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
38 lines
1.2 KiB
Plaintext
38 lines
1.2 KiB
Plaintext
#include <thrust/fill.h>
|
|
#include <thrust/mr/new.h>
|
|
|
|
#include <unittest/unittest.h>
|
|
|
|
template <typename MemoryResource>
|
|
void TestAlignment(MemoryResource memres, std::size_t size, std::size_t alignment)
|
|
{
|
|
void* ptr = memres.do_allocate(size, alignment);
|
|
ASSERT_EQUAL(reinterpret_cast<std::size_t>(ptr) % alignment, 0u);
|
|
|
|
char* char_ptr = reinterpret_cast<char*>(ptr);
|
|
thrust::fill(char_ptr, char_ptr + size, char{});
|
|
|
|
memres.do_deallocate(ptr, size, alignment);
|
|
}
|
|
|
|
static const std::size_t MinTestedSize = 32;
|
|
static const std::size_t MaxTestedSize = 8 * 1024;
|
|
static const std::size_t TestedSizeStep = 1;
|
|
|
|
static const std::size_t MinTestedAlignment = 16;
|
|
static const std::size_t MaxTestedAlignment = 4 * 1024;
|
|
static const std::size_t TestedAlignmentShift = 1;
|
|
|
|
void TestNewDeleteResourceAlignedAllocation()
|
|
{
|
|
for (std::size_t size = MinTestedSize; size <= MaxTestedSize; size += TestedSizeStep)
|
|
{
|
|
for (std::size_t alignment = MinTestedAlignment; alignment <= MaxTestedAlignment;
|
|
alignment <<= TestedAlignmentShift)
|
|
{
|
|
TestAlignment(thrust::mr::new_delete_resource(), size, alignment);
|
|
}
|
|
}
|
|
}
|
|
DECLARE_UNITTEST(TestNewDeleteResourceAlignedAllocation);
|