Deep Dive on NVIDIA Tesla V100 GPU Archtecture - Volta

FrgMstr

FrgMstr

Just Plain Mean
Staff member
Joined
May 18, 1997
Messages
55,598
Looking for some Monday evening reading...and possibly some Tuesday reading as well? NVIDIA has just kicked out its Volta Architecture Whitepaper! You will have to register to get access, but odds are if you are reading HardOCP, NVIDIA got your 411 a long time ago. So fire up PDF readers and dig in. That is what I am doing now.

The GV100 GPU includes 21.1 billion transistors with a die size of 815 mm2. It is fabricated on a new TSMC 12 nm FFN (FinFET NVIDIA) high-performance manufacturing process customized for NVIDIA. GV100 delivers considerably more compute performance, and adds many new features compared to the prior Pascal GPU generation. Further simplifying GPU programming and application porting, GV100 also improves GPU resource utilization. GV100 is an extremely powerefficient processor, delivering exceptional performance per watt.
 
GV100 is Quadro while V100 is Tesla, I believe? I can only wonder the normal layman's question of how this will translate to GV102.
 
You must log in or register to reply here.
Back
Top