Repository navigation
Merge recent PRs in development - #2761
Closed
chuanyuf wants to merge 2 commits into
Closed
chuanyuf wants to merge 2 commits into
chuanyuf wants to merge 2 commits into
Conversation
Copy link
Copy Markdown
Contributor
Sorry, something went wrong.
2025.3 Guided Debugging Sample updates
Updates for oneAPI 2026.0 tools and drivers
Copy link
Copy Markdown
There was a problem hiding this comment.
Pull request overview
Updates several guided debugging matrix-multiplication samples for Intel® oneAPI 2026.0 by refreshing documentation/tooling requirements, bumping CMake minimum version, and addressing USM lifetime management.
Changes:
- Add explicit sycl::free(...) calls to release USM allocations after use in multiple samples.
- Refresh README prerequisites/instructions for oneAPI 2026.0 (compiler/GDB/PTI versions, driver guidance, updated troubleshooting steps).
- Increase cmake_minimum_required from 3.4 to 3.5 for the affected sample projects.
Reviewed changes
Copilot reviewed 19 out of 19 changed files in this pull request and generated 13 comments.
Show a summary per file| File | Description |
|---|---|
| Tools/ApplicationDebugger/guided_matrix_mult_SLMSize/src/1_matrix_mul_SLM_size.cpp | Frees USM allocations after host copy-back. |
| Tools/ApplicationDebugger/guided_matrix_mult_SLMSize/src/2_matrix_mul.cpp | Frees USM allocations after host copy-back. |
| Tools/ApplicationDebugger/guided_matrix_mult_SLMSize/README.md | Updates oneAPI 2026.0 prerequisites/instructions; minor wording changes. |
| Tools/ApplicationDebugger/guided_matrix_mult_SLMSize/CMakeLists.txt | Bumps CMake minimum version to 3.5. |
| Tools/ApplicationDebugger/guided_matrix_mult_RaceCondition/README.md | Updates oneAPI 2026.0 prerequisites/instructions; refines debugging narrative. |
| Tools/ApplicationDebugger/guided_matrix_mult_RaceCondition/CMakeLists.txt | Bumps CMake minimum version to 3.5. |
| Tools/ApplicationDebugger/guided_matrix_mult_InvalidContexts/src/1_matrix_mul_invalid_contexts.cpp | Adds device enumeration/selection logic and frees USM allocations. |
| Tools/ApplicationDebugger/guided_matrix_mult_InvalidContexts/src/2_matrix_mul.cpp | Adds device enumeration output and frees USM allocations. |
| Tools/ApplicationDebugger/guided_matrix_mult_InvalidContexts/README.md | Updates oneAPI 2026.0 prerequisites/instructions; adds device-order caveats. |
| Tools/ApplicationDebugger/guided_matrix_mult_InvalidContexts/CMakeLists.txt | Bumps CMake minimum version to 3.5. |
| Tools/ApplicationDebugger/guided_matrix_mult_Exceptions/src/1_matrix_mul_null_pointer.cpp | Frees USM allocations after host copy-back. |
| Tools/ApplicationDebugger/guided_matrix_mult_Exceptions/src/2_matrix_mul_multi_offload.cpp | Frees USM allocations after host copy-back. |
| Tools/ApplicationDebugger/guided_matrix_mult_Exceptions/src/3_matrix_mul.cpp | Frees USM allocations after host copy-back. |
| Tools/ApplicationDebugger/guided_matrix_mult_Exceptions/README.md | Updates oneAPI 2026.0 prerequisites/instructions and debugging notes. |
| Tools/ApplicationDebugger/guided_matrix_mult_Exceptions/CMakeLists.txt | Bumps CMake minimum version to 3.5. |
| Tools/ApplicationDebugger/guided_matrix_mult_BadBuffers/src/b1_matrix_mul_null_usm.cpp | Frees USM allocations after host copy-back. |
| Tools/ApplicationDebugger/guided_matrix_mult_BadBuffers/src/b2_matrix_mul_usm.cpp | Frees USM allocations after host copy-back. |
| Tools/ApplicationDebugger/guided_matrix_mult_BadBuffers/README.md | Updates oneAPI 2026.0 prerequisites/instructions; expands sanitizer/debugger walkthroughs. |
| Tools/ApplicationDebugger/guided_matrix_mult_BadBuffers/CMakeLists.txt | Bumps CMake minimum version to 3.5. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Sorry, something went wrong.
Comment thread
...ApplicationDebugger/guided_matrix_mult_InvalidContexts/src/1_matrix_mul_invalid_contexts.cpp
| // used to enqueue kernels. It encapsulates all states needed for execution. | ||
| { | ||
| queue q(default_selector_v); | ||
| property_list propList = property_list{property::queue::enable_profiling()}; |
Comment thread
...ApplicationDebugger/guided_matrix_mult_InvalidContexts/src/1_matrix_mul_invalid_contexts.cpp
Comment on lines
+68
to
+70
| std::vector<sycl::device> devices = sycl::device::get_devices(); | ||
| cout << "Devices:" << std::endl; | ||
|
|
| @@ -65,6 +65,19 @@ int main() { | |||
| { | |||
| property_list propList = property_list{property::queue::enable_profiling()}; | |||
Comment on lines
+33
to
+34
| | Intel GraphicsHardware | GEN9 or newer | ||
| | Software | Intel® oneAPI DPC++/C++ Compiler 2026.0 <br> Intel® Distribution for GDB* 2026.0 <br> Unified Tracing and Profiling Tool 2.3.0, which is available from the [following Github repository](https://github.com/intel/pti-gpu/tree/master/tools/unitrace). |
| ``` | ||
|
|
||
| Similarly, we specify targeting the CPU, which sometimes can avoid problems in your code that are specific to offloading to the GPU. | ||
| Similarly, we an force the program to run on the CPU, which sometimes can avoid problems in your code that are specific to offloading to the GPU. |
Comment on lines
+9
to
10
| | What you will learn | A method to determine the root cause problems from passing bad data through the SYCL runtime. | ||
| | Time to complete | 50 minutes |
| | Software | Intel® oneAPI DPC++/C++ Compiler 2025.1 <br> Intel® Distribution for GDB* 2025.1 <br> Unified Tracing and Profiling Tool 2.1.2, which is available from the [following Github repository](https://github.com/intel/pti-gpu/tree/master/tools/unitrace). | ||
| | Intel GPU Driver | Intel® General-Purpose GPU Rolling Release driver 2507.12 or later from https://dgpu-docs.intel.com/releases/releases.html | ||
| | Intel Graphics Hardware | GEN9 or newer | ||
| | Software | Intel® oneAPI DPC++/C++ Compiler 2026.0 <br> Intel® Distribution for GDB* 2026.0 <br> Unified Tracing and Profiling Tool 2.3.0, which is available from the [following Github repository](https://github.com/intel/pti-gpu/tree/master/tools/unitrace). |
| | Software | Intel® oneAPI DPC++/C++ Compiler 2025.1 <br> Intel® Distribution for GDB* 2025.1 <br> Unified Tracing and Profiling Tool 2.1.2, which is available from the [following Github repository](https://github.com/intel/pti-gpu/tree/master/tools/unitrace). | ||
| | Intel GPU Driver | Intel® General-Purpose GPU Rolling Release driver 2507.12 or later from https://dgpu-docs.intel.com/releases/releases.html | ||
| | Intel Graphics Hardware | GEN9 or newer | ||
| | Software | Intel® oneAPI DPC++/C++ Compiler 2026.0 <br> Intel® Distribution for GDB* 2026.0 <br> Unified Tracing and Profiling Tool 2.3.0, which is available from the [following Github repository](https://github.com/intel/pti-gpu/tree/master/tools/unitrace). |
| ### Identify the Problem without Code Inspection | ||
|
|
||
| You must have already built the [Unified Tracing and Profiling Tool](#getting-the-tracing-and-profiling-tool). Once you have built the utility, you can start it before your program (similar to using GBD). | ||
| You need to build the [Unified Tracing and Profiling Tool](#getting-the-tracing-and-profiling-tool) before completing this section. Once you have built the utility, you can start it before your program (similar to using GBD). |
| #### Debugging the Problem | ||
|
|
||
| Why did we try with multiple backends? If one had shown correct or incorrect results, and one had crashed, we might be facing a race condition that only occasionally manifests as something that goes terribly wrong. Or one of the backbends might have a bug. But here all three crash, so it's likely the program is doing something illegal to memory. The host CPU is a particularly good place to test for illegal memory accesses, because the CPU never allows pointers with an address within a few kilobytes of address 0x0, while this may be legally allocated memory on the GPU. | ||
| Why did we try with multiple backends? If one had shown correct or incorrect results, and one had crashed, we might be facing a race condition that only occasionally manifests when something goes terribly wrong. Or one of the backbends might have a bug while the others do not. But here all three crash, so it's likely the program is doing something illegal to memory. The host CPU is a particularly good place to test for illegal memory accesses, because the CPU never allows pointers with an address within a few kilobytes of address `0x0`, while this may be legally allocated memory on the GPU. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Existing Sample Changes
Description
Guided Debugging Sample updates, Updates for oneAPI 2026.0 tools and drivers
Update cmake to at least 3.5, update readme document, and ensure memory release after use.
No new functions added for the PRs.
How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration