GPU data transfer overhead amortization

diku-dk / bfast

GPU Implementation for BFAST

GNU General Public License v3.0

37 stars 17 forks source link

GPU data transfer overhead amortization #36

Open mortvest opened 3 years ago

mortvest commented 3 years ago

Can we amortize the data transfer overheads (host -> device and device -> host with kernel execution) when running with multiple chunks using multithreading?