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
22 lines
668 B
Plaintext
22 lines
668 B
Plaintext
// %PARAM% TEST_ERR err 0:1:2:3
|
|
|
|
// This compilation sometimes passes, sometimes fails.
|
|
// It's role is to ensure that exit code is not checked for regex matches and binary objects are cleaned
|
|
// before each test run.
|
|
// This allows the failure machinery to test for non-fatal warnings.
|
|
|
|
// Used if not specified otherwise:
|
|
// expected-error {{"fail generic"}}
|
|
|
|
#if TEST_ERR == 0
|
|
# pragma message "fail zero" // expected-error-0 {{"fail zero"}}
|
|
#elif TEST_ERR == 1
|
|
# pragma message "fail generic"
|
|
#elif TEST_ERR == 2
|
|
static_assert(false, "fail two"); // expected-error-2 {{"fail two"}}
|
|
#elif TEST_ERR == 3
|
|
static_assert(false, "fail generic");
|
|
#endif
|
|
|
|
int main() {}
|