[SYSTEMDS-2691] Code generation for CUDA - ASF JIRA

Attach files

Attach Screenshot

Add vote

Voters

Watch issue

Watchers

Create sub-task

Link

Clone

Update Comment Author

Replace String in Comment

Update Comment Visibility

Delete Comments

XML

Word

Printable

JSON

This epic holds the tasks/issues related to cuda codegen

SYSTEMDS-2692	move cuda codebase	Resolved	Mark Dokter	Actions
SYSTEMDS-2698	Initial cuda codegen functionality	Resolved	Mark Dokter	Actions
SYSTEMDS-2825	Avoid recompiling generated cuda operators	Closed	Mark Dokter	Actions
SYSTEMDS-2826	Sparse input support for CUDA codegen	Closed	Mark Dokter	Actions
SYSTEMDS-2827	Rowwise template for CUDA codegen	Resolved	Mark Dokter	Actions
SYSTEMDS-2852	Improve SPOOF CUDA compilation	Closed	Mark Dokter	Actions
SYSTEMDS-2853	Refactor spoof cuda runtime operations	Resolved	Mark Dokter	Actions
SYSTEMDS-2874	Implement MultiAggregate template	Open	Mark Dokter	Actions
SYSTEMDS-2875	Implement OuterProduct template	Open	Mark Dokter	Actions
SYSTEMDS-2876	Complete supported operators in CUDA codegen	Open	Mark Dokter	Actions
SYSTEMDS-2930	Remove function pointer based matrix accessor	Closed	Mark Dokter	Actions
SYSTEMDS-3023	Cuda Codegen Sparse I/O failing	Resolved	Mark Dokter	Actions
SYSTEMDS-3024	Improve performance by batching data descriptor transfers	Resolved	Mark Dokter	Actions
SYSTEMDS-3030	Separate operator information form generated code in SPOOF ops	Open	Mark Dokter	Actions
SYSTEMDS-3031	Improve SPOOF CUDA rowwise handling of intermediate memory	Open	Mark Dokter	Actions
SYSTEMDS-3032	Use CUDA Occupancy API	In Progress	Mark Dokter	Actions
SYSTEMDS-3352	CUDA code gen support for connected components algorithm	Resolved	Mark Dokter	Actions
SYSTEMDS-3362	CUDA code gen stream synchronization	Resolved	Unassigned	Actions