Skip to content

Use an explicit std::min for byte alignment calculation #1465

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 5 commits into from
Oct 28, 2025
Merged

Use an explicit std::min for byte alignment calculation #1465

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
a87860c
Use std::min for byte alignment calculation
maxwbuckley Oct 25, 2025
93d2f27
Update copyright year to 2025 to satisfy the failing presubmit
maxwbuckley Oct 27, 2025
e0ba2ea
Merge branch 'main' into patch-1
maxwbuckley Oct 27, 2025
81c3507
Merge branch 'main' into patch-1
benfred Oct 27, 2025
324b308
Merge branch 'main' into patch-1
mythrocks Oct 28, 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
4 changes: 2 additions & 2 deletions cpp/src/distance/detail/pairwise_matrix/dispatch_layout.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
/*
* SPDX-FileCopyrightText: Copyright (c) 2023-2024, NVIDIA CORPORATION.
* SPDX-FileCopyrightText: Copyright (c) 2023-2025, NVIDIA CORPORATION.
* SPDX-License-Identifier: Apache-2.0
*/
#pragma once
Expand Down Expand Up @@ -46,7 +46,7 @@ int determine_vec_len(pairwise_matrix_params<IdxT, DataT, OutT, FinOpT> params)
{
size_t align_x = alignment_of_2d_array(params.x, params.ldx);
size_t align_y = alignment_of_2d_array(params.y, params.ldy);
size_t byte_alignment = min(align_x, align_y);
size_t byte_alignment = std::min(align_x, align_y);
Copy link
Copy Markdown
Contributor

@mythrocks mythrocks Oct 27, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Silly question: Should we consider converting this to cuda::std::min instead?

Copy link
Copy Markdown
Contributor

@mythrocks mythrocks Oct 27, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

(I ask because this is function template in a .cuh file.)

Copy link
Copy Markdown
Contributor

@tarang-jain tarang-jain Oct 28, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Even though its a .cuh file, the function itself is still a purely host function, so that is not necessary.

Copy link
Copy Markdown
Contributor

@mythrocks mythrocks Oct 28, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ok, thanks for confirming that this template isn't used in __device__ code. 👍


// Since alignment is in bytes, it could be smaller than sizeof(DataT).
// Handle this (unlikely) case here.
Expand Down