- Mar 16, 2024
-
-
-
-
Mathieu Faverge authored
ipiv: Rename ipiv_init and ipiv_reducek functions as INSERT_TASK and make them match the INSERT_TASK API
-
- Mar 14, 2024
-
-
Mathieu Faverge authored
Mapv: Add some missing fixes, and make the map kernel non runtime dependent. See merge request !445
-
Mathieu Faverge authored
-
Mathieu Faverge authored
-
Mathieu Faverge authored
-
Mathieu Faverge authored
-
Mathieu Faverge authored
parsec/map: Fix the map codelet to always use a tile interface and do not enforce the user to check for the runtime used in the map functions.
-
Mathieu Faverge authored
header/coreblas: add the tile version of the functions into the main header to ease the access in map functions
-
Mathieu Faverge authored
Modify the map function to take into parameters an variadic number of data See merge request !201
-
Mathieu Faverge authored
-
Mathieu Faverge authored
-
Mathieu Faverge authored
-
Mathieu Faverge authored
compute/map: Improve the map function to take into account multiple descriptor and multiple implementations for the kernel to apply.
-
Mathieu Faverge authored
-
- Mar 12, 2024
-
-
Mathieu Faverge authored
-
Mathieu Faverge authored
-
Mathieu Faverge authored
correct zgetrf filters See merge request !442
-
LISITO Alycia authored
-
- Mar 05, 2024
-
-
Mathieu Faverge authored
doc: fix typo See merge request !443
-
Nathalie Furmento authored
-
- Feb 23, 2024
-
-
Mathieu Faverge authored
Added _starpu_mpi_redux_wrapup_data detection for MPI reductions See merge request !441
-
Matthieu Kuhn authored
-
Matthieu Kuhn authored
Added _starpu_mpi_redux_wrapup_data detection so that automatic MPI reduction can be used for partial pivoting (see also RUNTIME_ipiv_reducek).
-
- Feb 18, 2024
-
-
Mathieu Faverge authored
-
Mathieu Faverge authored
small fix (filter in insert_task getrf) See merge request !439
-
-
-
- Feb 09, 2024
-
-
PRUVOST Florent authored
Prevent using PARSEC with MPI cmake+doc See merge request !433
-
PRUVOST Florent authored
-
Mathieu Faverge authored
Remove the use of CHAMELEON_PRECISIONS that is an upper duplicate of... Closes #124 See merge request !432
-
- Feb 08, 2024
-
-
Remove the use of CHAMELEON_PRECISIONS that is an upper duplicate of CHAMELEON_PRECISION provided by cmake_morse (Fix #124)
-
- Feb 05, 2024
-
-
Mathieu Faverge authored
Fix issue #124: RP_CHAMELEON_PRECISION is the set of supported precisions,... Closes #124 See merge request !428
-
Mathieu Faverge authored
Fix issue 124: RP_CHAMELEON_PRECISION is the set of supported precisions, while CHAMELEON_PRECISION is the set of enabled precisions
-
- Jan 30, 2024
-
-
Mathieu Faverge authored
Expose __half type only if the cuda_fp16.h header is included (see... See merge request solverstack/chameleon!427
-
PRUVOST Florent authored
Expose __half type only if the cuda_fp16.h header is included (see gpucublas.h) where __half is actually defined.
-
- Jan 25, 2024
-
-
Mathieu Faverge authored
Disable StarPU/lapcy optimization for now and Fix a major issue with descriptor global allocation in distributed See merge request !425
-
- Jan 24, 2024
-
-
Mathieu Faverge authored
-
Mathieu Faverge authored
-