351
edits
Maumontero (talk | contribs) No edit summary |
Maumontero (talk | contribs) No edit summary |
||
Line 4: | Line 4: | ||
The same Volta GPU architecture that powers NVIDIA high-performance computing (HPC) products was adapted for use in Xavier series modules. The Volta architecture features a new Streaming Multiprocessor (SM) optimized for deep learning. | The same Volta GPU architecture that powers NVIDIA high-performance computing (HPC) products was adapted for use in Xavier series modules. The Volta architecture features a new Streaming Multiprocessor (SM) optimized for deep learning. | ||
__TOC__ | |||
=Volta Streaming Multiprocessor= | =Volta Streaming Multiprocessor= | ||
Line 21: | Line 23: | ||
=Features= | =Features= | ||
#512-core | |||
#End-to-end lossless compression. | #End-to-end lossless compression. | ||
#Tile Caching. | #Tile Caching. |
edits