Failed to fetch fork details. Try again later.
-
Martin Bauer authored- small (length < 5) arrays with shape and stride information had to be memcpy'd to the GPU before every kernel call - instead of passing the information as arrays, the single elements are passed - leads to more function arguments, but simplifies GPU kernel calls -> changes in all backends required
7a94740d
Forked from
pycodegen / pystencils
Source project has a limited visibility.