{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T15:33:58Z","timestamp":1776440038746,"version":"3.51.2"},"reference-count":57,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2022,12,24]],"date-time":"2022-12-24T00:00:00Z","timestamp":1671840000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Des. Autom. Electron. Syst."],"published-print":{"date-parts":[[2023,3,31]]},"abstract":"<jats:p>High-level Synthesis\u00a0(HLS) Design-Space Exploration\u00a0(DSE) aims at identifying Pareto-optimal synthesis configurations whose exhaustive search is unfeasible due to the design-space dimensionality and the prohibitive computational cost of the synthesis process. Within this framework, we address the design automation problem by proposing graph neural networks that jointly predict acceleration performance and hardware costs of a synthesized behavioral specification given optimization directives. Learned models can be used to rapidly approach the Pareto curve by guiding the DSE, taking into account performance and cost estimates. The proposed method outperforms traditional HLS-driven DSE approaches, by accounting for the arbitrary length of computer programs and the invariant properties of the input. We propose a novel hybrid control and dataflow graph representation that enables training the graph neural network on specifications of different hardware accelerators. Our approach achieves prediction accuracy comparable with that of state-of-the-art simulators without having access to analytical models of the HLS compiler. Finally, the learned representation can be exploited for DSE in unexplored configuration spaces by fine-tuning on a small number of samples from the new target domain. The outcome of the empirical evaluation of this transfer learning shows strong results against state-of-the-art baselines in relevant benchmarks.<\/jats:p>","DOI":"10.1145\/3570925","type":"journal-article","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T10:58:12Z","timestamp":1668164292000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":33,"title":["Graph Neural Networks for High-Level Synthesis Design Space Exploration"],"prefix":"10.1145","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8935-6796","authenticated-orcid":false,"given":"Lorenzo","family":"Ferretti","sequence":"first","affiliation":[{"name":"University of California, Los Angeles, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3219-9360","authenticated-orcid":false,"given":"Andrea","family":"Cini","sequence":"additional","affiliation":[{"name":"IDSIA, Universit\u00e0 della Svizzera italiana, Lugano, Svizzera, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6644-5200","authenticated-orcid":false,"given":"Georgios","family":"Zacharopoulos","sequence":"additional","affiliation":[{"name":"Computing Systems Lab, Huawei Zurich Research Center, Z\u00fcrich Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3819-0025","authenticated-orcid":false,"given":"Cesare","family":"Alippi","sequence":"additional","affiliation":[{"name":"IDSIA, Universit\u00e0 della Svizzera italiana, Lugano, Svizzera, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1083-8782","authenticated-orcid":false,"given":"Laura","family":"Pozzi","sequence":"additional","affiliation":[{"name":"Universit\u00e0 della Svizzera italiana, Lugano, Svizzera, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,12,24]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/PCCC.1994.504159"},{"key":"e_1_3_2_3_2","unstructured":"P. W. Battaglia J. B. Hamrick V. Bapst A. Sanchez-Gonzalez V. Zambaldi M. Malinowski A. Tacchetti D. Raposo A. Santoro R. Faulkner et\u00a0al. 2018. Relational inductive biases deep learning and graph networks. arXiv preprint arXiv:1806.01261."},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240850"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.2970597"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240815"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2017.8203844"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240838"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC.2018.8465940"},{"key":"e_1_3_2_11_2","unstructured":"P. Cuoq F. Kirchner N. Kosmatov V. Prevosto J. Signoles and B. Yakobowski. 2012. Frama-C: A software analysis perspective(SEFM\u201912). 9 1 (2012) 35\u201343."},{"issue":"99","key":"e_1_3_2_12_2","first-page":"1","article-title":"Cluster-based heuristic for high level synthesis design space exploration","author":"Ferretti L.","year":"2018","unstructured":"L. Ferretti, G. Ansaloni, and L. Pozzi. 2018. Cluster-based heuristic for high level synthesis design space exploration. IEEE Transactions on Emerging Topics in Computing99 (2018), 1\u20139.","journal-title":"IEEE Transactions on Emerging Topics in Computing"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2018.00040"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/LES.2021.3066882"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.3012750"},{"key":"e_1_3_2_16_2","first-page":"1263","volume-title":"International Conference on Machine Learning","author":"Gilmer J.","year":"2017","unstructured":"J. Gilmer, S. S. Schoenholz, P. F. Riley, O. Vinyals, and G. E. Dahl. 2017. Neural message passing for quantum chemistry. In International Conference on Machine Learning. PMLR, 1263\u20131272."},{"key":"e_1_3_2_17_2","first-page":"126","volume-title":"International Symposium on Industrial Embedded Systems","author":"Holzer Martin","year":"2007","unstructured":"Martin Holzer, Bastian Knerr, and Markus Rupp. 2007. Design space exploration with evolutionary multi-objective optimisation. In International Symposium on Industrial Embedded Systems. IEEE, 126\u2013133."},{"key":"e_1_3_2_18_2","volume-title":"ACM\/IEEE Workshop on Machine Learning for CAD (MLCAD\u201920)","author":"Kwon J.","year":"2020","unstructured":"J. Kwon and L. P. Carloni. 2020. Transfer learning for design-space exploration with high-level synthesis. In ACM\/IEEE Workshop on Machine Learning for CAD (MLCAD\u201920)."},{"key":"e_1_3_2_19_2","first-page":"75","volume-title":"International Symposium on Code Generation and Optimization","author":"Lattner C.","year":"2004","unstructured":"C. Lattner and V. Adve. 2004. LLVM: A compilation framework for lifelong program analysis and transformation. In International Symposium on Code Generation and Optimization. 75."},{"key":"e_1_3_2_20_2","first-page":"3835","volume-title":"International Conference on Machine Learning","author":"Li Y.","year":"2019","unstructured":"Y. Li, C. Gu, T. Dullien, O. Vinyals, and P. Kohli. 2019. Graph matching networks for learning the similarity of graph structured objects. In International Conference on Machine Learning. PMLR, 3835\u20133845."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2664067"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/2463209.2488795"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ESLsyn.2014.6850383"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2011.2177457"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.3850\/9783981537079_0350"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/1391469.1391712"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2009.2028681"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/774789.774804"},{"issue":"5","key":"e_1_3_2_29_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3126566","article-title":"Cosmos: Coordination of high-level synthesis and memory optimization for hardware accelerators","volume":"16","author":"Piccolboni Luca","year":"2017","unstructured":"Luca Piccolboni, Paolo Mantovani, Giuseppe Di Guglielmo, and Luca P. Carloni. 2017. Cosmos: Coordination of high-level synthesis and memory optimization for hardware accelerators. ACM Transactions on Embedded Computing Systems (TECS) 16, 5s (2017), 1\u201322.","journal-title":"ACM Transactions on Embedded Computing Systems (TECS)"},{"key":"e_1_3_2_30_2","first-page":"110","volume-title":"IEEE International Symposium on Workload Characterization","author":"Reagen B.","year":"2014","unstructured":"B. Reagen, R. Adolf, Y. S. Shao, G.-Y. Wei, and D. Brooks. 2014. MachSuite: Benchmarks for accelerator design and customized architectures. In IEEE International Symposium on Workload Characterization. 110\u2013119."},{"key":"e_1_3_2_31_2","article-title":"Development of multiobjective high-level synthesis for FPGAs","volume":"2020","author":"Bulnes Darian Reyes Fernandez de","year":"2020","unstructured":"Darian Reyes Fernandez de Bulnes, Yazmin Maldonado, and Leonardo Trujillo. 2020. Development of multiobjective high-level synthesis for FPGAs. Scientific Programming 2020 (2020).","journal-title":"Scientific Programming"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2015.2472007"},{"key":"e_1_3_2_33_2","first-page":"106","volume-title":"International Symposium on VLSI Design, Automation and Test","author":"Schafer Benjamin Carrion","year":"2009","unstructured":"Benjamin Carrion Schafer, Takashi Takenaka, and Kazutoshi Wakabayashi. 2009. Adaptive simulated annealer for high level synthesis design space exploration. In International Symposium on VLSI Design, Automation and Test. IEEE, 106\u2013109."},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/2209291.2209302"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2943570"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2014.6853196"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-8636-6_55"},{"key":"e_1_3_2_38_2","volume-title":"Neural Information Processing Systems","author":"Si X.","year":"2018","unstructured":"X. Si, H. Dai, M. Raghothaman, M. Naik, and L. Song. 2018. Learning loop invariants for program verification. In Neural Information Processing Systems."},{"key":"e_1_3_2_39_2","first-page":"488","volume-title":"IEEE Computer Society Annual Symposium on VLSI","author":"Silvano C.","year":"2010","unstructured":"C. Silvano, W. Fornaciari, G. Palermo, V. Zaccaria, F. Castro, M. Martinez, S. Bocchio, R. Zafalon, P. Avasare, G. Vanmeerbeeck, C. Ykman-Couvreur, M. Wouters, C. Kavka, L. Onesti, A. Turco, U. Bondik, G. Mariani, H. Posadas, E. Villar, C. Wu, F. Dongrui, Z. Hao, and T. Shibin. 2010. MULTICUBE: Multi-objective design space exploration of multi-core architectures. In IEEE Computer Society Annual Symposium on VLSI. 488\u2013493."},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2015.7372553"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415657"},{"key":"e_1_3_2_42_2","first-page":"6000","volume-title":"Neural Information Processing Systems","author":"Vaswani A.","year":"2017","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N Gomez, \u0141. Kaiser, and I. Polosukhin. 2017. Attention is all you need. In Neural Information Processing Systems. 6000\u20136010."},{"key":"e_1_3_2_43_2","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107 P.","year":"2018","unstructured":"P. Veli\u010dkovi\u0107, G. Cucurull, A. Casanova, A. Romero, P. Li\u00f2, and Y. Bengio. 2018. Graph attention networks. In International Conference on Learning Representations.","journal-title":"In International Conference on Learning Representations"},{"key":"e_1_3_2_44_2","unstructured":"VivadoHLS. 2018. Vivado High-Level Synthesis. Retrieved December 1 2022 from https:\/\/www.xilinx.com\/products\/design-tools\/vivado\/integration\/esl-design.html."},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062251"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE48585.2020.9116309"},{"key":"e_1_3_2_47_2","first-page":"39","volume-title":"IRONMAN: GNN-Assisted Design Space ExploRAtiOn in High-Level SyNThesis via ReinforceMEnt LeARNIng","author":"Wu N.","year":"2021","unstructured":"N. Wu, Y. Xie, and C. Hao. 2021. IRONMAN: GNN-Assisted Design Space ExploRAtiOn in High-Level SyNThesis via ReinforceMEnt LeARNIng. 39\u201344."},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2014.2363392"},{"key":"e_1_3_2_49_2","article-title":"Design space for graph neural networks","volume":"33","author":"You J.","year":"2020","unstructured":"J. You, Z. Ying, and J. Leskovec. 2020. Design space for graph neural networks. Neural Information Processing Systems 33 (2020).","journal-title":"Neural Information Processing Systems"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCS.2018.00030"},{"key":"e_1_3_2_51_2","volume-title":"Neural Information Processing Systems","author":"Zaheer M.","year":"2017","unstructured":"M. Zaheer, S. Kottur, S. Ravanbakhsh, B. Poczos, R. R. Salakhutdinov, and A. J. Smola. 2017. Deep sets. In Neural Information Processing Systems, Vol. 30."},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2017.8203809"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2017.8203809"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2898040"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2017.7927161"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2014.6974719"},{"key":"e_1_3_2_57_2","volume-title":"Neural Information Processing Systems","author":"Zhou Y.","year":"2020","unstructured":"Y. Zhou, S. Roy, A. Abdolrashidi, D. Wong, P. Ma, Q. Xu, H. Liu, P. Phothilimtha, S. Wang, A. Goldie, A. Mirhoseini, and J. Laudon. 2020. Transferable graph optimizers for ML compilers. In Neural Information Processing Systems."},{"key":"e_1_3_2_58_2","first-page":"119","volume-title":"ACM SIGPLAN Notices","author":"Zuluaga Marcela","year":"2012","unstructured":"Marcela Zuluaga, Andreas Krause, Peter Milder, and Markus P\u00fcschel. 2012. Smart design space sampling to predict Pareto-optimal solutions. In ACM SIGPLAN Notices. 119\u2013128."}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3570925","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3570925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:12Z","timestamp":1750182552000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3570925"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,24]]},"references-count":57,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,3,31]]}},"alternative-id":["10.1145\/3570925"],"URL":"https:\/\/doi.org\/10.1145\/3570925","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"value":"1084-4309","type":"print"},{"value":"1557-7309","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,24]]},"assertion":[{"value":"2022-02-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-10-31","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}