Merge branch 'dev' into heterogeneous-lookup-example

Author: PointKernel

.devcontainer/cuda11.8-gcc11/devcontainer.json

@@ -1,6 +1,6 @@
 {
   "shutdownAction": "stopContainer",
-  "image": "rapidsai/devcontainers:25.06-cpp-gcc12-cuda12.8-ubuntu22.04",
+  "image": "rapidsai/devcontainers:25.08-cpp-gcc12-cuda12.8-ubuntu22.04",
   "hostRequirements": {
     "gpu": true
   },

.devcontainer/cuda12.8-gcc12/devcontainer.json

@@ -1,6 +1,6 @@
 {
   "shutdownAction": "stopContainer",
-  "image": "rapidsai/devcontainers:25.06-cpp-gcc13-cuda12.8-ubuntu22.04",
+  "image": "rapidsai/devcontainers:25.08-cpp-gcc13-cuda12.8-ubuntu22.04",
   "hostRequirements": {
     "gpu": true
   },

.devcontainer/cuda12.8-gcc13/devcontainer.json

@@ -1,6 +1,6 @@
 {
   "shutdownAction": "stopContainer",
-  "image": "rapidsai/devcontainers:25.06-cpp-gcc13-cuda12.8-ubuntu22.04",
+  "image": "rapidsai/devcontainers:25.08-cpp-gcc13-cuda12.8-ubuntu22.04",
   "hostRequirements": {
     "gpu": true
   },

.devcontainer/devcontainer.json

@@ -15,7 +15,7 @@
 #=============================================================================
 cmake_minimum_required(VERSION 3.23.1 FATAL_ERROR)
 
-set(rapids-cmake-version 25.06)
+set(rapids-cmake-version 25.08)
 if(NOT EXISTS ${CMAKE_CURRENT_BINARY_DIR}/CUCO_RAPIDS.cmake)
     file(DOWNLOAD
       https://raw.githubusercontent.com/rapidsai/rapids-cmake/branch-${rapids-cmake-version}/RAPIDS.cmake

CMakeLists.txt

@@ -27,7 +27,8 @@ function(ConfigureBench BENCH_NAME)
                                         RUNTIME_OUTPUT_DIRECTORY "${CMAKE_BINARY_DIR}/benchmarks")
     target_include_directories(${BENCH_NAME} PRIVATE
                                              "${CMAKE_CURRENT_SOURCE_DIR}")
-    target_compile_options(${BENCH_NAME} PRIVATE --expt-extended-lambda -lineinfo)
+    target_compile_options(${BENCH_NAME} PRIVATE --compiler-options=-Wall --compiler-options=-Wextra
+      -Wno-deprecated-gpu-targets --expt-extended-lambda -Xcompiler -Wno-subobject-linkage -lineinfo)
     target_link_libraries(${BENCH_NAME} PRIVATE
                                         nvbench::main
                                         pthread

README.md

@@ -56,7 +56,7 @@ void bloom_filter_add(nvbench::state& state,
   auto const pattern_bits   = WordsPerBlock;
 
   try {
-    auto const policy = policy_type{static_cast<std::uint32_t>(pattern_bits)};
+    [[maybe_unused]] auto const policy = policy_type{static_cast<uint32_t>(pattern_bits)};
   } catch (std::exception const& e) {
     state.skip(e.what());  // skip invalid configurations
   }

benchmarks/CMakeLists.txt

@@ -62,7 +62,7 @@ void bloom_filter_contains(
   auto const pattern_bits   = WordsPerBlock;
 
   try {
-    auto const policy = policy_type{static_cast<uint32_t>(pattern_bits)};
+    [[maybe_unused]] auto const policy = policy_type{static_cast<uint32_t>(pattern_bits)};
   } catch (std::exception const& e) {
     state.skip(e.what());  // skip invalid configurations
   }

benchmarks/bloom_filter/add_bench.cu

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2023-2024, NVIDIA CORPORATION.
+ * Copyright (c) 2023-2025, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -64,7 +64,7 @@ std::enable_if_t<(sizeof(Key) == sizeof(Value)), void> dynamic_map_insert(
                                         launch.get_stream()};
 
       timer.start();
-      for (std::size_t i = 0; i < num_keys; i += batch_size) {
+      for (int64_t i = 0; i < num_keys; i += batch_size) {
         map.insert(pairs.begin() + i, pairs.begin() + i + batch_size, {}, {}, launch.get_stream());
       }
       timer.stop();