Skip to content
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

Jump to bottom

patch thrust to fix intmax num elements limitation in scan_by_key #8199

Merged
merged 4 commits into from
May 11, 2021
Merged

patch thrust to fix intmax num elements limitation in scan_by_key #8199

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ffaa54c
patch thrust to fix > intmax num scan limitation
cwharris May 10, 2021
e618498
fix error where Type was not yet available.
cwharris May 11, 2021
afecb58
Merge branch 'branch-0.20' of github.com:rapidsai/cudf into thrust-pa…
cwharris May 11, 2021
5207afb
Merge branch 'thrust-patch-intmax-scan' of github.com:cwharris/cudf i…
cwharris May 11, 2021
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
22 changes: 22 additions & 0 deletions cpp/cmake/thrust.patch
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,3 +42,25 @@ index 1ffeef0..5e80800 100644
for (int ITEM = 1; ITEM < ITEMS_PER_THREAD; ++ITEM)
{
if (ITEMS_PER_THREAD * tid + ITEM < num_remaining)
diff --git a/thrust/system/cuda/detail/scan_by_key.h b/thrust/system/cuda/detail/scan_by_key.h
index fe4b321c..b3974c69 100644
--- a/thrust/system/cuda/detail/scan_by_key.h
+++ b/thrust/system/cuda/detail/scan_by_key.h
@@ -513,7 +513,7 @@ namespace __scan_by_key {
scan_op(scan_op_)
{
int tile_idx = blockIdx.x;
- Size tile_base = ITEMS_PER_TILE * tile_idx;
+ Size tile_base = ITEMS_PER_TILE * static_cast<Size>(tile_idx);
Size num_remaining = num_items - tile_base;

if (num_remaining > ITEMS_PER_TILE)
@@ -734,7 +734,7 @@ namespace __scan_by_key {
ScanOp scan_op,
AddInitToScan add_init_to_scan)
{
- int num_items = static_cast<int>(thrust::distance(keys_first, keys_last));
+ size_t num_items = static_cast<size_t>(thrust::distance(keys_first, keys_last));
size_t storage_size = 0;
cudaStream_t stream = cuda_cub::stream(policy);
bool debug_sync = THRUST_DEBUG_SYNC_FLAG;