Show simple item record

dc.contributor.author
Gautschi, Michael
dc.contributor.author
Schaffner, Michael
dc.contributor.author
Gürkaynak, Frank Kagan
dc.contributor.author
Benini, Luca
dc.contributor.editor
Fujino, Laura C.
dc.date.accessioned
2022-06-03T11:50:40Z
dc.date.available
2017-06-12T04:12:28Z
dc.date.available
2021-07-15T11:13:52Z
dc.date.available
2022-06-03T11:50:40Z
dc.date.issued
2016
dc.identifier.isbn
978-1-4673-9466-6
en_US
dc.identifier.issn
0193-6530
dc.identifier.issn
2376-8606
dc.identifier.other
10.1109/ISSCC.2016.7417917
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/115156
dc.description.abstract
Energy-efficient computing and ultra-low-power operation are requirements for many application areas, such as IoT and wearables. While for some applications, integer and fixed-point processor instructions suffice, others (e.g. simultaneous localization and mapping - SLAM, stereo vision, nonlinear regression and classification) require a larger dynamic range, typically obtained using single/double-precision floating point (FP) instructions. Logarithmic number systems (LNS) have been proposed [1,2] as an energy-efficient alternative to conventional FP, as several complex operations such as MUL, DIV, and EXP translate into simpler arithmetic operations in the logarithmic space and can be efficiently calculated using integer arithmetic units. However, ADD and SUB become nonlinear and have to be approximated by look-up tables (LUTs) and interpolation, which is typically implemented in a dedicated LNS unit (LNU) [1,2]. The area of LNUs grows exponentially with the desired precision, and an LNU with accuracy comparable to IEEE single-precision format is larger than a traditional floating-point unit (FPU). However, we show that in multi-core systems optimized for ultra-low-power operation such as the PULP system [3], one LNU can be efficiently shared in a cluster as indicated in Fig. 4.6.1. This arrangement not only reduces the per-core area overhead, but more importantly, allows several costly operations such as FP MUL/DIV to be processed without contention within the integer cores without additional overhead. We show that for typical nonlinear processing tasks, our LNU design can be up to 4.2× more energy efficient than a private-FP design.
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.title
A 65nm CMOS 6.4-to-29.2pJ/FLOP@0.8V shared logarithmic floating point unit for acceleration of nonlinear function kernels in a tightly coupled processor cluster
en_US
dc.type
Other Conference Item
dc.date.published
2016-02-25
ethz.book.title
2016 IEEE International Solid-State Circuits Conference (ISSCC)
en_US
ethz.journal.title
Digest of Technical Papers / IEEE International Solid State Circuits Conference
ethz.journal.volume
59
en_US
ethz.journal.abbreviated
Dig. tech. pap.- IEEE Int. Solid-State Circuits Conf.
ethz.pages.start
82
en_US
ethz.pages.end
84
en_US
ethz.event
63rd IEEE International Solid-State Circuits Conference (ISSCC 2016)
en_US
ethz.event.location
San Francisco, CA, USA
en_US
ethz.event.date
January 31 - February 4, 2016
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
Piscataway, NJ
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02636 - Institut für Integrierte Systeme / Integrated Systems Laboratory::03996 - Benini, Luca / Benini, Luca
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02636 - Institut für Integrierte Systeme / Integrated Systems Laboratory::03996 - Benini, Luca / Benini, Luca
ethz.date.deposited
2017-06-12T04:17:33Z
ethz.source
ECIT
ethz.identifier.importid
imp5936544e0436925546
ethz.ecitpid
pub:176974
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2017-07-20T15:42:48Z
ethz.rosetta.lastUpdated
2022-03-29T10:26:04Z
ethz.rosetta.exportRequired
true
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=A%2065nm%20CMOS%206.4-to-29.2pJ/FLOP@0.8V%20shared%20logarithmic%20floating%20point%20unit%20for%20acceleration%20of%20nonlinear%20function%20kernels%20in%20a%20tightly%&rft.jtitle=Digest%20of%20Technical%20Papers%20/%20IEEE%20International%20Solid%20State%20Circuits%20Conference&rft.date=2016&rft.volume=59&rft.spage=82&rft.epage=84&rft.issn=0193-6530&2376-8606&rft.au=Gautschi,%20Michael&Schaffner,%20Michael&G%C3%BCrkaynak,%20Frank%20Kagan&Benini,%20Luca&rft.isbn=978-1-4673-9466-6&rft.genre=unknown&rft_id=info:doi/10.1109/ISSCC.2016.7417917&rft.btitle=2016%20IEEE%20International%20Solid-State%20Circuits%20Conference%20(ISSCC)
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record