Serving DNNs in Real Time at Datacenter Scale with Project Brainwave

S. Chung, Eric; Fowers, Jeremy; Ovtcharov, Kalin; Papamichael, Michael; M. Caulfield, Adrian; Massengill, Todd; Liu, Ming; Lo, Daniel; Alkalay, Shlomi; Haselman, Michael; Abeydeera, Maleen; Adams, Logan; Angepat, Hari; Boehn, Christian; Chiou, Derek; Firestein, Oren; Forin, Alessandro; Su Gatlin, Kang; Ghandi, Mahdi; Heil, Stephen; Holohan, Kyle; El Husseini, Ahmad; Juhász, Tamás; Kagi, Kara; K. Kovvuri, Ratna; Lanka, Sitaram; van Megen, Friedel; Mukhortov, Dima; Patel, Prerak; Perez, Brandon; Rapsang, Amanda; K. Reinhardt, Steven; Darvish Rouhani, Bita; Sapek, Adam; Seera, Raja; Shekar, Sangeetha; Sridharan, Balaji; Weisz, Gabriel; Woods, Lisa; Yi Xiao, Phillip; Zhang, Dan; Zhao, Ritchie; Burger, Doug

doi:10.1109/mm.2018.022071131

Public

Serving DNNs in Real Time at Datacenter Scale with Project Brainwave

Shared by NobleBlocks on Mar 1, 2018 • 12:00 AM UTC

Authors:

Eric S. Chung

Jeremy Fowers

Kalin Ovtcharov

Abstract

To meet the computational demands required of deep learning, cloud operators are turning toward specialized hardware for improved efficiency and performance. Project Brainwave, Microsofts principal infrastructure for AI serving in real time, accelerates deep neural network (DNN) inferencing in major...

Subject

Computer science

Microservices

Stratix

Finding related papers...

Discussions

(0)

No comments yet

Be the first to share your thoughts!