Bill Dally
Chief scientist and SVP of Research at NVIDIA; co-author of Deep Compression; former Stanford CS chair
Bill Dally is chief scientist at NVIDIA and senior vice president of NVIDIA Research, which Dally joined in 2009 after 12 years at Stanford University, where Dally chaired the computer science department. Before Stanford, Dally's team at MIT built the J-Machine and M-Machine experimental parallel computers, and at Caltech Dally designed the MOSSIM Simulation Engine and the Torus Routing chip. With Song Han and Huizi Mao, Dally co-authored Deep Compression (2015), which shrinks neural networks through pruning, trained quantization and Huffman coding. NVIDIA's pages list Dally as a member of the National Academy of Engineering, a Fellow of the American Academy of Arts & Sciences, the IEEE and the ACM, and a recipient of the ACM Eckert-Mauchly Award, the IEEE Seymour Cray Award and the ACM Maurice Wilkes Award.123
Work
Deep Compression (external site: arxiv.org)Published research
Co-author, with Song Han and Huizi Mao, of "Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding" (2015), which reports shrinking AlexNet and VGG-16 storage without loss of accuracy.3
J-Machine and M-Machine
At MIT from 1986 to 1997, Dally and team built the J-Machine and M-Machine experimental parallel computer systems, which separated mechanism from programming models and showed low-overhead synchronization and communication.2
Other documented roles
Roles the sources document but that are not confirmed as current.
- Chairman of the computer science department and Willard R. and Inez Kerr Bell Professor of Engineering, Stanford University1
- Led the team that built the J-Machine and M-Machine (1986–1997), Massachusetts Institute of Technology2
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.