Project

General

Profile

Task #2528

PME GPU tuning

Added by Aleksei Iupinov 5 months ago. Updated 5 months ago.

Status:
New
Priority:
Normal
Assignee:
-
Category:
-
Target version:
2019
Difficulty:
hard
Close

Description

Currently PME kernels are preferring block sizes which were set long ago (c_[spread/gather/solve]MaxWarpsPerBlock).
These should be specialized for OpenCL. Actually, could be looked at again for CUDA as well. Actually, it should be a reocurring pre-release task, not just for PME :-) As long as anyone steps up.

Associated revisions

Revision 442845fd (diff)
Added by Aleksei Iupinov 5 months ago

Gather the PME GPU constants/macros in a single header

Those will be translated to defines by the OpenCL kernel compiler.

Refs #2453, #2528

Change-Id: I03062c908db6dad9bbc8c62accdc4707b03ff527

History

#1 Updated by Mark Abraham 5 months ago

I suggest we re-work this redmine into that set of recurring tasks

#2 Updated by Gerrit Code Review Bot 5 months ago

Gerrit received a related patchset '6' for Issue #2528.
Uploader: Mark Abraham ()
Change-Id: gromacs~master~I03062c908db6dad9bbc8c62accdc4707b03ff527
Gerrit URL: https://gerrit.gromacs.org/7861

Also available in: Atom PDF