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
26 lines
1.1 KiB
Plaintext
26 lines
1.1 KiB
Plaintext
#include <stdio.h>
|
|
|
|
#define CUDA_CALL(...) \
|
|
do \
|
|
{ \
|
|
cudaError_t err = __VA_ARGS__; \
|
|
if (err != cudaSuccess) \
|
|
{ \
|
|
printf("CUDA ERROR: %s: %s\n", cudaGetErrorName(err), cudaGetErrorString(err)); \
|
|
return err; \
|
|
} \
|
|
} while (false)
|
|
|
|
int main()
|
|
{
|
|
int selected_device;
|
|
CUDA_CALL(cudaGetDevice(&selected_device));
|
|
|
|
cudaDeviceProp device_prop;
|
|
CUDA_CALL(cudaGetDeviceProperties(&device_prop, selected_device));
|
|
|
|
FILE* output = fopen("sm", "w");
|
|
fprintf(output, "%d%d\n", device_prop.major, device_prop.minor);
|
|
fclose(output);
|
|
}
|