{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:45:05Z","timestamp":1787017505594,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,2,24]],"date-time":"2018-02-24T00:00:00Z","timestamp":1519430400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["1618620, 1464157"],"award-info":[{"award-number":["1618620, 1464157"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DoE","award":["66150"],"award-info":[{"award-number":["66150"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,2,24]]},"DOI":"10.1145\/3168831","type":"proceedings-article","created":{"date-parts":[[2018,3,1]],"date-time":"2018-03-01T15:06:04Z","timestamp":1519916764000},"page":"214-227","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":37,"title":["CUDAAdvisor: LLVM-based runtime profiling for modern GPUs"],"prefix":"10.1145","author":[{"given":"Du","family":"Shen","sequence":"first","affiliation":[{"name":"College of William and Mary, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuaiwen Leon","family":"Song","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Laboratory, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ang","family":"Li","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Laboratory, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Liu","sequence":"additional","affiliation":[{"name":"College of William and Mary, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2018,2,24]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2017. NVIDIA Visual Profiler. NVIDIA. http:\/\/docs.nvidia.com\/cuda\/ profiler-users-guide"},{"key":"e_1_3_2_1_2_1","volume-title":"Top500 supercomputer sites. https:\/\/www.top500.org\/lists\/ 2017\/06 . (Jun","year":"2017","unstructured":"Jun. 2017. Top500 supercomputer sites. https:\/\/www.top500.org\/lists\/ 2017\/06 . (Jun. 2017)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.v22:6"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2015.38"},{"key":"e_1_3_2_1_5_1","volume-title":"2009 IEEE International Symposium on Performance Analysis of Systems and Software. 163\u2013174","author":"Bakhoda A.","unstructured":"A. Bakhoda, G. L. Yuan, W. W. L. Fung, H. Wong, and T. M. Aamodt. 2009. Analyzing CUDA workloads using a detailed GPU simulator. In 2009 IEEE International Symposium on Performance Analysis of Systems and Software. 163\u2013174."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934661"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503299"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830818"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.11"},{"key":"e_1_3_2_1_11_1","volume-title":"CUDA Tools SDK CUPTI User\u2019s Guide DA-05679-001_v01. https:\/\/developer.nvidia.com\/nvidia-visual-profiler . (October","author":"NVIDIA Corp. 2011.","year":"2011","unstructured":"NVIDIA Corp. 2011. CUDA Tools SDK CUPTI User\u2019s Guide DA-05679-001_v01. https:\/\/developer.nvidia.com\/nvidia-visual-profiler . (October 2011)."},{"key":"e_1_3_2_1_12_1","unstructured":"NVIDIA Corp. 2017. NVIDIA Nsight. http:\/\/www.nvidia.com\/object\/ nsight.html . (2017)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2012.18"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1854273.1854318"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","unstructured":"Chen Ding and Zhong Yuntao. 2001. Reuse Distance Analysis. In Computer Science at University of Rochester Tech report UR-CS-TR-741. U of Rochester.","DOI":"10.5555\/898449"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540742"},{"key":"e_1_3_2_1_17_1","volume-title":"Innovative Parallel Computing (InPar)","author":"Grauer-Gray Scott","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 Innovative Parallel Computing (InPar). IEEE."},{"key":"e_1_3_2_1_18_1","volume-title":"LLVM: User Guide for NVPTX Back-end. http: \/\/llvm.org\/docs\/NVPTXUsage.html .","author":"LLVM Group","year":"2016","unstructured":"LLVM Group. 2016. LLVM: User Guide for NVPTX Back-end. http: \/\/llvm.org\/docs\/NVPTXUsage.html . (2016)."},{"key":"e_1_3_2_1_19_1","unstructured":"NVIDIA Group. 2017. NVIDIA DGX-1 AI Supercomputer. http:\/\/www. nvidia.com\/object\/deep-learning-system.html . (2017)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.1725"},{"key":"e_1_3_2_1_21_1","unstructured":"Google Inc. 2017. TensorFlow: An open-source software library for Machine Intelligence. https:\/\/www.tensorflow.org . (2017)."},{"key":"e_1_3_2_1_22_1","volume-title":"Intel VTune Amplifier XE 2017","author":"Intel","year":"2017","unstructured":"Intel 2017. Intel VTune Amplifier XE 2017. http:\/\/software.intel.com\/ en-us\/intel-vtune-amplifier-xe . (April 2017)."},{"key":"e_1_3_2_1_24_1","volume-title":"2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA). 272\u2013283","author":"Jia W.","unstructured":"W. Jia, K. A. Shaw, and M. Martonosi. 2014. MRPB: Memory request prioritization for massively parallel processors. In 2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA). 272\u2013283."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2508148.2485951"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/2523721.2523745"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/977395.977673"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.44"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2013.6494995"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037709"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807606"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751237"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926253"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2011.71"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815992"},{"key":"e_1_3_2_1_36_1","volume-title":"2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA). 37\u201348","author":"Nugteren C.","unstructured":"C. Nugteren, G. J. van den Braak, H. Corporaal, and H. Bal. 2014. A detailed GPU cache model based on reuse distance theory. In 2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA). 37\u201348."},{"key":"e_1_3_2_1_37_1","unstructured":"NVIDIA. 2015. CUDA 7.5: Pinpoint Performance Problems with Instruction-Level Profiling. https:\/\/devblogs.nvidia.com\/parallelforall\/ cuda-7-5-pinpoint-performance-problems-instruction-level-profiling . (2015)."},{"key":"e_1_3_2_1_38_1","unstructured":"NVIDIA. 2015. CUDA Programming Guide. (2015). http:\/\/docs.nvidia. com\/cuda\/cuda-c-programming-guide"},{"key":"e_1_3_2_1_39_1","unstructured":"Oracle. 2012. Oracle Solaris Studio. http:\/\/www.oracle.com\/ technetwork\/server-storage\/solarisstudio\/overview\/index.html . (2012)."},{"key":"e_1_3_2_1_40_1","unstructured":"Keshav Pingal. 2014. Galois. http:\/\/iss.ices.utexas.edu\/?p=projects\/ galois . (2014)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1006\/jcph.1995.1039"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540717"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540718"},{"key":"e_1_3_2_1_45_1","volume-title":"2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA). 174\u2013185","author":"Sethia A.","unstructured":"A. Sethia, D. A. Jamshidi, and S. Mahlke. 2015. Mascar: Speeding up GPU warps by reducing memory pitstops. In 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA). 174\u2013185."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.73"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750375"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2010.69"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967951"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1002\/spe.4380230407"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2854038.2854041"},{"key":"e_1_3_2_1_52_1","volume-title":"2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA). 284\u2013295","author":"Xiang P.","unstructured":"P. Xiang, Y. Yang, and H. Zhou. 2014. Warp-level divergence in GPUs: Characterization, impact, and mitigation. In 2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA). 284\u2013295."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830813"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.5555\/2561828.2561929"},{"key":"e_1_3_2_1_55_1","volume-title":"2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA). 76\u201388","author":"Xie X.","unstructured":"X. Xie, Y. Liang, Y. Wang, G. Sun, and T. Wang. 2015. Coordinated static and dynamic cache bypassing for GPUs. In 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA). 76\u201388."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/1961295.1950408"}],"event":{"name":"CGO '18: 16th Annual IEEE\/ACM International Symposium on Code Generation and Optimization","location":"Vienna Austria","acronym":"CGO '18","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing","IEEE-CS Computer Society"]},"container-title":["Proceedings of the 2018 International Symposium on Code Generation and Optimization"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3168831","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3168831","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3168831","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:30:33Z","timestamp":1750203033000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3168831"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2,24]]},"references-count":55,"alternative-id":["10.1145\/3168831","10.1145\/3179541"],"URL":"https:\/\/doi.org\/10.1145\/3168831","relation":{},"subject":[],"published":{"date-parts":[[2018,2,24]]},"assertion":[{"value":"2018-02-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}