{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T19:42:35Z","timestamp":1765827755889,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,2,16]],"date-time":"2019-02-16T00:00:00Z","timestamp":1550275200000},"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":[[2019,2,16]]},"DOI":"10.1145\/3302516.3307350","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T19:37:34Z","timestamp":1550173054000},"page":"2-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["PPOpenCL: a performance-portable OpenCL compiler with host and kernel thread code fusion"],"prefix":"10.1145","author":[{"given":"Ying","family":"Liu","sequence":"first","affiliation":[{"name":"Institute of Computing Technology at Chinese Academy of Sciences, China"}]},{"given":"Lei","family":"Huang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology at Chinese Academy of Sciences, China"}]},{"given":"Mingchuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology at Chinese Academy of Sciences, China \/ University of Chinese Academy of Sciences, China"}]},{"given":"Huimin","family":"Cui","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology at Chinese Academy of Sciences, China \/ University of Chinese Academy of Sciences, China"}]},{"given":"Fang","family":"Lv","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology at Chinese Academy of Sciences, China"}]},{"given":"Xiaobing","family":"Feng","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology at Chinese Academy of Sciences, China \/ University of Chinese Academy of Sciences, China"}]},{"given":"Jingling","family":"Xue","sequence":"additional","affiliation":[{"name":"UNSW, Australia"}]}],"member":"320","published-online":{"date-parts":[[2019,2,16]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.30"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195653"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.33"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2355585.2355587"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2400682.2400694"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735702"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/781131.781159"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2011.10.002"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2909437.2909447"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-015-1483-z"},{"key":"e_1_3_2_1_11_1","unstructured":"Haohuan Fu Junfeng Liao Jinzhe Yang Lanning Wang etal 2016. The Sunway TaihuLight supercomputer: system and applications. SCIENCE CHINA Information Sciences 59 7 (2016) 072001:1\u2013072001:16.  Haohuan Fu Junfeng Liao Jinzhe Yang Lanning Wang et al. 2016. The Sunway TaihuLight supercomputer: system and applications. SCIENCE CHINA Information Sciences 59 7 (2016) 072001:1\u2013072001:16."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/3049832.3049838"},{"key":"e_1_3_2_1_13_1","unstructured":"Khronos Group. 2018. OpenCL Overview. https:\/\/www.khronos.org\/opencl\/  Khronos Group. 2018. OpenCL Overview. https:\/\/www.khronos.org\/opencl\/"},{"key":"e_1_3_2_1_14_1","unstructured":"OpenACC User Group. 2017. NAS SHOC OpenACC 2.5. https: \/\/github.com\/OpenACCUserGroup\/openacc-users-group\/tree\/master\/ Contributed_Sample_Codes\/NAS_SHOC_OpenACC_2.5  OpenACC User Group. 2017. NAS SHOC OpenACC 2.5. https: \/\/github.com\/OpenACCUserGroup\/openacc-users-group\/tree\/master\/ Contributed_Sample_Codes\/NAS_SHOC_OpenACC_2.5"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751236"},{"key":"e_1_3_2_1_16_1","unstructured":"ACM 143\u2013153.  ACM 143\u2013153."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-014-0320-y"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178496"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3204919.3204920"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of 5th International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS\u201914)","author":"Juckeland Guido","year":"2014","unstructured":"Guido Juckeland , William C. Brantley , Sunita Chandrasekaran , 2014 . SPEC ACCEL: A Standard Application Suite for Measuring Hardware Accelerator Performance . In Proceedings of 5th International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS\u201914) . Springer, New Orleans, LA, USA, 46\u201367. Guido Juckeland, William C. Brantley, Sunita Chandrasekaran, et al. 2014. SPEC ACCEL: A Standard Application Suite for Measuring Hardware Accelerator Performance. In Proceedings of 5th International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS\u201914). Springer, New Orleans, LA, USA, 46\u201367."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/2738600.2738632"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/349299.349320"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1854273.1854301"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628087"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503268"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2892208.2892210"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/233561.233564"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of Cray Users Group Meeting (CUG \u201914)","author":"Miles Douglas","year":"2014","unstructured":"Douglas Miles , David Norton , and Michael Wolfe . 2014 . Performance Portability and OpenACC . In Proceedings of Cray Users Group Meeting (CUG \u201914) . Lugano, Switzerland, 1\u20138. Douglas Miles, David Norton, and Michael Wolfe. 2014. Performance Portability and OpenACC. In Proceedings of Cray Users Group Meeting (CUG \u201914). Lugano, Switzerland, 1\u20138."},{"key":"e_1_3_2_1_29_1","unstructured":"NVIDIA. 2018. CUDA C Programming Guide. https:\/\/docs.nvidia.com\/cuda\/ cuda-c-programming-guide\/index.html  NVIDIA. 2018. CUDA C Programming Guide. https:\/\/docs.nvidia.com\/cuda\/ cuda-c-programming-guide\/index.html"},{"key":"e_1_3_2_1_30_1","unstructured":"NVIDIA. 2018. NVIDIA OpenCL SDK Code Samples. https:\/\/developer.nvidia. com\/opencl  NVIDIA. 2018. NVIDIA OpenCL SDK Code Samples. https:\/\/developer.nvidia. com\/opencl"},{"key":"e_1_3_2_1_31_1","unstructured":"NVIDIA. 2018. Performance Portability from GPUs to CPUs with OpenACC. https:\/\/devblogs.nvidia.com\/performance-portability-gpus-cpus-openacc\/  NVIDIA. 2018. Performance Portability from GPUs to CPUs with OpenACC. https:\/\/devblogs.nvidia.com\/performance-portability-gpus-cpus-openacc\/"},{"key":"e_1_3_2_1_32_1","unstructured":"OpenACC. 2018. OpenACC Specification. https:\/\/www.openacc.org\/ specification  OpenACC. 2018. OpenACC Specification. https:\/\/www.openacc.org\/ specification"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2012.07.005"},{"key":"e_1_3_2_1_34_1","unstructured":"PGI. 2018. PGI Accelerator Compilers with OpenACC Directives. https:\/\/www. pgroup.com\/resources\/accel.htm  PGI. 2018. PGI Accelerator Compilers with OpenACC Directives. https:\/\/www. pgroup.com\/resources\/accel.htm"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3078155.3078173"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967967"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178500"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2884045.2884046"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2145816.2145825"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2664666.2664674"},{"volume-title":"Proceedings of 27th International Workshop on Languages and Compilers for Parallel Computing (LCPC \u201914)","author":"Sabne Amit","key":"e_1_3_2_1_41_1","unstructured":"Amit Sabne , Putt Sakdhnagool , Seyong Lee , and Jeffrey S. Vetter . 2014. Evaluating Performance Portability of OpenACC . In Proceedings of 27th International Workshop on Languages and Compilers for Parallel Computing (LCPC \u201914) . Springer, Hillsboro, OR, USA, 51\u201366. Amit Sabne, Putt Sakdhnagool, Seyong Lee, and Jeffrey S. Vetter. 2014. Evaluating Performance Portability of OpenACC. In Proceedings of 27th International Workshop on Languages and Compilers for Parallel Computing (LCPC \u201914). Springer, Hillsboro, OR, USA, 51\u201366."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/2523721.2523772"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807629"},{"key":"e_1_3_2_1_44_1","volume-title":"Adve","author":"Srivastava Prakalp","year":"2016","unstructured":"Prakalp Srivastava , Maria Kotsifakou , and Vikram S . Adve . 2016 . HPVM : A Portable Virtual Instruction Set for Heterogeneous Parallel Systems. CoRR abs\/1611.00860 (2016). arXiv: 1611.00860 Prakalp Srivastava, Maria Kotsifakou, and Vikram S. Adve. 2016. HPVM: A Portable Virtual Instruction Set for Heterogeneous Parallel Systems. CoRR abs\/1611.00860 (2016). arXiv: 1611.00860"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2784731.2784754"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/2968455.2968521"},{"key":"e_1_3_2_1_47_1","volume-title":"Parboil: A Revised Benchmark Suite for Scientific and Commercial Throughput Computing. Technical Report","author":"Stratton John A.","year":"2012","unstructured":"John A. Stratton , Christopher Rodrigues , I- Jui Sung , Nady Obeid , Li-Wen Chang , Nasser Anssari , Geng D. Liu , and W.W. Hwu . 2012 . Parboil: A Revised Benchmark Suite for Scientific and Commercial Throughput Computing. Technical Report . University of Illinois at Urbana-Champaign. PPOpenCL CC \u201919 , February 16\u201317, 2019, Washington, DC, USA John A. Stratton, Christopher Rodrigues, I-Jui Sung, Nady Obeid, Li-Wen Chang, Nasser Anssari, Geng D. Liu, and W.W. Hwu. 2012. Parboil: A Revised Benchmark Suite for Scientific and Commercial Throughput Computing. Technical Report. University of Illinois at Urbana-Champaign. PPOpenCL CC \u201919, February 16\u201317, 2019, Washington, DC, USA"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2892208.2892235"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3078633.3081040"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.21"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021730"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2854038.2854041"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/11688839_13"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/2207222.2207225"},{"volume-title":"Proceedings of the 28th International Supercomputing Conference (ISC \u201913)","author":"Zhang Yao","key":"e_1_3_2_1_55_1","unstructured":"Yao Zhang , Mark Sinclair II, and Andrew A. Chien . 2013. Improving Performance Portability in OpenCL Programs . In Proceedings of the 28th International Supercomputing Conference (ISC \u201913) . Springer, Leipzig, Germany, 136\u2013150. Yao Zhang, Mark Sinclair II, and Andrew A. Chien. 2013. Improving Performance Portability in OpenCL Programs. In Proceedings of the 28th International Supercomputing Conference (ISC \u201913). Springer, Leipzig, Germany, 136\u2013150."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/1854273.1854298"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/2886101"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/2854038.2854054"},{"volume-title":"Supercompilers for Parallel and Vector Computers","author":"Zima Hans","key":"e_1_3_2_1_59_1","unstructured":"Hans Zima and Barbara Chapman . 1991. Supercompilers for Parallel and Vector Computers . ACM , New York, NY, USA . Hans Zima and Barbara Chapman. 1991. Supercompilers for Parallel and Vector Computers. ACM, New York, NY, USA."}],"event":{"name":"CC '19: 28th International Conference on Compiler Construction","acronym":"CC '19","location":"Washington DC USA"},"container-title":["Proceedings of the 28th International Conference on Compiler Construction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3302516.3307350","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3302516.3307350","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:53:55Z","timestamp":1750204435000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3302516.3307350"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,16]]},"references-count":59,"alternative-id":["10.1145\/3302516.3307350","10.1145\/3302516"],"URL":"https:\/\/doi.org\/10.1145\/3302516.3307350","relation":{},"subject":[],"published":{"date-parts":[[2019,2,16]]},"assertion":[{"value":"2019-02-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}