{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T07:42:32Z","timestamp":1768635752318,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,8,5]],"date-time":"2019-08-05T00:00:00Z","timestamp":1564963200000},"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":[],"published-print":{"date-parts":[[2019,8,5]]},"DOI":"10.1145\/3337821.3337907","type":"proceedings-article","created":{"date-parts":[[2019,7,25]],"date-time":"2019-07-25T12:34:36Z","timestamp":1564058076000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["HPAS"],"prefix":"10.1145","author":[{"given":"Emre","family":"Ates","sequence":"first","affiliation":[{"name":"Boston University, Dept. of Electrical and Computer Eng., Boston, MA, USA"}]},{"given":"Yijia","family":"Zhang","sequence":"additional","affiliation":[{"name":"Boston University, Dept. of Electrical and Computer Eng., Boston, MA, USA"}]},{"given":"Burak","family":"Aksar","sequence":"additional","affiliation":[{"name":"Boston University, Dept. of Electrical and Computer Eng., Boston, MA, USA"}]},{"given":"Jim","family":"Brandt","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, Albuquerque, NM, USA"}]},{"given":"Vitus J.","family":"Leung","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, Albuquerque, NM, USA"}]},{"given":"Manuel","family":"Egele","sequence":"additional","affiliation":[{"name":"Boston University, Dept. of Electrical and Computer Eng., Boston, MA, USA"}]},{"given":"Ayse K.","family":"Coskun","sequence":"additional","affiliation":[{"name":"Boston University, Dept. of Electrical and Computer Eng., Boston, MA, USA"}]}],"member":"320","published-online":{"date-parts":[[2019,8,5]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.18"},{"key":"e_1_3_2_1_2_1","unstructured":"Bob Alverson Edwin Froese Larry Kaplan and Duncan Roweth. 2012. Cray XC series network. https:\/\/www.cray.com\/sites\/default\/files\/resources\/CrayXCNetwork.pdf  Bob Alverson Edwin Froese Larry Kaplan and Duncan Roweth. 2012. Cray XC series network. https:\/\/www.cray.com\/sites\/default\/files\/resources\/CrayXCNetwork.pdf"},{"key":"e_1_3_2_1_3_1","volume-title":"Analyzing Network Health and Congestion in Dragonfly-Based Supercomputers. In IEEE International Parallel and Distributed Processing Symposium (IPDPS). 93--102","author":"Bhatele A.","unstructured":"A. Bhatele , N. Jain , Y. Livnat , V. Pascucci , and P. Bremer . 2016 . Analyzing Network Health and Congestion in Dragonfly-Based Supercomputers. In IEEE International Parallel and Distributed Processing Symposium (IPDPS). 93--102 . A. Bhatele, N.Jain, Y. Livnat, V. Pascucci, and P. Bremer. 2016. Analyzing Network Health and Congestion in Dragonfly-Based Supercomputers. In IEEE International Parallel and Distributed Processing Symposium (IPDPS). 93--102."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503247"},{"key":"e_1_3_2_1_5_1","unstructured":"D. M. Blough and Peng Liu. 2000. FIMD-MPI: a tool for injecting faults into MPI application. In IPDPS. 241--247.   D. M. Blough and Peng Liu. 2000. FIMD-MPI: a tool for injecting faults into MPI application. In IPDPS. 241--247."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1552526.1552528"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSNW.2010.5542629"},{"key":"e_1_3_2_1_8_1","volume-title":"Cisco Bug: CSCtf52095 - Manually Flushing OS Cache during load impacts server. https:\/\/quickview.cloudapps.cisco.com\/quickview\/bug\/CSCtf52095.","year":"2017","unstructured":"Cisco. 2017 . Cisco Bug: CSCtf52095 - Manually Flushing OS Cache during load impacts server. https:\/\/quickview.cloudapps.cisco.com\/quickview\/bug\/CSCtf52095. Cisco. 2017. Cisco Bug: CSCtf52095 - Manually Flushing OS Cache during load impacts server. https:\/\/quickview.cloudapps.cisco.com\/quickview\/bug\/CSCtf52095."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Brandon Cook et al. 2017. Performance Variability on Xeon Phi. In High Performance Computing. Springer International Publishing Cham 419--429.  Brandon Cook et al. 2017. Performance Variability on Xeon Phi. In High Performance Computing. Springer International Publishing Cham 419--429.","DOI":"10.1007\/978-3-319-67630-2_31"},{"key":"e_1_3_2_1_10_1","volume-title":"IEEE International Symposium on Workload Characterization (IISWC). 23--33","author":"Delimitrou C.","unstructured":"C. Delimitrou and C. Kozyrakis . 2013. iBench: Quantifying interference for datacenter applications . In IEEE International Symposium on Workload Characterization (IISWC). 23--33 . C. Delimitrou and C. Kozyrakis. 2013. iBench: Quantifying interference for datacenter applications. In IEEE International Symposium on Workload Characterization (IISWC). 23--33."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.27"},{"key":"e_1_3_2_1_12_1","volume-title":"Annual IEEE International Conference on Local Computer Networks. 538--547","author":"Evans J. J.","unstructured":"J. J. Evans , W. D. Groop , and C. S. Hood . 2003. Exploring the relationship between parallel application run-time and network performance in clusters . In Annual IEEE International Conference on Local Computer Networks. 538--547 . J. J. Evans, W. D. Groop, and C. S. Hood. 2003. Exploring the relationship between parallel application run-time and network performance in clusters. In Annual IEEE International Conference on Local Computer Networks. 538--547."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2015.31"},{"key":"e_1_3_2_1_14_1","unstructured":"Valerio Formicola et al. 2017. Understanding Fault Scenarios and Impacts through Fault Injection Experiments in Cielo. Cray User Group (2017).  Valerio Formicola et al. 2017. Understanding Fault Scenarios and Impacts through Fault Injection Experiments in Cielo. Cray User Group (2017)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2831129.2831133"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/PRDC.2013.40"},{"key":"e_1_3_2_1_17_1","volume-title":"Technical Report SAND2009-5574. Sandia National Laboratories.","author":"Heroux Michael A","year":"2009","unstructured":"Michael A Heroux 2009 . Improving Performance via Mini-applications . Technical Report SAND2009-5574. Sandia National Laboratories. Michael A Heroux et al. 2009. Improving Performance via Mini-applications. Technical Report SAND2009-5574. Sandia National Laboratories."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807644"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.12"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/2.585157"},{"key":"e_1_3_2_1_21_1","unstructured":"IEEE and The Open Group. 2018. POSIX Standard: dd. http:\/\/pubs.opengroup.org\/onlinepubs\/9699919799\/utilities\/dd.html.  IEEE and The Open Group. 2018. POSIX Standard: dd. http:\/\/pubs.opengroup.org\/onlinepubs\/9699919799\/utilities\/dd.html."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807638"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/1855511.1855515"},{"key":"e_1_3_2_1_24_1","volume-title":"Chapman & Hall\/CRC Computational Science","volume":"3","author":"Kate","unstructured":"Kate Keahey et al. 2018. Chameleon: a Scalable Production Testbed for Computer Science Research. In Contemporary High Performance Computing: From Petascale toward Exascale . Chapman & Hall\/CRC Computational Science , Vol. 3 . Chapter 5. Kate Keahey et al. 2018. Chameleon: a Scalable Production Testbed for Computer Science Research. In Contemporary High Performance Computing: From Petascale toward Exascale. Chapman & Hall\/CRC Computational Science, Vol. 3. Chapter 5."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2018.00075"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"J. Klinkenberg C. Terboven S. Lankes and M.S. M\u00fcller. 2017. Data Mining-Based Analysis of HPC Center Operations. In CLUSTER. 766--773.  J. Klinkenberg C. Terboven S. Lankes and M.S. M\u00fcller. 2017. Data Mining-Based Analysis of HPC Center Operations. In CLUSTER. 766--773.","DOI":"10.1109\/CLUSTER.2017.23"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225125"},{"key":"e_1_3_2_1_28_1","volume-title":"Kramer et al","author":"William T.","year":"2003","unstructured":"William T. C. Kramer et al . 2003 . Performance Variability of Highly Parallel Architectures. In Computational Science~ICCS 2003. 560--569. William T. C. Kramer et al. 2003. Performance Variability of Highly Parallel Architectures. In Computational Science~ICCS 2003. 560--569."},{"key":"e_1_3_2_1_29_1","volume-title":"KRIPKE-a massively parallel transport mini-app","author":"Kunen AJ","unstructured":"AJ Kunen , TS Bailey , and PN Brown . 2015. KRIPKE-a massively parallel transport mini-app . Technical Report. Lawrence Livermore National Laboratory . AJ Kunen, TS Bailey, and PN Brown. 2015. KRIPKE-a massively parallel transport mini-app. Technical Report. Lawrence Livermore National Laboratory."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"C. Kuo A. Shah A. Nomura S. Matsuoka and F. Wolf. 2014. How file access patterns influence interference among cluster applications. In CLUSTER. 185--193.  C. Kuo A. Shah A. Nomura S. Matsuoka and F. Wolf. 2014. How file access patterns influence interference among cluster applications. In CLUSTER. 185--193.","DOI":"10.1109\/CLUSTER.2014.6968743"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2009.52"},{"key":"e_1_3_2_1_32_1","unstructured":"Lawrence Livermore National Laboratory. 2018. IOR benchmark application. https:\/\/github.com\/hpc\/ior.  Lawrence Livermore National Laboratory. 2018. IOR benchmark application. https:\/\/github.com\/hpc\/ior."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3149412.3149421"},{"key":"e_1_3_2_1_34_1","volume-title":"Taming Performance Variability. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Aleksander","unstructured":"Aleksander Maricq et al. 2018 . Taming Performance Variability. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18) . 409--425. Aleksander Maricq et al. 2018. Taming Performance Variability. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). 409--425."},{"key":"e_1_3_2_1_35_1","volume-title":"Memory Bandwidth and Machine Balance in Current High Performance Computers","author":"McCalpin John D.","year":"1995","unstructured":"John D. McCalpin . 1995. Memory Bandwidth and Machine Balance in Current High Performance Computers . IEEE Computer Society Technical Committee on Computer Architecture (TCCA) Newsletter ( Dec. 1995 ), 19--25. John D. McCalpin. 1995. Memory Bandwidth and Machine Balance in Current High Performance Computers. IEEE Computer Society Technical Committee on Computer Architecture (TCCA) Newsletter (Dec. 1995), 19--25."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00021"},{"key":"e_1_3_2_1_37_1","volume-title":"2010 IEEE International Symposium on Performance Analysis of Systems Software (ISPASS). 87--96","author":"McCurdy C.","unstructured":"C. McCurdy and J. Vetter . 2010. Memphis: Finding and fixing NUMA-related performance problems on multi-core platforms . In 2010 IEEE International Symposium on Performance Analysis of Systems Software (ISPASS). 87--96 . C. McCurdy and J. Vetter. 2010. Memphis: Finding and fixing NUMA-related performance problems on multi-core platforms. In 2010 IEEE International Symposium on Performance Analysis of Systems Software (ISPASS). 87--96."},{"key":"e_1_3_2_1_39_1","volume-title":"FINJ: A Fault Injection Tool for HPC Systems. https:\/\/arxiv.org\/abs\/1807.10056. arXiv:cs.DC\/1807.10056","author":"Alessio Netti","year":"2018","unstructured":"Alessio Netti et al. 2018 . FINJ: A Fault Injection Tool for HPC Systems. https:\/\/arxiv.org\/abs\/1807.10056. arXiv:cs.DC\/1807.10056 Alessio Netti et al. 2018. FINJ: A Fault Injection Tool for HPC Systems. https:\/\/arxiv.org\/abs\/1807.10056. arXiv:cs.DC\/1807.10056"},{"key":"e_1_3_2_1_40_1","volume-title":"Panda et al","author":"Dhabaleswar","year":"2018","unstructured":"Dhabaleswar K. Panda et al . 2018 . OSU Micro-Benchmarks . http:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/. Dhabaleswar K. Panda et al. 2018. OSU Micro-Benchmarks. http:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/."},{"key":"e_1_3_2_1_41_1","volume-title":"IEEE International Conference on Dependable Systems and Networks (DSN). 472--481","author":"Pattabiraman K.","unstructured":"K. Pattabiraman , N. Nakka , Z. Kalbarczyk , and R. Iyer . 2008. SymPLFIED: Symbolic program-level fault injection and error detection framework . In IEEE International Conference on Dependable Systems and Networks (DSN). 472--481 . K. Pattabiraman, N. Nakka, Z. Kalbarczyk, and R. Iyer. 2008. SymPLFIED: Symbolic program-level fault injection and error detection framework. In IEEE International Conference on Dependable Systems and Networks (DSN). 472--481."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018767"},{"key":"e_1_3_2_1_43_1","unstructured":"M Schulz et al. 2014. Performance analysis techniques for the exascale co-design process. Advances in Parallel Computing 25 (01 2014) 19--32.  M Schulz et al. 2014. Performance analysis techniques for the exascale co-design process. Advances in Parallel Computing 25 (01 2014) 19--32."},{"key":"e_1_3_2_1_44_1","volume-title":"SW4 final report for iCOE","author":"Sjogreen Bjorn","unstructured":"Bjorn Sjogreen . 2018. SW4 final report for iCOE . Technical Report. Lawrence Livermore National Laboratory (LLNL), Livermore, CA. Bjorn Sjogreen. 2018. SW4 final report for iCOE. Technical Report. Lawrence Livermore National Laboratory (LLNL), Livermore, CA."},{"key":"e_1_3_2_1_45_1","volume-title":"IEEE Workload Characterization Symposium. 137--149","author":"Skinner D.","unstructured":"D. Skinner and W. Kramer . 2005. Understanding the causes of performance variability in HPC workloads . In IEEE Workload Characterization Symposium. 137--149 . D. Skinner and W. Kramer. 2005. Understanding the causes of performance variability in HPC workloads. In IEEE Workload Characterization Symposium. 137--149."},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings IEEE International Computer Performance and Dependability Symposium. 91--100","author":"Stott D. T.","unstructured":"D. T. Stott , B. Floering , D. Burke , Z. Kalbarczpk , and R. K. Iyer . 2000. NFTAPE: a framework for assessing dependability in distributed systems with lightweight fault injectors . In Proceedings IEEE International Computer Performance and Dependability Symposium. 91--100 . D. T. Stott, B. Floering, D. Burke, Z. Kalbarczpk, and R. K. Iyer. 2000. NFTAPE: a framework for assessing dependability in distributed systems with lightweight fault injectors. In Proceedings IEEE International Computer Performance and Dependability Symposium. 91--100."},{"key":"e_1_3_2_1_47_1","volume-title":"Tools for High Performance Computing","author":"Terpstra Dan","year":"2009","unstructured":"Dan Terpstra , Heike Jagode , Haihang You , and Jack Dongarra . 2010. Collecting Performance Data with PAPI-C . In Tools for High Performance Computing 2009 . 157--173. Dan Terpstra, Heike Jagode, Haihang You, and Jack Dongarra. 2010. Collecting Performance Data with PAPI-C. In Tools for High Performance Computing 2009. 157--173."},{"key":"e_1_3_2_1_48_1","unstructured":"The MIMD Lattice Computation (MILC) Collaboration. 2016. MILC benchmark application. http:\/\/www.physics.utah.edu\/~detar\/milc\/.  The MIMD Lattice Computation (MILC) Collaboration. 2016. MILC benchmark application. http:\/\/www.physics.utah.edu\/~detar\/milc\/."},{"key":"e_1_3_2_1_49_1","volume-title":"International Supercomputing Conference (ISC-HPC). 355--373","author":"Ozan","unstructured":"Ozan Tuncer et al. 2017. Diagnosing Performance Variations in HPC Applications using Machine Learning . In International Supercomputing Conference (ISC-HPC). 355--373 . Ozan Tuncer et al. 2017. Diagnosing Performance Variations in HPC Applications using Machine Learning. In International Supercomputing Conference (ISC-HPC). 355--373."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2870403"},{"key":"e_1_3_2_1_51_1","volume-title":"Tangram: Colocating HPC Applications with Oversubscription. In IEEE High Performance Extreme Computing Conference. 1--7.","author":"Xiong Qingqing","year":"2018","unstructured":"Qingqing Xiong , Emre Ates , Martin C. Herbordt , and Ayse Kivilcim Coskun . 2018 . Tangram: Colocating HPC Applications with Oversubscription. In IEEE High Performance Extreme Computing Conference. 1--7. Qingqing Xiong, Emre Ates, Martin C. Herbordt, and Ayse Kivilcim Coskun. 2018. Tangram: Colocating HPC Applications with Oversubscription. In IEEE High Performance Extreme Computing Conference. 1--7."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-009-0369-3"}],"event":{"name":"ICPP 2019: 48th International Conference on Parallel Processing","location":"Kyoto Japan","acronym":"ICPP 2019","sponsor":["University of Tsukuba University of Tsukuba"]},"container-title":["Proceedings of the 48th International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3337821.3337907","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3337821.3337907","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:25:42Z","timestamp":1750206342000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3337821.3337907"}},"subtitle":["An HPC Performance Anomaly Suite for Reproducing Performance Variations"],"short-title":[],"issued":{"date-parts":[[2019,8,5]]},"references-count":51,"alternative-id":["10.1145\/3337821.3337907","10.1145\/3337821"],"URL":"https:\/\/doi.org\/10.1145\/3337821.3337907","relation":{},"subject":[],"published":{"date-parts":[[2019,8,5]]},"assertion":[{"value":"2019-08-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}