dylanyunlong/project_6
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

sync: update cccl_upstream benchmarks to latest NVIDIA/cccl main

Browse Source 
- Updated 5 modified benchmark files (select/if, select/flagged, select/unique, histogram_common, for_each/extents)
- Added 3 new benchmark files (bitonic_sort: warp_keys.cu, warp_pairs.cu, bitonic_common.cuh)
- Now at parity with NVIDIA/cccl main for all 23 benchmark algorithm dirs
- Full inventory: 91 benchmark files, 18 cub examples, 243 test files, 60 thrust examples
This commit is contained in:
muh-bot
2026-08-07 01:32:29 +00:00
parent d15dcea7c6
commit c8d79e2b02
8 changed files with 267 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
cccl_upstream/cub/benchmarks/bench/select/flagged.cu
View File

@@ -17,12 +17,13 @@
// %RANGE% TUNE_MAGIC_NS ns 0:2048:4
// %RANGE% TUNE_DELAY_CONSTRUCTOR_ID dcid 0:7:1
// %RANGE% TUNE_L2_WRITE_LATENCY_NS l2w 0:1200:5
// %RANGE% TUNE_PREFETCH pf 0:3:1
#if !TUNE_BASE
template <typename InputT>
struct bench_policy_selector
{
[[nodiscard]] _CCCL_API constexpr auto operator()(cuda::compute_capability) const -> cub::SelectPolicy
[[nodiscard]] _CCCL_HOST_DEVICE_API constexpr auto operator()(cuda::compute_capability) const -> cub::SelectPolicy
{
return {cub::SelectAlgorithm::lookback,
{TUNE_THREADS_PER_BLOCK,
@@ -30,7 +31,8 @@ struct bench_policy_selector
(TUNE_TRANSPOSE == 0 ? cub::BLOCK_LOAD_DIRECT : cub::BLOCK_LOAD_WARP_TRANSPOSE),
(TUNE_LOAD == 0 ? cub::LOAD_DEFAULT : cub::LOAD_CA),
cub::BLOCK_SCAN_WARP_SCANS,
lookback_delay_policy}};
lookback_delay_policy,
static_cast<cub::detail::LoadPrefetch>(TUNE_PREFETCH)}};
}
};
#endif // !TUNE_BASE

2
cccl_upstream/cub/benchmarks/bench/select/if.cu
View File

@@ -24,7 +24,7 @@
template <typename InputT>
struct bench_policy_selector
{
[[nodiscard]] _CCCL_API constexpr auto operator()(cuda::compute_capability) const -> cub::SelectPolicy
[[nodiscard]] _CCCL_HOST_DEVICE_API constexpr auto operator()(cuda::compute_capability) const -> cub::SelectPolicy
{
return {cub::SelectAlgorithm::lookback,
{TUNE_THREADS_PER_BLOCK,

2
cccl_upstream/cub/benchmarks/bench/select/unique.cu
View File

@@ -22,7 +22,7 @@
template <typename InputT>
struct bench_policy_selector
{
[[nodiscard]] _CCCL_API constexpr auto operator()(cuda::compute_capability) const -> cub::SelectPolicy
[[nodiscard]] _CCCL_HOST_DEVICE_API constexpr auto operator()(cuda::compute_capability) const -> cub::SelectPolicy
{
return {cub::SelectAlgorithm::lookback,
{TUNE_THREADS_PER_BLOCK,