Skip to content
This repository was archived by the owner on Mar 21, 2024. It is now read-only.

Mask of all ones in SHFL_IDX_SYNC in block radix rank #579

Merged
merged 1 commit into from
Oct 12, 2022
Merged

Mask of all ones in SHFL_IDX_SYNC in block radix rank #579

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
4 changes: 2 additions & 2 deletions cub/block/block_radix_rank.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1075,7 +1075,7 @@ struct BlockRadixRankMatchEarlyCounts
// atomic is a bit faster
warp_offset = atomicAdd(&warp_offsets[bin], popc);
}
warp_offset = SHFL_IDX_SYNC(warp_offset, leader, bin_mask);
warp_offset = SHFL_IDX_SYNC(warp_offset, leader, WARP_MASK);
if (lane == leader) *p_match_mask = 0;
WARP_SYNC(WARP_MASK);
ranks[u] = warp_offset + popc - 1;
Expand Down Expand Up @@ -1105,7 +1105,7 @@ struct BlockRadixRankMatchEarlyCounts
// atomic is a bit faster
warp_offset = atomicAdd(&warp_offsets[bin], popc);
}
warp_offset = SHFL_IDX_SYNC(warp_offset, leader, bin_mask);
warp_offset = SHFL_IDX_SYNC(warp_offset, leader, WARP_MASK);
ranks[u] = warp_offset + popc - 1;
}
}
Expand Down