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

Forward-merge branch-24.02 to branch-24.04 #2128

Merged
merged 2 commits into from
Jan 24, 2024
Merged

Forward-merge branch-24.02 to branch-24.04 #2128

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8743ac9
[BUG] Fix `SPMM` strided view (#2124)
lowener Jan 24, 2024
3ce00d3
ANN bench fix latency measurement overhead (#2084)
tfeher Jan 24, 2024
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
18 changes: 8 additions & 10 deletions cpp/bench/ann/src/common/benchmark.hpp
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 @@ -287,11 +287,11 @@ void bench_search(::benchmark::State& state,
std::make_shared<buf<std::size_t>>(current_algo_props->query_memory_type, k * query_set_size);

cuda_timer gpu_timer;
auto start = std::chrono::high_resolution_clock::now();
{
nvtx_case nvtx{state.name()};

auto algo = dynamic_cast<ANN<T>*>(current_algo.get())->copy();
auto algo = dynamic_cast<ANN<T>*>(current_algo.get())->copy();
auto start = std::chrono::high_resolution_clock::now();
for (auto _ : state) {
[[maybe_unused]] auto ntx_lap = nvtx.lap();
[[maybe_unused]] auto gpu_lap = gpu_timer.lap();
Expand All @@ -314,17 +314,15 @@ void bench_search(::benchmark::State& state,

queries_processed += n_queries;
}
auto end = std::chrono::high_resolution_clock::now();
auto duration = std::chrono::duration_cast<std::chrono::duration<double>>(end - start).count();
if (state.thread_index() == 0) { state.counters.insert({{"end_to_end", duration}}); }
state.counters.insert({"Latency", {duration, benchmark::Counter::kAvgIterations}});
}
auto end = std::chrono::high_resolution_clock::now();
auto duration = std::chrono::duration_cast<std::chrono::duration<double>>(end - start).count();
if (state.thread_index() == 0) { state.counters.insert({{"end_to_end", duration}}); }
state.counters.insert(
{"Latency", {duration / double(state.iterations()), benchmark::Counter::kAvgThreads}});

state.SetItemsProcessed(queries_processed);
if (cudart.found()) {
double gpu_time_per_iteration = gpu_timer.total_time() / (double)state.iterations();
state.counters.insert({"GPU", {gpu_time_per_iteration, benchmark::Counter::kAvgThreads}});
state.counters.insert({"GPU", {gpu_timer.total_time(), benchmark::Counter::kAvgIterations}});
}

// This will be the total number of queries across all threads
Expand Down
8 changes: 2 additions & 6 deletions cpp/include/raft/sparse/linalg/spmm.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ namespace linalg {
* @param[in] x input raft::device_csr_matrix_view
* @param[in] y input raft::device_matrix_view
* @param[in] beta scalar
* @param[out] z output raft::device_matrix_view
* @param[inout] z input-output raft::device_matrix_view
*/
template <typename ValueType,
typename IndexType,
Expand All @@ -60,19 +60,15 @@ void spmm(raft::resources const& handle,
{
bool is_row_major = detail::is_row_major(y, z);

auto z_tmp = raft::make_device_matrix<ValueType, IndexType>(handle, z.extent(0), z.extent(1));
auto z_tmp_view = raft::make_device_strided_matrix_view<ValueType, IndexType, LayoutPolicyZ>(
z_tmp.data_handle(), z.extent(0), z.extent(1), is_row_major ? z.stride(0) : z.stride(1));
z.data_handle(), z.extent(0), z.extent(1), is_row_major ? z.stride(0) : z.stride(1));

auto descr_x = detail::create_descriptor(x);
auto descr_y = detail::create_descriptor(y);
auto descr_z = detail::create_descriptor(z_tmp_view);

detail::spmm(handle, trans_x, trans_y, is_row_major, alpha, descr_x, descr_y, beta, descr_z);

raft::copy(
z.data_handle(), z_tmp.data_handle(), z_tmp.size(), raft::resource::get_cuda_stream(handle));

RAFT_CUSPARSE_TRY_NO_THROW(cusparseDestroySpMat(descr_x));
RAFT_CUSPARSE_TRY_NO_THROW(cusparseDestroyDnMat(descr_y));
RAFT_CUSPARSE_TRY_NO_THROW(cusparseDestroyDnMat(descr_z));
Expand Down