Sciweavers

7 search results - page 1 / 2
» Bit matrix multiplication in commodity processors
Sort
View
ASAP
2008
IEEE
118views Hardware» more  ASAP 2008»
13 years 10 months ago
Bit matrix multiplication in commodity processors
Registers in processors generally contain words or, with the addition of multimedia extensions, short vectors of subwords of bytes or 16-bit elements. In this paper, we view the c...
Yedidya Hilewitz, Cédric Lauradoux, Ruby B....
ISPDC
2010
IEEE
13 years 2 months ago
Pretty Good Accuracy in Matrix Multiplication with GPUs
—With systems such as Road Runner, there is a trend in super computing to offload parallel tasks to special purpose co-processors, composed of many relatively simple scalar proc...
Matthew Badin, Lubomir Bic, Michael B. Dillencourt...
ICPP
1993
IEEE
13 years 8 months ago
Dependence Analysis and Architecture Design for Bit-Level Algorithms
:. In designing application-specific bit-level architectures and in programming existing bit-level processor arrays, it is necessary to expand a word-level algorithm into its bit-...
Weijia Shang, Benjamin W. Wah
ACMMSP
2006
ACM
260views Hardware» more  ACMMSP 2006»
13 years 10 months ago
Seven at one stroke: results from a cache-oblivious paradigm for scalable matrix algorithms
A blossoming paradigm for block-recursive matrix algorithms is presented that, at once, attains excellent performance measured by • time, • TLB misses, • L1 misses, • L2 m...
Michael D. Adams, David S. Wise
ISCAS
2005
IEEE
133views Hardware» more  ISCAS 2005»
13 years 10 months ago
Minimal activity mixed-signal VLSI architecture for real-time linear transforms in video
Abstract— The mixed-signal processor performs digital vectormatrix multiplication using internally analog fine-grain parallel computing. The three-transistor CID/DRAM unit cell ...
Rafal Karakiewicz, Roman Genov