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

[BUG] Fix num_cta_per_query div #2107

Merged
merged 1 commit into from
Jan 23, 2024
Merged

[BUG] Fix num_cta_per_query div #2107

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
7 changes: 4 additions & 3 deletions cpp/include/raft/neighbors/detail/cagra/search_multi_cta.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
/*
* Copyright (c) 2023, NVIDIA CORPORATION.
* Copyright (c) 2023-2024, 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 @@ -111,7 +111,8 @@ struct search : public search_plan_impl<DATA_T, INDEX_T, DISTANCE_T, SAMPLE_FILT
constexpr unsigned muti_cta_itopk_size = 32;
this->itopk_size = muti_cta_itopk_size;
search_width = 1;
num_cta_per_query = max(params.search_width, params.itopk_size / muti_cta_itopk_size);
num_cta_per_query =
max(params.search_width, raft::ceildiv(params.itopk_size, (size_t)muti_cta_itopk_size));
result_buffer_size = itopk_size + search_width * graph_degree;
typedef raft::Pow2<32> AlignBytes;
unsigned result_buffer_size_32 = AlignBytes::roundUp(result_buffer_size);
Expand Down Expand Up @@ -184,7 +185,7 @@ struct search : public search_plan_impl<DATA_T, INDEX_T, DISTANCE_T, SAMPLE_FILT
RAFT_EXPECTS(num_cta_per_query * 32 >= topk,
"`num_cta_per_query` (%u) * 32 must be equal to or greater than "
"`topk` (%u) when 'search_mode' is \"multi-cta\". "
"(`num_cta_per_query`=max(`search_width`, `itopk_size`/32))",
"(`num_cta_per_query`=max(`search_width`, ceildiv(`itopk_size`, 32)))",
num_cta_per_query,
topk);
}
Expand Down
2 changes: 1 addition & 1 deletion cpp/include/raft/neighbors/detail/cagra/search_plan.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -154,7 +154,7 @@ struct search_plan_impl : public search_plan_impl_base {
if (algo == search_algo::MULTI_CTA) {
mc_itopk_size = 32;
mc_search_width = 1;
mc_num_cta_per_query = max(search_width, itopk_size / 32);
mc_num_cta_per_query = max(search_width, raft::ceildiv(itopk_size, (size_t)32));
RAFT_LOG_DEBUG("# mc_itopk_size: %u", mc_itopk_size);
RAFT_LOG_DEBUG("# mc_search_width: %u", mc_search_width);
RAFT_LOG_DEBUG("# mc_num_cta_per_query: %u", mc_num_cta_per_query);
Expand Down