Project

General

Profile

Feature #873

send messages from non-PE threads

Added by Jim Phillips almost 3 years ago. Updated 18 days ago.

Status:
Resolved
Priority:
Normal
Category:
Machine Layers
Target version:
Start date:
10/28/2015
Due date:
% Done:

0%


Description

CUDA has the ability to call back to the CPU when a kernel finishes, but the callback executes in a thread that is launched by the CUDA runtime so messages sends fail. If messages could be sent from this thread then it would not be necessary to poll the GPU for kernel completion. This would only need to be supported in smp/multicore versions. This could also be used for dedicated I/O threads.

History

#1 Updated by Eric Bohm over 1 year ago

  • Target version changed from 6.8.0 to 6.9.0

#2 Updated by Sam White over 1 year ago

  • Category set to Machine Layers

#3 Updated by Jim Phillips over 1 year ago

I observe that #1393 seems to have solved this issue for GPUManager.

#4 Updated by Eric Bohm 12 months ago

  • Assignee set to Michael Robson

#5 Updated by Michael Robson 11 months ago

  • Status changed from New to Implemented

See above comments about 1393 solving this issue

#6 Updated by Michael Robson 18 days ago

  • Status changed from Implemented to Resolved

#1393 Merged

Also available in: Atom PDF