 @@ jobs:
target_devices: level_zero:gpu;opencl:gpu;opencl:cpu
extra_lit_opts: --param test-preview-mode=True
binaries_artifact: e2e_bin_preview
- name: L0 v2
runner: '["L0v2_arl"]'
target_devices: level_zero_v2:arch-intel_gpu_mtl_u
Copy link
Contributor

@pbalcer pbalcer Dec 15, 2025 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

mtl? shouldn't this be arl?

Copy link
Contributor

@mateuszpn mateuszpn Dec 15, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lscpu: "Intel(R) Core(TM) Ultra 7 265"
sycl-ls: "Architecture: intel_gpu_mtl_u"

Copy link
Contributor

@pbalcer pbalcer Dec 16, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

So the tool is incorrectly identifying the architecture. That seems like a bug.

Copy link
Contributor

@mateuszpn mateuszpn Dec 16, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

#20910

extra_lit_opts: --param test-preview-mode=True

# We're in an ABI-breaking window, so these don't make sense for now.
- name: ABI compatibility / sycl-rel-6_2
Expand Down
2 changes: 2 additions & 0 deletions .github/workflows/sycl-linux-run-tests.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -158,6 +158,7 @@ on:
- '["Linux", "build"]'
- '["cuda"]'
- '["PVC_PERF"]'
- '["L0v2_arl"]'
image:
type: choice
options:
Expand All @@ -181,6 +182,7 @@ on:
- 'opencl:gpu'
- 'hip:gpu'
- 'cuda:gpu'
- 'level_zero_v2:arch-intel_gpu_mtl_u'
tests_selector:
type: choice
options:
Expand Down
3 changes: 3 additions & 0 deletions sycl/test-e2e/Adapters/level_zero/ext_intel_cslice.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,9 @@
// XFAIL: windows && arch-intel_gpu_bmg_g21
// XFAIL-TRACKER: https://github.com/intel/llvm/issues/18576

// XFAIL: linux && arch-intel_gpu_mtl_u
// XFAIL-TRACKER: https://github.com/intel/llvm/issues/20896

// RUN: %{build} -Wno-error=deprecated-declarations -o %t.out

// TODO: at this time PVC 1T systems are not correctly supporting CSLICE
Expand Down
3 changes: 3 additions & 0 deletions sycl/test-e2e/Adapters/level_zero/ext_intel_queue_index.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,9 @@
// XFAIL: windows && arch-intel_gpu_bmg_g21
// XFAIL-TRACKER: https://github.com/intel/llvm/issues/18576

// XFAIL: linux && arch-intel_gpu_mtl_u
// XFAIL-TRACKER: https://github.com/intel/llvm/issues/20896

// RUN: %{build} -o %t.out

// TODO: at this time PVC 1T systems are not correctly supporting CSLICE
Expand Down
3 changes: 3 additions & 0 deletions sycl/test-e2e/AddressSanitizer/lit.local.cfg
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,9 @@ config.unsupported_features += ['spirv-backend']
# https://github.com/intel/llvm/issues/16920
config.unsupported_features += ['arch-intel_gpu_bmg_g21']

# https://github.com/intel/llvm/issues/20894
config.unsupported_features += ['arch-intel_gpu_mtl_u']

# https://github.com/intel/llvm/issues/20142
config.unsupported_features += ['target-native_cpu']
unsupported_san_flags = [
Expand Down
4 changes: 4 additions & 0 deletions sycl/test-e2e/Basic/interop/ze_context_device.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,8 @@
// REQUIRES: level_zero, level_zero_dev_kit

// UNSUPPORTED: arch-intel_gpu_mtl_u
// UNSUPPORTED-TRACKER: https://github.com/intel/llvm/issues/20898

// RUN: %{build} -o %t.out %level_zero_options
// RUN: %{run} %t.out

Expand Down
3 changes: 3 additions & 0 deletions sycl/test-e2e/Config/allowlist.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,6 @@
// UNSUPPORTED: linux && arch-intel_gpu_mtl_u
// UNSUPPORTED-TRACKER: https://github.com/intel/llvm/issues/20899

// RUN: %{build} -o %t.out
//
// RUN: env PRINT_DEVICE_INFO=1 %{run-unfiltered-devices} %t.out > %t1.conf
Expand Down
2 changes: 1 addition & 1 deletion sycl/test-e2e/GroupAlgorithm/SYCL2020/group_sort/group_and_joint_sort.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
// UNSUPPORTED: target-nvidia || target-amd
// UNSUPPORTED-INTENDED: subgroup size requirement implicitly make nvptx/amdgcn
// not supported
// XFAIL: linux && run-mode && (gpu-intel-gen12 || gpu-intel-dg2)
// XFAIL: linux && run-mode && (gpu-intel-gen12 || gpu-intel-dg2 || arch-intel_gpu_mtl_u)
// XFAIL-TRACKER: https://github.com/intel/llvm/issues/18577

// RUN: %{build} -fsycl-device-code-split=per_kernel -o %t.out
Expand Down
3 changes: 2 additions & 1 deletion sycl/test-e2e/KernelAndProgram/free_function_kernels.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
// REQUIRES: aspect-usm_shared_allocations
// RUN: %{build} -o %t.out
// RUN: %{run} %t.out
// UNSUPPORTED: run-mode && (gpu-intel-gen12 || gpu-intel-dg2 || gpu-intel-pvc-1T || arch-intel_gpu_bmg_g21 )
// UNSUPPORTED: run-mode && (gpu-intel-gen12 || gpu-intel-dg2 || gpu-intel-pvc-1T)
// UNSUPPORTED: run-mode && (arch-intel_gpu_bmg_g21 || arch-intel_gpu_mtl_u)
// UNSUPPORTED-TRACKER: https://github.com/intel/llvm/issues/20244
// This test tests free function kernel code generation and execution.

Expand Down
4 changes: 4 additions & 0 deletions sycl/test-e2e/Regression/cache_test.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,8 @@
// REQUIRES: level_zero, level_zero_dev_kit

// UNSUPPORTED: arch-intel_gpu_mtl_u
// UNSUPPORTED-TRACKER: https://github.com/intel/llvm/issues/20900

// RUN: %{build} %level_zero_options -o %t.out
// RUN: %{run} %t.out

Expand Down
2 changes: 1 addition & 1 deletion sycl/test-e2e/bindless_images/read_sampled.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
// UNSUPPORTED: hip
// UNSUPPORTED-INTENDED: Returning non-FP values from sampling fails on HIP.

// UNSUPPORTED: linux && arch-intel_gpu_bmg_g21 && level_zero_v2_adapter
// UNSUPPORTED: linux && ( arch-intel_gpu_bmg_g21 || arch-intel_gpu_mtl_u ) && level_zero_v2_adapter
// UNSUPPORTED-TRACKER: https://github.com/intel/llvm/issues/20223

// RUN: %{build} -o %t.out
Expand Down
Loading