mirror-github-bspeice/cuburn
1
0
Fork 0
mirror of https://github.com/stevenrobertson/cuburn.git synced 2025-02-05 11:40:04 -05:00
Code Issues Actions Packages Projects Releases Wiki Activity

Add an important comment

Browse Source
This commit is contained in:
Steven Robertson 2013-01-06 21:58:14 -08:00
parent 6aac026a6b
commit 6938ac715b
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
cuburn/code/iter.py
View File

@ -190,8 +190,11 @@ iter(uint64_t out_ptr, uint64_t atom_ptr,
{{if not chaos_used}}
// Shared memory size can be reduced by a factor of four using a slower
// 4-stage reduce, but on Fermi hardware shmem use isn't a bottleneck
// 4-stage reduce, but on Fermi hardware shmem use isn't a bottleneck.
__shared__ float swap[{{4*NTHREADS}}];
// Cooperative branch selection, used for deciding when all threads in a
// warp should share a branch.
__shared__ float cosel[{{2*NWARPS}}];
// This is normally done after the swap-sync in the main loop