Skip to content

GPU RTC: Fix launch bounds, cut 3rd runtime parameter to force number of blocks started #14127

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
davidrohr merged 1 commit into from
Mar 28, 2025
Merged

GPU RTC: Fix launch bounds, cut 3rd runtime parameter to force number of blocks started #14127

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions GPU/GPUTracking/Definitions/GPUDefParametersDefault.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,8 @@
#include "GPUCommonDef.h"
#include "GPUDefMacros.h"

// Launch bound definition, 3 optional parameters: maxThreads per block, minBlocks per multiprocessor, force number of blocks (not passed to compiler as launch bounds)

// GPU Run Configuration
#ifdef GPUCA_GPUCODE
#if defined(GPUCA_GPUTYPE_MI2xx)
Expand Down
2 changes: 1 addition & 1 deletion GPU/GPUTracking/Definitions/GPUDefParametersLoad.template.inc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,7 +37,7 @@ static GPUDefParameters GPUDefParametersLoad()
if (par.par_LB_minBlocks[i] > 0) { \
o << ", " << par.par_LB_minBlocks[i]; \
} \
if (par.par_LB_forceBlocks[i] > 0) { \
if (!forRTC && par.par_LB_forceBlocks[i] > 0) { \
o << ", " << par.par_LB_forceBlocks[i]; \
} \
o << "\n"; \
Expand Down