Accelerating Numerical Linear Algebra Kernels on a Scalable Run Time Reconfigurable Platform

Numerical Linear Algebra (NLA) kernels are at the heart of all computational problems. These kernels require hardware acceleration for increased throughput. NLA Solvers for dense and sparse matrices differ in the way the matrices are stored and operated upon although they exhibit similar computation...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2010 IEEE Computer Society Annual Symposium on VLSI s. 161 - 166
Hlavní autoři: Biswas, Prasenjit, Udupa, Pramod P, Mondal, Rajdeep, Varadarajan, Keshavan, Alle, Mythri, Nandy, S K, Narayan, Ranjani
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.07.2010
Témata:
Arrays
Conjugate Gradient
Delay
Direct Solver
Faddeev's algorithm
Hardware
Iterative Solver
Kernel
Numerical Linear Algebra
Runtime reconfiguration
Sparse matrices
Systolic array
Throughput
Tiles
ISBN:1424473217, 9781424473212
ISSN:2159-3469
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Numerical Linear Algebra (NLA) kernels are at the heart of all computational problems. These kernels require hardware acceleration for increased throughput. NLA Solvers for dense and sparse matrices differ in the way the matrices are stored and operated upon although they exhibit similar computational properties. While ASIC solutions for NLA Solvers can deliver high performance, they are not scalable, and hence are not commercially viable. In this paper, we show how NLA kernels can be accelerated on REDEFINE, a scalable runtime reconfigurable hardware platform. Compared to a software implementation, Direct Solver (Modified Faddeev's algorithm) on REDEFINE shows a 29X improvement on an average and Iterative Solver (Conjugate Gradient algorithm) shows a 15-20% improvement. We further show that solution on REDEFINE is scalable over larger problem sizes without any notable degradation in performance.
ISBN:1424473217
9781424473212
ISSN:2159-3469
DOI:10.1109/ISVLSI.2010.65