Too Big to Fail? Active Few-Shot Learning Guided Logic Synthesis. Chowdhury, A. B., Tan, B., Carey, R., Jain, T., Karri, R., & Garg, S. April, 2022. Number: arXiv:2204.02368 arXiv:2204.02368 [cs]![Too Big to Fail? Active Few-Shot Learning Guided Logic Synthesis [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex Generating sub-optimal synthesis transformation sequences ("synthesis recipe") is an important problem in logic synthesis. Manually crafted synthesis recipes have poor quality. State-of-the art machine learning (ML) works to generate synthesis recipes do not scale to large netlists as the models need to be trained from scratch, for which training data is collected using time consuming synthesis runs. We propose a new approach, Bulls-Eye, that fine-tunes a pre-trained model on past synthesis data to accurately predict the quality of a synthesis recipe for an unseen netlist. This approach on achieves 2x-10x run-time improvement and better quality-of-result (QoR) than state-of-the-art machine learning approaches.
@misc{chowdhury_too_2022,
title = {Too {Big} to {Fail}? {Active} {Few}-{Shot} {Learning} {Guided} {Logic} {Synthesis}},
shorttitle = {Too {Big} to {Fail}?},
url = {http://arxiv.org/abs/2204.02368},
abstract = {Generating sub-optimal synthesis transformation sequences ("synthesis recipe") is an important problem in logic synthesis. Manually crafted synthesis recipes have poor quality. State-of-the art machine learning (ML) works to generate synthesis recipes do not scale to large netlists as the models need to be trained from scratch, for which training data is collected using time consuming synthesis runs. We propose a new approach, Bulls-Eye, that fine-tunes a pre-trained model on past synthesis data to accurately predict the quality of a synthesis recipe for an unseen netlist. This approach on achieves 2x-10x run-time improvement and better quality-of-result (QoR) than state-of-the-art machine learning approaches.},
urldate = {2022-06-04},
publisher = {arXiv},
author = {Chowdhury, Animesh Basak and Tan, Benjamin and Carey, Ryan and Jain, Tushit and Karri, Ramesh and Garg, Siddharth},
month = apr,
year = {2022},
note = {Number: arXiv:2204.02368
arXiv:2204.02368 [cs]},
keywords = {\#broken, Computer Science - Artificial Intelligence, Computer Science - Hardware Architecture, Computer Science - Machine Learning, Jab/\#Pre},
}
Downloads: 0
{"_id":"8G8tNCJzPS4xYuANE","bibbaseid":"chowdhury-tan-carey-jain-karri-garg-toobigtofailactivefewshotlearningguidedlogicsynthesis-2022","author_short":["Chowdhury, A. B.","Tan, B.","Carey, R.","Jain, T.","Karri, R.","Garg, S."],"bibdata":{"bibtype":"misc","type":"misc","title":"Too Big to Fail? Active Few-Shot Learning Guided Logic Synthesis","shorttitle":"Too Big to Fail?","url":"http://arxiv.org/abs/2204.02368","abstract":"Generating sub-optimal synthesis transformation sequences (\"synthesis recipe\") is an important problem in logic synthesis. Manually crafted synthesis recipes have poor quality. State-of-the art machine learning (ML) works to generate synthesis recipes do not scale to large netlists as the models need to be trained from scratch, for which training data is collected using time consuming synthesis runs. We propose a new approach, Bulls-Eye, that fine-tunes a pre-trained model on past synthesis data to accurately predict the quality of a synthesis recipe for an unseen netlist. This approach on achieves 2x-10x run-time improvement and better quality-of-result (QoR) than state-of-the-art machine learning approaches.","urldate":"2022-06-04","publisher":"arXiv","author":[{"propositions":[],"lastnames":["Chowdhury"],"firstnames":["Animesh","Basak"],"suffixes":[]},{"propositions":[],"lastnames":["Tan"],"firstnames":["Benjamin"],"suffixes":[]},{"propositions":[],"lastnames":["Carey"],"firstnames":["Ryan"],"suffixes":[]},{"propositions":[],"lastnames":["Jain"],"firstnames":["Tushit"],"suffixes":[]},{"propositions":[],"lastnames":["Karri"],"firstnames":["Ramesh"],"suffixes":[]},{"propositions":[],"lastnames":["Garg"],"firstnames":["Siddharth"],"suffixes":[]}],"month":"April","year":"2022","note":"Number: arXiv:2204.02368 arXiv:2204.02368 [cs]","keywords":"#broken, Computer Science - Artificial Intelligence, Computer Science - Hardware Architecture, Computer Science - Machine Learning, Jab/#Pre","bibtex":"@misc{chowdhury_too_2022,\n\ttitle = {Too {Big} to {Fail}? {Active} {Few}-{Shot} {Learning} {Guided} {Logic} {Synthesis}},\n\tshorttitle = {Too {Big} to {Fail}?},\n\turl = {http://arxiv.org/abs/2204.02368},\n\tabstract = {Generating sub-optimal synthesis transformation sequences (\"synthesis recipe\") is an important problem in logic synthesis. Manually crafted synthesis recipes have poor quality. State-of-the art machine learning (ML) works to generate synthesis recipes do not scale to large netlists as the models need to be trained from scratch, for which training data is collected using time consuming synthesis runs. We propose a new approach, Bulls-Eye, that fine-tunes a pre-trained model on past synthesis data to accurately predict the quality of a synthesis recipe for an unseen netlist. This approach on achieves 2x-10x run-time improvement and better quality-of-result (QoR) than state-of-the-art machine learning approaches.},\n\turldate = {2022-06-04},\n\tpublisher = {arXiv},\n\tauthor = {Chowdhury, Animesh Basak and Tan, Benjamin and Carey, Ryan and Jain, Tushit and Karri, Ramesh and Garg, Siddharth},\n\tmonth = apr,\n\tyear = {2022},\n\tnote = {Number: arXiv:2204.02368\narXiv:2204.02368 [cs]},\n\tkeywords = {\\#broken, Computer Science - Artificial Intelligence, Computer Science - Hardware Architecture, Computer Science - Machine Learning, Jab/\\#Pre},\n}\n\n","author_short":["Chowdhury, A. B.","Tan, B.","Carey, R.","Jain, T.","Karri, R.","Garg, S."],"key":"chowdhury_too_2022","id":"chowdhury_too_2022","bibbaseid":"chowdhury-tan-carey-jain-karri-garg-toobigtofailactivefewshotlearningguidedlogicsynthesis-2022","role":"author","urls":{"Paper":"http://arxiv.org/abs/2204.02368"},"keyword":["#broken","Computer Science - Artificial Intelligence","Computer Science - Hardware Architecture","Computer Science - Machine Learning","Jab/#Pre"],"metadata":{"authorlinks":{}}},"bibtype":"misc","biburl":"https://api.zotero.org/users/4645877/collections/5QADJUWI/items?key=OGCZ3uLZZq4lLIXadnuJrB1J&format=bibtex&limit=100","dataSources":["Wsv2bQ4jPuc7qme8R","TRtmubHSqHw6999cH"],"keywords":["#broken","computer science - artificial intelligence","computer science - hardware architecture","computer science - machine learning","jab/#pre"],"search_terms":["big","fail","active","few","shot","learning","guided","logic","synthesis","chowdhury","tan","carey","jain","karri","garg"],"title":"Too Big to Fail? Active Few-Shot Learning Guided Logic Synthesis","year":2022}