416
edits
Changes
GPU
,→Memory Model
* __global - usually VRAM, accessable by all work-items resp. threads.
===Memory Examples===
Here the data for the Nvidia GeForce GTX 580 ([https://en.wikipedia.org/wiki/Fermi_%28microarchitecture%29 Fermi)] as an example: <ref>CUDA C Programming Guide v7.0, Appendix G.COMPUTE CAPABILITIES</ref>
* 768 KiB L2 cache
* 3 GiB to 6 GiB global memory
===Unified Memory===
Usually data has to be transfered/copied between a CPU host and a discrete GPU device, but different architectures from different vendors on different operating systems with different frameworks may offer a unified and accessible address space between CPU and GPU.
=Instruction Throughput=
