Mikael Simberg

Results 232 issues of Mikael Simberg

Nowadays `stdexec` should be feature-complete for DLA-Future's use cases. We should test that it works equivalently and add CI configurations for: - [x] GCC ( #930) - [x] clang (#1024)...

Priority:Medium
Category:std::execution

The `with_temporary_tile` test is currently by far the largest test, at 175 MB (with CUDA): https://gitlab.com/cscs-ci/ci-testing/webhook-ci/mirrors/4700071344751697/7514005670787789/-/jobs/5289553001#L3156. While not critical, it may be worth looking into whether it's possible to decrease...

Priority:Low
Type:Refactoring
Type:Cleanup

For example: ``` [0] [0] 0.00350707s -204.11GFlop/s d (1024, 1024) (1024, 1024) 1024 (1, 1) 8 GPU [1] [1] 0.000240678s -2974.21GFlop/s d (1024, 1024) (1024, 1024) 1024 (1, 1) 8...

Type:Bug
Priority:Low

Use some type of semaphore to limit the number of algorithms that can be scheduled concurrently instead of "unrolling" the full pipeline in one go. This may improve memory locality...

Priority:Medium
Type:Optimization

See https://github.com/eth-cscs/DLA-Future/pull/898#discussion_r1238751326. In the worst case this may need support in `async_rw_mutex` in pika. Needs further investigation. Some investigation on where and if this actually could lead to a performance...

Priority:Medium
Type:Optimization

https://github.com/eth-cscs/DLA-Future/pull/908#discussion_r1234124259. Depends on #905.

Priority:Low
Type:Refactoring

E.g. like in https://github.com/eth-cscs/DLA-Future/pull/714#issuecomment-1310485151. Related to #712 and #714.

Type:New Feature
Priority:Low
Type:Refactoring

C.f. https://github.com/eth-cscs/DLA-Future/pull/834.

Type:New Feature
Category:CI
Priority:Low

E.g. 15 or 16.

Type:New Feature
TODO:Task
Category:CI
Priority:Low

Umpire expects to find a GPU when it has been compiled with GPU support. If a GPU-enabled build of DLA-Future is used on a node without GPUs DLA-Future will fail...

Type:New Feature
Priority:Low