fix: require CUDA_STANDARD 20 in Plugins/Cuda

[wdconinc]

This PR requires CUDA_STANDARD 20 in the CUDA plugin, which is required since the use of the numbers header in #3781 (specifically through Acts/Definitions/Units.hpp.

--- END COMMIT MESSAGE ---

It does not see that Plugins/ExaTrkX needs CUDA_STANDARD 20 just yet, since it does not seem that

Summary by CodeRabbit

• Chores
  • Updated GPU configuration to require the latest standard, ensuring enhanced compatibility and stability with modern GPU technologies.

[coderabbitai]

Walkthrough

Changes made, they have. In the CMake configuration of the ActsPluginCuda2 library, new CUDA properties added are. The CUDA standard now set to version 20 and its requirement enabled, these changes are. Existing properties such as CUDA_SEPARABLE_COMPILATION and POSITION_INDEPENDENT_CODE, unchanged they remain. Focusing solely on property declarations, the file’s configuration is enhanced with these precise settings.

Changes

File(s)	Change Summary
Plugins/Cuda/CMakeLists.txt	Updated target properties for ActsPluginCuda2: added CUDA_STANDARD 20 and CUDA_STANDARD_REQUIRED ON; retained existing CUDA_SEPARABLE_COMPILATION ON and POSITION_INDEPENDENT_CODE ON.

Suggested labels

Component - Plugins, automerge

Suggested reviewers

• stephenswat
• paulgessinger

Poem

In the cmake realm, new force we set,
CUDA 20 shines like a rising sunset.
Properties align as the wise ones decree,
Stable and strong, our code, it will be.
Mmm, celebrate we must, for progress is true!
Enjoy the change, young padawan, you do.

---

📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between d781484 and fee739d.

📒 Files selected for processing (1)

• Plugins/Cuda/CMakeLists.txt (1 hunks)

⏰ Context from checks skipped due to timeout of 90000ms (21)

• GitHub Check: merge-sentinel
• GitHub Check: CI Bridge / build_gnn_tensorrt
• GitHub Check: unused_files
• GitHub Check: missing_includes
• GitHub Check: linux_ubuntu_extra (ubuntu2204, 20, clang++)
• GitHub Check: CI Bridge / lcg_106a: [alma9, clang16]
• GitHub Check: linux_ubuntu_extra (ubuntu2204, 20, g++)
• GitHub Check: CI Bridge / lcg_106a: [alma9, gcc14]
• GitHub Check: CI Bridge / lcg_106a: [alma9, gcc13]
• GitHub Check: CI Bridge / lcg_105: [alma9, clang16]
• GitHub Check: CI Bridge / lcg_105: [alma9, gcc13]
• GitHub Check: CI Bridge / build_linux_ubuntu
• GitHub Check: CI Bridge / linux_ubuntu_2204_clang
• GitHub Check: CI Bridge / linux_ubuntu_2204
• GitHub Check: CI Bridge / build_exatrkx
• GitHub Check: linux_ubuntu
• GitHub Check: CI Bridge / build_exatrkx_cpu
• GitHub Check: CI Bridge / clang_tidy
• GitHub Check: build_debug
• GitHub Check: docs
• GitHub Check: macos

🔇 Additional comments (2)

Plugins/Cuda/CMakeLists.txt (2)

48-55: Wise changes these are, hmmmm.

Correctly set, the CUDA standard properties are. Align with the PR objectives, they do, as the numbers header through Acts/Definitions/Units.hpp, CUDA 20 requires.

---

48-55: Verify the build configuration, we must.

For different CUDA toolkit versions, test the build we should. Ensure backward compatibility or proper error messages, we must.

❌ Verification inconclusive

🏁 Script executed:

#!/bin/bash
# Description: Check minimum CUDA version requirement in the build system

# Search for CUDA version checks in CMake files
rg -g "CMakeLists.txt" -g "*.cmake" "find_package\(.*CUDA.*\)" -A 3

Length of output: 292

---

Build configuration for CUDA versions requires manual verification, it does.

The main CMakeLists.txt uses find_package(CUDAToolkit REQUIRED) and the CUDA target is set with CUDA_STANDARD 20, which implies a recent toolkit is expected. However, no explicit version check is visible to guarantee backward compatibility or to emit clear error messages when older CUDA versions are used. Testing with various CUDA toolkit versions remains advisable, it is.

• The build system relies on CMake’s built-in detection via find_package(CUDAToolkit REQUIRED).
• No explicit minimum version is enforced beyond the target property for CUDA standard.
• Manual testing across different CUDA versions is recommended to ensure proper error reporting if an unsupported version is installed.

---

Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Generate unit testing code for this file.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai generate unit testing code for this file.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read src/utils.ts and generate unit testing code.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai generate docstrings to generate docstrings for this PR. (Beta)
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.

[github-actions]

📊: Physics performance monitoring for fee739d

Full contents

physmon summary

• ✅ Particles fatras
• ✅ Particles geant4
• ✅ Particles ttbar
• ✅ Vertices ttbar
• ✅ Truth tracking (KF)
• ✅ Truth tracking (GSF)
• ✅ Truth tracking (GX2F)
• ✅ Truth tracking (KF refit)
• ✅ Truth tracking (GSF refit)
• ✅ CKF finding performance | trackfinding | single muon | truth smeared seeding
• ✅ CKF fitting performance | trackfinding | single muon | truth smeared seeding
• ✅ CKF track summary | trackfinding | single muon | truth smeared seeding
• ✅ Seeding trackfinding | single muon | truth estimated seeding
• ✅ CKF finding performance | trackfinding | single muon | truth estimated seeding
• ✅ CKF fitting performance | trackfinding | single muon | truth estimated seeding
• ✅ CKF track summary | trackfinding | single muon | truth estimated seeding
• ✅ Seeding trackfinding | single muon | default seeding
• ✅ CKF finding performance | trackfinding | single muon | default seeding
• ✅ CKF fitting performance | trackfinding | single muon | default seeding
• ✅ CKF track summary | trackfinding | single muon | default seeding
• ✅ Seeding trackfinding | single muon | orthogonal seeding
• ✅ CKF finding performance | trackfinding | single muon | orthogonal seeding
• ✅ CKF fitting performance | trackfinding | single muon | orthogonal seeding
• ✅ CKF track summary | trackfinding | single muon | orthogonal seeding
• ✅ Seeding trackfinding | 4 muon x 50 vertices | default seeding
• ✅ CKF finding performance | trackfinding | 4 muon x 50 vertices | default seeding
• ✅ CKF fitting performance | trackfinding | 4 muon x 50 vertices | default seeding
• ✅ CKF track summary | trackfinding | 4 muon x 50 vertices | default seeding
• ✅ Ambisolver finding performance | trackfinding | 4 muon x 50 vertices | default seeding
• ✅ IVF notime | trackfinding | 4 muon x 50 vertices | default seeding
• ✅ AMVF gauss notime | trackfinding | 4 muon x 50 vertices | default seeding
• ✅ AMVF grid time | trackfinding | 4 muon x 50 vertices | default seeding
• ✅ Seeding trackfinding | ttbar with 200 pileup | default seeding
• ✅ CKF finding performance | trackfinding | ttbar with 200 pileup | default seeding
• ✅ CKF fitting performance | trackfinding | ttbar with 200 pileup | default seeding
• ✅ CKF track summary | trackfinding | ttbar with 200 pileup | default seeding
• ✅ Ambisolver finding performance | trackfinding | ttbar with 200 pileup | default seeding
• ✅ ML Ambisolver | trackfinding | ttbar with 200 pileup | default seeding
• ✅ AMVF gauss notime | trackfinding | ttbar with 200 pileup | default seeding
• ✅ AMVF grid time | trackfinding | ttbar with 200 pileup | default seeding

[sonarqubecloud]

Quality Gate passed

Issues
0 New issues
0 Accepted issues

Measures
0 Security Hotspots
0.0% Coverage on New Code
0.0% Duplication on New Code

See analysis details on SonarQube Cloud

[krasznaa]

This formalism seems fine to solve the current issue.

I personally prefer to set C++ standards for the different languages through cache variables. For instance CMAKE_CUDA_STANDARD in this case. Similar to what we do in traccc.

https://github.com/acts-project/traccc/blob/main/CMakeLists.txt#L11-L17

(As it makes it easier to try a different standards in the CI for instance.)

But as I started, for this largely defunct library this seems like a fine solution.