64-BitBrainstorm_2026/AMSS-NCKU
8
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Unpack intermediate sync stages directly to GPU

Browse Source
This commit is contained in:
CGH0S7
2026-04-09 19:01:12 +08:00
parent 4484635f0d
commit 4463f1d23e
5 changed files with 195 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
AMSS_NCKU_source/Parallel.h
View File

@@ -134,10 +134,10 @@ namespace Parallel
AsyncSyncState() : req_no(0), active(false), mpi_tag(0), req_node(0), req_is_recv(0), pending_recv(0) {}
};
void Sync_start(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry,
SyncCache &cache, AsyncSyncState &state);
void Sync_finish(SyncCache &cache, AsyncSyncState &state,
MyList<var> *VarList, int Symmetry);
void Sync_start(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry,
SyncCache &cache, AsyncSyncState &state);
void Sync_finish(SyncCache &cache, AsyncSyncState &state,
MyList<var> *VarList, int Symmetry, bool unpack_to_host = true);
void OutBdLow2Hi(Patch *Patc, Patch *Patf,
MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
int Symmetry);