{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:07:23Z","timestamp":1750306043544,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,2,4]],"date-time":"2017-02-04T00:00:00Z","timestamp":1486166400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100005144","name":"Qualcomm","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005144","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,2,4]]},"DOI":"10.1145\/3038228.3038236","type":"proceedings-article","created":{"date-parts":[[2017,2,16]],"date-time":"2017-02-16T15:18:54Z","timestamp":1487258334000},"page":"32-41","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Launch-Time Optimization of OpenCL GPU Kernels"],"prefix":"10.1145","author":[{"given":"Andrew S. D.","family":"Lee","sequence":"first","affiliation":[{"name":"University of Toronto, The Edward S. Rogers Sr. Department of Electrical and Computer Engineering, Toronto, Ontario, Canada"}]},{"given":"Tarek S.","family":"Abdelrahman","sequence":"additional","affiliation":[{"name":"University of Toronto, The Edward S. Rogers Sr. Department of Electrical and Computer Engineering, Toronto, Ontario, Canada"}]}],"member":"320","published-online":{"date-parts":[[2017,2,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11970-5_14"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/12276.13327"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1854273.1854318"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1964179.1964192"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2015.39"},{"volume-title":"Heterogeneous Computing with OpenCL","author":"Gaster Benedict","key":"e_1_3_2_1_6_1","unstructured":"Benedict Gaster , Lee Howes , David R. Kaeli , Perhaad Mistry , and Dana Schaa . 2011. Heterogeneous Computing with OpenCL . Morgan Kaufmann Publishers Inc . Benedict Gaster, Lee Howes, David R. Kaeli, Perhaad Mistry, and Dana Schaa. 2011. Heterogeneous Computing with OpenCL. Morgan Kaufmann Publishers Inc."},{"volume-title":"An Introduction to OpenCL C++","author":"Guillon A J","key":"e_1_3_2_1_7_1","unstructured":"A J Guillon . 2015. An Introduction to OpenCL C++ . Khronos Group . A J Guillon. 2015. An Introduction to OpenCL C++. Khronos Group."},{"key":"e_1_3_2_1_8_1","volume-title":"Proc. of ADAPT.","author":"Han Tianyi David","year":"2015","unstructured":"Tianyi David Han and Tarek Abdelrahman . 2015 . Automatic Tuning of Local Memory Use on GPGPUs . In Proc. of ADAPT. Tianyi David Han and Tarek Abdelrahman. 2015. Automatic Tuning of Local Memory Use on GPGPUs. In Proc. of ADAPT."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1964179.1964184"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2458523.2458525"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/977395.977673"},{"volume-title":"Launch-Time Optimization of OpenCL GPU Kernels (In Progress). Master's thesis","author":"Lee Andrew","key":"e_1_3_2_1_12_1","unstructured":"Andrew Lee . 2017. Launch-Time Optimization of OpenCL GPU Kernels (In Progress). Master's thesis . University of Toronto . Andrew Lee. 2017. Launch-Time Optimization of OpenCL GPU Kernels (In Progress). Master's thesis. University of Toronto."},{"volume-title":"Advanced Compiler Design and Implementation","author":"Muchnick Steven S.","key":"e_1_3_2_1_13_1","unstructured":"Steven S. Muchnick . 1997. Advanced Compiler Design and Implementation . Morgan Kaufmann Publishers Inc . Steven S. Muchnick. 1997. Advanced Compiler Design and Implementation. Morgan Kaufmann Publishers Inc."},{"volume-title":"The OpenCL Specification 1.2","author":"Munshi Aaftab","key":"e_1_3_2_1_14_1","unstructured":"Aaftab Munshi . 2012. The OpenCL Specification 1.2 . Khronos OpenCL Working Group . Aaftab Munshi. 2012. The OpenCL Specification 1.2. Khronos OpenCL Working Group."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1365490.1365500"},{"key":"e_1_3_2_1_16_1","unstructured":"NVIDIA 2012. NVIDIAs Next Generation CUDA Compute Architecture: Kepler GK110 (1.0 ed.). Nvidia.  NVIDIA 2012. NVIDIAs Next Generation CUDA Compute Architecture: Kepler GK110 (1.0 ed.). Nvidia."},{"key":"e_1_3_2_1_17_1","unstructured":"NVIDIA 2015. Parallel Thread Execution ISA Application Guide (4.3 ed.). Nvidia.  NVIDIA 2015. Parallel Thread Execution ISA Application Guide (4.3 ed.). Nvidia."},{"key":"e_1_3_2_1_18_1","unstructured":"NVIDIA 2016. CUDA C Programming Guide (8.0 ed.). Nvidia.  NVIDIA 2016. CUDA C Programming Guide (8.0 ed.). Nvidia."},{"key":"e_1_3_2_1_19_1","unstructured":"NVIDIA 2016. CUDA Compiler Driver NVCC Reference Guide (8.0 ed.). Nvidia.  NVIDIA 2016. CUDA Compiler Driver NVCC Reference Guide (8.0 ed.). Nvidia."},{"key":"e_1_3_2_1_20_1","unstructured":"NVIDIA. 2016. NVIDIA OpenCL SDK Code Samples. https:\/\/developer.nvidia.com\/opencl. (2016). Accessed: 2016-11-08.  NVIDIA. 2016. NVIDIA OpenCL SDK Code Samples. https:\/\/developer.nvidia.com\/opencl. (2016). Accessed: 2016-11-08."},{"volume-title":"libclc","author":"Project LLVM","key":"e_1_3_2_1_21_1","unstructured":"LLVM Project . 2016. libclc . http:\/\/libclc.llvm.org\/. (2016). Accessed: 2016-11-17. LLVM Project. 2016. libclc. http:\/\/libclc.llvm.org\/. (2016). Accessed: 2016-11-17."},{"volume-title":"User Guide for AMDGPU Back-end","author":"Project LLVM","key":"e_1_3_2_1_22_1","unstructured":"LLVM Project . 2016. User Guide for AMDGPU Back-end . http:\/\/llvm.org\/docs\/AMDGPUUsage.html. (2016). Accessed: 2016-11-14. LLVM Project. 2016. User Guide for AMDGPU Back-end. http:\/\/llvm.org\/docs\/AMDGPUUsage.html. (2016). Accessed: 2016-11-14."},{"volume-title":"User Guide for NVPTX Back-end","author":"Project LLVM","key":"e_1_3_2_1_23_1","unstructured":"LLVM Project . 2016. User Guide for NVPTX Back-end . http:\/\/llvm.org\/docs\/NVPTXUsage.html. (2016). Accessed: 2016-11-08. LLVM Project. 2016. User Guide for NVPTX Back-end. http:\/\/llvm.org\/docs\/NVPTXUsage.html. (2016). Accessed: 2016-11-08."},{"key":"e_1_3_2_1_24_1","first-page":"3","article-title":"OpenCL: A Parallel Programming Standard for Heterogeneous Computing Systems","volume":"12","author":"Stone John E.","year":"2010","unstructured":"John E. Stone , David Gohara , and Guochun Shi . 2010 . OpenCL: A Parallel Programming Standard for Heterogeneous Computing Systems . IEEE Des. Test 12 , 3 (May 2010), 66--73. John E. Stone, David Gohara, and Guochun Shi. 2010. OpenCL: A Parallel Programming Standard for Heterogeneous Computing Systems. IEEE Des. Test 12, 3 (May 2010), 66--73.","journal-title":"IEEE Des. Test"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1854273.1854336"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2854038.2854041"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1693453.1693472"}],"event":{"name":"PPoPP '17: 22nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages"],"location":"Austin TX USA","acronym":"PPoPP '17"},"container-title":["Proceedings of the General Purpose GPUs"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3038228.3038236","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3038228.3038236","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:03:11Z","timestamp":1750215791000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3038228.3038236"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,2,4]]},"references-count":27,"alternative-id":["10.1145\/3038228.3038236","10.1145\/3038228"],"URL":"https:\/\/doi.org\/10.1145\/3038228.3038236","relation":{},"subject":[],"published":{"date-parts":[[2017,2,4]]},"assertion":[{"value":"2017-02-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}