[SYCLTLA] Upgrade SYCLTLA version to v0.9

[LuFinch]

No description provided.

[Copilot]

Pull request overview

Read skill file(s): .github/skills/xpu-ops-pr-review/SKILL.md.

This PR updates the build-time FetchContent pin for the SYCL-TLA dependency used by the XPU build, moving the fetched intel/sycl-tla tag forward to v0.9.

Changes:

• Bump intel/sycl-tla FetchContent GIT_TAG from v0.8 to v0.9.

[Copilot]

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated no new comments.

[chuanqi129]

@copilot New UT failures detected in op_ut tests (5 total). Please check these new failures and analyze whether they are caused by the PR changes.

Important: Do NOT update the plan in the PR description directly. Use reply comments to update the status.

Job log: https://github.com/intel/torch-xpu-ops/actions/runs/26081527992
Full new failure report: https://github.com/intel/torch-xpu-ops/actions/runs/26081527992/artifacts/7091170862

New failures:

Category	Class name	Test name	Status	Message
op_ut	third_party.torch-xpu-ops.test.xpu.dynamo.test_regional_inductor_xpu.RegionalInductorInvokeSubgraphTests	test_max_autotune_no_cudagraphs_serialize_False	failed	AttributeError: module 'torch._inductor' has no attribute 'compile_fx'
op_ut	third_party.torch-xpu-ops.test.xpu.functorch.test_control_flow_xpu.TestControlFlowTraced	test_while_loop_autograd_simple	failed	AssertionError: 'clas[152 chars] zeros: "i64[]" = torch.ops.aten.zeros.def[3514 chars]1)\n' != 'clas[152 chars] clone: "f32[3, 3]" = torch.ops.aten.clone[3636 chars]1)\n'
op_ut		third_party.torch-xpu-ops.test.xpu.functorch.test_ops_xpu	error	ImportError: cannot import name 'skipOps' from 'common_utils' (/__w/torch-xpu-ops/torch-xpu-ops/pytorch/third_party/torch-xpu-ops/test/xpu/../../../../test/functorch/common_utils.py)
op_ut		third_party.torch-xpu-ops.test.xpu.functorch.test_vmap_xpu	error	ImportError: cannot import name 'skipOps' from 'common_utils' (/__w/torch-xpu-ops/torch-xpu-ops/pytorch/third_party/torch-xpu-ops/test/xpu/../../../../test/functorch/common_utils.py)
op_ut		third_party.torch-xpu-ops.test.xpu.test_decomp_xpu	error	ImportError: cannot import name 'skip' from 'torch.testing._internal.common_methods_invocations' (/tmp/xpu-tool/Python/3.10.20/x64/lib/python3.10/site-packages/torch/testing/_internal/common_methods_invocations.py)

Instructions:

1. Download the full new failure report artifact for complete error messages
2. Analyze whether the failures are caused by PR changes
3. If caused by PR changes, fix those failures on this PR branch directly
4. Add failing test cases with pytest commands in the PR description for the reproducer job to use
5. Use reply comments to report analysis status - do NOT modify the PR description plan directly

[Copilot]

@copilot New UT failures detected in op_ut tests (5 total). Please check these new failures and analyze whether they are caused by the PR changes.

**Important: Do NOT update the plan in the PR de...

Checked run 26081527992 logs + artifacts (New-UT-Failures and Inductor-XPU-UT-Data) and analyzed against commit 2fa1831.

Conclusion: these failures are not caused by this PR change. This PR only bumps cmake/SYCLTLA.cmake GIT_TAG (v0.8 -> v0.9) for build-time FetchContent; the reported failures are Python test/API mismatch and expected-text drift (torch._inductor.compile_fx missing, skipOps/skip import changes, functorch expected graph text mismatch), which are outside this CMake pin change.

I also see 2 additional new op_ut failures in the same new_ut_failure_list.csv artifact (test_pre_grad, test_get_device_properties_tensor_device) with similar upstream API drift symptoms.

Reproducer commands (from repo root pytorch/third_party/torch-xpu-ops/test/xpu):

• pytest -sv dynamo/test_regional_inductor_xpu.py -k test_max_autotune_no_cudagraphs_serialize_False
• pytest -sv functorch/test_control_flow_xpu.py -k test_while_loop_autograd_simple
• pytest -sv functorch/test_ops_xpu.py
• pytest -sv functorch/test_vmap_xpu.py
• pytest -sv test_decomp_xpu.py