Loading…
Accelerating SPICE Model-Evaluation using FPGAs
Single-FPGA spatial implementations can provide an order of magnitude speedup over sequential microprocessor implementations for data-parallel, floating-point computation in SPICE model-evaluation. Model-evaluation is a key component of the SPICE circuit simulator and it is characterized by large ir...
Saved in:
Main Authors: | , |
---|---|
Format: | Conference Proceeding |
Language: | English |
Subjects: | |
Citations: | Items that cite this one |
Online Access: | Request full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c256t-5e3b726094036671363d0d2e17fa189de118796b1df584a67e5e8fd680f00d2c3 |
---|---|
cites | |
container_end_page | 44 |
container_issue | |
container_start_page | 37 |
container_title | |
container_volume | |
creator | Kapre, N. DeHon, A. |
description | Single-FPGA spatial implementations can provide an order of magnitude speedup over sequential microprocessor implementations for data-parallel, floating-point computation in SPICE model-evaluation. Model-evaluation is a key component of the SPICE circuit simulator and it is characterized by large irregular floating-point compute graphs. We show how to exploit the parallelism available in these graphs on single-FPGA designs with a low-overhead VLIW-scheduled architecture. Our architecture uses spatial floating-point operators coupled to local high-bandwidth memories and interconnected by a time-shared network. We retime operation inputs in the model-evaluation to allow independent scheduling of computation and communication. With this approach, we demonstrate speedups of 2-18times over a dual-core 3 GHz Intel Xeon 5160 when using a Xilinx Virtex 5 LX330T for a variety of SPICE device models. |
doi_str_mv | 10.1109/FCCM.2009.14 |
format | conference_proceeding |
fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5290957</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5290957</ieee_id><sourcerecordid>5290957</sourcerecordid><originalsourceid>FETCH-LOGICAL-c256t-5e3b726094036671363d0d2e17fa189de118796b1df584a67e5e8fd680f00d2c3</originalsourceid><addsrcrecordid>eNotjEFLw0AQhRekoNbcvHnJH0g6k83O7hxDSGqhxYJ6LtvsRCKxlaQV_Pem1Hf54H2Pp9QjQooIvKjLcpNmAJxifqMitg4ssdEWCWbq_mIYKLd4q6Jx_IQpRKzJ3KlF0TTSy-BP3eEjft2uyireHIP0SfXj-_NUHw_xebzIerssxgc1a30_SvTPuXqvq7fyOVm_LFdlsU6azNApMaL3NiPgHDSRRU06QMgEbevRcRBEZ5n2GFrjck9WjLg2kIMWpl2j5-rp-tuJyO576L788LszGQMbq_8AHb9BGw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Accelerating SPICE Model-Evaluation using FPGAs</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Kapre, N. ; DeHon, A.</creator><creatorcontrib>Kapre, N. ; DeHon, A.</creatorcontrib><description>Single-FPGA spatial implementations can provide an order of magnitude speedup over sequential microprocessor implementations for data-parallel, floating-point computation in SPICE model-evaluation. Model-evaluation is a key component of the SPICE circuit simulator and it is characterized by large irregular floating-point compute graphs. We show how to exploit the parallelism available in these graphs on single-FPGA designs with a low-overhead VLIW-scheduled architecture. Our architecture uses spatial floating-point operators coupled to local high-bandwidth memories and interconnected by a time-shared network. We retime operation inputs in the model-evaluation to allow independent scheduling of computation and communication. With this approach, we demonstrate speedups of 2-18times over a dual-core 3 GHz Intel Xeon 5160 when using a Xilinx Virtex 5 LX330T for a variety of SPICE device models.</description><identifier>ISBN: 9780769537160</identifier><identifier>ISBN: 0769537162</identifier><identifier>DOI: 10.1109/FCCM.2009.14</identifier><identifier>LCCN: 2009906471</identifier><language>eng</language><publisher>IEEE</publisher><subject>Acceleration ; Analog Circuit Simulator ; Circuit simulation ; Computational modeling ; Computer architecture ; Coupling circuits ; Field programmable gate arrays ; Floating-Point ; Integrated circuit interconnections ; Loop Unrolling ; Microprocessors ; Parallel processing ; Spatial Computation ; SPICE ; VLIW Scheduling</subject><ispartof>2009 17th IEEE Symposium on Field Programmable Custom Computing Machines, 2009, p.37-44</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c256t-5e3b726094036671363d0d2e17fa189de118796b1df584a67e5e8fd680f00d2c3</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/5290957$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5290957$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Kapre, N.</creatorcontrib><creatorcontrib>DeHon, A.</creatorcontrib><title>Accelerating SPICE Model-Evaluation using FPGAs</title><title>2009 17th IEEE Symposium on Field Programmable Custom Computing Machines</title><addtitle>FCCM</addtitle><description>Single-FPGA spatial implementations can provide an order of magnitude speedup over sequential microprocessor implementations for data-parallel, floating-point computation in SPICE model-evaluation. Model-evaluation is a key component of the SPICE circuit simulator and it is characterized by large irregular floating-point compute graphs. We show how to exploit the parallelism available in these graphs on single-FPGA designs with a low-overhead VLIW-scheduled architecture. Our architecture uses spatial floating-point operators coupled to local high-bandwidth memories and interconnected by a time-shared network. We retime operation inputs in the model-evaluation to allow independent scheduling of computation and communication. With this approach, we demonstrate speedups of 2-18times over a dual-core 3 GHz Intel Xeon 5160 when using a Xilinx Virtex 5 LX330T for a variety of SPICE device models.</description><subject>Acceleration</subject><subject>Analog Circuit Simulator</subject><subject>Circuit simulation</subject><subject>Computational modeling</subject><subject>Computer architecture</subject><subject>Coupling circuits</subject><subject>Field programmable gate arrays</subject><subject>Floating-Point</subject><subject>Integrated circuit interconnections</subject><subject>Loop Unrolling</subject><subject>Microprocessors</subject><subject>Parallel processing</subject><subject>Spatial Computation</subject><subject>SPICE</subject><subject>VLIW Scheduling</subject><isbn>9780769537160</isbn><isbn>0769537162</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2009</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotjEFLw0AQhRekoNbcvHnJH0g6k83O7hxDSGqhxYJ6LtvsRCKxlaQV_Pem1Hf54H2Pp9QjQooIvKjLcpNmAJxifqMitg4ssdEWCWbq_mIYKLd4q6Jx_IQpRKzJ3KlF0TTSy-BP3eEjft2uyireHIP0SfXj-_NUHw_xebzIerssxgc1a30_SvTPuXqvq7fyOVm_LFdlsU6azNApMaL3NiPgHDSRRU06QMgEbevRcRBEZ5n2GFrjck9WjLg2kIMWpl2j5-rp-tuJyO576L788LszGQMbq_8AHb9BGw</recordid><startdate>20090101</startdate><enddate>20090101</enddate><creator>Kapre, N.</creator><creator>DeHon, A.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20090101</creationdate><title>Accelerating SPICE Model-Evaluation using FPGAs</title><author>Kapre, N. ; DeHon, A.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c256t-5e3b726094036671363d0d2e17fa189de118796b1df584a67e5e8fd680f00d2c3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2009</creationdate><topic>Acceleration</topic><topic>Analog Circuit Simulator</topic><topic>Circuit simulation</topic><topic>Computational modeling</topic><topic>Computer architecture</topic><topic>Coupling circuits</topic><topic>Field programmable gate arrays</topic><topic>Floating-Point</topic><topic>Integrated circuit interconnections</topic><topic>Loop Unrolling</topic><topic>Microprocessors</topic><topic>Parallel processing</topic><topic>Spatial Computation</topic><topic>SPICE</topic><topic>VLIW Scheduling</topic><toplevel>online_resources</toplevel><creatorcontrib>Kapre, N.</creatorcontrib><creatorcontrib>DeHon, A.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Kapre, N.</au><au>DeHon, A.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Accelerating SPICE Model-Evaluation using FPGAs</atitle><btitle>2009 17th IEEE Symposium on Field Programmable Custom Computing Machines</btitle><stitle>FCCM</stitle><date>2009-01-01</date><risdate>2009</risdate><spage>37</spage><epage>44</epage><pages>37-44</pages><isbn>9780769537160</isbn><isbn>0769537162</isbn><abstract>Single-FPGA spatial implementations can provide an order of magnitude speedup over sequential microprocessor implementations for data-parallel, floating-point computation in SPICE model-evaluation. Model-evaluation is a key component of the SPICE circuit simulator and it is characterized by large irregular floating-point compute graphs. We show how to exploit the parallelism available in these graphs on single-FPGA designs with a low-overhead VLIW-scheduled architecture. Our architecture uses spatial floating-point operators coupled to local high-bandwidth memories and interconnected by a time-shared network. We retime operation inputs in the model-evaluation to allow independent scheduling of computation and communication. With this approach, we demonstrate speedups of 2-18times over a dual-core 3 GHz Intel Xeon 5160 when using a Xilinx Virtex 5 LX330T for a variety of SPICE device models.</abstract><pub>IEEE</pub><doi>10.1109/FCCM.2009.14</doi><tpages>8</tpages><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISBN: 9780769537160 |
ispartof | 2009 17th IEEE Symposium on Field Programmable Custom Computing Machines, 2009, p.37-44 |
issn | |
language | eng |
recordid | cdi_ieee_primary_5290957 |
source | IEEE Electronic Library (IEL) Conference Proceedings |
subjects | Acceleration Analog Circuit Simulator Circuit simulation Computational modeling Computer architecture Coupling circuits Field programmable gate arrays Floating-Point Integrated circuit interconnections Loop Unrolling Microprocessors Parallel processing Spatial Computation SPICE VLIW Scheduling |
title | Accelerating SPICE Model-Evaluation using FPGAs |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T09%3A25%3A51IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Accelerating%20SPICE%20Model-Evaluation%20using%20FPGAs&rft.btitle=2009%2017th%20IEEE%20Symposium%20on%20Field%20Programmable%20Custom%20Computing%20Machines&rft.au=Kapre,%20N.&rft.date=2009-01-01&rft.spage=37&rft.epage=44&rft.pages=37-44&rft.isbn=9780769537160&rft.isbn_list=0769537162&rft_id=info:doi/10.1109/FCCM.2009.14&rft_dat=%3Cieee_6IE%3E5290957%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c256t-5e3b726094036671363d0d2e17fa189de118796b1df584a67e5e8fd680f00d2c3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5290957&rfr_iscdi=true |