Project

General

Profile

Support #1450

Feature #1393: Redesign of GPUManager to utilize concurrent kernel execution and stream callbacks

Refactor CUDA example programs to fit new GPUManager design

Added by Jaemin Choi 26 days ago. Updated 26 days ago.

Status:
Resolved
Priority:
Normal
Assignee:
Category:
GPU Support
Target version:
Start date:
02/28/2017
Due date:
% Done:

0%


Description

CUDA example programs under examples/charm++/cuda need to be refactored with the new design of GPUManager.
Especially, lazy host memory allocation & deallocation is no longer possible due to the removal of polling,
and those calls should be replaced by either hapi_poolMalloc or hapi_poolFree.

History

#1 Updated by Jaemin Choi 26 days ago

  • Status changed from New to Resolved

Also available in: Atom PDF