{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T02:31:41Z","timestamp":1769826701614,"version":"3.49.0"},"reference-count":41,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,2]]},"DOI":"10.1109\/hpca.2014.6835948","type":"proceedings-article","created":{"date-parts":[[2014,7,28]],"date-time":"2014-07-28T18:48:01Z","timestamp":1406573281000},"page":"380-391","source":"Crossref","is-referenced-by-count":25,"title":["DraMon: Predicting memory bandwidth usage of multi-threaded programs with high accuracy and low overhead"],"prefix":"10.1109","author":[{"given":"Wei","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tanima","family":"Dey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jack W.","family":"Davidson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mary Lou","family":"Soffa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2012.128"},{"key":"35","author":"wang","year":"2005","journal-title":"Modern dram memory systems Performance analysis and scheduling algorithm"},{"key":"17","article-title":"The openmp implementation of nas parallel benchmarks and its performance","author":"jin","year":"1999","journal-title":"Technical Report"},{"key":"36","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"18","article-title":"An analytical model to predict performance impact of dram bank partitioning","author":"kim","year":"2013","journal-title":"Memory Systems Performance and Correctness"},{"key":"33","doi-asserted-by":"crossref","DOI":"10.1145\/1508244.1508259","article-title":"Rapid MRC: Approximating l2 miss rate curves on commodity systems for online optimizations","author":"tam","year":"2009","journal-title":"Proc Int l Conf Architectural Support for Programming Languages and Operating Systems"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1145\/2038698.2038710"},{"key":"34","article-title":"Efficient FFTs on IRAM","author":"thomas","year":"1999","journal-title":"Work-Shop on Media Processors and DSPs"},{"key":"16","author":"jacob","year":"2010","journal-title":"Memory Systems Cache DRAM Disk"},{"key":"39","article-title":"Dynamic classification of program memory behaviors in cmps","author":"xie","year":"2008","journal-title":"Proc of the Workshopon Chip Multiprocessor Memory Systems and Interconnects"},{"key":"13","author":"hennessy","year":"2012","journal-title":"Computer Architecture A Quantitative Approach"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2012.173"},{"key":"37","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2011.66"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485930"},{"key":"38","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2012.139"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1145\/1810479.1810509"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1145\/2370816.2370869"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815996"},{"key":"41","article-title":"A hybrid analytical dram performance model","author":"yuan","year":"2009","journal-title":"Workshop on Modeling Benchmarking and Simulation"},{"key":"40","doi-asserted-by":"publisher","DOI":"10.1145\/1854273.1854306"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1145\/1065010.1065034"},{"key":"23","article-title":"Lmbench: Portable tools for performance analysis","author":"mcvoy","year":"1996","journal-title":"USENIX Annual Technical Conference"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2012.6168945"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451137"},{"key":"26","article-title":"Fundamental latency tradeoff in architecting DRAM caches: Outperforming impractical SRAM-tags with a simple and practical design","author":"qureshi","year":"2012","journal-title":"Int'l Symp on Microarchitecture"},{"key":"27","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555801"},{"key":"28","year":"0"},{"key":"29","article-title":"Notes on kullback-leibler divergence and likelihood theory","author":"shlens","year":"2007","journal-title":"Systems Neurobiology Laboratory"},{"key":"3","doi-asserted-by":"crossref","DOI":"10.1145\/2366231.2337207","article-title":"Staged memory scheduling: Achieving high performance and scalability in heterogeneous systems","author":"ausavarungnirun","year":"2012","journal-title":"Int'l Symp on Computer Architecture"},{"key":"2","year":"2013","journal-title":"BIOS and Kernel Developer's Guide (BKDG) for AMD Family 10h Processors"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2012.52"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1145\/1188455.1188540"},{"key":"30","article-title":"A framework for performance modeling and prediction","author":"snavely","year":"2002","journal-title":"Int'l Conf on Supercomputing"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2011.5762716"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2012.6168943"},{"key":"32","doi-asserted-by":"crossref","DOI":"10.1145\/1346281.1346317","article-title":"Feedbackdriven threading: Power-efficient and high-performance execution of multi-threaded workloads on cmps","author":"suleman","year":"2008","journal-title":"Proc Int l Conf Architectural Support for Programming Languages and Operating Systems"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2005.27"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815972"},{"key":"4","author":"bienia","year":"2011","journal-title":"Benchmarking Modern Multiprocessors"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1145\/781131.781159"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.36"}],"event":{"name":"2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA)","location":"Orlando, FL, USA","start":{"date-parts":[[2014,2,15]]},"end":{"date-parts":[[2014,2,19]]}},"container-title":["2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6823235\/6835920\/06835948.pdf?arnumber=6835948","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T14:50:59Z","timestamp":1689432659000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6835948\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,2]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/hpca.2014.6835948","relation":{},"subject":[],"published":{"date-parts":[[2014,2]]}}}