Merge branch 'branch-24.04' into fea-cache-ivf-pq-params

cpp/bench/ann/src/raft/raft_cagra_wrapper.h

@@ -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.
@@ -159,7 +159,8 @@ void RaftCagra<T, IdxT>::build(const T* dataset, size_t nrow, cudaStream_t strea
                                                     index_params_.nn_descent_params,
                                                     index_params_.ivf_pq_refine_rate,
                                                     index_params_.ivf_pq_build_params,
-                                                    index_params_.ivf_pq_search_params)));
+                                                    index_params_.ivf_pq_search_params,
+                                                    false)));
 
   handle_.stream_wait(stream);  // RAFT stream -> bench stream
 }

cpp/cmake/thirdparty/get_hnswlib.cmake

@@ -50,20 +50,30 @@ function(find_and_configure_hnswlib)
       install(TARGETS hnswlib EXPORT hnswlib-exports)
       install(DIRECTORY "${hnswlib_SOURCE_DIR}/hnswlib/" DESTINATION include/hnswlib)
 
-      # write export rules
-      rapids_export(
-        BUILD hnswlib
-        VERSION ${PKG_VERSION}
-        EXPORT_SET hnswlib-exports
-        GLOBAL_TARGETS hnswlib
-        NAMESPACE hnswlib::)
+      # write install export rules
       rapids_export(
         INSTALL hnswlib
         VERSION ${PKG_VERSION}
         EXPORT_SET hnswlib-exports
         GLOBAL_TARGETS hnswlib
         NAMESPACE hnswlib::)
     endif()
+
+    # write build export rules
+    rapids_export(
+      BUILD hnswlib
+      VERSION ${PKG_VERSION}
+      EXPORT_SET hnswlib-exports
+      GLOBAL_TARGETS hnswlib
+      NAMESPACE hnswlib::)
+
+    include("${rapids-cmake-dir}/export/find_package_root.cmake")
+
+    # When using RAFT from the build dir, ensure hnswlib is also found in RAFT's build dir. This
+    # line adds `set(hnswlib_ROOT "${CMAKE_CURRENT_LIST_DIR}")` to build/raft-dependencies.cmake
+    rapids_export_find_package_root(
+      BUILD hnswlib [=[${CMAKE_CURRENT_LIST_DIR}]=] EXPORT_SET raft-exports
+    )
   endif()
 endfunction()
 

cpp/include/raft/neighbors/cagra_types.hpp

@@ -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.
@@ -145,7 +145,7 @@ struct index : ann::index {
   /** Total length of the index (number of vectors). */
   [[nodiscard]] constexpr inline auto size() const noexcept -> IdxT
   {
-    return dataset_view_.extent(0);
+    return dataset_view_.extent(0) ? dataset_view_.extent(0) : graph_view_.extent(0);
   }
 
   /** Dimensionality of the data. */

cpp/include/raft/neighbors/detail/cagra/cagra_build.cuh

@@ -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.
@@ -296,7 +296,8 @@ index<T, IdxT> build(
   std::optional<experimental::nn_descent::index_params> nn_descent_params = std::nullopt,
   std::optional<float> refine_rate                                        = std::nullopt,
   std::optional<ivf_pq::index_params> pq_build_params                     = std::nullopt,
-  std::optional<ivf_pq::search_params> search_params                      = std::nullopt)
+  std::optional<ivf_pq::search_params> search_params                      = std::nullopt,
+  bool construct_index_with_dataset                                       = true)
 {
   size_t intermediate_degree = params.intermediate_graph_degree;
   size_t graph_degree        = params.graph_degree;
@@ -334,12 +335,22 @@ index<T, IdxT> build(
 
   auto cagra_graph = raft::make_host_matrix<IdxT, int64_t>(dataset.extent(0), graph_degree);
 
+  RAFT_LOG_INFO("optimizing graph");
   optimize<IdxT>(res, knn_graph->view(), cagra_graph.view());
 
   // free intermediate graph before trying to create the index
   knn_graph.reset();
 
+  RAFT_LOG_INFO("Graph optimized, creating index");
   // Construct an index from dataset and optimized knn graph.
-  return index<T, IdxT>(res, params.metric, dataset, raft::make_const_mdspan(cagra_graph.view()));
+  if (construct_index_with_dataset) {
+    return index<T, IdxT>(res, params.metric, dataset, raft::make_const_mdspan(cagra_graph.view()));
+  } else {
+    // We just add the graph. User is expected to update dataset separately. This branch is used
+    // if user needs special control of memory allocations for the dataset.
+    index<T, IdxT> idx(res, params.metric);
+    idx.update_graph(res, raft::make_const_mdspan(cagra_graph.view()));
+    return idx;
+  }
 }
 }  // namespace raft::neighbors::cagra::detail

cpp/include/raft/neighbors/detail/cagra/cagra_serialize.cuh

@@ -65,8 +65,11 @@ void serialize(raft::resources const& res,
   serialize_scalar(res, os, index_.metric());
   serialize_mdspan(res, os, index_.graph());
 
+  include_dataset &= (index_.dataset().extent(0) > 0);
+
   serialize_scalar(res, os, include_dataset);
   if (include_dataset) {
+    RAFT_LOG_INFO("Saving CAGRA index with dataset");
     auto dataset = index_.dataset();
     // Remove padding before saving the dataset
     auto host_dataset = make_host_matrix<T, int64_t>(dataset.extent(0), dataset.extent(1));
@@ -80,6 +83,8 @@ void serialize(raft::resources const& res,
                                     resource::get_cuda_stream(res)));
     resource::sync_stream(res);
     serialize_mdspan(res, os, host_dataset.view());
+  } else {
+    RAFT_LOG_INFO("Saving CAGRA index WITHOUT dataset");
   }
 }