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

Fix the pool size alignment issue #16024

Merged
merged 4 commits into from
Jun 14, 2024
Merged

Fix the pool size alignment issue #16024

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
52385d3
Fix the pool size alignment issue
PointKernel Jun 13, 2024
5ff7ad9
cleanup: use CUDA alignment instead
PointKernel Jun 13, 2024
2d16cea
Move roundup logic to the pool mr ctor
PointKernel Jun 13, 2024
bff9aa8
Formatting
PointKernel Jun 13, 2024
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
Next Next commit
Fix the pool size alignment issue
  • Loading branch information
@PointKernel
PointKernel committed Jun 13, 2024
commit 52385d3211d14d198df2b449b32d06d506ca222d
2 changes: 1 addition & 1 deletion cpp/src/utilities/pinned_memory.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -142,7 +142,7 @@ CUDF_EXPORT rmm::host_device_async_resource_ref& make_default_pinned_mr(

auto const total = rmm::available_device_memory().second;
// 0.5% of the total device memory, capped at 100MB
return std::min(total / 200, size_t{100} * 1024 * 1024);
return std::min(rmm::align_up(total / 200, rmm::CUDA_ALLOCATION_ALIGNMENT), size_t{100} * 1024 * 1024);
}();

// rmm requires the pool size to be a multiple of 256 bytes
Expand Down
Loading