A Vector-Like Reconfigurable Floating-Point Unit for the Logarithm

The use of reconfigurable computing for accelerating floating-point intensive codes is becoming common due to the availability of DSPs in new-generation FPGAs. We present the design of an efficient, pipelined floating-point datapath for calculating the logarithm function on reconfigurable devices. W...

Full description

Saved in:
Bibliographic Details
Main Authors: Nikolaos Alachiotis, Alexandros Stamatakis
Format: Article
Language:English
Published: Wiley 2011-01-01
Series:International Journal of Reconfigurable Computing
Online Access:http://dx.doi.org/10.1155/2011/341510
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832559375564144640
author Nikolaos Alachiotis
Alexandros Stamatakis
author_facet Nikolaos Alachiotis
Alexandros Stamatakis
author_sort Nikolaos Alachiotis
collection DOAJ
description The use of reconfigurable computing for accelerating floating-point intensive codes is becoming common due to the availability of DSPs in new-generation FPGAs. We present the design of an efficient, pipelined floating-point datapath for calculating the logarithm function on reconfigurable devices. We integrate the datapath into a stand-alone LUT-based (Lookup Table) component, the LAU (Logarithm Approximation Unit). We extended the LAU, by integrating two architecturally independent, LAU-based datapaths into a larger component, the VLAU (vector-like LAU). The VLAU produces 2 results/cycle, while occupying the same amount of memory as the LAU. Under single precision, one LAU is 12 and 1.7 times faster than the GNU and Intel Math Kernel Library (MKL) implementations, respectively. The LAU is also 1.6 times faster than the FloPoCo reconfigurable logarithm architecture. Under double precision, one LAU is 20 and 2.6 times faster than the respective GNU and MKL functions and 1.4 times faster than the FloPoCo logarithm. The VLAU is approximately twice as fast as the LAU, both under single and double precision.
format Article
id doaj-art-d0c66827ee65417e988d93d6185758d3
institution Kabale University
issn 1687-7195
1687-7209
language English
publishDate 2011-01-01
publisher Wiley
record_format Article
series International Journal of Reconfigurable Computing
spelling doaj-art-d0c66827ee65417e988d93d6185758d32025-02-03T01:30:15ZengWileyInternational Journal of Reconfigurable Computing1687-71951687-72092011-01-01201110.1155/2011/341510341510A Vector-Like Reconfigurable Floating-Point Unit for the LogarithmNikolaos Alachiotis0Alexandros Stamatakis1The Exelixis Lab, Scientific Computing Group, Heidelberg Institute for Theoretical Studies, 69118 Heidelberg, GermanyThe Exelixis Lab, Scientific Computing Group, Heidelberg Institute for Theoretical Studies, 69118 Heidelberg, GermanyThe use of reconfigurable computing for accelerating floating-point intensive codes is becoming common due to the availability of DSPs in new-generation FPGAs. We present the design of an efficient, pipelined floating-point datapath for calculating the logarithm function on reconfigurable devices. We integrate the datapath into a stand-alone LUT-based (Lookup Table) component, the LAU (Logarithm Approximation Unit). We extended the LAU, by integrating two architecturally independent, LAU-based datapaths into a larger component, the VLAU (vector-like LAU). The VLAU produces 2 results/cycle, while occupying the same amount of memory as the LAU. Under single precision, one LAU is 12 and 1.7 times faster than the GNU and Intel Math Kernel Library (MKL) implementations, respectively. The LAU is also 1.6 times faster than the FloPoCo reconfigurable logarithm architecture. Under double precision, one LAU is 20 and 2.6 times faster than the respective GNU and MKL functions and 1.4 times faster than the FloPoCo logarithm. The VLAU is approximately twice as fast as the LAU, both under single and double precision.http://dx.doi.org/10.1155/2011/341510
spellingShingle Nikolaos Alachiotis
Alexandros Stamatakis
A Vector-Like Reconfigurable Floating-Point Unit for the Logarithm
International Journal of Reconfigurable Computing
title A Vector-Like Reconfigurable Floating-Point Unit for the Logarithm
title_full A Vector-Like Reconfigurable Floating-Point Unit for the Logarithm
title_fullStr A Vector-Like Reconfigurable Floating-Point Unit for the Logarithm
title_full_unstemmed A Vector-Like Reconfigurable Floating-Point Unit for the Logarithm
title_short A Vector-Like Reconfigurable Floating-Point Unit for the Logarithm
title_sort vector like reconfigurable floating point unit for the logarithm
url http://dx.doi.org/10.1155/2011/341510
work_keys_str_mv AT nikolaosalachiotis avectorlikereconfigurablefloatingpointunitforthelogarithm
AT alexandrosstamatakis avectorlikereconfigurablefloatingpointunitforthelogarithm
AT nikolaosalachiotis vectorlikereconfigurablefloatingpointunitforthelogarithm
AT alexandrosstamatakis vectorlikereconfigurablefloatingpointunitforthelogarithm