{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:14:46Z","timestamp":1771956886923,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,6,26]],"date-time":"2019-06-26T00:00:00Z","timestamp":1561507200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702546"],"award-info":[{"award-number":["61702546"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003398","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003398","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,6,26]]},"DOI":"10.1145\/3330345.3331059","type":"proceedings-article","created":{"date-parts":[[2019,6,18]],"date-time":"2019-06-18T12:14:30Z","timestamp":1560860070000},"page":"319-329","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["WCCV"],"prefix":"10.1145","author":[{"given":"Huihui","family":"Sun","sequence":"first","affiliation":[{"name":"University of M\u00fcnster, M\u00fcnster, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Fey","sequence":"additional","affiliation":[{"name":"University of M\u00fcnster, M\u00fcnster, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhao","sequence":"additional","affiliation":[{"name":"State key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergei","family":"Gorlatch","sequence":"additional","affiliation":[{"name":"University of M\u00fcnster, M\u00fcnster, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,6,26]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/567067.567085"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/73560.73561"},{"key":"e_1_3_2_1_3_1","volume-title":"http:\/\/code.google.eom\/p\/aobench. accessed","year":"2019","unstructured":"AOBench. 2019. http:\/\/code.google.eom\/p\/aobench. accessed May 2019 . AOBench. 2019. http:\/\/code.google.eom\/p\/aobench. accessed May 2019."},{"key":"e_1_3_2_1_4_1","volume-title":"Joseph James Gebis, Parry Husbands, Kurt Keutzer, David A Patterson, William Lester Plishker, John Shalf, Samuel Webb Williams, et al.","author":"Asanovic Krste","year":"2006","unstructured":"Krste Asanovic , Ras Bodik , Bryan Christopher Catanzaro , Joseph James Gebis, Parry Husbands, Kurt Keutzer, David A Patterson, William Lester Plishker, John Shalf, Samuel Webb Williams, et al. 2006 . The landscape of parallel computing research: A view from Berkeley. Technical Report. Technical Report UCB\/EECS-2006-183, EECS Department, University of California , Berkeley. Krste Asanovic, Ras Bodik, Bryan Christopher Catanzaro, Joseph James Gebis, Parry Husbands, Kurt Keutzer, David A Patterson, William Lester Plishker, John Shalf, Samuel Webb Williams, et al. 2006. The landscape of parallel computing research: A view from Berkeley. Technical Report. Technical Report UCB\/EECS-2006-183, EECS Department, University of California, Berkeley."},{"key":"e_1_3_2_1_5_1","volume-title":"d.}. OpenMP Application Programming Interface. accessed","author":"Architecture Review Board MP","year":"2019","unstructured":"Open MP Architecture Review Board . {n. d.}. OpenMP Application Programming Interface. accessed May 2019 . OpenMP Architecture Review Board. {n. d.}. OpenMP Application Programming Interface. accessed May 2019."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_7_1","volume-title":"d.}. Using the GNU Compiler Collection (GCC). https:\/\/gcc.gnu.org\/onlinedocs\/gcc\/. accessed","author":"Foundation Free Software","year":"2019","unstructured":"Free Software Foundation . {n. d.}. Using the GNU Compiler Collection (GCC). https:\/\/gcc.gnu.org\/onlinedocs\/gcc\/. accessed May 2019 . Free Software Foundation. {n. d.}. Using the GNU Compiler Collection (GCC). https:\/\/gcc.gnu.org\/onlinedocs\/gcc\/. accessed May 2019."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3148173.3148185"},{"key":"e_1_3_2_1_9_1","volume-title":"d.}. Intel 64 and IA-32 Architectures Optimization Reference Manual. accessed","year":"2019","unstructured":"Intel. {n. d.}. Intel 64 and IA-32 Architectures Optimization Reference Manual. accessed May 2019 . Intel. {n. d.}. Intel 64 and IA-32 Architectures Optimization Reference Manual. accessed May 2019."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/2190025.2190061"},{"key":"e_1_3_2_1_11_1","volume-title":"d.}. The open standard for parallel programming of heterogeneous systems. accessed","author":"Khronos Group","year":"2019","unstructured":"Khronos Group . {n. d.}. The open standard for parallel programming of heterogeneous systems. accessed May 2019 . Khronos Group. {n. d.}. The open standard for parallel programming of heterogeneous systems. accessed May 2019."},{"key":"e_1_3_2_1_12_1","volume-title":"John A Stratton, and Wen-Mei W Hwu.","author":"Kim Hee-Seok","year":"2014","unstructured":"Hee-Seok Kim , Izzat El Hajj , John A Stratton, and Wen-Mei W Hwu. 2014 . Multi-tier Dynamic Vectorization for Translating GPU Optimizations into CPU Performance. Center for Reliable and High-Performance Computing ( 2014). Hee-Seok Kim, Izzat El Hajj, John A Stratton, and Wen-Mei W Hwu. 2014. Multi-tier Dynamic Vectorization for Translating GPU Optimizations into CPU Performance. Center for Reliable and High-Performance Computing (2014)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/349299.349320"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the International Symposium on Code Generation and Optimization (CGO)","author":"Lattner Chris","unstructured":"Chris Lattner and Vikram S. Adve . 2004. LLVM: A Compilation Framework for Lifelong Program Analysis & Transformation . In Proceedings of the International Symposium on Code Generation and Optimization (CGO) , San Jose, CA, USA. IEEE, 75--88. Chris Lattner and Vikram S. Adve. 2004. LLVM: A Compilation Framework for Lifelong Program Analysis & Transformation. In Proceedings of the International Symposium on Code Generation and Optimization (CGO), San Jose, CA, USA. IEEE, 75--88."},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 2013 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO), February 23--27","author":"Lee Yunsup","year":"2013","unstructured":"Yunsup Lee , Ronny Krashinsky , Vinod Grover , Stephen W. Keckler , and Krste Asanovic . 2013 . Convergence and scalarization for data-parallel architectures . In Proceedings of the 2013 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO), February 23--27 , 2013, Shenzhen, China. 32:1--32:11. Yunsup Lee, Ronny Krashinsky, Vinod Grover, Stephen W. Keckler, and Krste Asanovic. 2013. Convergence and scalarization for data-parallel architectures. In Proceedings of the 2013 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO), February 23--27, 2013, Shenzhen, China. 32:1--32:11."},{"key":"e_1_3_2_1_16_1","volume-title":"d.}. The Region Vectorizer(RV). https:\/\/github.com\/cdl-saarland\/rv. accessed","author":"Moll Simon","year":"2019","unstructured":"Simon Moll . {n. d.}. The Region Vectorizer(RV). https:\/\/github.com\/cdl-saarland\/rv. accessed May 2019 . Simon Moll. {n. d.}. The Region Vectorizer(RV). https:\/\/github.com\/cdl-saarland\/rv. accessed May 2019."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3192366.3192413"},{"key":"e_1_3_2_1_18_1","volume-title":"d.}. CUDA COMPILER DRIVER NVCC. accessed","author":"NVIDIA.","year":"2019","unstructured":"NVIDIA. {n. d.}. CUDA COMPILER DRIVER NVCC. accessed May 2019 . NVIDIA. {n. d.}. CUDA COMPILER DRIVER NVCC. accessed May 2019."},{"key":"e_1_3_2_1_19_1","volume-title":"Innovative Parallel Computing (InPar)","author":"Pharr Matt","year":"2012","unstructured":"Matt Pharr and William R Mark . 2012. ispc: A SPMD compiler for high-performance CPU programming . In Innovative Parallel Computing (InPar) , 2012 . IEEE , 1--13. Matt Pharr and William R Mark. 2012. ispc: A SPMD compiler for high-performance CPU programming. In Innovative Parallel Computing (InPar), 2012. IEEE, 1--13."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3207719.3207721"},{"key":"e_1_3_2_1_21_1","volume-title":"ATF: A generic directive-based auto-tuning framework. Concurrency and Computation: Practice and Experience","author":"Rasch Ari","year":"2018","unstructured":"Ari Rasch and Sergei Gorlatch . 2018 . ATF: A generic directive-based auto-tuning framework. Concurrency and Computation: Practice and Experience (2018). Ari Rasch and Sergei Gorlatch. 2018. ATF: A generic directive-based auto-tuning framework. Concurrency and Computation: Practice and Experience (2018)."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the International Conference on Parallel Computing (ParCo), 1--4","author":"Reyes Ruyman","year":"2015","unstructured":"Ruyman Reyes and Victor Lom\u00fcller . 2015 . SYCL: Single-source C++ accelerator programming . In Proceedings of the International Conference on Parallel Computing (ParCo), 1--4 September 2015, Edinburgh, Scotland, UK. 673--682. Ruyman Reyes and Victor Lom\u00fcller. 2015. SYCL: Single-source C++ accelerator programming. In Proceedings of the International Conference on Parallel Computing (ParCo), 1--4 September 2015, Edinburgh, Scotland, UK. 673--682."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2523815"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2687355"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2005.33"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2009.02.002"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007559022013"},{"key":"e_1_3_2_1_28_1","volume-title":"Euro-Par 2018: Parallel Processing Workshops - Euro-Par 2018 International Workshops, Turin, Italy, August 27--28","author":"Sun Huihui","year":"2018","unstructured":"Huihui Sun , Sergei Gorlatch , and Rongcai Zhao . 2018. Refactoring Loops with Nested IFs for SIMD Extensions Without Masked Instructions . In Euro-Par 2018: Parallel Processing Workshops - Euro-Par 2018 International Workshops, Turin, Italy, August 27--28 , 2018 , Revised Selected Papers . 769--781. Huihui Sun, Sergei Gorlatch, and Rongcai Zhao. 2018. Refactoring Loops with Nested IFs for SIMD Extensions Without Masked Instructions. In Euro-Par 2018: Parallel Processing Workshops - Euro-Par 2018 International Workshops, Turin, Italy, August 27--28, 2018, Revised Selected Papers. 769--781."},{"key":"e_1_3_2_1_29_1","volume-title":"A catalogue of optimizing transformations. Englewood Cliffs","author":"Thomas J.","unstructured":"J. Thomas , FE Allen , and J Cocke . 1971. A catalogue of optimizing transformations. Englewood Cliffs , N.J. : Prentice-Hall . 1--30 pages. J. Thomas, FE Allen, and J Cocke. 1971. A catalogue of optimizing transformations. Englewood Cliffs, N.J.: Prentice-Hall. 1--30 pages."},{"key":"e_1_3_2_1_30_1","volume-title":"Workshop on Programming Models for SIMD\/Vector Processing (WPMVP), Feburary 16th","author":"Timnat Shahar","year":"2014","unstructured":"Shahar Timnat , Ohad Shacham , and Ayal Zaks . 2014 . Predicate vectors if you must . In Workshop on Programming Models for SIMD\/Vector Processing (WPMVP), Feburary 16th , 2014, Orlando, Florida, USA. Shahar Timnat, Ohad Shacham, and Ayal Zaks. 2014. Predicate vectors if you must. In Workshop on Programming Models for SIMD\/Vector Processing (WPMVP), Feburary 16th, 2014, Orlando, Florida, USA."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2568058.2568059"}],"event":{"name":"ICS '19: 2019 International Conference on Supercomputing","location":"Phoenix Arizona","acronym":"ICS '19","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3330345.3331059","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3330345.3331059","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:53:26Z","timestamp":1750204406000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3330345.3331059"}},"subtitle":["improving the vectorization of IF-statements with warp-coherent conditions"],"short-title":[],"issued":{"date-parts":[[2019,6,26]]},"references-count":31,"alternative-id":["10.1145\/3330345.3331059","10.1145\/3330345"],"URL":"https:\/\/doi.org\/10.1145\/3330345.3331059","relation":{},"subject":[],"published":{"date-parts":[[2019,6,26]]},"assertion":[{"value":"2019-06-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}