Explaining cache SER anomaly using DUE AVF measurement

作者: Arijit Biswas , Charles Recchia , Shubhendu S. Mukherjee , Vinod Ambrose , Leo Chan

DOI: 10.1109/HPCA.2010.5416629

关键词:

摘要: We have discovered that processors can experience a super-linear increase in detected unrecoverable errors (DUE) when the write-back L2 cache is doubled size. This paper explains how an tag's Architectural Vulnerability Factor or AVF caused such DUE rate. expresses fraction of faults become user-visible errors. Our hypothesis this by “dirty” data residence times cache. Using proton beam irradiation, we measured rates from tags and analyzed to show our holds. utilized combination simulation measurements help develop prove hypothesis. investigation reveals two methods which dirty line residency causes increases AVF. One reduction miss as move larger part, resulting fewer evictions required for architecturally correct execution. The second occurrence strided access patterns, cause significant lines without increasing

参考文章(15)
Shubu Mukherjee, Architecture Design for Soft Errors ,(2008)
D.M. Hiemstra, A. Baril, Single event upset characterization of the Pentium(R) MMX and Pentium(R) II microprocessors using proton irradiation IEEE Transactions on Nuclear Science. ,vol. 46, pp. 1453- 1460 ,(1999) , 10.1109/23.819107
P. N. Sanda, J. W. Kellington, P. Kudva, R. Kalla, R. B. McBeth, J. Ackaret, R. Lockwood, J. Schumann, C. R. Jones, Soft-error resilience of the IBM POWER6 processor Ibm Journal of Research and Development. ,vol. 52, pp. 275- 284 ,(2008) , 10.1147/RD.523.0275
Chi-Keung Luk, Robert Muth, Harish Patil, Richard Weiss, P. Geoffrey Lowney, Robert Cohn, Profile-guided post-link stride prefetching international conference on supercomputing. pp. 167- 178 ,(2002) , 10.1145/514191.514217
J. Emer, P. Ahuja, E. Borch, A. Klauser, Chi-Keung Luk, S. Manne, S.S. Mukherjee, H. Patil, S. Wallace, N. Binkert, R. Espasa, T. Juan, Asim: a performance model framework IEEE Computer. ,vol. 35, pp. 68- 76 ,(2002) , 10.1109/2.982918
N. Seifert, P. Slankard, M. Kirsch, B. Narasimham, V. Zia, C. Brookreson, A. Vo, S. Mitra, B. Gill, J. Maiz, Radiation-Induced Soft Error Rates of Advanced CMOS Bulk Devices international reliability physics symposium. pp. 217- 225 ,(2006) , 10.1109/RELPHY.2006.251220
Xiaodong Li, Sarita V. Adve, Pradip Bose, Jude A. Rivers, Online Estimation of Architectural Vulnerability Factor for Soft Errors ACM SIGARCH Computer Architecture News. ,vol. 36, pp. 341- 352 ,(2008) , 10.1145/1394608.1382150
Arijit Biswas, Paul Racunas, Razvan Cheveresan, Joel Emer, Shubhendu S. Mukherjee, Ram Rangan, Computing Architectural Vulnerability Factors for Address-Based Structures ACM SIGARCH Computer Architecture News. ,vol. 33, pp. 532- 543 ,(2005) , 10.1145/1080695.1070014
H.T. Nguyen, Y. Yagil, N. Seifert, M. Reitsma, Chip-level soft error estimation method IEEE Transactions on Device and Materials Reliability. ,vol. 5, pp. 365- 381 ,(2005) , 10.1109/TDMR.2005.858334