2026-09-20T01:41:08Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/46706 2023-07-11 col_2142_8888 col_2142_5131 com_2142_8887 com_2142_234 com_2142_5130

Kumar, Rakesh Kumar, Rakesh Vaidya, Nitin H. Gropp, William D. Abraham, Jacob A. Bronevetsky, Greg Sloan, Joseph 2014-01-16T17:59:47Z 2014-01-16T17:59:47Z 2013-12 2014-01-16T17:59:47Z 2013-12 As late-CMOS process scaling leads to increasingly variable circuits/logic and as most post-CMOS technologies in sight appear to have largely stochastic characteristics, hardware reliability has become a first-order design concern. To make matters worse, emerging computing systems are becoming increasingly power constrained. Traditional hardware/software approaches are likely to be impractical for these power constrained systems due to their heavy reliance on redundant, worstcase, and conservative designs. The primary goal of this research has been to investigate how we can leverage inherent application and algorithm characteristics (e.g. natural error resilience, spatial and temporal reuse, and fault containment) to build more efficient robust systems. This dissertation research describes algorithmic approaches that leverage application and algorithm-awareness for building such systems. These approaches include (a) application-specific techniques for low-overhead fault detection, (b) an algorithmic approach for error correction using localization, (c) selection of scientific computing solver schemes to leverage application-level error resilience, and (d) a numerical optimization-based methodology for converting applications into a more error tolerant form. This dissertation shows that application and algorithm-awareness can significantly increase the robustness of computing systems, while also reducing the cost of meeting reliability targets. Item withdrawn by Laura Spradlin (lspradl2@illinois.edu) on 2013-12-05T14:57:50Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 2 dissertation_source.zip: 59965604 bytes, checksum: f2b95d29fef65a07833ceb1535339cb7 (MD5) Sloan_Joseph.pdf: 13053478 bytes, checksum: 6e6f1983cb827f5dde7906d4b1b3dfa5 (MD5) Made available in DSpace on 2014-01-16T17:59:47Z (GMT). No. of bitstreams: 3 Joseph_Sloan.pdf: 13053478 bytes, checksum: 6e6f1983cb827f5dde7906d4b1b3dfa5 (MD5) dissertation_source.zip: 59965604 bytes, checksum: f2b95d29fef65a07833ceb1535339cb7 (MD5) license.txt: 4060 bytes, checksum: d044cbe9eb15bf6fe3d113cee62e3613 (MD5) http://hdl.handle.net/2142/46706 en Copyright 2013 Joseph Augustyn Sloan Fault Tolerance Application-level Error Tolerance Algorithmic Based Fault Tolerance (ABFT) Application Robustification Stochastic Processors Reliability and Hardware Variability Error localization Partial Recomputation Robust Sparse Linear Algebra Algorithmic Selection for Error Resilience Algorithmic approaches to enhancing and exploiting application-level error tolerance text Electrical & Computer Engineering 1933 Electrical & Computer Engineering 1200 University of Illinois at Urbana-Champaign Dissertation Ph.D. PHD:Electr & Computer Eng-UIUC 10KS1200PHD