Reliable high-throughput FPGA interconnect using source-synchronous surfing and wave pipelining
FPGA clock frequencies are slow enough that only a fraction of the interconnect’s bandwidth is used. By exploiting this bandwidth, the transfer of large amounts of data can be greatly accelerated. Alternatively, it may also be possible to save area on fixed-bandwidth links by using on-chip serial...
Main Author: | |
---|---|
Language: | English |
Published: |
University of British Columbia
2008
|
Subjects: | |
Online Access: | http://hdl.handle.net/2429/2767 |
id |
ndltd-LACETR-oai-collectionscanada.gc.ca-BVAU.2429-2767 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-LACETR-oai-collectionscanada.gc.ca-BVAU.2429-27672014-03-26T03:35:22Z Reliable high-throughput FPGA interconnect using source-synchronous surfing and wave pipelining Teehan, Paul Leonard Circuit design Field-programmable gate arrays On-chip interconnect FPGA clock frequencies are slow enough that only a fraction of the interconnect’s bandwidth is used. By exploiting this bandwidth, the transfer of large amounts of data can be greatly accelerated. Alternatively, it may also be possible to save area on fixed-bandwidth links by using on-chip serial signaling. For datapath-intensive designs which operate on words instead of bits, this can reduce wiring congestion as well. This thesis proposes relatively simple circuit-level modifications to FPGA interconnect to enable high-bandwidth communication. High-level area estimates indicate a potential interconnect area savings of 10 to 60% when serial links are used. Two interconnect pipelining techniques, wave pipelining and surfing, are adapted to FPGAs and compared against each other and against regular FPGA interconnect in terms of throughput, reliability, area, power, and latency. Source-synchronous signaling is used to achieve high data rates with simple receiver design. Statistical models for high-frequency power supply noise are developed and used to estimate the probability of error of wave pipelined and surfing links as a function of link length and operating speed. Surfing is generally found to be more reliable and less sensitive to noise than wave pipelining. Simulation results in a 65nm process demonstrate a throughput of 3Gbps per wire across a 50-stage, 25mm link. 2008-11-12T14:17:20Z 2008-11-12T14:17:20Z 2008 2008-11-12T14:17:20Z 2009-05 Electronic Thesis or Dissertation http://hdl.handle.net/2429/2767 eng University of British Columbia |
collection |
NDLTD |
language |
English |
sources |
NDLTD |
topic |
Circuit design Field-programmable gate arrays On-chip interconnect |
spellingShingle |
Circuit design Field-programmable gate arrays On-chip interconnect Teehan, Paul Leonard Reliable high-throughput FPGA interconnect using source-synchronous surfing and wave pipelining |
description |
FPGA clock frequencies are slow enough that only a fraction of the interconnect’s
bandwidth is used. By exploiting this bandwidth, the transfer of large amounts of
data can be greatly accelerated. Alternatively, it may also be possible to save area
on fixed-bandwidth links by using on-chip serial signaling. For datapath-intensive
designs which operate on words instead of bits, this can reduce wiring congestion
as well. This thesis proposes relatively simple circuit-level modifications to FPGA
interconnect to enable high-bandwidth communication. High-level area estimates
indicate a potential interconnect area savings of 10 to 60% when serial links are used.
Two interconnect pipelining techniques, wave pipelining and surfing, are adapted
to FPGAs and compared against each other and against regular FPGA interconnect
in terms of throughput, reliability, area, power, and latency. Source-synchronous
signaling is used to achieve high data rates with simple receiver design. Statistical
models for high-frequency power supply noise are developed and used to estimate the
probability of error of wave pipelined and surfing links as a function of link length
and operating speed. Surfing is generally found to be more reliable and less sensitive
to noise than wave pipelining. Simulation results in a 65nm process demonstrate a
throughput of 3Gbps per wire across a 50-stage, 25mm link. |
author |
Teehan, Paul Leonard |
author_facet |
Teehan, Paul Leonard |
author_sort |
Teehan, Paul Leonard |
title |
Reliable high-throughput FPGA interconnect using source-synchronous surfing and wave pipelining |
title_short |
Reliable high-throughput FPGA interconnect using source-synchronous surfing and wave pipelining |
title_full |
Reliable high-throughput FPGA interconnect using source-synchronous surfing and wave pipelining |
title_fullStr |
Reliable high-throughput FPGA interconnect using source-synchronous surfing and wave pipelining |
title_full_unstemmed |
Reliable high-throughput FPGA interconnect using source-synchronous surfing and wave pipelining |
title_sort |
reliable high-throughput fpga interconnect using source-synchronous surfing and wave pipelining |
publisher |
University of British Columbia |
publishDate |
2008 |
url |
http://hdl.handle.net/2429/2767 |
work_keys_str_mv |
AT teehanpaulleonard reliablehighthroughputfpgainterconnectusingsourcesynchronoussurfingandwavepipelining |
_version_ |
1716654881011400704 |