Skip to content

Check for output offsets int32 overflow in list APIs #23652

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

Open
davidwendt wants to merge 1 commit into
base: main
Choose a base branch
from
+17 −11
Open

Check for output offsets int32 overflow in list APIs #23652

Show file tree
Hide file tree
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
17 changes: 11 additions & 6 deletions cpp/src/lists/combine/concatenate_rows.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
/*
* SPDX-FileCopyrightText: Copyright (c) 2021-2026, NVIDIA CORPORATION.
* SPDX-FileCopyrightText: Copyright (c) 2021-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
* SPDX-License-Identifier: Apache-2.0
*/

Expand All @@ -10,6 +10,7 @@
#include <cudf/detail/gather.cuh>
#include <cudf/detail/iterator.cuh>
#include <cudf/detail/nvtx/ranges.hpp>
#include <cudf/detail/sizes_to_offsets_iterator.cuh>
#include <cudf/lists/combine.hpp>
#include <cudf/utilities/default_stream.hpp>
#include <cudf/utilities/error.hpp>
Expand Down Expand Up @@ -110,11 +111,15 @@ generate_regrouped_offsets_and_null_mask(table_device_view const& input,
stream);

// convert to offsets
thrust::exclusive_scan(rmm::exec_policy_nosync(stream, cudf::get_current_device_resource_ref()),
offsets->view().begin<size_type>(),
offsets->view().begin<size_type>() + input.num_rows() + 1,
offsets->mutable_view().begin<size_type>(),
0);
auto total_size =
cudf::detail::sizes_to_offsets(offsets->view().begin<size_type>(),
offsets->view().begin<size_type>() + input.num_rows() + 1,
offsets->mutable_view().begin<size_type>(),
0,
stream);
CUDF_EXPECTS(total_size <= static_cast<decltype(total_size)>(std::numeric_limits<int32_t>::max()),
"Size of offsets exceeds maximum int32 limit",
std::overflow_error);

// generate appropriate null mask
auto [null_mask, null_count] = [&]() {
Expand Down
11 changes: 6 additions & 5 deletions cpp/src/lists/interleave_columns.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
/*
* SPDX-FileCopyrightText: Copyright (c) 2021-2026, NVIDIA CORPORATION.
* SPDX-FileCopyrightText: Copyright (c) 2021-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
* SPDX-License-Identifier: Apache-2.0
*/

Expand Down Expand Up @@ -76,10 +76,11 @@ generate_list_offsets_and_validities(table_view const& input,
}));

// Compute offsets from sizes.
thrust::exclusive_scan(rmm::exec_policy_nosync(stream, cudf::get_current_device_resource_ref()),
d_offsets,
d_offsets + num_output_lists + 1,
d_offsets);
auto total_size = cudf::detail::sizes_to_offsets(
d_offsets, d_offsets + num_output_lists + 1, d_offsets, 0, stream);
CUDF_EXPECTS(total_size <= static_cast<decltype(total_size)>(std::numeric_limits<int32_t>::max()),
"Size of offsets exceeds maximum int32 limit",
std::overflow_error);

return {std::move(list_offsets), std::move(validities)};
}
Expand Down
Loading