Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Jason Thong"'
Autor:
Niayesh Ilkhani, Martin Langhammer, Andrei Hagiescu, Philip Colangelo, Bogdan Pasca, Jason Thong
Publikováno v:
ReConFig
This paper describes the architecture of a FPGA-based high-performance training accelerator for neural networks. Our accelerator uses a hybrid embedded floating point and soft logic approach to implement truncated floating-point datapaths, including
Autor:
Stephen F. Heil, Sitaram Lanka, Eric S. Chung, Adrian M. Caulfield, Oren Firestein, Doug Burger, Raja Seera, Kyle Holohan, Michael Haselman, Michael K. Papamichael, Derek Chiou, Puneet Kaur, Rimon Tadros, Andrew Putnam, Matt Humphrey, Shlomi Alkalay, Hari Angepat, Jason Thong, Lisa Woods, Todd Massengill, Tamas Juhasz, Kalin Ovtcharov, Lo Daniel
Publikováno v:
FPGA
In 2015, a team of software and hardware developers at Microsoft shipped the world?s first commercial search engine accelerated using FPGAs in the datacenter. During the sprint to production, new algorithms in the Bing ranking service were ported int
Autor:
Jason Thong, Nicola Nicolici
Publikováno v:
2015 IEEE/ACM International Conference on Computer-Aided Design (ICCAD).
Autor:
Jason Thong, Nicola Nicolici
Publikováno v:
2013 IEEE/ACM International Conference on Computer-Aided Design (ICCAD).
Autor:
Jason Thong, Nicola Nicolici
Publikováno v:
ICCD
We propose new optimal and heuristic approaches for solving the multiple constant multiplication (MCM) problem. Bounded depth first search (BDFS), our proposed optimal algorithm, is benchmarked on problem sizes that are impractical for the existing o
Autor:
Nicola Nicolici, Jason Thong
Publikováno v:
DAC
Existing optimal single constant multiplication (SCM) algorithms are limited to 19 bit constants. We propose an exact SCM algorithm. For 32 bit constants, the average run time is under 10 seconds. Optimality is ensured via an exhaustive search. The n
Autor:
Phillip Yi Xiao, Gopi Prashanth Gopal, James R. Larus, Sitaram Lanka, Hadi Esmaeilzadeh, Adrian M. Caulfield, Simon Pope, Derek Chiou, Michael Haselman, Doug Burger, Amir Hormati, Aaron L. Smith, Kypros Constantinides, Scott Hauck, Jeremy Fowers, Andrew Putnam, John Demme, Eric C. Peterson, Eric S. Chung, Stephen F. Heil, Jason Thong, Joo-Young Kim, Jan Gray
Publikováno v:
ISCA
Datacenter workloads demand high computational capabilities, flexibility, power efficiency, and low cost. It is challenging to improve all of these factors simultaneously. To advance datacenter capabilities beyond what commodity server designs can pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::93dde8168ff072abf700ce19557d1fa5
https://infoscience.epfl.ch/record/200356
https://infoscience.epfl.ch/record/200356