{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T09:48:52Z","timestamp":1767260932304},"reference-count":76,"publisher":"Springer Science and Business Media LLC","issue":"16","license":[{"start":{"date-parts":[[2023,5,13]],"date-time":"2023-05-13T00:00:00Z","timestamp":1683936000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,13]],"date-time":"2023-05-13T00:00:00Z","timestamp":1683936000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1007\/s11227-023-05375-0","type":"journal-article","created":{"date-parts":[[2023,5,13]],"date-time":"2023-05-13T09:02:38Z","timestamp":1683968558000},"page":"18340-18374","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Reducing branch divergence to speed up parallel execution of unit testing on GPUs"],"prefix":"10.1007","volume":"79","author":[{"given":"Taghreed","family":"Bagies","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Le","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeremy","family":"Sheaffer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Jannesari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,13]]},"reference":[{"key":"5375_CR1","doi-asserted-by":"publisher","unstructured":"Yaneva V, Rajan A, Dubach C (2017) Compiler-assisted test acceleration on gpus for embedded software. In: Proceedings of the 26th ACM SIGSOFT International Symposium on Software Testing and Analysis. ISSTA 2017, pp. 35\u201345. ACM, New York, NY, USA. https:\/\/doi.org\/10.1145\/3092703.3092720","DOI":"10.1145\/3092703.3092720"},{"key":"5375_CR2","doi-asserted-by":"publisher","unstructured":"Harrold MJ (2000) Testing: A roadmap. In: Proceedings of the Conference on The Future of Software Engineering. ICSE \u201900, pp. 61\u201372. ACM, New York, NY, USA. https:\/\/doi.org\/10.1145\/336512.336532","DOI":"10.1145\/336512.336532"},{"key":"5375_CR3","doi-asserted-by":"publisher","unstructured":"Shete N, Jadhav A (2014) An empirical study of test cases in software testing. In: International Conference on Information Communication and Embedded Systems (ICICES2014), pp. 1\u20135. https:\/\/doi.org\/10.1109\/ICICES.2014.7033883","DOI":"10.1109\/ICICES.2014.7033883"},{"key":"5375_CR4","unstructured":"Sommerville I (2015) Software Engineering, 10th edn. Pearson, ???"},{"issue":"10","key":"5375_CR5","doi-asserted-by":"publisher","first-page":"929","DOI":"10.1109\/32.962562","volume":"27","author":"G Rothermel","year":"2001","unstructured":"Rothermel G, Untch RH, Chu C, Harrold MJ (2001) Prioritizing test cases for regression testing. IEEE Trans Software Eng 27(10):929\u2013948. https:\/\/doi.org\/10.1109\/32.962562","journal-title":"IEEE Trans Software Eng"},{"key":"5375_CR6","doi-asserted-by":"crossref","unstructured":"Gambi A, Kappler S, Lampel J, Zeller A (2017) Cut: Automatic unit testing in the cloud. In: Proceedings of the 26th ACM SIGSOFT International Symposium on Software Testing and Analysis. ISSTA 2017, pp. 364\u2013367. ACM, New York, NY, USA","DOI":"10.1145\/3092703.3098222"},{"key":"5375_CR7","doi-asserted-by":"publisher","unstructured":"Kappler S (2016) Finding and breaking test dependencies to speed up test execution. In: Proceedings of the 2016 24th ACM SIGSOFT International Symposium on Foundations of Software Engineering. FSE 2016, pp. 1136\u20131138. ACM, New York, NY, USA. https:\/\/doi.org\/10.1145\/2950290.2983974","DOI":"10.1145\/2950290.2983974"},{"key":"5375_CR8","doi-asserted-by":"publisher","unstructured":"Liu C-H, Chen S-L, Chen W-K (2017) Cost-benefit evaluation on parallel execution for improving test efficiency over cloud. In: 2017 International Conference on Applied System Innovation (ICASI), pp. 199\u2013202. https:\/\/doi.org\/10.1109\/ICASI.2017.7988384","DOI":"10.1109\/ICASI.2017.7988384"},{"key":"5375_CR9","doi-asserted-by":"publisher","unstructured":"Oriol M, Ullah F (2010) Yeti on the cloud. In: 2010 Third International Conference on Software Testing, Verification, and Validation Workshops, pp. 434\u2013437. https:\/\/doi.org\/10.1109\/ICSTW.2010.68","DOI":"10.1109\/ICSTW.2010.68"},{"key":"5375_CR10","doi-asserted-by":"publisher","unstructured":"Parveen T, Tilley S, Daley N, Morales P (2009) Towards a distributed execution framework for junit test cases. In: 2009 IEEE International Conference on Software Maintenance, pp. 425\u2013428. https:\/\/doi.org\/10.1109\/ICSM.2009.5306292","DOI":"10.1109\/ICSM.2009.5306292"},{"key":"5375_CR11","doi-asserted-by":"publisher","unstructured":"Gambi A, Gorla A, Zeller A (2017) O!snap: Cost-efficient testing in the cloud. In: 2017 IEEE International Conference on Software Testing, Verification and Validation (ICST), pp. 454\u2013459. https:\/\/doi.org\/10.1109\/ICST.2017.51","DOI":"10.1109\/ICST.2017.51"},{"key":"5375_CR12","doi-asserted-by":"crossref","unstructured":"von Hof V, Fuchs A (2018) Automatic scalable parallel test case execution. introducing the m\u00fcnster distributed test case runner for java (midstr). In: Proceedings of the 33rd Annual ACM Symposium on Applied Computing, pp. 1062\u20131064","DOI":"10.1145\/3167132.3167408"},{"key":"5375_CR13","doi-asserted-by":"publisher","unstructured":"Koong C-S, Shih C-H, Wu C-C, Hsiung P-A (2013) The architecture of parallelized cloud-based automatic testing system. In: 2013 Seventh International Conference on Complex, Intelligent, and Software Intensive Systems, pp. 467\u2013470. https:\/\/doi.org\/10.1109\/CISIS.2013.85","DOI":"10.1109\/CISIS.2013.85"},{"key":"5375_CR14","doi-asserted-by":"crossref","unstructured":"Duarte A, Cirne W, Brasileiro F, Machado P (2006) Gridunit: software testing on the grid. In: Proceedings of the 28th International Conference on Software Engineering, pp. 779\u2013782","DOI":"10.1145\/1134285.1134410"},{"key":"5375_CR15","doi-asserted-by":"publisher","unstructured":"Rajan A, Sharma S, Schrammel P, Kroening D (2014) Accelerated test execution using gpus. In: Proceedings of the 29th ACM\/IEEE International Conference on Automated Software Engineering. ASE \u201914, pp. 97\u2013102. ACM, New York, NY, USA. https:\/\/doi.org\/10.1145\/2642937.2642957","DOI":"10.1145\/2642937.2642957"},{"key":"5375_CR16","doi-asserted-by":"publisher","unstructured":"Han TD, Abdelrahman TS (2011) Reducing branch divergence in gpu programs. In: Proceedings of the Fourth Workshop on General Purpose Processing on Graphics Processing Units. GPGPU-4, pp. 3\u2013138. ACM, New York, NY, USA. https:\/\/doi.org\/10.1145\/1964179.1964184","DOI":"10.1145\/1964179.1964184"},{"key":"5375_CR17","doi-asserted-by":"publisher","unstructured":"Zhang EZ, Jiang Y, Guo Z, Shen X (2010) Streamlining gpu applications on the fly: Thread divergence elimination through runtime thread-data remapping. In: Proceedings of the 24th ACM International Conference on Supercomputing. ICS \u201910, pp. 115\u2013126. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/1810085.1810104","DOI":"10.1145\/1810085.1810104"},{"key":"5375_CR18","doi-asserted-by":"crossref","unstructured":"Yu Z, Eeckhout L, Xu C (2016) Thread similarity matrix: Visualizing branch divergence in gpgpu programs. In: 2016 45th International Conference on Parallel Processing (ICPP), pp. 179\u2013184","DOI":"10.1109\/ICPP.2016.27"},{"key":"5375_CR19","doi-asserted-by":"crossref","unstructured":"Coutinho B, Sampaio D, Pereira FMQ, Meira\u00a0Jr W (2011) Divergence analysis and optimizations. In: 2011 International Conference on Parallel Architectures and Compilation Techniques, pp. 320\u2013329. IEEE","DOI":"10.1109\/PACT.2011.63"},{"key":"5375_CR20","doi-asserted-by":"crossref","unstructured":"Sampaio D, Martins R, Collange S, Pereira FMQ (2012) Divergence analysis with affine constraints. In: 2012 IEEE 24th International Symposium on Computer Architecture and High Performance Computing, pp. 67\u201374","DOI":"10.1109\/SBAC-PAD.2012.22"},{"key":"5375_CR21","doi-asserted-by":"publisher","unstructured":"Kerr A, Diamos G, Yalamanchili S (2009) A characterization and analysis of ptx kernels, pp. 3\u201312. https:\/\/doi.org\/10.1109\/IISWC.2009.5306801","DOI":"10.1109\/IISWC.2009.5306801"},{"issue":"2","key":"5375_CR22","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1109\/TMM.2012.2232647","volume":"15","author":"J Sartori","year":"2013","unstructured":"Sartori J, Kumar R (2013) Branch and data herding: reducing control and memory divergence for error-tolerant gpu applications. IEEE Trans Multimedia 15(2):279\u2013290","journal-title":"IEEE Trans Multimedia"},{"key":"5375_CR23","doi-asserted-by":"crossref","unstructured":"Vespa LVL (2018) Unraveling the divergence of gpu threads. In: 2018 International Conference on Computational Science and Computational Intelligence (CSCI), pp. 1398\u20131403","DOI":"10.1109\/CSCI46756.2018.00270"},{"issue":"8","key":"5375_CR24","doi-asserted-by":"publisher","first-page":"1121","DOI":"10.1002\/cpe.2931","volume":"25","author":"I Chakroun","year":"2013","unstructured":"Chakroun I, Mezmaz M, Melab N, Bendjoudi A (2013) Reducing thread divergence in a gpu-accelerated branch-and-bound algorithm. Concurr Comput Pract Exp 25(8):1121\u20131136","journal-title":"Concurr Comput Pract Exp"},{"key":"5375_CR25","unstructured":"Li Y, Liu R (2016) High throughput gpu polar decoder. In: 2016 2nd IEEE International Conference on Computer and Communications (ICCC), pp. 1123\u20131127"},{"key":"5375_CR26","doi-asserted-by":"crossref","unstructured":"Carrillo S, Siegel J, Li X (2009) A control-structure splitting optimization for gpgpu. In: Proceedings of the 6th ACM Conference on Computing Frontiers, pp. 147\u2013150","DOI":"10.1145\/1531743.1531766"},{"key":"5375_CR27","doi-asserted-by":"crossref","unstructured":"Reissmann N, Falch TL, Bj\u00f8rnseth BA, Bahmann H, Meyer JC, Jahre M (2016) Efficient control flow restructuring for gpus. In: 2016 International Conference on High Performance Computing Simulation (HPCS), pp. 48\u201357","DOI":"10.1109\/HPCSim.2016.7568315"},{"key":"5375_CR28","doi-asserted-by":"crossref","unstructured":"Anantpur J, Govindarajan R (2014) Taming control divergence in gpus through control flow linearization. In: International Conference on Compiler Construction, pp. 133\u2013153. Springer","DOI":"10.1007\/978-3-642-54807-9_8"},{"key":"5375_CR29","unstructured":"Zone ND (2021) CUDA Toolkit Documentation. https:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/index.html#simt-architecture. Accessed on 23 June 2021"},{"key":"5375_CR30","unstructured":"Gupta P (2020) CUDA Refresher: The CUDA Programming Model. https:\/\/developer.nvidia.com\/blog\/cuda-refresher-cuda-programming-model\/. Accessed on 27 June 2021"},{"issue":"1","key":"5375_CR31","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1109\/TPDS.2010.62","volume":"22","author":"TD Han","year":"2011","unstructured":"Han TD, Abdelrahman TS (2011) hicuda: High-level gpgpu programming. IEEE Trans Parallel Distrib Syst 22(1):78\u201390. https:\/\/doi.org\/10.1109\/TPDS.2010.62","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"5375_CR32","unstructured":"Lin Y, Grover V (2012) Using CUDA warp-level primitives. https:\/\/devblogs.nvidia.com\/using-cuda-warp-level-primitives\/. Accessed on 14 Oct 2018"},{"key":"5375_CR33","unstructured":"Workshop V (2019) Introduction to GPGPU and CUDA programming: thread divergence. https:\/\/cvw.cac.cornell.edu\/gpu\/thread_div. Accessed on 20 Aug 2019"},{"key":"5375_CR34","doi-asserted-by":"crossref","unstructured":"Srivastava A, Thiagarajan J (2002) Effectively prioritizing tests in development environment. In: Proceedings of the 2002 ACM SIGSOFT International Symposium on Software Testing and Analysis, pp. 97\u2013106","DOI":"10.1145\/566172.566187"},{"key":"5375_CR35","doi-asserted-by":"crossref","unstructured":"Wong WE, Horgan JR, London S, Agrawal H (1997) A study of effective regression testing in practice. In: Proceedings The Eighth International Symposium on Software Reliability Engineering. pp 264\u2013274","DOI":"10.1109\/ISSRE.1997.630875"},{"key":"5375_CR36","doi-asserted-by":"publisher","unstructured":"Beller M, Gousios G, Panichella A, Zaidman A (2015) When, how, and why developers (do not) test in their ides. In: Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering. ESEC\/FSE 2015, pp. 179\u2013190. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/2786805.2786843","DOI":"10.1145\/2786805.2786843"},{"key":"5375_CR37","doi-asserted-by":"crossref","unstructured":"Rothermel G, Untch RH, Chu C, Harrold MJ (1999) Test case prioritization: An empirical study. In: Proceedings IEEE International Conference on Software Maintenance-1999 (ICSM\u201999).\u2019Software Maintenance for Business Change\u2019(Cat. No. 99CB36360), pp. 179\u2013188. IEEE","DOI":"10.1109\/ICSM.1999.792604"},{"key":"5375_CR38","doi-asserted-by":"crossref","unstructured":"Zhang S, Jalali D, Wuttke J, Mu\u015flu K, Lam W, Ernst MD, Notkin D (2014) Empirically revisiting the test independence assumption. In: Proceedings of the 2014 International Symposium on Software Testing and Analysis, pp. 385\u2013396","DOI":"10.1145\/2610384.2610404"},{"key":"5375_CR39","unstructured":"Lam W, Zhang S, Ernst MD (2015) When tests collide: evaluating and coping with the impact of test dependence. University of Washington Department of Computer Science and Engineering, Tech, Rep"},{"key":"5375_CR40","doi-asserted-by":"crossref","unstructured":"Schwahn O, Coppik N, Winter S, Suri N (2019) Assessing the state and improving the art of parallel testing for c. In: Proceedings of the 28th ACM SIGSOFT International Symposium on Software Testing and Analysis, pp. 123\u2013133","DOI":"10.1145\/3293882.3330573"},{"key":"5375_CR41","doi-asserted-by":"publisher","unstructured":"Hu H, Jiang C-H, Ye F, Cai K-Y, Huang D, Yau SS (2010) A parallel implementation strategy of adaptive testing. In: 2010 IEEE 34th Annual Computer Software and Applications Conference Workshops, pp. 214\u2013219. https:\/\/doi.org\/10.1109\/COMPSACW.2010.44","DOI":"10.1109\/COMPSACW.2010.44"},{"key":"5375_CR42","doi-asserted-by":"crossref","unstructured":"Misailovic S, Milicevic A, Petrovic N, Khurshid S, Marinov D (2007) Parallel test generation and execution with korat. In: Proceedings of the the 6th Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on The Foundations of Software Engineering, pp. 135\u2013144","DOI":"10.1145\/1287624.1287645"},{"key":"5375_CR43","doi-asserted-by":"publisher","unstructured":"Siddiqui JH, Khurshid S (2009) Pkorat: Parallel generation of structurally complex test inputs. In: 2009 International Conference on Software Testing Verification and Validation, pp. 250\u2013259. https:\/\/doi.org\/10.1109\/ICST.2009.48","DOI":"10.1109\/ICST.2009.48"},{"key":"5375_CR44","doi-asserted-by":"crossref","unstructured":"Fung WWL, Sham I, Yuan G, Aamodt TM (2007) Dynamic warp formation and scheduling for efficient gpu control flow. In: 40th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO 2007), pp. 407\u2013420","DOI":"10.1109\/MICRO.2007.30"},{"key":"5375_CR45","doi-asserted-by":"crossref","unstructured":"Brunie N, Collange S, Diamos G (2012) Simultaneous branch and warp interweaving for sustained gpu performance. In: 2012 39th Annual International Symposium on Computer Architecture (ISCA), pp. 49\u201360","DOI":"10.1109\/ISCA.2012.6237005"},{"issue":"3","key":"5375_CR46","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1145\/2366231.2337167","volume":"40","author":"M Rhu","year":"2012","unstructured":"Rhu M, Erez M (2012) Capri: prediction of compaction-adequacy for handling control-divergence in gpgpu architectures. ACM SIGARCH Comput Arch News 40(3):61\u201371","journal-title":"ACM SIGARCH Comput Arch News"},{"key":"5375_CR47","doi-asserted-by":"crossref","unstructured":"Rhu M, Erez M (2013) Maximizing simd resource utilization in gpgpus with simd lane permutation. In: Proceedings of the 40th Annual International Symposium on Computer Architecture. pp. 356\u2013367","DOI":"10.1145\/2485922.2485953"},{"key":"5375_CR48","doi-asserted-by":"crossref","unstructured":"Fung WWL, Aamodt TM (2011) Thread block compaction for efficient simt control flow. In: Proceedings of the 2011 IEEE 17th International Symposium on High Performance Computer Architecture. HPCA \u201911, pp. 25\u201336. IEEE Computer Society, USA","DOI":"10.1109\/HPCA.2011.5749714"},{"key":"5375_CR49","doi-asserted-by":"publisher","first-page":"684","DOI":"10.1049\/cje.2015.10.004","volume":"24","author":"B Li","year":"2015","unstructured":"Li B, Wei J, Guo W, Sun J (2015) Improving simd utilization with thread-lane shuffled compaction in gpgpu. Chin J Electron 24:684\u2013688. https:\/\/doi.org\/10.1049\/cje.2015.10.004","journal-title":"Chin J Electron"},{"issue":"2","key":"5375_CR50","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1049\/cje.2015.04.010","volume":"24","author":"H Yang","year":"2015","unstructured":"Yang H, Chen S, Wan J, Xu X (2015) Divergent branch threads compaction for efficient simd control flow. Chin J Electron 24(2):288\u2013294","journal-title":"Chin J Electron"},{"key":"5375_CR51","doi-asserted-by":"publisher","unstructured":"Narasiman V, Shebanow M, Lee CJ, Miftakhutdinov R, Mutlu O, Patt YN (2011) Improving gpu performance via large warps and two-level warp scheduling. In: Proceedings of the 44th Annual IEEE\/ACM International Symposium on Microarchitecture. MICRO-44, pp. 308\u2013317. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/2155620.2155656","DOI":"10.1145\/2155620.2155656"},{"key":"5375_CR52","doi-asserted-by":"crossref","unstructured":"Meng J, Tarjan D, Skadron K (2010) Dynamic warp subdivision for integrated branch and memory divergence tolerance. In: Proceedings of the 37th Annual International Symposium on Computer Architecture. pp. 235\u2013246","DOI":"10.1145\/1815961.1815992"},{"key":"5375_CR53","doi-asserted-by":"crossref","unstructured":"Tarjan D, Meng J, Skadron K (2009) Increasing memory miss tolerance for simd cores. In: Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis. pp. 1\u201311","DOI":"10.1145\/1654059.1654082"},{"key":"5375_CR54","unstructured":"Emmery C (2017) Euclidean vs. cosine distance. https:\/\/cmry.github.io\/notes\/euclidean-v-cosine. Accessed on 27 June 2021"},{"key":"5375_CR55","doi-asserted-by":"crossref","unstructured":"Ladd JR (2020) Understanding and using common similarity measures for text analysis. https:\/\/programminghistorian.org\/en\/lessons\/common-similarity-measures. Accessed on 11 Jul 2021","DOI":"10.46430\/phen0089"},{"key":"5375_CR56","unstructured":"Nvidia (2018) cuda-c-programming-guide. https:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/index.html#features-and-technical-specifications__technical-specifications-per-compute-capability. Accessed on 28 Jul 2018"},{"key":"5375_CR57","unstructured":"die.net (2011) clock_gettime(3); Linux man page. https:\/\/linux.die.net\/man\/3\/clock_gettime. Accessed on 16 Oct 2018"},{"key":"5375_CR58","doi-asserted-by":"publisher","unstructured":"Yang C-T, Huang C-L, Lin C-F (2011) Hybrid cuda, openmp and mpi parallel programming on multicore gpu clusters. Comput Phys Commun. 182(1):266\u2013269. https:\/\/doi.org\/10.1016\/j.cpc.2010.06.035. Computer Physics Communications Special Edition for Conference on Computational Physics Kaohsiung, Taiwan, Dec 15\u201319, 2009","DOI":"10.1016\/j.cpc.2010.06.035"},{"key":"5375_CR59","unstructured":"Harris M (2011) How to Implement Performance Metrics in CUDA C\/C++. https:\/\/devblogs.nvidia.com\/how-implement-performance-metrics-cuda-cc\/. Accessed on 16 Oct 2018"},{"key":"5375_CR60","unstructured":"NVIDIA (2012) NVIDIA CUDA C Programming Guide. https:\/\/developer.download.nvidia.com\/compute\/DevZone\/docs\/html\/C\/doc\/CUDA_C_Programming_Guide.pdf. Accessed on 26 Jan 2019"},{"key":"5375_CR61","unstructured":"Pouchet LN (2016) PolyBench\/C 3.2. http:\/\/polybench.sourceforge.net. Accessed on 14 Oct 2018"},{"key":"5375_CR62","doi-asserted-by":"crossref","unstructured":"Kalliamvakou E, Damian D, Blincoe K, Singer L, German DM (2015) Open source-style collaborative development practices in commercial projects using github. In: Proceedings of the 37th International Conference on Software Engineering: Volume 1. ICSE \u201915, pp. 574\u2013585. IEEE Press, Piscataway, NJ, USA. http:\/\/dl.acm.org\/citation.cfm?id=2818754.2818825","DOI":"10.1109\/ICSE.2015.74"},{"key":"5375_CR63","unstructured":"Quijada M (2014) image-manipulation-in-c. https:\/\/github.com\/mauryquijada\/image-manipulation-in-c.git. Accessed on 29 Jul 2018"},{"key":"5375_CR64","unstructured":"Yerburgh E (2017) c-sorting-algorithms. https:\/\/github.com\/eddyerburgh\/c-sorting-algorithms\/tree\/master\/algorithms. Accessed on 17 Aug 2019"},{"key":"5375_CR65","unstructured":"Felipe L (2018) VAR-solutions. https:\/\/github.com\/luizok\/GraphAlgorithms\/blob\/master\/graphalgs.c. Accessed on 14 Jan 2020"},{"key":"5375_CR66","unstructured":"Varshney R (2018) VAR-solutions. https:\/\/github.com\/VAR-solutions\/Algorithms\/tree\/dev\/Dynamic%20Programming. Accessed on 14 Jan 2020"},{"key":"5375_CR67","unstructured":"Corporation N (2019) Nsight Compute CLI. https:\/\/docs.nvidia.com\/nsight-compute\/NsightComputeCli\/index.html. Accessed on 4 Sep 2019"},{"key":"5375_CR68","unstructured":"NVIDIA (2018) NVIDIACUDA Toolkit Documentation. https:\/\/docs.nvidia.com\/cuda\/profiler-users-guide\/index.html#metrics-reference. Accessed on 14 Oct 2018"},{"key":"5375_CR69","unstructured":"Corporation N (2019) Nsight Compute CLI-5.3. Metric Comparison. https:\/\/docs.nvidia.com\/nsight-compute\/NsightComputeCli\/index.html#nvprof-metric-comparison. Accessed on 4 Sept 2019"},{"key":"5375_CR70","unstructured":"Family SP (2021) Sonargraph-Architect. https:\/\/www.hello2morrow.com\/products\/sonargraph\/architect9. Accessed on 16 Nov 2021"},{"key":"5375_CR71","unstructured":"Whitehead N, Fit-Florea A (2011) Precision & performance: floating point and ieee 754 compliance for nvidia gpus. rn (A+ B) 21(1):18749\u201319424"},{"key":"5375_CR72","unstructured":"NVIDIA (2017) NVIDIA TESLA V100 GPU ARCHITECTURE. https:\/\/images.nvidia.com\/content\/volta-architecture\/pdf\/volta-architecture-whitepaper.pdf. Accessed on 28 Apr 2023"},{"key":"5375_CR73","unstructured":"Repository S-aI: SIR Usage Information. https:\/\/sir.csc.ncsu.edu\/portal\/usage.php. Accessed on 3 Apr 2019"},{"key":"5375_CR74","doi-asserted-by":"publisher","unstructured":"Bagies T, Jannesari A (2021) An empirical study of parallelizing test execution using cuda unified memory and openmp gpu offloading. In: 2021 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW), pp. 271\u2013278. https:\/\/doi.org\/10.1109\/ICSTW52544.2021.00052","DOI":"10.1109\/ICSTW52544.2021.00052"},{"key":"5375_CR75","doi-asserted-by":"crossref","unstructured":"Zhang L (2018) Hybrid regression test selection. In: 2018 IEEE\/ACM 40th International Conference on Software Engineering (ICSE), pp. 199\u2013209","DOI":"10.1145\/3180155.3180198"},{"key":"5375_CR76","doi-asserted-by":"crossref","unstructured":"Marijan D, Liaaen M (2018) Practical selective regression testing with effective redundancy in interleaved tests. In: 2018 IEEE\/ACM 40th International Conference on Software Engineering: Software Engineering in Practice Track (ICSE-SEIP), pp. 153\u2013162","DOI":"10.1145\/3183519.3183532"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05375-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-023-05375-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05375-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T08:08:39Z","timestamp":1695024519000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-023-05375-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,13]]},"references-count":76,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["5375"],"URL":"https:\/\/doi.org\/10.1007\/s11227-023-05375-0","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,13]]},"assertion":[{"value":"3 May 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}