Skip to content

Support deferred freeing for CUDA memory

Sujin Philip requested to merge sujin.philip/vtk-m:cuda-deferred-free into master

Calls to 'cudaFree' block execution on all cuda devices. Reduce the number of times this happens by having a deferred free mechanism that frees a pool of pointers together when a threshold is reached.

Especially helpful during virtual object transfers that requires a few small allocations and frees.

Based on @robertmaynard's code in !1155 (closed).

Edited by Sujin Philip

Merge request reports