19.11.2014 Views

Tutorial: Introduction to CUDA Fortran | GTC 2013

Tutorial: Introduction to CUDA Fortran | GTC 2013

Tutorial: Introduction to CUDA Fortran | GTC 2013

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

Heterogeneous Programming<br />

• Host = CPU and its memory<br />

• Device = GPU and its memory<br />

Host<br />

Device<br />

• Typical code progression<br />

– Allocate memory on host and device<br />

– Transfer data from host <strong>to</strong> device<br />

– Execute kernel (device computation)<br />

CPU<br />

DRAM<br />

PCIe<br />

GPU<br />

DRAM<br />

– Transfer result from device <strong>to</strong> host<br />

– Deallocate memory

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!