Proceedings of the 45th Annual Design Automation Conference 2008
DOI: 10.1145/1391469.1391524
|View full text |Cite
|
Sign up to set email alerts
|

Speedpath prediction based on learning from a small set of examples

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
25
0

Year Published

2009
2009
2023
2023

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 45 publications
(25 citation statements)
references
References 6 publications
0
25
0
Order By: Relevance
“…For a fabricated chip, the degree of variation might be such that the delays of some of the paths exceed their timing requirements. We assume such paths are isolated and their delays are measured as discussed in [1], [3], [5], [7], [9]. Moreover, we assume the delays of additional speedpaths are also measured.…”
Section: Preliminariesmentioning
confidence: 99%
See 2 more Smart Citations
“…For a fabricated chip, the degree of variation might be such that the delays of some of the paths exceed their timing requirements. We assume such paths are isolated and their delays are measured as discussed in [1], [3], [5], [7], [9]. Moreover, we assume the delays of additional speedpaths are also measured.…”
Section: Preliminariesmentioning
confidence: 99%
“…Note that our focus is on the segment identification problem, assuming the failing speedpaths are provided. We assume isolation of failing speedpaths is done using existing works such as [1], [3], [5], [7], while post-silicon path delay measurement is done using existing techniques such as [9].…”
Section: Problem Definitionmentioning
confidence: 99%
See 1 more Smart Citation
“…is a key question that was raised by the authors of [1], hoping to spur more research on learning from silicon data in order to achieve better silicon-to-model correlation. Indeed, this question touches on the widely accepted reality, that silicon speed-limiting paths, or simply silicon speedpaths, are not always accurately predicted by existing timing flows [2]. This can be attributed to a number of effects, including process, design, or environmental effects, that are either not fully understood or too difficult to model in modern designs.…”
Section: Introductionmentioning
confidence: 99%
“…The delays of the paths from silicon are not used in the analysis, and the authors do not try to reconcile actual measurements with the models. On the other hand, the authors of [2] employ a machine-learning approach that uses a small number of identified speedpaths to predict a larger set of paths that are potentially speed-limiting. They do this without identifying the root causes, which they say saves time and reduces the time to market.…”
Section: Introductionmentioning
confidence: 99%