COMPUTER ARCHITECTURE RESEARCH

Fundamental research in computer architecture and hardware/software interaction.

The slowing down of Moore's law for semiconductor manufacturing requires innovative approaches to continue increasing computer system performance and capability. Our research scientists examine emerging application demands and technology capabilities to develop new processor and memory designs that can deliver higher performance, consume less power, and be more resilient to errors than those available today. Recent publications include:

SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks, and 

MCM-GPU: Multi-Chip-Module GPUs for Continued Performance Scalability.

FEATURED PUBLICATIONS

SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks
SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks
MCM-GPU: Multi-Chip-Module GPUs for Continued Performance Scalability
MCM-GPU: Multi-Chip-Module GPUs for Continued Performance Scalability
EXPLORE ALL PUBLICATIONS
Research at NVIDIA
More
NVIDIA