Drop thrust/functional it is almost not used at all

[miscco]

No description provided.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between b8b40b7 and 4626336.

📒 Files selected for processing (1)

• cpp/src/tsne/distances.cuh

🚧 Files skipped from review as they are similar to previous changes (1)

• cpp/src/tsne/distances.cuh

---

📝 Walkthrough

Summary by CodeRabbit

• Chores

  • Updated copyright years to 2026 across multiple files.
  • Streamlined internal header/dependency usage to reduce unused includes.

• Compatibility

  • Switched a few internal utilities to CUDA-standard equivalents to improve consistency and build robustness.

Walkthrough

Removed unused <thrust/functional.h> includes across multiple CUDA/C++ sources, replaced one thrust::logical_not<bool>() with cuda::std::logical_not<bool>(), and updated several copyright years from 2025 to 2026.

Changes

Cohort / File(s)	Summary
DBSCAN vertexdeg cpp/src/dbscan/vertexdeg/algo.cuh	Removed several Thrust includes (execution_policy, functional, constant_iterator, counting_iterator, transform); updated copyright year 2025→2026.
HDBSCAN & utilities cpp/src/hdbscan/condensed_hierarchy.cu, cpp/src/hdbscan/detail/select.cuh, cpp/src/hdbscan/detail/utils.h	Removed unused <thrust/functional.h> includes; no other logic or API changes.
GLM & TSNE files cpp/src/glm/qn/glm_base.cuh, cpp/src/tsne/distances.cuh, cpp/src/tsne/fft_tsne.cuh	Updated copyright years (2025→2026 variants) and removed <thrust/functional.h> includes; replaced thrust::maximum with cuda::maximum in normalize_distances.
Genetic / TimeSeries / Primitives / Tests cpp/src/genetic/fitness.cuh, cpp/src_prims/timeSeries/stationarity.cuh, cpp/tests/sg/rf_test.cu	Removed unused <thrust/functional.h> includes; no behavioral or API changes.
TSA auto_arima cpp/src/tsa/auto_arima.cuh	Switched to <cuda/std/functional> and replaced thrust::logical_not<bool>() with cuda::std::logical_not<bool>() in divide_by_mask_build_index.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Suggested reviewers

• dantegd
• lowener
• csadorf

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 inconclusive)

Check name	Status	Explanation	Resolution
Description check	❓ Inconclusive	No pull request description was provided by the author. While this is not ideal, the title and changeset context are sufficient to understand the purpose.	Add a description explaining why thrust/functional is being removed and its impact on the codebase.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change: removing thrust/functional header includes across multiple files. It is specific and directly related to the changeset.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment

Tip

Issue Planner is now in beta. Read the docs and try it out! Share your feedback on Discord.

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (1)

cpp/src/tsne/distances.cuh (1)

141-148: ⚠️ Potential issue | 🔴 Critical

thrust::maximum<value_t>() requires thrust/functional.h, which was removed in the recent refactoring.

At Line 146, the code uses thrust::maximum<value_t>() from a header that is no longer included. While thrust/transform_reduce.h may transitively pull it in, this is an undocumented implementation detail that can break with future Thrust library changes.

<cuda/functional> is already included (Line 24) and provides the direct replacement: cuda::maximum<value_t>{}. This aligns with the preference for libcudacxx facilities over Thrust equivalents.

Proposed fix

-                                             thrust::maximum<value_t>());
+                                             cuda::maximum<value_t>{});

🤖 Prompt for AI Agents

Verify each finding against the current code and only fix it if needed.

In `@cpp/src/tsne/distances.cuh` around lines 141 - 148, Replace the use of
thrust::maximum<value_t>() in the transform_reduce that computes maxNorm with
cuda::maximum<value_t>{} (since <cuda/functional> is already included) to avoid
relying on the removed thrust/functional header; update the call site in the
block that computes maxNorm (the thrust::transform_reduce over
distances/total_nn that assigns to maxNorm) so it uses cuda::maximum and leaves
the subsequent raft::linalg::scalarMultiply(distances, distances, 1.0f /
maxNorm, total_nn, stream) unchanged.

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Outside diff comments:
In `@cpp/src/tsne/distances.cuh`:
- Around line 141-148: Replace the use of thrust::maximum<value_t>() in the
transform_reduce that computes maxNorm with cuda::maximum<value_t>{} (since
<cuda/functional> is already included) to avoid relying on the removed
thrust/functional header; update the call site in the block that computes
maxNorm (the thrust::transform_reduce over distances/total_nn that assigns to
maxNorm) so it uses cuda::maximum and leaves the subsequent
raft::linalg::scalarMultiply(distances, distances, 1.0f / maxNorm, total_nn,
stream) unchanged.

---

ℹ️ Review info

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 237e589 and b8b40b7.

📒 Files selected for processing (11)

• cpp/src/dbscan/vertexdeg/algo.cuh
• cpp/src/genetic/fitness.cuh
• cpp/src/glm/qn/glm_base.cuh
• cpp/src/hdbscan/condensed_hierarchy.cu
• cpp/src/hdbscan/detail/select.cuh
• cpp/src/hdbscan/detail/utils.h
• cpp/src/tsa/auto_arima.cuh
• cpp/src/tsne/distances.cuh
• cpp/src/tsne/fft_tsne.cuh
• cpp/src_prims/timeSeries/stationarity.cuh
• cpp/tests/sg/rf_test.cu

💤 Files with no reviewable changes (6)

• cpp/src/genetic/fitness.cuh
• cpp/tests/sg/rf_test.cu
• cpp/src/hdbscan/detail/utils.h
• cpp/src_prims/timeSeries/stationarity.cuh
• cpp/src/hdbscan/detail/select.cuh
• cpp/src/hdbscan/condensed_hierarchy.cu

[lowener]

LGTM

[aamijar]

/merge