{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T10:15:17Z","timestamp":1784888117489,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,23]],"date-time":"2024-06-23T00:00:00Z","timestamp":1719100800000},"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":[],"published-print":{"date-parts":[[2024,6,23]]},"DOI":"10.1145\/3649329.3655898","type":"proceedings-article","created":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T19:27:22Z","timestamp":1731007642000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["G2PM: Performance Modeling for ACAP Architecture with Dual-Tiered Graph Representation Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0684-7299","authenticated-orcid":false,"given":"Tuo","family":"Dai","sequence":"first","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8665-1132","authenticated-orcid":false,"given":"Bizhao","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4932-3655","authenticated-orcid":false,"given":"Guojie","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"IEEE Hot Chips 31 Symposium (HCS).","author":"Sagheer","unstructured":"Sagheer Ahmad et al. 2019. Xilinx First 7nm Device: Versal AI Core (VC1902). In IEEE Hot Chips 31 Symposium (HCS)."},{"key":"e_1_3_2_1_2_1","unstructured":"AMD\/Xilinx. 2020. AI Engine Development. https:\/\/docs.xilinx.com\/p\/ai-engine-development"},{"key":"e_1_3_2_1_3_1","unstructured":"AMD\/Xilinx. 2022. MLIR-based AIEngine toolchain. https:\/\/github.com\/Xilinx\/mlir-aie"},{"key":"e_1_3_2_1_4_1","unstructured":"AMD\/Xilinx. 2022. Vitis AI Library User Guide."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Jason Ansel et al. 2014. OpenTuner: An extensible framework for program autotuning. In PACT.","DOI":"10.1145\/2628071.2628092"},{"key":"e_1_3_2_1_6_1","volume-title":"Vyasa: A High-Performance Vectorizing Compiler for Tensor Convolutions on the Xilinx AI Engine. In HPEC.","author":"Prasanth Chatarasi","year":"2020","unstructured":"Prasanth Chatarasi et al. 2020. Vyasa: A High-Performance Vectorizing Compiler for Tensor Convolutions on the Xilinx AI Engine. In HPEC."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Zhangyin Feng et al. 2020. CodeBERT: A Pre-Trained Model for Programming and Natural Languages. In EMNLP.","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Joseph A. Fisher. 1983. Very Long Instruction Word Architectures and the ELI-512. In ISCA.","DOI":"10.1145\/800046.801649"},{"key":"e_1_3_2_1_9_1","unstructured":"Daya Guo et al. 2021. GraphCodeBERT: Pre-training Code Representations with Data Flow. In ICLR."},{"key":"e_1_3_2_1_10_1","volume-title":"Hamilton et al","author":"William L.","year":"2017","unstructured":"William L. Hamilton et al. 2017. Representation Learning on Graphs: Methods and Applications. IEEE Data Eng. Bull."},{"key":"e_1_3_2_1_11_1","unstructured":"Jonathan Ho et al. 2020. Denoising Diffusion Probabilistic Models. In NeurIPS."},{"key":"e_1_3_2_1_12_1","volume-title":"Kingma et al","author":"Diederik P.","year":"2015","unstructured":"Diederik P. Kingma et al. 2015. Adam: A Method for Stochastic Optimization. In ICLR."},{"key":"e_1_3_2_1_13_1","unstructured":"Zhijing Li et al. 2022. Compiler-Driven Simulation of Reconfigurable Hardware Accelerators. In HPCA."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Oumaima Matoussi. 2021. NoC Performance Model for Efficient Network Latency Estimation. In DATE.","DOI":"10.23919\/DATE51398.2021.9474101"},{"key":"e_1_3_2_1_15_1","unstructured":"Adam Paszke et al. 2019. PyTorch: An Imperative Style High-Performance Deep Learning Library. In NeurIPS."},{"key":"e_1_3_2_1_16_1","article-title":"A graph-based model for build optimization sequences","author":"Nilton Luiz Queiroz","year":"2023","unstructured":"Nilton Luiz Queiroz et al. 2023. A graph-based model for build optimization sequences. Journal of Computer Languages.","journal-title":"Journal of Computer Languages."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Atefeh Sohrabizadeh et al. 2022. Automated Accelerator Optimization Aided by Graph Neural Networks. In DAC.","DOI":"10.1145\/3489517.3530409"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3418463"},{"key":"e_1_3_2_1_19_1","volume-title":"CHARM: Composing Heterogeneous AcceleRators for Matrix Multiply on Versal ACAP Architecture. In FPGA.","author":"Jinming Zhuang","year":"2023","unstructured":"Jinming Zhuang et al. 2023. CHARM: Composing Heterogeneous AcceleRators for Matrix Multiply on Versal ACAP Architecture. In FPGA."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Jinming Zhuang et al. 2023. High Performance Low Power Matrix Multiply Design on ACAP: from Architecture Design Challenges and DSE Perspectives. In DAC.","DOI":"10.1109\/DAC56929.2023.10247981"}],"event":{"name":"DAC '24: 61st ACM\/IEEE Design Automation Conference","location":"San Francisco CA USA","acronym":"DAC '24","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE-CEDA","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 61st ACM\/IEEE Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3655898","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649329.3655898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:48Z","timestamp":1750295868000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3655898"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,23]]},"references-count":20,"alternative-id":["10.1145\/3649329.3655898","10.1145\/3649329"],"URL":"https:\/\/doi.org\/10.1145\/3649329.3655898","relation":{},"subject":[],"published":{"date-parts":[[2024,6,23]]},"assertion":[{"value":"2024-11-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}