Skip to content

Use signed offset type for DevicePartition #8971

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
davebayer merged 1 commit into from
May 13, 2026
Merged

Use signed offset type for DevicePartition #8971

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
18 changes: 16 additions & 2 deletions cub/cub/device/device_partition.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -321,7 +321,14 @@ public:
{
_CCCL_NVTX_RANGE_SCOPE("cub::DevicePartition::Flagged");

using offset_t = detail::choose_offset_t<NumItemsT>;
using ChooseOffsetT = detail::choose_signed_offset<NumItemsT>;
using offset_t = typename ChooseOffsetT::type;

// Check if the number of items exceeds the range covered by the selected signed offset type
if (const cudaError_t error = ChooseOffsetT::is_exceeding_offset_type(num_items))
{
return error;
}

// Dispatch with environment - handles all boilerplate
return detail::dispatch_with_env(env, [&]([[maybe_unused]] auto tuning, void* storage, size_t& bytes, auto stream) {
Expand Down Expand Up @@ -565,7 +572,14 @@ public:
{
_CCCL_NVTX_RANGE_SCOPE("cub::DevicePartition::If");

using offset_t = detail::choose_offset_t<NumItemsT>;
using ChooseOffsetT = detail::choose_signed_offset<NumItemsT>;
using offset_t = typename ChooseOffsetT::type;

// Check if the number of items exceeds the range covered by the selected signed offset type
if (const cudaError_t error = ChooseOffsetT::is_exceeding_offset_type(num_items))
{
return error;
}

// Dispatch with environment - handles all boilerplate
return detail::dispatch_with_env(env, [&]([[maybe_unused]] auto tuning, void* storage, size_t& bytes, auto stream) {
Expand Down
Loading