Sciweavers

772 search results - page 28 / 155
» Hyper-Systolic Matrix Multiplication
Sort
View
ASAP
2011
IEEE
228views Hardware» more  ASAP 2011»
12 years 7 months ago
A high-performance, low-power linear algebra core
—Achieving high-performance while reducing power consumption is a key concern as technology scaling is reaching its limits. It is well-accepted that application-specific custom ...
Ardavan Pedram, Andreas Gerstlauer, Robert A. van ...
SADM
2008
178views more  SADM 2008»
13 years 7 months ago
Fast Projection-Based Methods for the Least Squares Nonnegative Matrix Approximation Problem
: Nonnegative matrix approximation (NNMA) is a popular matrix decomposition technique that has proven to be useful across a diverse variety of fields with applications ranging from...
Dongmin Kim, Suvrit Sra, Inderjit S. Dhillon
ACMMSP
2006
ACM
260views Hardware» more  ACMMSP 2006»
14 years 1 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
IPPS
2006
IEEE
14 years 1 months ago
Algorithm-based checkpoint-free fault tolerance for parallel matrix computations on volatile resources
As the desire of scientists to perform ever larger computations drives the size of today’s high performance computers from hundreds, to thousands, and even tens of thousands of ...
Zizhong Chen, Jack Dongarra
ISSAC
2007
Springer
94views Mathematics» more  ISSAC 2007»
14 years 1 months ago
Solving toeplitz- and vandermonde-like linear systems with large displacement rank
Linear systems with structures such as Toeplitz-, Vandermonde- or Cauchy-likeness can be solved in O˜(α2 n) operations, where n is the matrix size, α is its displacement rank, ...
Alin Bostan, Claude-Pierre Jeannerod, Éric ...