A learning bridge from architectural synthesis to physical design for exploring power efficient high-performance adders. Roy, S., Ma, Y., Miao, J., & Yu, B. In 2017 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED), pages 1–6, July, 2017. doi abstract bibtex In spite of maturity to the modern electronic design automation (EDA) tools, optimized designs at architectural stage may become sub-optimal after going through physical design flow. Adder design has been such a long studied fundamental problem in VLSI industry yet designers cannot achieve optimal solutions by running EDA tools on the set of available prefix adder architectures. In this paper, we enhance a state-of-the-art prefix adder synthesis algorithm to obtain a much wider solution space in architectural domain. On top of that, a machine learning based design space exploration methodology is applied to predict the Pareto frontier of the adders in physical domain, which is infeasible by exhaustively running EDA tools for innumerable architectural solutions. Experimental results demonstrate that our framework can achieve near-optimal delay vs. power/area Pareto frontier over a wide design space, bridging the gap between architeon the set of available prefix adder architectures. In this paper, we enhance a state-of-the-art prefix adder synthesis algorithm to obtain a much wider solution space in architectural domain. On top of that, a machine learning based design space exploration methodology is applied to predict the Pareto frontier of the adders in physical domain, which is infeasible by exhaustively running EDA tools for innumerable architectural solutions. Experimental results demonstrate that our framework can achieve near-optimal delay vs. power/area Pareto frontier over a wide design space, bridging the gap between architectural andctural and physical designs.
@inproceedings{roy_learning_2017,
title = {A learning bridge from architectural synthesis to physical design for exploring power efficient high-performance adders},
doi = {10.1109/ISLPED.2017.8009168},
abstract = {In spite of maturity to the modern electronic design automation (EDA) tools, optimized designs at architectural stage may become sub-optimal after going through physical design flow. Adder design has been such a long studied fundamental problem in VLSI industry yet designers cannot achieve optimal solutions by running EDA tools on the set of available prefix adder architectures. In this paper, we enhance a state-of-the-art prefix adder synthesis algorithm to obtain a much wider solution space in architectural domain. On top of that, a machine learning based design space exploration methodology is applied to predict the Pareto frontier of the adders in physical domain, which is infeasible by exhaustively running EDA tools for innumerable architectural solutions. Experimental results demonstrate that our framework can achieve near-optimal delay vs. power/area Pareto frontier over a wide design space, bridging the gap between architeon the set of available prefix adder architectures. In this paper, we enhance a state-of-the-art prefix adder synthesis algorithm to obtain a much wider solution space in architectural domain. On top of that, a machine learning based design space exploration methodology is applied to predict the Pareto frontier of the adders in physical domain, which is infeasible by exhaustively running EDA tools for innumerable architectural solutions. Experimental results demonstrate that our framework can achieve near-optimal delay vs. power/area Pareto frontier over a wide design space, bridging the gap between architectural andctural and physical designs.},
booktitle = {2017 {IEEE}/{ACM} {International} {Symposium} on {Low} {Power} {Electronics} and {Design} ({ISLPED})},
author = {Roy, S. and Ma, Y. and Miao, J. and Yu, B.},
month = jul,
year = {2017},
keywords = {Adders, Algorithm design and analysis, Delays, Machine learning algorithms, Pareto frontier, Physical design, Tools, VLSI industry, adders, architectural synthesis, design space, design space exploration methodology, electronic design automation, learning (artificial intelligence), learning bridge, machine learning, modern electronic design automation tools, physical design flow, power efficient high-performance adders, prefix adder architectures},
pages = {1--6},
}
Downloads: 0
{"_id":"C9WzrvdKNKFgM8taN","bibbaseid":"roy-ma-miao-yu-alearningbridgefromarchitecturalsynthesistophysicaldesignforexploringpowerefficienthighperformanceadders-2017","author_short":["Roy, S.","Ma, Y.","Miao, J.","Yu, B."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"A learning bridge from architectural synthesis to physical design for exploring power efficient high-performance adders","doi":"10.1109/ISLPED.2017.8009168","abstract":"In spite of maturity to the modern electronic design automation (EDA) tools, optimized designs at architectural stage may become sub-optimal after going through physical design flow. Adder design has been such a long studied fundamental problem in VLSI industry yet designers cannot achieve optimal solutions by running EDA tools on the set of available prefix adder architectures. In this paper, we enhance a state-of-the-art prefix adder synthesis algorithm to obtain a much wider solution space in architectural domain. On top of that, a machine learning based design space exploration methodology is applied to predict the Pareto frontier of the adders in physical domain, which is infeasible by exhaustively running EDA tools for innumerable architectural solutions. Experimental results demonstrate that our framework can achieve near-optimal delay vs. power/area Pareto frontier over a wide design space, bridging the gap between architeon the set of available prefix adder architectures. In this paper, we enhance a state-of-the-art prefix adder synthesis algorithm to obtain a much wider solution space in architectural domain. On top of that, a machine learning based design space exploration methodology is applied to predict the Pareto frontier of the adders in physical domain, which is infeasible by exhaustively running EDA tools for innumerable architectural solutions. Experimental results demonstrate that our framework can achieve near-optimal delay vs. power/area Pareto frontier over a wide design space, bridging the gap between architectural andctural and physical designs.","booktitle":"2017 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED)","author":[{"propositions":[],"lastnames":["Roy"],"firstnames":["S."],"suffixes":[]},{"propositions":[],"lastnames":["Ma"],"firstnames":["Y."],"suffixes":[]},{"propositions":[],"lastnames":["Miao"],"firstnames":["J."],"suffixes":[]},{"propositions":[],"lastnames":["Yu"],"firstnames":["B."],"suffixes":[]}],"month":"July","year":"2017","keywords":"Adders, Algorithm design and analysis, Delays, Machine learning algorithms, Pareto frontier, Physical design, Tools, VLSI industry, adders, architectural synthesis, design space, design space exploration methodology, electronic design automation, learning (artificial intelligence), learning bridge, machine learning, modern electronic design automation tools, physical design flow, power efficient high-performance adders, prefix adder architectures","pages":"1–6","bibtex":"@inproceedings{roy_learning_2017,\n\ttitle = {A learning bridge from architectural synthesis to physical design for exploring power efficient high-performance adders},\n\tdoi = {10.1109/ISLPED.2017.8009168},\n\tabstract = {In spite of maturity to the modern electronic design automation (EDA) tools, optimized designs at architectural stage may become sub-optimal after going through physical design flow. Adder design has been such a long studied fundamental problem in VLSI industry yet designers cannot achieve optimal solutions by running EDA tools on the set of available prefix adder architectures. In this paper, we enhance a state-of-the-art prefix adder synthesis algorithm to obtain a much wider solution space in architectural domain. On top of that, a machine learning based design space exploration methodology is applied to predict the Pareto frontier of the adders in physical domain, which is infeasible by exhaustively running EDA tools for innumerable architectural solutions. Experimental results demonstrate that our framework can achieve near-optimal delay vs. power/area Pareto frontier over a wide design space, bridging the gap between architeon the set of available prefix adder architectures. In this paper, we enhance a state-of-the-art prefix adder synthesis algorithm to obtain a much wider solution space in architectural domain. On top of that, a machine learning based design space exploration methodology is applied to predict the Pareto frontier of the adders in physical domain, which is infeasible by exhaustively running EDA tools for innumerable architectural solutions. Experimental results demonstrate that our framework can achieve near-optimal delay vs. power/area Pareto frontier over a wide design space, bridging the gap between architectural andctural and physical designs.},\n\tbooktitle = {2017 {IEEE}/{ACM} {International} {Symposium} on {Low} {Power} {Electronics} and {Design} ({ISLPED})},\n\tauthor = {Roy, S. and Ma, Y. and Miao, J. and Yu, B.},\n\tmonth = jul,\n\tyear = {2017},\n\tkeywords = {Adders, Algorithm design and analysis, Delays, Machine learning algorithms, Pareto frontier, Physical design, Tools, VLSI industry, adders, architectural synthesis, design space, design space exploration methodology, electronic design automation, learning (artificial intelligence), learning bridge, machine learning, modern electronic design automation tools, physical design flow, power efficient high-performance adders, prefix adder architectures},\n\tpages = {1--6},\n}\n\n","author_short":["Roy, S.","Ma, Y.","Miao, J.","Yu, B."],"key":"roy_learning_2017","id":"roy_learning_2017","bibbaseid":"roy-ma-miao-yu-alearningbridgefromarchitecturalsynthesistophysicaldesignforexploringpowerefficienthighperformanceadders-2017","role":"author","urls":{},"keyword":["Adders","Algorithm design and analysis","Delays","Machine learning algorithms","Pareto frontier","Physical design","Tools","VLSI industry","adders","architectural synthesis","design space","design space exploration methodology","electronic design automation","learning (artificial intelligence)","learning bridge","machine learning","modern electronic design automation tools","physical design flow","power efficient high-performance adders","prefix adder architectures"],"metadata":{"authorlinks":{}},"downloads":0,"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/bxt101","dataSources":["Wsv2bQ4jPuc7qme8R"],"keywords":["adders","algorithm design and analysis","delays","machine learning algorithms","pareto frontier","physical design","tools","vlsi industry","adders","architectural synthesis","design space","design space exploration methodology","electronic design automation","learning (artificial intelligence)","learning bridge","machine learning","modern electronic design automation tools","physical design flow","power efficient high-performance adders","prefix adder architectures"],"search_terms":["learning","bridge","architectural","synthesis","physical","design","exploring","power","efficient","high","performance","adders","roy","ma","miao","yu"],"title":"A learning bridge from architectural synthesis to physical design for exploring power efficient high-performance adders","year":2017}