Commit Graph

4 Commits

Author SHA1 Message Date
Dmitriy Korchemkin 77ad8bb4e5 Change storage in BlockRandomAccessSparseMatrix
- TripletSparseMatrix in BlockRandomAccessSparseMatrix is replaced with
   BlockSparseMatrix
 - BlockSparseMatrix::ToCompressedRowSparseMatrix is performed in a
   direct sort-less way

Change-Id: Ib951fda1b9394050e2c47a9721172c5e3c674801
2023-04-18 01:34:30 +03:00
Joydeep Biswas 344929647a Add CUDA GPU and Runtime Detection
* Added GPU device and CUDA compute capability identification.
* Added GpuMemoryAvailable() to aid downstream optimizations based
  on GPU memory availability.

Change-Id: I326dc1e4b7a6a7f5571b7e5479eb9aa300ad1075
2022-08-18 17:07:32 -05:00
Sameer Agarwal 6ab435d774 Fix a missing CERES_NO_CUDA guard
Also run format_all.sh.

Change-Id: I13902c1d3eb0d3a97548540fee13ec67c490a5ff
2022-08-14 16:58:09 -07:00
Joydeep Biswas c560bc2be5 CUDA CGNR, Part 3: CudaSparseMatrix
* Added CudaSparseMatrix to manage and operate on sparse matrices with
  cuSparse.
* Added tests for CudaSparseMatrix.
* Added a new sparse linear operator benchmark.

Change-Id: Id09df46de3b40be1f14441528088b54dab5844af
2022-08-14 18:48:55 -05:00