{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:45:48Z","timestamp":1772725548147,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":84,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,6,11]],"date-time":"2020-06-11T00:00:00Z","timestamp":1591833600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2016M3C4A7952587"],"award-info":[{"award-number":["NRF-2016M3C4A7952587"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BK21 Plus program for Pioneers in Innovative Computing","award":["21A20151113068"],"award-info":[{"award-number":["21A20151113068"]}]},{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","award":["2018-0-00581"],"award-info":[{"award-number":["2018-0-00581"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014718","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1750503"],"award-info":[{"award-number":["1750503"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,6,11]]},"DOI":"10.1145\/3385412.3386033","type":"proceedings-article","created":{"date-parts":[[2020,6,7]],"date-time":"2020-06-07T01:40:10Z","timestamp":1591494010000},"page":"989-1004","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":29,"title":["Compiler-directed soft error resilience for lightweight GPU register file protection"],"prefix":"10.1145","author":[{"given":"Hongjune","family":"Kim","sequence":"first","affiliation":[{"name":"Seoul National University, South Korea"}]},{"given":"Jianping","family":"Zeng","sequence":"additional","affiliation":[{"name":"Purdue University, USA"}]},{"given":"Qingrui","family":"Liu","sequence":"additional","affiliation":[{"name":"Annapurna Labs, USA"}]},{"given":"Mohammad","family":"Abdel-Majeed","sequence":"additional","affiliation":[{"name":"University of Jordan, Jordan"}]},{"given":"Jaejin","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University, South Korea"}]},{"given":"Changhee","family":"Jung","sequence":"additional","affiliation":[{"name":"Purdue University, USA"}]}],"member":"320","published-online":{"date-parts":[[2020,6,11]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2017."},{"key":"e_1_3_2_1_2_1","unstructured":"NVIDIA Tesla V100 GPU Architecture. Technical Report. Nvidia."},{"key":"e_1_3_2_1_3_1","unstructured":"Gene M Amdahl. 2013."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2013.266"},{"key":"e_1_3_2_1_5_1","volume-title":"Henry Wong, and Tor M Aamodt.","author":"Bakhoda Ali","year":"2009","unstructured":"Ali Bakhoda, George L Yuan, Wilson WL Fung, Henry Wong, and Tor M Aamodt. 2009. Analyzing CUDA workloads using a detailed GP U simulator. In ISPASS\u201909."},{"key":"e_1_3_2_1_6_1","unstructured":"Rajeev Balasubramonian Sandhya Dwarkadas and David H Albonesi. 2001. Reducing the complexity of the register file in dynamic superscalar processors. In MICRO 34."},{"key":"e_1_3_2_1_7_1","volume-title":"Exascale Computer-a fact or a fiction. Keynote address: IEEE International Parallel and Distributed Processing Symposium","author":"Borkar Shekhar","year":"2013","unstructured":"Shekhar Borkar. 2013. Exascale Computer-a fact or a fiction. Keynote address: IEEE International Parallel and Distributed Processing Symposium (2013)."},{"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","unstructured":"Jongouk Choi Hyunwoo Joe Yongjoo Kim and Changhee Jung. 2019."},{"key":"e_1_3_2_1_10_1","volume-title":"2019 IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS). IEEE, 331\u2013344","author":"Achieving","unstructured":"Achieving stagnation-free intermittent computation with boundaryfree adaptive execution. In 2019 IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS). IEEE, 331\u2013344."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358279"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Cristian Constantinescu. 2003. Trends and Challenges in VLSI Circuit Reliability. In MICRO 36.","DOI":"10.1109\/MM.2003.1225959"},{"key":"e_1_3_2_1_13_1","unstructured":"W.J. Cook W.H. Cunningham W.R. Pulleyblank and A. Schrijver. 2011."},{"key":"e_1_3_2_1_14_1","unstructured":"Combinatorial Optimization. Wiley."},{"key":"e_1_3_2_1_15_1","unstructured":"Thomas H. Cormen Charles E. Leiserson Ronald L. Rivest and Clifford Stein. 2009."},{"key":"e_1_3_2_1_16_1","unstructured":"Introduction to Algorithms Third Edition (3rd ed.). The MIT Press."},{"key":"e_1_3_2_1_17_1","unstructured":"Marc de Kruijf Shuou Nomura and Karthikeyan Sankaralingam. 2010."},{"key":"e_1_3_2_1_18_1","unstructured":"Relax: An Architectural Framework for Software Recovery of Hardware Faults. In ISCA\u201910."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Marc de Kruijf and Karthikeyan Sankaralingam. 2013. Idempotent code generation: Implementation analysis and evaluation.. In CGO\u201913.","DOI":"10.1109\/CGO.2013.6495002"},{"key":"e_1_3_2_1_20_1","unstructured":"Marc A. De Kruijf. 2012."},{"key":"e_1_3_2_1_21_1","unstructured":"Compiler Construction of Idempotent Regions and Applications in Architecture Design. Ph.D. Dissertation. Madison WI USA. Advisor(s) Sankaralingam Karthikeyan."},{"key":"e_1_3_2_1_22_1","unstructured":"Marc A. de Kruijf Karthikeyan Sankaralingam and Somesh Jha. 2012."},{"key":"e_1_3_2_1_23_1","volume-title":"Analysis and Compiler Design for Idempotent Processing. In PLDI","author":"Static","year":"2012","unstructured":"Static Analysis and Compiler Design for Idempotent Processing. In PLDI 2012."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2003.1191529"},{"key":"e_1_3_2_1_25_1","first-page":"1931","volume":"38","author":"Egerv\u00e1ry Jeno","year":"1931","unstructured":"Jeno Egerv\u00e1ry. 1931. Matrixok kombinatorius tulajdons\u00e1gair\u00f3l. Matematikai \u00e9s Fizikai Lapok 38, 1931 (1931), 16\u201328.","journal-title":"Fizikai Lapok"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Hadi Esmaeilzadeh Emily Blem Renee St. Amant Karthikeyan Sankaralingam and Doug Burger. 2011. Dark Silicon and the End of Multicore Scaling. In ISCA\u201911.","DOI":"10.1145\/2000064.2000108"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"B. Fang K. Pattabiraman M. Ripeanu and S. Gurumurthi. 2014. GP UQin: A methodology for evaluating the error resilience of GPGP U applications. In ISPASS\u201914. IEEE.","DOI":"10.1109\/ISPASS.2014.6844486"},{"key":"e_1_3_2_1_28_1","volume-title":"A systematic methodology for evaluating the error resilience of GPGP U applications","author":"Fang Bo","year":"2016","unstructured":"Bo Fang, Karthik Pattabiraman, Matei Ripeanu, and Sudhanva Gurumurthi. 2016. A systematic methodology for evaluating the error resilience of GPGP U applications. IEEE Transactions on Parallel and Distributed Systems 27, 12 (2016), 3397\u20133411."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Shuguang Feng Shantanu Gupta Amin Ansari Scott A Mahlke and David I August. 2011. Encore: low-cost fine-grained transient fault recovery. In MICRO 44.","DOI":"10.1145\/2155620.2155667"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the conference on Design, Automation and Test in Europe. 341","author":"Gomez L Bautista","year":"2014","unstructured":"L Bautista Gomez, Franck Cappello, Luigi Carro, Nathan DeBardeleben, Bo Fang, Sudhanva Gurumurthi, Karthik Pattabiraman, Paolo Rech, and M Sonza Reorda. 2014. GPGP Us: how to combine high computational power with high reliability. In Proceedings of the conference on Design, Automation and Test in Europe. 341."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Nikos Hardavellas Michael Ferdman Babak Falsafi and Anastasia Ailamaki. 2011. Toward Dark Silicon in Servers. In MICRO 31.","DOI":"10.1109\/MM.2011.77"},{"key":"e_1_3_2_1_32_1","volume-title":"Reliable Onchip Systems in the Nano-era: Lessons Learnt and Future Trends. In DAC","author":"Henkel J\u00f6rg","year":"2013","unstructured":"J\u00f6rg Henkel, Lars Bauer, Nikil Dutt, Puneet Gupta, Sani Nassif, Muhammad Shafique, Mehdi Tahoori, and Norbert Wehn. 2013. Reliable Onchip Systems in the Nano-era: Lessons Learnt and Future Trends. In DAC 2013."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Himanshu Kaul Mark Anders Steven Hsu Amit Agarwal Ram Krishnamurthy and Shekhar Borkar. 2012. Near-Threshold Voltage (NTV) Design: Opportunities and Challenges. In DAC\u201912.","DOI":"10.1145\/2228360.2228572"},{"key":"e_1_3_2_1_34_1","unstructured":"Seon Wook Kim Chong-Liang Ooi Rudolf Eigenmann Babak Falsafi and T. N. Vijaykumar. 2006."},{"key":"e_1_3_2_1_35_1","unstructured":"Exploiting Reference Idempotency to Reduce Speculative Storage Overflow. In TOPLAS\u201906."},{"key":"e_1_3_2_1_36_1","unstructured":"Den\u00e9s Konig. 1931. Gr\u00e1fok \u00e9s m\u00e1trixok. Matematikai \u00e9s Fizikai Lapok."},{"key":"e_1_3_2_1_37_1","unstructured":"Lingbo Kou. 2014."},{"key":"e_1_3_2_1_38_1","unstructured":"Impact of Process Variations on Soft Error Sensitivity of 32-nm VLSI Circuits in Near-threshold Region. Master\u2019s thesis."},{"key":"e_1_3_2_1_39_1","volume-title":"Nam Sung Kim, Tor M. Aamodt, and Vijay Janapa Reddi.","author":"Leng Jingwen","year":"2013","unstructured":"Jingwen Leng, Tayler H. Hetherington, Ahmed ElTantawy, Syed Zohaib Gilani, Nam Sung Kim, Tor M. Aamodt, and Vijay Janapa Reddi. 2013."},{"key":"e_1_3_2_1_40_1","unstructured":"GP UWattch: enabling energy optimizations in GPGP Us. In ISCA\u201913."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Jingwen Leng Yazhou Zu and Vijay Janapa Reddi. 2015. GP U voltage noise: Characterization and hierarchical smoothing of spatial and temporal voltage noise interference in GP U architectures. In HPCA\u201915.","DOI":"10.1109\/HPCA.2015.7056030"},{"key":"e_1_3_2_1_42_1","unstructured":"Guanpeng Li Karthik Pattabiraman Chen-Yong Cher and Pradip Bose. 2016. Understanding Error Propagation in GPGP U Applications. In SC\u201916."},{"key":"e_1_3_2_1_43_1","volume-title":"Michael L Scott, Sam H Noh, and Changhee Jung.","author":"Liu Qingrui","year":"2018","unstructured":"Qingrui Liu, Joseph Izraelevitz, Se Kwon Lee, Michael L Scott, Sam H Noh, and Changhee Jung. 2018. iDO: Compiler-Directed Failure Atomicity for Nonvolatile Memory. In MICRO 51."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/NVMSA.2016.7547183"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2670529.2754959"},{"key":"e_1_3_2_1_46_1","unstructured":"Qingrui Liu Changhee Jung Dongyoon Lee and Devesh Tiwari. 2016."},{"key":"e_1_3_2_1_47_1","unstructured":"Compiler-Directed Lightweight Checkpointing for Fine-Grained Guaranteed Soft Error Recovery. In SC\u201916."},{"key":"e_1_3_2_1_48_1","unstructured":"Qingrui Liu Changhee Jung Dongyoon Lee and Devesh Tiwari. 2016."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"crossref","unstructured":"Compiler Directed Soft Error Detection and Recovery to Avoid DUE and SDC via Tail-DMR. TECS\u201916 (2016).","DOI":"10.1145\/2930667"},{"key":"e_1_3_2_1_50_1","unstructured":"Qingrui Liu Changhee Jung Dongyoon Lee and Devesh Tiwari. 2016."},{"key":"e_1_3_2_1_51_1","unstructured":"Low-Cost Soft Error Resilience with Unified Data Verification and Fine-Grained Recovery. In MICRO 49."},{"key":"e_1_3_2_1_52_1","volume-title":"Schlansker","author":"Mahlke Scott A.","year":"1992","unstructured":"Scott A. Mahlke, William Y. Chen, Wen-mei W. Hwu, B. Ramakrishna Rau, and Michael S. Schlansker. 1992. Sentinel Scheduling for VLIW and Superscalar Processors. In ASPLOS V."},{"key":"e_1_3_2_1_53_1","unstructured":"Gokhan Memik Masud H Chowdhury Arindam Mallik and Yehea I Ismail. 2005. Engineering over-clocking: Reliability-performance tradeoffs for high-performance register files. In DSN\u201905."},{"key":"e_1_3_2_1_54_1","unstructured":"Gokhan Memik Mahmut T. Kandemir and Ozcan Ozturk. 2005. Increasing Register File Immunity to Transient Errors. In DATE."},{"key":"e_1_3_2_1_55_1","volume-title":"Marc De Kruijf, and Karthikeyan Sankaralingam","author":"Menon Jaikrishnan","year":"2012","unstructured":"Jaikrishnan Menon, Marc De Kruijf, and Karthikeyan Sankaralingam. 2012. iGP U: Exception Support and Speculative Execution on GP Us. In ISCA\u201912."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"crossref","unstructured":"Pablo Montesinos Wei Liu and Josep Torrellas. 2007. Using register lifetime predictions to protect register files against soft errors. In DSN\u201907.","DOI":"10.1109\/DSN.2007.99"},{"key":"e_1_3_2_1_57_1","unstructured":"Todd K Moon. 2005."},{"key":"e_1_3_2_1_58_1","volume-title":"mathematical methods and algorithms","author":"Error","year":"2020","unstructured":"Error correction coding: mathematical methods and algorithms. John Wiley & Sons. PLDI \u201920, June 15\u201320, 2020, London, UK H. Kim, J. Zeng, Q. Liu, M. Abdel-Majeed, J. Lee, and C. Jung"},{"key":"e_1_3_2_1_59_1","unstructured":"S.S. Muchnick. 1997."},{"key":"e_1_3_2_1_60_1","unstructured":"Advanced Compiler Design and Implementation. Morgan Kaufmann Publishers."},{"key":"e_1_3_2_1_61_1","volume-title":"MICRO 51","author":"Nie Bin","unstructured":"Bin Nie, Lishan Yang, Adwait Jog, and Evgenia Smirni. 2018. Fault Site Pruning for Practical Reliability Analysis of GPGP U Applications. In MICRO 51. IEEE."},{"key":"e_1_3_2_1_62_1","unstructured":"Nvidia 2007."},{"key":"e_1_3_2_1_63_1","unstructured":"CUDA Programming Guide. Nvidia. http:\/\/developer.download.nvidia.com\/compute\/cuda."},{"key":"e_1_3_2_1_64_1","unstructured":"Nvidia 2013."},{"key":"e_1_3_2_1_65_1","unstructured":"CUDA Toolkit 5.5. Nvidia. https:\/\/developer.nvidia.com\/cuda-toolkit-55-archive."},{"key":"e_1_3_2_1_66_1","unstructured":"Robert Pawlowski. 2015."},{"key":"e_1_3_2_1_67_1","unstructured":"Measurement and Analysis of Soft Error Vulnerability of Low-Voltage Logic and Memory Circuits. Ph.D. Dissertation. Corvallis OR USA."},{"key":"e_1_3_2_1_68_1","unstructured":"William Wesley Peterson and EJ Weldon. 1972."},{"key":"e_1_3_2_1_69_1","unstructured":"Error-correcting codes. MIT press."},{"key":"e_1_3_2_1_70_1","unstructured":"George A Reis Jonathan Chang Neil Vachharajani Shubhendu S Mukherjee Ram Rangan and David I August. 2005."},{"key":"e_1_3_2_1_71_1","volume-title":"32nd International Symposium on Computer Architecture (ISCA\u201905)","author":"Design","unstructured":"Design and evaluation of hybrid fault-detection systems. In 32nd International Symposium on Computer Architecture (ISCA\u201905). IEEE, 148\u2013159."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"crossref","unstructured":"Muhammad Shafique Siddharth Garg J\u00f6rg Henkel and Diana Marculescu. 2014. The EDA Challenges in the Dark Silicon Era: Temperature Reliability and Variability Perspectives. In DAC \u201914.","DOI":"10.1145\/2593069.2593229"},{"key":"e_1_3_2_1_74_1","volume-title":"RTL and Guide, Modeling.","year":"2001","unstructured":"Synopsys. 2001. Compiler, Design and User, RTL and Guide, Modeling. (2001). http:\/\/www. synopsys. com."},{"key":"e_1_3_2_1_75_1","series-title":"SIAM journal on computing 1, 2","volume-title":"Depth-first search and linear graph algorithms","author":"Tarjan Robert","year":"1972","unstructured":"Robert Tarjan. 1972. Depth-first search and linear graph algorithms. SIAM journal on computing 1, 2 (1972), 146\u2013160."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"crossref","unstructured":"Michael B. Taylor. 2012. Is Dark Silicon Useful?: Harnessing the Four Horsemen of the Coming Dark Silicon Apocalypse. In DAC\u201912 (San Francisco California).","DOI":"10.1145\/2228360.2228567"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"crossref","unstructured":"D. Tiwari S. Gupta J. Rogers D. Maxwell P. Rech S. Vazhkudai D. Oliveira D. Londo N. DeBardeleben P. Navaux L. Carro and A. Bland. 2015. Understanding GP U errors on large-scale HPC systems and the implications for system design and operation. In HPCA \u201915. IEEE.","DOI":"10.1109\/HPCA.2015.7056044"},{"key":"e_1_3_2_1_78_1","unstructured":"Marc Tremblay and Yu Tamir. 1989."},{"key":"e_1_3_2_1_79_1","volume-title":"Circuits and Systems, 1989., IEEE International Symposium on. IEEE, 388\u2013392","author":"Support","unstructured":"Support for fault tolerance in VLSI processors. In Circuits and Systems, 1989., IEEE International Symposium on. IEEE, 388\u2013392."},{"key":"e_1_3_2_1_80_1","unstructured":"Joel Van Der Woude and Matthew Hicks. 2016."},{"key":"e_1_3_2_1_81_1","unstructured":"Intermittent computation without hardware support or programmer intervention. In OSDI\u201916."},{"key":"e_1_3_2_1_82_1","volume-title":"Implications of the Power Wall: Dim Cores and Reconfigurable Logic","author":"Wang Liang","year":"2013","unstructured":"Liang Wang and Kevin Skadron. 2013. Implications of the Power Wall: Dim Cores and Reconfigurable Logic. IEEE Micro (2013), 40\u201348."},{"key":"e_1_3_2_1_83_1","volume-title":"CACTI: An enhanced cache access and cycle time model. JSSC\u201996 (May","author":"Wilton S.J.E.","year":"1996","unstructured":"S.J.E. Wilton et al. 1996. CACTI: An enhanced cache access and cycle time model. JSSC\u201996 (May 1996)."},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"crossref","unstructured":"Mimi Xie Mengying Zhao Chao Pan Jingtong Hu Yongpan Liu and Chun Xue. 2015. Fixing the Broken Time Machine: Consistency-Aware Checkpointing for Energy Harvesting Powered Non-Volatile Processor. In DAC\u201915.","DOI":"10.1145\/2744769.2744842"},{"key":"e_1_3_2_1_85_1","volume-title":"CRAT: Enabling Coordinated Register Allocation and Thread-Level Parallelism Optimization for GP Us. TC\u201908","author":"Xie Xiaolong","year":"2018","unstructured":"Xiaolong Xie, Yun Liang, Xiuhong Li, Yudong Wu, Guangyu Sun, Tao Wang, and Dongrui Fan. 2018. CRAT: Enabling Coordinated Register Allocation and Thread-Level Parallelism Optimization for GP Us. TC\u201908 (2018)."}],"event":{"name":"PLDI '20: 41st ACM SIGPLAN International Conference on Programming Language Design and Implementation","location":"London UK","acronym":"PLDI '20","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages"]},"container-title":["Proceedings of the 41st ACM SIGPLAN Conference on Programming Language Design and Implementation"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3385412.3386033","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3385412.3386033","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:38:49Z","timestamp":1750199929000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3385412.3386033"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,11]]},"references-count":84,"alternative-id":["10.1145\/3385412.3386033","10.1145\/3385412"],"URL":"https:\/\/doi.org\/10.1145\/3385412.3386033","relation":{},"subject":[],"published":{"date-parts":[[2020,6,11]]},"assertion":[{"value":"2020-06-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}