Skip to content

Remove unnecessary synchronization (miss-sync) during Parquet reading (Part 1: device_scalar) #19055

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
rapids-bot merged 4 commits into from
Jun 4, 2025
Merged

Remove unnecessary synchronization (miss-sync) during Parquet reading (Part 1: device_scalar) #19055

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ae0053b
[No Miss-sync] Use only pinned_vector as bounce_buffer inside device_…
JigaoLuo May 31, 2025
a564a9b
Merge branch 'branch-25.08' into no-miss-sync-devicescalar
vuule Jun 2, 2025
396f14c
Merge branch 'branch-25.08' into no-miss-sync-devicescalar
vuule Jun 2, 2025
0720b03
Merge branch 'branch-25.08' into no-miss-sync-devicescalar
vuule Jun 4, 2025
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
8 changes: 4 additions & 4 deletions cpp/include/cudf/detail/device_scalar.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
/*
* Copyright (c) 2024, NVIDIA CORPORATION.
* Copyright (c) 2024-2025, NVIDIA CORPORATION.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
Expand Down Expand Up @@ -54,15 +54,15 @@ class device_scalar : public rmm::device_scalar<T> {
explicit device_scalar(
rmm::cuda_stream_view stream,
rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref())
: rmm::device_scalar<T>(stream, mr), bounce_buffer{make_host_vector<T>(1, stream)}
: rmm::device_scalar<T>(stream, mr), bounce_buffer{make_pinned_vector<T>(1, stream)}
{
}

explicit device_scalar(
T const& initial_value,
rmm::cuda_stream_view stream,
rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref())
: rmm::device_scalar<T>(stream, mr), bounce_buffer{make_host_vector<T>(1, stream)}
: rmm::device_scalar<T>(stream, mr), bounce_buffer{make_pinned_vector<T>(1, stream)}
{
bounce_buffer[0] = initial_value;
cuda_memcpy_async<T>(device_span<T>{this->data(), 1}, bounce_buffer, stream);
Expand All @@ -71,7 +71,7 @@ class device_scalar : public rmm::device_scalar<T> {
device_scalar(device_scalar const& other,
rmm::cuda_stream_view stream,
rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref())
: rmm::device_scalar<T>(other, stream, mr), bounce_buffer{make_host_vector<T>(1, stream)}
: rmm::device_scalar<T>(other, stream, mr), bounce_buffer{make_pinned_vector<T>(1, stream)}
{
}

Expand Down