{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:10:17Z","timestamp":1750219817058,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T00:00:00Z","timestamp":1691366400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["SHF-1763654"],"award-info":[{"award-number":["SHF-1763654"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"DOE U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-AC02-06CH11357"],"award-info":[{"award-number":["DE-AC02-06CH11357"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,7]]},"DOI":"10.1145\/3605731.3605885","type":"proceedings-article","created":{"date-parts":[[2023,9,7]],"date-time":"2023-09-07T23:50:00Z","timestamp":1694130600000},"page":"127-135","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Codelet Pipe: Realization of Dataflow Software Pipelining for Extended Codelet Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4832-0834","authenticated-orcid":false,"given":"Siddhisanket","family":"Raskar","sequence":"first","affiliation":[{"name":"Argonne National Laboratory, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7522-9449","authenticated-orcid":false,"given":"Thomas","family":"Applencourt","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6447-3195","authenticated-orcid":false,"given":"Kalyan","family":"Kumaran","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5265-7528","authenticated-orcid":false,"given":"Guang R","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Delaware, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,9,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/12.48862"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.1974.1050511"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1743546.1743560"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-017-1702-6"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","unstructured":"J.\u00a0B. Dennis G.\u00a0R. Gao and V. Sarkar. 2012. Determinacy and Repeatability of Parallel Program Schemata. In 2012 Data-Flow Execution Models for Extreme Scale Computing. 1\u20139. https:\/\/doi.org\/10.1109\/DFM.2012.10","DOI":"10.1109\/DFM.2012.10"},{"key":"e_1_3_2_1_6_1","unstructured":"Argonne Leadership\u00a0Computing Facility. 2023. ALCF AI Testbed. https:\/\/www.alcf.anl.gov\/alcf-ai-testbed."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/0743-7315(89)90041-5"},{"volume-title":"A Code Mapping Scheme for Dataflow Software Pipelining","author":"Gao R.","key":"e_1_3_2_1_9_1","unstructured":"Guang\u00a0R. Gao. 1990. A Code Mapping Scheme for Dataflow Software Pipelining. Kluwer Academic Publishers, Norwell, MA, USA."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","unstructured":"G.\u00a0R. Gao and R. Tio. 1989. Instruction set architecture of an efficient pipelined dataflow architecture. In [1989] Proceedings of the Twenty-Second Annual Hawaii International Conference on System Sciences. Volume 1: Architecture Track Vol.\u00a01. 385\u2013392 vol.1. https:\/\/doi.org\/10.1109\/HICSS.1989.47180","DOI":"10.1109\/HICSS.1989.47180"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342009347445"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","unstructured":"R. Govindarajan Guang\u00a0R. Gao and Palash Desai. 2002. Minimizing Buffer Requirements under Rate-Optimal Schedule in Regular Dataflow Networks. In Journal of VLSI signal processing systems for signal image and video technology Vol.\u00a031. 207\u2013229. https:\/\/doi.org\/10.1023\/A:1015452903532","DOI":"10.1023\/A:1015452903532"},{"key":"e_1_3_2_1_13_1","unstructured":"Khronos Group. 2015. OpenCL Specification version 2.0 (API). https:\/\/www.khronos.org\/registry\/cl\/specs\/opencl-2.0.pdf."},{"key":"e_1_3_2_1_14_1","unstructured":"Khronos Group. 2019. OpenCL C++ Language Specification. https:\/\/www.khronos.org\/registry\/OpenCL\/specs\/2.2\/pdf\/OpenCL_Cxx.pdf."},{"key":"e_1_3_2_1_15_1","unstructured":"Khronos Group. 2019. The SYCL 1.2.1 Specification. https:\/\/www.khronos.org\/registry\/SYCL\/specs\/sycl-1.2.1.pdf."},{"key":"e_1_3_2_1_16_1","unstructured":"Khronos Group. 2021. Khronos Group. https:\/\/www.khronos.org\/."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.1996.552551"},{"key":"e_1_3_2_1_18_1","unstructured":"Intel Inc. 2020. The Compute Architecture of The compute architecture of Intel Processor Graphics Gen 9. https:\/\/software.intel.com\/sites\/default\/files\/managed\/c5\/9a\/The-Compute-Architecture-of-Intel-Processor-Graphics-Gen9-v1d0.pdf."},{"key":"e_1_3_2_1_19_1","unstructured":"Intel Inc. 2020. Intel Unveils New GPU Architecture with High-Performance Computing and AI Acceleration and oneAPI Software Stack with Unified and Scalable Abstraction for Heterogeneous Architectures. https:\/\/newsroom.intel.com\/news-releases\/intel-unveils-new-gpu-architecture-optimized-for-hpc-ai-oneapi\/#gs.1y2s04."},{"key":"e_1_3_2_1_20_1","unstructured":"Intel Inc. 2021. Data Parallel C++ Language. https:\/\/software.intel.com\/content\/www\/us\/en\/develop\/tools\/oneapi\/data-parallel-c-plus-plus.html#gs.1dvgr2."},{"key":"e_1_3_2_1_21_1","unstructured":"Intel Inc. 2021. Intel OpenCL Built in Intrinsics. https:\/\/github.com\/intel\/pti-gpu\/blob\/ea615893938f9efd1e736cf8dbaf0bb1f25930ed\/chapters\/binary_instrumentation\/OpenCLBuiltIn.md."},{"key":"e_1_3_2_1_22_1","unstructured":"Argonne\u00a0National Lab. 2021. Aurora Supercomputer. https:\/\/www.alcf.anl.gov\/aurora."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","unstructured":"A. Munshi. 2009. The OpenCL specification. 314\u00a0pages. https:\/\/doi.org\/10.1109\/HOTCHIPS.2009.7478342","DOI":"10.1109\/HOTCHIPS.2009.7478342"},{"volume-title":"November","year":"2022","key":"e_1_3_2_1_24_1","unstructured":"Top500 Org. 2020. Top 500 Supercomputer List, November 2022. https:\/\/www.top500.org\/lists\/top500\/2022\/11\/."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","unstructured":"Nicolas Poggi Sherif Sakr and Albert\u00a0Y. Zomaya. 2019. Microbenchmark. Springer International Publishing Cham 1143\u20131152. https:\/\/doi.org\/10.1007\/978-3-319-77525-8_111","DOI":"10.1007\/978-3-319-77525-8_111"},{"key":"e_1_3_2_1_26_1","unstructured":"Siddhisanket Raskar. 2023. clCodeletPipe Library. https:\/\/github.com\/sraskar\/clCodeletPipe."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC.2019.10280"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC.2019.10280"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3578244.3583734"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/6.591665"},{"key":"e_1_3_2_1_31_1","volume-title":"EARTH: An Efficient Architecture for Running Threads. Ph.\u00a0D. Dissertation. McGill, Montreal.","author":"Theobald Kevin\u00a0Bryan","year":"1999","unstructured":"Kevin\u00a0Bryan Theobald. 1999. EARTH: An Efficient Architecture for Running Threads. Ph.\u00a0D. Dissertation. McGill, Montreal."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2000417.2000424"}],"event":{"name":"ICPP-W 2023: 52nd International Conference on Parallel Processing Workshops","acronym":"ICPP-W 2023","location":"Salt Lake City UT USA"},"container-title":["Proceedings of the 52nd International Conference on Parallel Processing Workshops"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605731.3605885","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3605731.3605885","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3605731.3605885","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:10Z","timestamp":1750178770000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605731.3605885"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,7]]},"references-count":31,"alternative-id":["10.1145\/3605731.3605885","10.1145\/3605731"],"URL":"https:\/\/doi.org\/10.1145\/3605731.3605885","relation":{},"subject":[],"published":{"date-parts":[[2023,8,7]]},"assertion":[{"value":"2023-09-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}