All organizations · GSoC 2026 · Science and medicine, Programming languages

Ste||ar group

Shaping a Scalable Future

The STE||AR Group is an international team of researchers who understand that a new approach to parallel computation is needed. Our work is crafted around the idea that we need to invent new ways to more efficiently use the resources that we have and use the knowledge that we gain to help guide the creation of the machines of tomorrow. This organization aims to support, coordinate, and distribute research done in this area by creating a marketplace of ideas where concepts are debated and solutions are transparently developed.

  • c++
  • hpc
  • library
  • optimization
  • parallel algorithms
  • hpx
  • application

Project ideas

43 ideas on its 2026 ideas page; of the 43 that state a difficulty: 6 easy, 12 medium, 25 hard. Sizes: 13 medium, 28 large. 24 mentors named.

  1. Annotate HPX with Contracts large hard
  2. Expose HPX using C++ Modules large hard
  3. Implement the makereceiverfor optimization for HPX Senders medium hard
  4. Implement hpx::systemscheduler as described in P2079 (System Execution Context) large hard
  5. Integrate HPX with the Tracy profiler large hard
  6. Use C++26 reflection for HPX remote operation large hard
  7. Hierarchical Collectives for HPX large medium
  8. Implement parallel hpx::uninitializedrelocate algorithms for overlapping ranges medium hard
  9. Add HPX to Compiler Explorer (godbolt.org) medium hard
  10. Improve ChplX - Source to Source Transformer for chapel to C++ using HPX large medium
  11. "Green out" our Continuous Integration tests medium easy
  12. Port HPX to iOS and Mac (M1 architecture) large easy
  13. Study the performance of Halide applications running on HPX threads. medium medium
  14. HPX distributed algorithms large hard
  15. (Re-)Implement executor API on top of sender/receiver infrastructure large medium
  16. Explicit Visualization of Accelerators for HPX Trace Visualization medium hard
  17. Improved Scalability for HPX OTF2 Trace Visualization medium hard
  18. Multiple File Load in HPX Trace Visualization medium hard
  19. Spatio-Temporal Extrapolation with Generative AI: Advancing Storm Surge Forecast Accuracy through Bi large hard
  20. Spatio-Temporal Extrapolation with GNN: Advancing Storm Surge Forecast Accuracy through Bias Correct large hard
  21. Transformer-based Image-to-Graph Conversion large hard
  22. Coroutine-like Interface large medium
  23. Async I/O using Coroutines and S/R medium easy
  24. Add Vectorization to parunseq Implementations of Parallel Algorithms large hard
  25. Conflict (Range-Based) Locks large hard
  26. Standardize and Visualize HPX Benchmarks large hard
  27. Rustize HPX! large medium
  28. Pythonize HPX! large medium
  29. Create Generic Histogram Performance Counter large medium
  30. Fix libCDS broken dependency large easy
  31. Implement your favorite Computational Algorithm in HPX medium easy
  32. Conduct a thorough Performance Analysis on HPX Parallel Algorithms (and optimize) large medium
  33. Implement Your Favorite Parcelport Backend large hard
  34. Implement a Faster Associative Container for GIDs large hard
  35. Create A Parcelport Based on WebSockets large hard
  36. All to All Communications medium hard
  37. Distributed Component Placement large hard
  38. Port Graph500 to HPX large medium
  39. Port Mantevo MiniApps to HPX medium medium
  40. Distributed solver and load balancing for Peridynamics using asynchronous parallelism large hard

Read the ideas page. Ideas are for scope reference; never copy one into a proposal.

History

In GSoC since 2016, 10 years. Projects per year: '16: 4, '17: 4, '18: 4, '20: 5, '21: 2, '22: 4, '23: 5, '24: 4, '25: 6, '26: 4.

On GitHub

4 repositories pushed to in the last year. Main languages: C++ (2), Dockerfile (1).

Links and channels

go deeper in your terminal
git-into-gsoc org "Ste||ar group" --shortlist
git-into-gsoc repos "Ste||ar group"
git-into-gsoc issues --org "Ste||ar group"
or ask your assistant:
"Which Ste||ar group repositories merge
newcomers' pull requests, and which beginner
issues are still free?"

Those commands read live data: which repositories merge outside pull requests, and which beginner issues nobody has claimed. Install in two minutes.