{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T16:17:44Z","timestamp":1786724264513,"version":"build-2736575974"},"reference-count":34,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"name":"Jiangsu Provincial Science and Technology Major Special","award":["BG2024032"],"award-info":[{"award-number":["BG2024032"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62204111"],"award-info":[{"award-number":["62204111"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Des. Autom. Electron. Syst."],"published-print":{"date-parts":[[2025,7,31]]},"abstract":"<jats:p>Over the past decades, Field-Programmable Gate Arrays (FPGAs) have become a choice for heterogeneous computing due to their flexibility, energy efficiency, and processing speed. OpenCL is used in FPGA heterogeneous computing for its high-level abstraction and cross-platform compatibility. Previous works have introduced optimization techniques in OpenCL for FPGAs to leverage FPGA-specific advantages. However, the multi-kernel pipeline technique, which can raise throughput and resource utilization, has not performed well. This article presents a CPU+FPGA heterogeneous platform with a novel execution model to optimize multi-kernel pipeline. Firstly, we extend OpenCL by introducing new APIs and additional functions to represent the execution model. Secondly, a hardware-software co-scheduling scheme is employed to manage execution. Thirdly, we design a holistic development flow and toolkit to facilitate the deployment of algorithms on the platform or the integration of RTL IP cores to the OpenCL environment. We validate the platform using a Range Doppler algorithm. The proposed development flow and integrated toolchain enhance the efficiency of integrating traditional RTL IP cores into the OpenCL environment. Experimental results demonstrate that, with a comparable processing speed (averaging 95%) to traditional RTL implementations, the platform successfully establishes the multi-kernel pipelines. Leveraging the multi-kernel pipeline, the platform achieves a significant improvement in multi-frame processing speed compared to traditional OpenCL.<\/jats:p>","DOI":"10.1145\/3744922","type":"journal-article","created":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T06:17:38Z","timestamp":1750313858000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A CPU+FPGA OpenCL Heterogeneous Computing Platform for Multi-Kernel Pipeline"],"prefix":"10.1145","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2523-6778","authenticated-orcid":false,"given":"Yuefei","family":"Wang","sequence":"first","affiliation":[{"name":"School of Electronic and Science and Engineering, Nanjing University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7345-7974","authenticated-orcid":false,"given":"Wendong","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Sun Yat-Sen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9943-0550","authenticated-orcid":false,"given":"Lang","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Sun Yat-Sen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0266-3583","authenticated-orcid":false,"given":"Jin","family":"Sha","sequence":"additional","affiliation":[{"name":"School of Electronic and Science and Engineering, Nanjing University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7227-4786","authenticated-orcid":false,"given":"Zhongfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic and Science and Engineering, Nanjing University","place":["Nanjing, China"]},{"name":"School of Integrated Circuits, Sun Yat-Sen University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,18]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICFPT52863.2021.9609930"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.3390\/e24101346"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/MAES.2018.170120"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2016.02.008"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.23919\/IRS.2018.8448262"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIIBMS46890.2019.8991468"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2014.6865605"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10172133"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/PHOSST.2019.8795003"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","unstructured":"Adel Ejjeh Vikram Adve and Rob A. Rutenbar. 2020. Studying the potential of automatic optimizations in the intel FPGA SDK for OpenCL. In Proceedings of the 2020 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA\u201920). Association for Computing Machinery Seaside CA USA 318. DOI:10.1145\/3373087.3375355","DOI":"10.1145\/3373087.3375355"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.13"},{"key":"e_1_3_1_13_2","doi-asserted-by":"crossref","DOI":"10.1002\/0470092939","volume-title":"RapidIO: The Embedded System Interconnect","author":"Fuller Sam","year":"2004","unstructured":"Sam Fuller. 2004. RapidIO: The Embedded System Interconnect. John Wiley & Sons."},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CISS60136.2023.10379935"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2017.7975269"},{"key":"e_1_3_1_16_2","unstructured":"Intel Corporation. oneAPI. (n.d.). Retrieved May 6 2025 from https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi.html"},{"key":"e_1_3_1_17_2","unstructured":"Intel Corporation. OpenCL SDK. (n.d.). Retrieved May 6 2025 from https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/opencl-sdk\/overview.html"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373087.3375313"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.1984.6499176"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/RTCSA.2018.00038"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3392717.3392757"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2009.7478342"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2011.19"},{"key":"e_1_3_1_25_2","first-page":"43","article-title":"An efficient implementation of range-doppler algorithm on GPGPU","volume":"45","author":"Ramakrishna R.V.","year":"2013","unstructured":"R.V. Ramakrishna, T. Tirupathi, R. Anuradha, Mahendra Pal, Pramod Konugurthi, and Gnanaprakash Varadan. 2013. An efficient implementation of range-doppler algorithm on GPGPU. Simulation Series 45, 01 (2013), 43\u201349.","journal-title":"Simulation Series"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC-CSS-ICESS.2015.210"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS54063.2022.9859281"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/FPT.2017.8280160"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1984.1676375"},{"key":"e_1_3_1_30_2","unstructured":"Wind River Systems. 1999. VxWorks: Programmer\u2019s Guide 5.4. Windriver. Retrieved from https:\/\/books.google.com.sg\/books?id=fryxMwAACAAJ"},{"key":"e_1_3_1_31_2","unstructured":"Xilinx Corporation. Vitis. (n.d.). Retrieved May 6 2025 from https:\/\/www.xilinx.com\/products\/design-tools\/vitis.html"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICFPT47387.2019.00036"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs16010191"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/IMCCC.2011.65"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123978"}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3744922","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T08:28:19Z","timestamp":1752827299000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3744922"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,18]]},"references-count":34,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,7,31]]}},"alternative-id":["10.1145\/3744922"],"URL":"https:\/\/doi.org\/10.1145\/3744922","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"value":"1084-4309","type":"print"},{"value":"1557-7309","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,18]]},"assertion":[{"value":"2025-02-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}