56fd68e7dd
CCCL (CUDA C++ Core Libraries) provides: - CUB: device/block/warp-level GPU primitives (reduce, scan, sort, topk) - Thrust: high-level parallel algorithms (transform_reduce, sort, scan) - libcudacxx: CUDA C++ standard library (atomics, barriers, memory) - cudax: experimental features (memory resources, allocators) - Tuning policies: per-SM hardware-specific algorithm parameters Competition optimization vectors mapped to CCCL: - Output TPS (83% weight): warp_reduce, block_reduce, device_topk - Input TPS (14% weight): device_scan, block_load, prefetch - Cache TPS (3% weight): prefix caching strategy patterns - Memory (0.9 util): pooled/cached/buddy allocators Source: https://github.com/NVIDIA/cccl (shallow clone, HEAD only) License: Apache-2.0
39 lines
1.0 KiB
Plaintext
39 lines
1.0 KiB
Plaintext
#include <cub/util_debug.cuh>
|
|
#include <cub/util_device.cuh>
|
|
|
|
#include <c2h/catch2_test_helper.h>
|
|
|
|
TEST_CASE("CubDebug returns input error", "[debug][utils]")
|
|
{
|
|
REQUIRE(CubDebug(cudaSuccess) == cudaSuccess);
|
|
REQUIRE(CubDebug(cudaErrorInvalidConfiguration) == cudaErrorInvalidConfiguration);
|
|
}
|
|
|
|
TEST_CASE("CubDebug returns new errors", "[debug][utils]")
|
|
{
|
|
cub::detail::EmptyKernel<int><<<0, 0>>>();
|
|
cudaError error = cudaPeekAtLastError();
|
|
|
|
REQUIRE(error != cudaSuccess);
|
|
REQUIRE(CubDebug(cudaSuccess) != cudaSuccess);
|
|
}
|
|
|
|
TEST_CASE("CubDebug prefers input errors", "[debug][utils]")
|
|
{
|
|
cub::detail::EmptyKernel<int><<<0, 0>>>();
|
|
cudaError error = cudaPeekAtLastError();
|
|
|
|
REQUIRE(error != cudaSuccess);
|
|
REQUIRE(CubDebug(cudaErrorMemoryAllocation) != cudaSuccess);
|
|
}
|
|
|
|
TEST_CASE("CubDebug resets last error", "[debug][utils]")
|
|
{
|
|
cub::detail::EmptyKernel<int><<<0, 0>>>();
|
|
cudaError error = cudaPeekAtLastError();
|
|
|
|
REQUIRE(error != cudaSuccess);
|
|
REQUIRE(CubDebug(cudaSuccess) != cudaSuccess);
|
|
REQUIRE(CubDebug(cudaSuccess) == cudaSuccess);
|
|
}
|