Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fix CUDA async stream. (#8380)

Browse Source
This commit is contained in:
Jiaming Yuan 2022-10-22 23:13:28 +08:00 committed by GitHub
parent 5761f27e5e
commit bb5e18c29c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/objective/adaptive.cu
View File

@ -67,6 +67,10 @@ void EncodeTreeLeafDevice(Context const* ctx, common::Span<bst_node_t const> pos
auto pinned = pinned_pool.GetSpan<char>(sizeof(size_t) + sizeof(bst_node_t)); auto pinned = pinned_pool.GetSpan<char>(sizeof(size_t) + sizeof(bst_node_t));
dh::CUDAStream copy_stream; dh::CUDAStream copy_stream;
size_t* h_num_runs = reinterpret_cast<size_t*>(pinned.subspan(0, sizeof(size_t)).data()); size_t* h_num_runs = reinterpret_cast<size_t*>(pinned.subspan(0, sizeof(size_t)).data());
dh::CUDAEvent e;
e.Record(dh::DefaultStream());
copy_stream.View().Wait(e);
// flag for whether there's ignored position // flag for whether there's ignored position
bst_node_t* h_first_unique = bst_node_t* h_first_unique =
reinterpret_cast<bst_node_t*>(pinned.subspan(sizeof(size_t), sizeof(bst_node_t)).data()); reinterpret_cast<bst_node_t*>(pinned.subspan(sizeof(size_t), sizeof(bst_node_t)).data());