Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Spracklen, Lawrence"'
In principle, sparse neural networks should be significantly more efficient than traditional dense networks. Neurons in the brain exhibit two types of sparsity; they are sparsely interconnected and sparsely active. These two types of sparsity, called
Externí odkaz:
http://arxiv.org/abs/2112.13896
Autor:
Spracklen, Lawrence A.
In recent years, the instruction sets of the majority of present day general purpose processors have been extended to include a variety of SWAR (SIMID Within A Register) instructions. These operations, which make possible the processing of multiple d
Externí odkaz:
http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.369118
Autor:
Laudon, James1 james.laudon@sun.com, Spracklen, Lawrence1 lawrence.spracklen@sun.com
Publikováno v:
International Journal of Parallel Programming. Jun2007, Vol. 35 Issue 3, p299-330. 32p. 5 Diagrams, 3 Charts, 12 Graphs.
Publikováno v:
2013 IEEE International Symposium on Workload Characterization (IISWC); 2013, p143-152, 10p
Autor:
Thuresson, Martin1 martin.thuresson@chalmers.se, Spracklen, Lawrence2 lazvrence.spracklen@sun.com, Stenstrom, Per1 pers@chalmers.se
Publikováno v:
IEEE Transactions on Computers. Jul2008, Vol. 57 Issue 7, p916-927. 12p.
Autor:
Hughes, James, Morton, Gary, Pechanec, Jan, Schuba, Christoph, Spracklen, Lawrence, Yenduri, Bhargava
Publikováno v:
2009 ICSE Workshop on Multicore Software Engineering; May2009, p81-88, 8p
Autor:
Spracklen, Lawrence
Publikováno v:
2009 IEEE Hot Chips 21 Symposium (HCS); 2009, p1-25, 25p
Publikováno v:
Proceedings of the 38th Annual IEEE ACM International Symposium Microarchitecture; 11/12/2005, p183-196, 14p
Publikováno v:
Proceedings of the 18th Annual International Conference: Supercomputing; 6/26/2004, p1-11, 11p
Autor:
Eberle, Hans, Shantz, Sheueling, Gupta, Vipul, Gura, Nils, Rarick, Leonard, Spracklen, Lawrence
Publikováno v:
IEEE Micro; Mar/Apr2005, Vol. 25 Issue 2, p52-59, 8p