The Best of ICCAD 2003
DOI: 10.1007/978-1-4615-0292-0_12
|View full text |Cite
|
Sign up to set email alerts
|

A Methodology for Correct-by-Construction Latency Insensitive Design

Abstract: In Deep Sub-Micron (DSM)

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
58
0

Year Published

2004
2004
2021
2021

Publication Types

Select...
4
3
2

Relationship

0
9

Authors

Journals

citations
Cited by 30 publications
(59 citation statements)
references
References 25 publications
1
58
0
Order By: Relevance
“…To efficiently source and sink data, two stream engines are employed with a FIFO capacity of 256x32 bit each. The test platform was an ACE-V ACS [16]. The relevant platform HW used here includes a 100MHz microSPARC IIep CPU with 64 MB of DRAM and a Virtex 1000 -4 FPGA.…”
Section: Hardware Experimental Resultsmentioning
confidence: 99%
“…To efficiently source and sink data, two stream engines are employed with a FIFO capacity of 256x32 bit each. The test platform was an ACE-V ACS [16]. The relevant platform HW used here includes a 100MHz microSPARC IIep CPU with 64 MB of DRAM and a Virtex 1000 -4 FPGA.…”
Section: Hardware Experimental Resultsmentioning
confidence: 99%
“…Hence, it is not surprising that the maximum number of hops at 45nm does not change much across the various router configurations because intermediate stateful repeaters such as relay stations [37] are needed to segment long interconnection links. The use of larger routers does not help to reduce the number of hops while it increases the chance of contention.…”
Section: Hop Countmentioning
confidence: 99%
“…A slightly modified version of a relay station [6] is used to prevent data loss when the successor primitive is full. Figure 2 illustrates the switching primitives in our MoT network.…”
Section: Memorymentioning
confidence: 99%