Skip to content

Keep the sparse Jensen-Shannon and Gram kernel epilogues in the input precision #2535

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
maxwbuckley wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Keep the sparse Jensen-Shannon and Gram kernel epilogues in the input precision #2535

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
23ef3b6
Keep the sparse Jensen-Shannon post-processing in the input precision
maxwbuckley Aug 31, 2026
df07908
Keep the polynomial and RBF Gram epilogues in the input precision
maxwbuckley Aug 31, 2026
ba762fd
Use the canonical NVIDIA copyright notice
maxwbuckley Sep 3, 2026
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/src/distance/detail/kernels/kernel_matrices.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
/*
* SPDX-FileCopyrightText: Copyright (c) 2019-2026, NVIDIA CORPORATION.
* SPDX-FileCopyrightText: Copyright (c) 2019-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
* SPDX-License-Identifier: Apache-2.0
*/

Expand Down Expand Up @@ -29,7 +29,7 @@ RAFT_KERNEL polynomial_kernel_nopad(
{
for (size_t tid = threadIdx.x + blockIdx.x * blockDim.x; tid < len;
tid += blockDim.x * gridDim.x) {
inout[tid] = pow(gain * inout[tid] + offset, exponent);
inout[tid] = pow(gain * inout[tid] + offset, (math_t)exponent);
}
}

Expand All @@ -51,7 +51,7 @@ RAFT_KERNEL polynomial_kernel(
tidy += blockDim.y * gridDim.y)
for (size_t tidx = threadIdx.x + blockIdx.x * blockDim.x; tidx < rows;
tidx += blockDim.x * gridDim.x) {
inout[tidx + tidy * ld] = pow(gain * inout[tidx + tidy * ld] + offset, exponent);
inout[tidx + tidy * ld] = pow(gain * inout[tidx + tidy * ld] + offset, (math_t)exponent);
}
}

Expand Down Expand Up @@ -118,7 +118,7 @@ RAFT_KERNEL rbf_kernel_expanded(
for (size_t tidx = threadIdx.x + blockIdx.x * blockDim.x; tidx < rows;
tidx += blockDim.x * gridDim.x) {
inout[tidx + tidy * ld] =
exp(-1.0 * gain * (norm_x[tidx] + norm_y_val - inout[tidx + tidy * ld] * 2));
exp(-gain * (norm_x[tidx] + norm_y_val - inout[tidx + tidy * ld] * 2));
}
}
}
Expand Down
4 changes: 2 additions & 2 deletions cpp/src/distance/detail/sparse/lp_distance.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
/*
* SPDX-FileCopyrightText: Copyright (c) 2024-2026, NVIDIA CORPORATION.
* SPDX-FileCopyrightText: Copyright (c) 2024-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
* SPDX-License-Identifier: Apache-2.0
*/

Expand Down Expand Up @@ -266,7 +266,7 @@ class jensen_shannon_unexpanded_distances_t : public distances_t<value_t> {
raft::linalg::map(
config_->handle,
raft::make_device_vector_view<value_t, int64_t>(out_dists, n),
[=] __device__(value_t input) { return raft::sqrt(0.5 * input); },
[=] __device__(value_t input) { return raft::sqrt(value_t(0.5) * input); },
raft::make_const_mdspan(raft::make_device_vector_view<const value_t, int64_t>(out_dists, n)));
}

Expand Down
Loading