64-BitBrainstorm_2026/AMSS-NCKU
8
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
146 Commits 49 Branches 0 Tags
d9c7ea8085d8923d858066b73447a2a73db868a3
Commit Graph

2 Commits

Author SHA1 Message Date
abnerluo
d9c7ea8085 Use cudaMemcpyAsync with dedicated transfer stream for H2D/D2H transfers 
Add cudaStream_t to GpuBuffers for async H2D/D2H transfers in BSSN and
Z4C substep functions. Adds cudaStreamSynchronize(0) before D2H to
enforce kernel/transfer ordering across streams, and a sync between
state and matter H2D uploads to prevent h_stage race on RK4==0.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-28 08:23:34 +08:00
ianchb
c689cc8dc9 [WIP] Add CUDA support for Z4C 
Rewritten done by Codex.
This still has errors, do not pick this one now.
 2026-04-27 11:58:43 +08:00