{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:10:16Z","timestamp":1750219816771,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":45,"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\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-AC05-00OR22725"],"award-info":[{"award-number":["DE-AC05-00OR22725"]}],"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\/3605731.3605744","type":"proceedings-article","created":{"date-parts":[[2023,9,7]],"date-time":"2023-09-07T23:50:00Z","timestamp":1694130600000},"page":"30-39","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Experience Deploying Graph Applications on GPUs with SYCL"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7197-780X","authenticated-orcid":false,"given":"Zheming","family":"Jin","sequence":"first","affiliation":[{"name":"Oak Ridge National Laboratory, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2449-6720","authenticated-orcid":false,"given":"Jeffrey S.","family":"Vetter","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, USA"}]}],"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\/MM.2008.57"},{"key":"e_1_3_2_1_2_1","unstructured":"Munshi A. Gaster B. Mattson T.G. and Ginsburg D. 2011. OpenCL programming guide. Pearson Education."},{"key":"e_1_3_2_1_3_1","unstructured":"Kaeli D. Mistry P. Schaa D. and Zhang D.P. 2015. Heterogeneous computing with OpenCL 2.0. Morgan Kaufmann."},{"volume-title":"2015 44th International Conference on Parallel Processing (pp. 959-968)","author":"Li P.","key":"e_1_3_2_1_4_1","unstructured":"Li, P., Brunet, E., Trahay, F., Parrot, C., Thomas, G. and Namyst, R., 2015, September. Automatic OpenCL code generation for multi-device heterogeneous architectures. In 2015 44th International Conference on Parallel Processing (pp. 959-968). IEEE."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-014-1213-y"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Reinders J. Ashbaugh B. Brodman J. Kinsner M. Pennycook J. and Tian X. 2021. Data Parallel C++: Mastering DPC++ for Programming of Heterogeneous Systems using C++ and SYCL. Springer Nature.","DOI":"10.1007\/978-1-4842-5574-2"},{"key":"e_1_3_2_1_7_1","unstructured":"Stroustrup B. 2013. The C++ Programming Language. Pearson Education."},{"key":"e_1_3_2_1_8_1","unstructured":"SYCL Extensions in DPC++. [online] https:\/\/github.com\/intel\/llvm\/blob\/sycl\/sycl\/doc\/extensions\/"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.6028\/jres.084.024"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/872726.806984"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2402.322385"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1137\/0720013"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1978.10481589"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Wu M. Li X. Kwoh C.K. and Ng S.K. 2009. A core-attachment based method to detect protein complexes in PPI networks. BMC bioinformatics 10(1) pp.1-16.","DOI":"10.1186\/1471-2105-10-169"},{"volume-title":"2010 10th International Conference on Intelligent Systems Design and Applications (pp. 320-324)","author":"Hossam M.M.","key":"e_1_3_2_1_15_1","unstructured":"Hossam, M.M., Hassanien, A.E. and Shoman, M., 2010, November. 3D brain tumor segmentation scheme using K-mean clustering and connected component labeling algorithms. In 2010 10th International Conference on Intelligent Systems Design and Applications (pp. 320-324). IEEE."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.04.018"},{"key":"e_1_3_2_1_17_1","first-page":"1","volume-title":"\u201cComputers and Intractability","author":"Garey R.","year":"2002","unstructured":"Garey, Michael R., and David S. Johnson. \u201cComputers and Intractability\u201d, vol. 29. W. H. Freeman and Company, New York (2002), pp 1-99."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1137\/0914041"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2012.07.001"},{"volume-title":"GPU Technology Conference (pp. 1-10)","author":"Cohen J.","key":"e_1_3_2_1_20_1","unstructured":"Cohen, J. and Castonguay, P., 2012, May. Efficient graph matching and coloring on the gpu. In GPU Technology Conference (pp. 1-10)."},{"volume-title":"Proceedings of the 26th ACM symposium on Parallelism in algorithms and architectures (pp. 166-177)","author":"Hasenplaugh W.","key":"e_1_3_2_1_21_1","unstructured":"Hasenplaugh, W., Kaler, T., Schardl, T.B. and Leiserson, C.E., 2014, June. Ordering heuristics for parallel graph coloring. In Proceedings of the 26th ACM symposium on Parallelism in algorithms and architectures (pp. 166-177)."},{"volume-title":"Proceedings of the 18th International Conference on Distributed Computing and Networking (pp. 1-7).","author":"Singhal N.","key":"e_1_3_2_1_22_1","unstructured":"Singhal, N., Peri, S. and Kalyanasundaram, S., 2017, January. Practical multi-threaded graph coloring algorithms for shared memory architecture. In Proceedings of the 18th International Conference on Distributed Computing and Networking (pp. 1-7)."},{"volume-title":"Proceedings 10th international conference on image analysis and processing (pp. 322-327)","author":"Di Stefano L.","key":"e_1_3_2_1_23_1","unstructured":"Di Stefano, L. and Bulgarelli, A., 1999, September. A simple and efficient connected components labeling algorithm. In Proceedings 10th international conference on image analysis and processing (pp. 322-327). IEEE."},{"volume-title":"November. Compressed In-memory Graphs for Accelerating GPU-based Analytics. In 2022 IEEE\/ACM Workshop on Irregular Applications: Architectures and Algorithms (IA3) (pp. 32-40)","author":"Azami N.","key":"e_1_3_2_1_24_1","unstructured":"Azami, N. and Burtscher, M., 2022, November. Compressed In-memory Graphs for Accelerating GPU-based Analytics. In 2022 IEEE\/ACM Workshop on Irregular Applications: Architectures and Algorithms (IA3) (pp. 32-40). IEEE."},{"volume-title":"Proceedings of the 27th International Symposium on High-Performance Parallel and Distributed Computing (pp. 92-104)","author":"Jaiganesh J.","key":"e_1_3_2_1_25_1","unstructured":"Jaiganesh, J. and Burtscher, M., 2018, June. A high-performance connected components implementation for GPUs. In Proceedings of the 27th International Symposium on High-Performance Parallel and Distributed Computing (pp. 92-104)."},{"volume-title":"Proceedings of the 25th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (pp. 262-275)","author":"Alabandi G.","key":"e_1_3_2_1_26_1","unstructured":"Alabandi, G., Powers, E. and Burtscher, M., 2020, February. Increasing the parallelism of graph coloring via shortcutting. In Proceedings of the 25th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (pp. 262-275)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2038037.1941590"},{"key":"e_1_3_2_1_28_1","unstructured":"The Intel DPC++ compiler. https:\/\/github.com\/intel\/llvm"},{"volume-title":"International Symposium on Code Generation and Optimization, 2004. CGO 2004. (pp. 75-86)","author":"Lattner C.","key":"e_1_3_2_1_29_1","unstructured":"Lattner, C. and Adve, V., 2004, March. LLVM: A compilation framework for lifelong program analysis & transformation. In International Symposium on Code Generation and Optimization, 2004. CGO 2004. (pp. 75-86). IEEE."},{"volume-title":"Proceedings of the International Workshop on OpenCL (pp. 1-1).","author":"Reyes R.","key":"e_1_3_2_1_30_1","unstructured":"Reyes, R., Brown, G. and Burns, R., 2020, April. Bringing performant support for NVIDIA hardware to SYCL. In Proceedings of the International Workshop on OpenCL (pp. 1-1)."},{"key":"e_1_3_2_1_31_1","unstructured":"https:\/\/github.com\/intel\/llvm\/blob\/sycl\/sycl\/doc\/PluginInterface.md"},{"key":"e_1_3_2_1_32_1","unstructured":"Radeon Open Compute (ROCm) Platform. https:\/\/rocmdocs.amd.com"},{"key":"e_1_3_2_1_33_1","unstructured":"https:\/\/github.com\/intel\/llvm-test-suite\/pull\/1687"},{"key":"e_1_3_2_1_34_1","unstructured":"https:\/\/userweb.cs.txstate.edu\/\u223cburtscher\/research\/ECLgraph\/index.html"},{"volume-title":"Proceedings of the International Workshop on OpenCL (pp. 1-7).","author":"Homerding B.","key":"e_1_3_2_1_35_1","unstructured":"Homerding, B. and Tramm, J., 2020, April. Evaluating the Performance of the hipSYCL Toolchain for HPC Kernels on NVIDIA V100 GPUs. In Proceedings of the International Workshop on OpenCL (pp. 1-7)."},{"volume-title":"2021 International Workshop on Performance, Portability and Productivity in HPC (P3HPC) (pp. 68-78)","author":"Haseeb M.","key":"e_1_3_2_1_36_1","unstructured":"Haseeb, M., Ding, N., Deslippe, J. and Awan, M., 2021, November. Evaluating Performance and Portability of a core bioinformatics kernel on multiple vendor GPUs. In 2021 International Workshop on Performance, Portability and Productivity in HPC (P3HPC) (pp. 68-78). IEEE."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3388333.3388643"},{"volume-title":"2019 IEEE\/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC) (pp. 14-25)","author":"Jo\u00f3 B.","key":"e_1_3_2_1_38_1","unstructured":"Jo\u00f3, B., Kurth, T., Clark, M.A., Kim, J., Trott, C.R., Ibanez, D., Sunderland, D. and Deslippe, J., 2019, November. Performance portability of a wilson dslash stencil operator mini-app using kokkos and SYCL. In 2019 IEEE\/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC) (pp. 14-25). IEEE."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Tsai Y.M. Cojean T. and Anzt H. 2021. Porting a sparse linear algebra math library to Intel GPUs. arXiv preprint arXiv:2103.10116.","DOI":"10.1007\/978-3-031-06156-1_5"},{"key":"e_1_3_2_1_40_1","unstructured":"Migdal M. 2021. From CUDA to SYCL. SYCL summer sessions. https:\/\/sycl.tech\/assets\/files\/Michel_Migdal_Codeplay_Porting_Tips_CDUA_To_SYCL.pdf"},{"key":"e_1_3_2_1_41_1","unstructured":"Jin Z. 2022. Experience of Migrating Parallel Graph Coloring from CUDA to SYCL (No. ORNL\/TM-2022\/2433). Oak Ridge National Lab.(ORNL) Oak Ridge TN (United States)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3585341.3585349"},{"volume-title":"June. Evaluating CUDA Portability with HIPCL and DPCT. In 2021 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) (pp. 371-376)","author":"Jin Z.","key":"e_1_3_2_1_43_1","unstructured":"Jin, Z. and Vetter, J., 2021, June. Evaluating CUDA Portability with HIPCL and DPCT. In 2021 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) (pp. 371-376). IEEE."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2022.03.017"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Tsai Y.H.M. Cojean T. and Anzt H. 2022. Providing performance portable numerics for Intel GPUs. Concurrency and Computation: Practice and Experience p.e7400","DOI":"10.1002\/cpe.7400"}],"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\/3605731.3605744","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3605731.3605744","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3605731.3605744","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\/3605731.3605744"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,7]]},"references-count":45,"alternative-id":["10.1145\/3605731.3605744","10.1145\/3605731"],"URL":"https:\/\/doi.org\/10.1145\/3605731.3605744","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"}}]}}