{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T16:26:01Z","timestamp":1790699161984,"version":"4.1.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2020,11,2]],"date-time":"2020-11-02T00:00:00Z","timestamp":1604275200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,11,2]],"date-time":"2020-11-02T00:00:00Z","timestamp":1604275200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1007\/s11227-020-03483-9","type":"journal-article","created":{"date-parts":[[2020,11,2]],"date-time":"2020-11-02T10:21:46Z","timestamp":1604312506000},"page":"5120-5147","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["SDAM: a combined stack distance-analytical modeling approach to estimate memory performance in GPUs"],"prefix":"10.1007","volume":"77","author":[{"given":"Mohsen","family":"Kiani","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amir","family":"Rajabzadeh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,2]]},"reference":[{"key":"3483_CR1","doi-asserted-by":"crossref","unstructured":"Aji AM, Daga M, Feng WC (2011) Bounding the effect of partition camping in GPU kernels. In: Proceedings of the 8th ACM International Conference on Computing Frontiers. ACM, pp 1\u201310","DOI":"10.1145\/2016604.2016637"},{"key":"3483_CR2","doi-asserted-by":"crossref","unstructured":"Arafa Y, Badawy AH, Chennupati G, Barai A, Santhi N, Eidenbenz, S (2020) Fast, accurate, and scalable memory modeling of GPGPUS using reuse profiles. In: Proceedings of the 34th ACM International Conference on Supercomputing, pp 1\u201312","DOI":"10.1145\/3392717.3392761"},{"issue":"1","key":"3483_CR3","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/LCA.2019.2904497","volume":"18","author":"Y Arafa","year":"2019","unstructured":"Arafa Y, Badawy AHA, Chennupati G, Santhi N, Eidenbenz S (2019) PPT-GPU: scalable GPU performance modeling. IEEE Comput Archit Lett 18(1):55\u201358","journal-title":"IEEE Comput Archit Lett"},{"key":"3483_CR4","unstructured":"Badr MJ (2020) New tools for evaluating parallel and heterogeneous architectures. Ph.D. thesis"},{"key":"3483_CR5","unstructured":"Baghsorkhi SS, Delahaye M, Gropp WD, Wen-mei WH (2009) Analytical performance prediction for evaluation and tuning of GPGPU applications. In: Workshop on EPHAM2009, in Conjunction with CGO, Citeseer, pp 1\u201310"},{"key":"3483_CR6","doi-asserted-by":"crossref","unstructured":"Bakhoda A, Yuan GL, Fung WW, Wong H, Aamodt TM (2009) Analyzing CUDA workloads using a detailed GPU simulator. In: IEEE International Symposium on Performance Analysis of Systems and Software, 2009 (ISPASS 2009). IEEE, pp 163\u2013174","DOI":"10.1109\/ISPASS.2009.4919648"},{"issue":"4","key":"3483_CR7","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1109\/MM.2015.72","volume":"35","author":"E Bolotin","year":"2015","unstructured":"Bolotin E, Nellans D, Villa O, O\u2019Connor M, Ramirez A, Keckler SW (2015) Designing efficient heterogeneous memory architectures. IEEE Micro 35(4):60\u201368. https:\/\/doi.org\/10.1109\/MM.2015.72","journal-title":"IEEE Micro"},{"key":"3483_CR8","doi-asserted-by":"crossref","unstructured":"Che S, Boyer M, Meng J, Tarjan D, Sheaffer JW, Lee SH, Skadron K (2009) Rodinia: a benchmark suite for heterogeneous computing. In: IEEE International Symposium on Workload Characterization, 2009 (IISWC 2009). IEEE, pp 44\u201354","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"3483_CR9","doi-asserted-by":"crossref","unstructured":"Diamos GF, Kerr AR, Yalamanchili S, Clark N (2010) Ocelot: a dynamic optimization framework for bulk-synchronous applications in heterogeneous systems. In: Proceedings of the 19th International Conference on Parallel Architectures and Compilation Techniques. ACM, pp 353\u2013364","DOI":"10.1145\/1854273.1854318"},{"key":"3483_CR10","unstructured":"Hartstein A, Srinivasan V, Puzak TR, Emma PG (2006) Cache miss behavior: Is it sqrt(2)? In: Proceedings of the 3rd Conference on Computing Frontiers. ACM, pp 313\u2013320"},{"key":"3483_CR11","doi-asserted-by":"crossref","unstructured":"Hong S, Kim H (2009) An analytical model for a GPU architecture with memory-level and thread-level parallelism awareness. In: Proceedings of the 36th Annual International Symposium on Computer Architecture (ISCA\u201909). ACM, New York, NY, USA, pp 152\u2013163","DOI":"10.1145\/1555754.1555775"},{"key":"3483_CR12","doi-asserted-by":"crossref","unstructured":"Huang JC, Lee JH, Kim H, Lee HHS (2014) Gpumech: GPU performance modeling technique based on interval analysis. In: Proceedings of the 47th Annual IEEE\/ACM International Symposium on Microarchitecture. IEEE Computer Society, pp 268\u2013279","DOI":"10.1109\/MICRO.2014.59"},{"key":"3483_CR13","doi-asserted-by":"crossref","unstructured":"Huang Y, Li D (2017) Performance modeling for optimal data placement on GPU with heterogeneous memory systems. In: 2017 IEEE International Conference on Cluster Computing (CLUSTER). IEEE, pp 166\u2013177","DOI":"10.1109\/CLUSTER.2017.42"},{"issue":"2","key":"3483_CR14","doi-asserted-by":"publisher","first-page":"35:1","DOI":"10.1145\/3224430","volume":"2","author":"A Jain","year":"2018","unstructured":"Jain A, Khairy M, Rogers TG (2018) A quantitative evaluation of contemporary GPU simulation methodology. Proc ACM Meas Anal Comput Syst 2(2):35:1\u201335:28. https:\/\/doi.org\/10.1145\/3224430","journal-title":"Proc ACM Meas Anal Comput Syst"},{"issue":"1","key":"3483_CR15","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1109\/TPDS.2010.107","volume":"22","author":"B Jang","year":"2011","unstructured":"Jang B, Schaa D, Mistry P, Kaeli D (2011) Exploiting memory access patterns to improve memory performance in data-parallel architectures. IEEE Trans Parallel Distrib Syst 22(1):105\u2013118","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"8","key":"3483_CR16","doi-asserted-by":"publisher","first-page":"2900","DOI":"10.1007\/s11227-014-1338-z","volume":"71","author":"A Karami","year":"2015","unstructured":"Karami A, Khunjush F, Mirsoleimani SA (2015) A statistical performance analyzer framework for opencl kernels on NVIDIA GPUS. J Supercomput 71(8):2900\u20132921","journal-title":"J Supercomput"},{"key":"3483_CR17","doi-asserted-by":"crossref","unstructured":"Kerr A, Diamos G, Yalamanchili S (2010) Modeling GPU-CPU workloads and systems. In: Proceedings of the 3rd Workshop on General-Purpose Computation on Graphics Processing Units, pp 31\u201342","DOI":"10.1145\/1735688.1735696"},{"key":"3483_CR18","unstructured":"Khairy M, Akshay J, Aamodt T, Rogers TG (2018) Exploring modern GPU memory system design challenges through accurate modeling. arXiv preprint arXiv:1810.07269"},{"issue":"6","key":"3483_CR19","doi-asserted-by":"publisher","first-page":"1740","DOI":"10.1109\/TPDS.2016.2627560","volume":"28","author":"M Khairy","year":"2017","unstructured":"Khairy M, Zahran M, Wassal A (2017) Sacat: streaming-aware conflict-avoiding thrashing-resistant GPGPU cache management scheme. IEEE Trans Parallel Distrib Syst 28(6):1740\u20131753. https:\/\/doi.org\/10.1109\/TPDS.2016.2627560","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"3483_CR20","doi-asserted-by":"publisher","unstructured":"Kharbutli M, Irwin K, Solihin Y, Lee J (2004) Using prime numbers for cache indexing to eliminate conflict misses. In: Proceedings of the 10th International Symposium on High Performance Computer Architecture (HPCA\u201904). IEEE Computer Society, Washington, DC, USA, pp 288\u2013299. https:\/\/doi.org\/10.1109\/HPCA.2004.10015","DOI":"10.1109\/HPCA.2004.10015"},{"key":"3483_CR21","doi-asserted-by":"publisher","unstructured":"Kiani M, Rajabzadeh A (2017) Skerd: reuse distance analysis for simultaneous multiple GPU kernel executions. In: 2017 19th International Symposium on Computer Architecture and Digital Systems (CADS), pp 1\u20136. https:\/\/doi.org\/10.1109\/CADS.2017.8310677","DOI":"10.1109\/CADS.2017.8310677"},{"key":"3483_CR22","doi-asserted-by":"publisher","unstructured":"Kiani M, Rajabzadeh A (2017) Vlag: a very fast locality approximation model for GPU kernels with regular access patterns. In: 2017 7th International Conference on Computer and Knowledge Engineering (ICCKE), pp 260\u2013265. https:\/\/doi.org\/10.1109\/ICCKE.2017.8167887","DOI":"10.1109\/ICCKE.2017.8167887"},{"issue":"4","key":"3483_CR23","doi-asserted-by":"publisher","first-page":"58:1","DOI":"10.1145\/3291051","volume":"15","author":"M Kiani","year":"2018","unstructured":"Kiani M, Rajabzadeh A (2018) Efficient cache performance modeling in GPUS using reuse distance analysis. ACM Trans Archit Code Optim 15(4):58:1\u201358:24. https:\/\/doi.org\/10.1145\/3291051","journal-title":"ACM Trans Archit Code Optim"},{"key":"3483_CR24","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1016\/j.simpat.2018.12.003","volume":"91","author":"M Kiani","year":"2019","unstructured":"Kiani M, Rajabzadeh A (2019) Analyzing data locality in GPU kernels using memory footprint analysis. Simul Model Pract Theory 91:102\u2013122. https:\/\/doi.org\/10.1016\/j.simpat.2018.12.003","journal-title":"Simul Model Pract Theory"},{"issue":"2","key":"3483_CR25","doi-asserted-by":"publisher","first-page":"421","DOI":"10.31577\/cai_2019_2_421","volume":"38","author":"M Kiani","year":"2019","unstructured":"Kiani M, Rajabzadeh A (2019) Rdgc: a reuse distance-based approach to GPU cache performance analysis. Comput Inform 38(2):421\u2013453","journal-title":"Comput Inform"},{"issue":"14","key":"3483_CR26","doi-asserted-by":"publisher","first-page":"1950245,1","DOI":"10.1142\/S0218126619502451","volume":"28","author":"M Kiani","year":"2019","unstructured":"Kiani M, Rajabzadeh A (2019) Rdmke: applying reuse distance analysis to multiple GPU kernel executions. J Circuits Syst Comput 28(14):1950245,1\u20131950245,26","journal-title":"J Circuits Syst Comput"},{"issue":"2","key":"3483_CR27","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1147\/sj.92.0078","volume":"9","author":"RL Mattson","year":"1970","unstructured":"Mattson RL, Gecsei J, Slutz DR, Traiger IL (1970) Evaluation techniques for storage hierarchies. IBM Syst J 9(2):78\u2013117. https:\/\/doi.org\/10.1147\/sj.92.0078","journal-title":"IBM Syst J"},{"issue":"08","key":"3483_CR28","doi-asserted-by":"publisher","first-page":"1430002,1","DOI":"10.1142\/S0218126614300025","volume":"23","author":"S Mittal","year":"2014","unstructured":"Mittal S (2014) A survey of techniques for managing and leveraging caches in GPUS. J Circuits Syst Comput 23(08):1430002,1\u20131430002,15","journal-title":"J Circuits Syst Comput"},{"key":"3483_CR29","doi-asserted-by":"crossref","unstructured":"Nugteren C, van\u00a0den Braak GJ, Corporaal H, Bal H (2014) A detailed GPU cache model based on reuse distance theory. In: 2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA). IEEE, pp 37\u201348","DOI":"10.1109\/HPCA.2014.6835955"},{"key":"3483_CR30","unstructured":"NVIDIA: Cuda best practice (2017) http:\/\/docs.nvidia.com\/cuda\/cuda-c-best-practices-guide\/#axzz4ZymoX69i\/. Accessed 12 Jan 2017"},{"key":"3483_CR31","unstructured":"NVIDIA: Maxwell tuning guide (2017). http:\/\/docs.nvidia.com\/cuda\/maxwell-tuning-guide\/#axzz4ZymoX69i\/. Accessed 18 Feb 2017"},{"key":"3483_CR32","unstructured":"NVIDIA: Nvprof pforiler (2017). http:\/\/docs.nvidia.com\/cuda\/profiler-users-guide\/#nvprof-overview\/. Accessed 12 Feb 2017"},{"key":"3483_CR33","doi-asserted-by":"publisher","unstructured":"Parakh AK, Balakrishnan M, Paul K (2012) Performance estimation of GPUS with cache. In: 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops PhD Forum, pp 2384\u20132393. https:\/\/doi.org\/10.1109\/IPDPSW.2012.328","DOI":"10.1109\/IPDPSW.2012.328"},{"key":"3483_CR34","unstructured":"Pouchet LN (2012) Polybench: the polyhedral benchmark suite. http:\/\/www. cs. ucla. edu\/pouchet\/software\/polybench"},{"issue":"2","key":"3483_CR35","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1007\/s10586-019-03011-2","volume":"23","author":"MH Shafiabadi","year":"2020","unstructured":"Shafiabadi MH, Pedram H, Reshadi M, Reza A (2020) Comprehensive regression-based model to predict performance of general-purpose graphics processing unit. Clust Comput 23(2):1505\u20131516","journal-title":"Clust Comput"},{"key":"3483_CR36","doi-asserted-by":"crossref","unstructured":"Sim J, Dasgupta A, Kim H, Vuduc R (2012) A performance analysis framework for identifying potential benefits in GPGPU applications. In: Proceedings of the 17th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP\u201912). ACM, New York, NY, USA, pp 11\u201322","DOI":"10.1145\/2145816.2145819"},{"key":"3483_CR37","unstructured":"Singh JP, Stone HS, Thiebaut DF (1988) An analytical model for fully associative cache memories. IBM TJ Watson Research Center"},{"key":"3483_CR38","unstructured":"Supercomputer T (2019) Top500 june 2019 list"},{"key":"3483_CR39","doi-asserted-by":"crossref","unstructured":"Tang T, Yang X, Lin Y (2011) Cache miss analysis for GPU programs based on stack distance profile. In: 2011 31st International Conference on Distributed Computing Systems (ICDCS). IEEE, pp 623\u2013634","DOI":"10.1109\/ICDCS.2011.16"},{"key":"3483_CR40","doi-asserted-by":"publisher","unstructured":"Vijaykumar N, Pekhimenko G, Jog A, Bhowmick A, Ausavarungnirun R, Das C, Kandemir M, Mowry TC, Mutlu O (2015) A case for core-assisted bottleneck acceleration in GPUS: enabling flexible data compression with assist warps. In: Proceedings of the 42nd Annual International Symposium on Computer Architecture (ISCA\u201915). ACM, New York, NY, USA, pp 41\u201353. https:\/\/doi.org\/10.1145\/2749469.2750399","DOI":"10.1145\/2749469.2750399"},{"key":"3483_CR41","doi-asserted-by":"crossref","unstructured":"Villa O, Stephenson M, Nellans D, Keckler SW (2019) Nvbit: a dynamic binary instrumentation framework for NVIDIA GPUS. In: Proceedings of the 52nd Annual IEEE\/ACM International Symposium on Microarchitecture, pp 372\u2013383","DOI":"10.1145\/3352460.3358307"},{"key":"3483_CR42","doi-asserted-by":"crossref","unstructured":"Wang D, Xiao W (2016) A reuse distance based performance analysis on GPU L1 data cache. In: 2016 IEEE 35th International Performance Computing and Communications Conference (IPCCC). IEEE, pp 1\u20138","DOI":"10.1109\/PCCC.2016.7820638"},{"issue":"12","key":"3483_CR43","doi-asserted-by":"publisher","first-page":"2865","DOI":"10.1109\/TPDS.2020.3004623","volume":"31","author":"Q Wang","year":"2020","unstructured":"Wang Q, Chu X (2020) GPGPU performance estimation with core and memory frequency scaling. IEEE Trans Parallel Distrib Syst 31(12):2865\u20132881","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"6","key":"3483_CR44","doi-asserted-by":"publisher","first-page":"20:1","DOI":"10.1145\/1552309.1552310","volume":"31","author":"Y Zhong","year":"2009","unstructured":"Zhong Y, Shen X, Ding C (2009) Program locality analysis using reuse distance. ACM Trans Program Lang Syst 31(6):20:1\u201320:39. https:\/\/doi.org\/10.1145\/1552309.1552310","journal-title":"ACM Trans Program Lang Syst"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03483-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-020-03483-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03483-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,26]],"date-time":"2021-03-26T17:26:18Z","timestamp":1616779578000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-020-03483-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,2]]},"references-count":44,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2021,5]]}},"alternative-id":["3483"],"URL":"https:\/\/doi.org\/10.1007\/s11227-020-03483-9","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,2]]},"assertion":[{"value":"21 October 2020","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 November 2020","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}