{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:49:41Z","timestamp":1750308581961,"version":"3.41.0"},"reference-count":26,"publisher":"Association for Computing Machinery (ACM)","issue":"5s","license":[{"start":{"date-parts":[[2017,9,27]],"date-time":"2017-09-27T00:00:00Z","timestamp":1506470400000},"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":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2017,10,31]]},"abstract":"<jats:p>\n            Heterogeneous multiprocessor system-on-chip architectures are endowed with accelerators such as embedded GPUs and FPGAs capable of general-purpose computation. The application developers for such platforms need to carefully choose the accelerator with the maximum performance benefit. For a given application, usually, the reference code is specified in a high-level single-threaded programming language such as C. The performance of an application kernel on an accelerator is a complex interplay among the exposed parallelism, the compiler, and the accelerator architecture. Thus, determining the performance of a kernel requires its redevelopment into each accelerator-specific language, causing substantial wastage of time and effort. To aid the developer in this early design decision, we present an analytical framework\n            <jats:italic>CGPredict<\/jats:italic>\n            to predict the performance of a computational kernel on an embedded GPU architecture from un-optimized, single-threaded C code. The analytical approach provides insights on application characteristics which suggest further application-specific optimizations. The estimation error is as low as 2.66% (average 9%) compared to the performance of the same kernel written in native CUDA code running on NVIDIA Kepler embedded GPU. This low performance estimation error enables CGPredict to provide an early design recommendation of the accelerator starting from C code.\n          <\/jats:p>","DOI":"10.1145\/3126546","type":"journal-article","created":{"date-parts":[[2017,9,27]],"date-time":"2017-09-27T12:33:53Z","timestamp":1506515633000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["CGPredict"],"prefix":"10.1145","volume":"16","author":[{"given":"Siqi","family":"Wang","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanwen","family":"Zhong","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tulika","family":"Mitra","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2017,9,27]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830780"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1693453.1693470"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11970-5_14"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1950413.1950423"},{"key":"e_1_2_1_5_1","volume-title":"Dinero IV trace-driven uniprocessor cache simulator. urlhttp:\/\/www.cs.wisc.edu\/&sim;markhill\/DineroIV\/","author":"Edler Jan","year":"1998","unstructured":"Jan Edler . 1998. Dinero IV trace-driven uniprocessor cache simulator. urlhttp:\/\/www.cs.wisc.edu\/&sim;markhill\/DineroIV\/ ( 1998 ). Jan Edler. 1998. Dinero IV trace-driven uniprocessor cache simulator. urlhttp:\/\/www.cs.wisc.edu\/&sim;markhill\/DineroIV\/ (1998)."},{"volume-title":"Auto-tuning a high-level language targeted to GPU codes. In 2012 Innovative Parallel Computing (InPar\u201912)","author":"Grauer-Gray Scott","key":"e_1_2_1_6_1","unstructured":"Scott Grauer-Gray , Lifan Xu , Robert Searles , Sudhee Ayalasomayajula , and John Cavazos . 2012. Auto-tuning a high-level language targeted to GPU codes. In 2012 Innovative Parallel Computing (InPar\u201912) . IEEE , 1--10. Scott Grauer-Gray, Lifan Xu, Robert Searles, Sudhee Ayalasomayajula, and John Cavazos. 2012. Auto-tuning a high-level language targeted to GPU codes. In 2012 Innovative Parallel Computing (InPar\u201912). IEEE, 1--10."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555775"},{"key":"e_1_2_1_8_1","unstructured":"Khronos. 2017. OpenCL: The open standard for parallel programming of heterogeneous systems. (2017). https:\/\/www.khronos.org\/opencl\/.  Khronos. 2017. OpenCL: The open standard for parallel programming of heterogeneous systems. (2017). https:\/\/www.khronos.org\/opencl\/."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/977395.977673"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1837274.1837362"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2549523"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063402"},{"volume-title":"2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA\u201914)","author":"Nugteren Cedric","key":"e_1_2_1_13_1","unstructured":"Cedric Nugteren , Gert-Jan van den Braak, Henk Corporaal, and Henri Bal. 2014. A detailed GPU cache model based on reuse distance theory . In 2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA\u201914) . IEEE, 37--48. Cedric Nugteren, Gert-Jan van den Braak, Henk Corporaal, and Henri Bal. 2014. A detailed GPU cache model based on reuse distance theory. In 2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA\u201914). IEEE, 37--48."},{"key":"e_1_2_1_14_1","unstructured":"NVIDIA. 2017. CUDA Toolkit Documentation. (2017). http:\/\/docs.nvidia.com\/cuda\/index.html.  NVIDIA. 2017. CUDA Toolkit Documentation. (2017). http:\/\/docs.nvidia.com\/cuda\/index.html."},{"key":"e_1_2_1_15_1","volume-title":"CUDA C Programming Guide v8.0","author":"NVIDIA.","year":"2017","unstructured":"NVIDIA. 2017. NVIDIA. CUDA C Programming Guide v8.0 2017 . (2017). https:\/\/docs.nvidia.com\/cuda\/pdf\/CUDA_C_Programming_Guide.pdf. NVIDIA. 2017. NVIDIA. CUDA C Programming Guide v8.0 2017. (2017). https:\/\/docs.nvidia.com\/cuda\/pdf\/CUDA_C_Programming_Guide.pdf."},{"key":"e_1_2_1_16_1","unstructured":"NVIDIA. 2017. Parallel Thread Execution ISA Version 5.0. (2017). http:\/\/docs.nvidia.com\/cuda\/parallel-thread-execution.  NVIDIA. 2017. Parallel Thread Execution ISA Version 5.0. (2017). http:\/\/docs.nvidia.com\/cuda\/parallel-thread-execution."},{"key":"e_1_2_1_17_1","unstructured":"NVIDIA. 2017. Tuning CUDA Applications for Kepler. (2017). http:\/\/docs.nvidia.com\/cuda\/kepler-tuning-guide\/.  NVIDIA. 2017. Tuning CUDA Applications for Kepler. (2017). http:\/\/docs.nvidia.com\/cuda\/kepler-tuning-guide\/."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2012.328"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2011.16"},{"key":"e_1_2_1_20_1","volume-title":"K1: A New Era in Mobile Computing. Nvidia","author":"Tegra NVIDIA","year":"2014","unstructured":"NVIDIA Tegra . 2014. K1: A New Era in Mobile Computing. Nvidia , Corp., White Paper ( 2014 ). NVIDIA Tegra. 2014. K1: A New Era in Mobile Computing. Nvidia, Corp., White Paper (2014)."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2010.5452013"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056063"},{"key":"e_1_2_1_23_1","unstructured":"Xilinx. 2017. Vivado design suite. (2017). https:\/\/www.xilinx.com\/products\/design-tools\/vivado.html.  Xilinx. 2017. Vivado design suite. (2017). https:\/\/www.xilinx.com\/products\/design-tools\/vivado.html."},{"key":"e_1_2_1_24_1","unstructured":"Xilinx. 2017. XILINX inc. (2017). http:\/\/www.xilinx.com.  Xilinx. 2017. XILINX inc. (2017). http:\/\/www.xilinx.com."},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2898040"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/3130379.3130649"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3126546","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3126546","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T19:05:02Z","timestamp":1750273502000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3126546"}},"subtitle":["Embedded GPU Performance Estimation from Single-Threaded Applications"],"short-title":[],"issued":{"date-parts":[[2017,9,27]]},"references-count":26,"journal-issue":{"issue":"5s","published-print":{"date-parts":[[2017,10,31]]}},"alternative-id":["10.1145\/3126546"],"URL":"https:\/\/doi.org\/10.1145\/3126546","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"type":"print","value":"1539-9087"},{"type":"electronic","value":"1558-3465"}],"subject":[],"published":{"date-parts":[[2017,9,27]]},"assertion":[{"value":"2017-04-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2017-07-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2017-09-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}