Filters








32,601 Hits in 4.9 sec

Designing reliable algorithms in unreliable memories

Irene Finocchi, Fabrizio Grandoni, Giuseppe F. Italiano
2007 Computer Science Review  
In this paper we will survey some recent work on reliable computation in the presence of memory faults.  ...  An algorithm is resilient to memory faults if, despite the corruption of some memory values before or during its execution, it is nevertheless able to get a correct output at least on the set of uncorrupted  ...  Unfortunately, even very few memory faults may jeopardize the correctness of the underlying algorithms, and thus the quest for reliable computation in unreliable memories arises in an increasing number  ... 
doi:10.1016/j.cosrev.2007.10.001 fatcat:y4723guad5fcdba72a43asc25u

Designing Reliable Algorithms in Unreliable Memories [chapter]

Irene Finocchi, Fabrizio Grandoni, Giuseppe F. Italiano
2005 Lecture Notes in Computer Science  
In this paper we will survey some recent work on reliable computation in the presence of memory faults.  ...  An algorithm is resilient to memory faults if, despite the corruption of some memory values before or during its execution, it is nevertheless able to get a correct output at least on the set of uncorrupted  ...  Unfortunately, even very few memory faults may jeopardize the correctness of the underlying algorithms, and thus the quest for reliable computation in unreliable memories arises in an increasing number  ... 
doi:10.1007/11561071_1 fatcat:ght6kmcoanbnhchrwbcele5wu4

Resilience in Numerical Methods: A Position on Fault Models and Methodologies [article]

James Elliott and Mark Hoemmen and Frank Mueller
2014 arXiv   pre-print
Given a selective reliability programming model that requires reliability only when and where needed, such checks can make algorithms reliable despite unbounded faults.  ...  We argue instead that numerical algorithms can benefit from a numerical unreliability fault model, where faults manifest as unbounded perturbations to floating-point data.  ...  We argue that resilient numerical methods should be designed around an abstract fault model of numerical unreliability, in much the same way C/R is designed around an abstract model of system unreliability  ... 
arXiv:1401.3013v1 fatcat:jqj3gp44gbcj7ps5ac72hmx3r4

The impact of faulty memory bit cells on the decoding of spatially-coupled LDPC codes

Jiandong Mu, Aida Vosoughi, Joao Andrade, Alexios Balatsoukas-Stimming, Georgios Karakonstantis, Andreas Burg, Gabriel Falcao, Vitor Silva, Joseph R. Cavallaro
2015 2015 49th Asilomar Conference on Signals, Systems and Computers  
Approximate computing is such an alternative design paradigm, where 100% reliable operation requirements are relaxed in order to limit the overhead of classical fault mitigation techniques [5] .  ...  to close to the case where the memory is reliable.  ... 
doi:10.1109/acssc.2015.7421423 dblp:conf/acssc/MuVABKBFSC15 fatcat:arvalduocvhk5lh7vtvujjc22q

Energy Efficiency through Significance-Based Computing

Dimitrios S. Nikolopoulos, Hans Vandierendonck, Nikolaos Bellas, Christos D. Antonopoulos, Spyros Lalis, Georgios Karakonstantis, Andreas Burg, Uwe Naumann
2014 Computer  
Hardware architecture At the base of the system, we've designed and developed a many-core platform where cores and their respective cache memories can operate in a conventional, fully reliable mode, as  ...  In addition, unreliable CPUs should offer a special set of reliable instructions and hardened memory areas that the system software and/or application code can use to implement critical operations, such  ... 
doi:10.1109/mc.2014.182 fatcat:np6xvscp3jaathoz4ach3j4ivi

Fault-tolerant linear solvers via selective reliability [article]

Patrick G. Bridges, Kurt B. Ferreira, Michael A. Heroux, Mark Hoemmen
2012 arXiv   pre-print
Furthermore, they store most of their data unreliably, and spend most of their time in unreliable mode.  ...  However, many algorithms only need reliability for certain data and phases of computation. This suggests an algorithm and system codesign approach.  ...  Acknowledgment This work was supported in part by a faculty sabbatical appointment from Sandia National Laboratories and a grant from the U.S. Department of Energy and  ... 
arXiv:1206.1390v1 fatcat:ttowhmggzrbb5hsawtvli7pgue

Synergistic Architecture and Programming Model Support for Approximate Micropower Computing

Giuseppe Tagliavini, Davide Rossi, Luca Benini, Andrea Marongiu
2015 2015 IEEE Computer Society Annual Symposium on VLSI  
Using aggressive voltage scaling can reduce power consumption, but memory operations become unreliable.  ...  A compiler pass places data into memory regions with different reliability guarantees according to their tolerance to errors.  ...  RM is the reliable memory (SCM), NM is the unreliable memory (6T-SRAM), and finally TM is the tolerant memory that can be optionally activated.  ... 
doi:10.1109/isvlsi.2015.64 dblp:conf/isvlsi/TagliaviniRBM15 fatcat:do3naxkiibh33lxwddhvyhwiwq

Cooperative Application/OS DRAM Fault Recovery [chapter]

Patrick G. Bridges, Mark Hoemmen, Kurt B. Ferreira, Michael A. Heroux, Philip Soltero, Ron Brightwell
2012 Lecture Notes in Computer Science  
In this paper, we describe work on a cross-layer application / OS framework to handle uncorrected memory errors.  ...  Unfortunately, many fault-tolerance methods in use, such as rollback recovery, are unsuitable for many expected errors, for example DRAM failures.  ...  The algorithm accomplishes this by dividing its computations into reliable and unreliable phases.  ... 
doi:10.1007/978-3-642-29740-3_28 fatcat:yatljdnp3zahpkipe6s6t3wroa

A facility reliability problem: Formulation, properties, and algorithm

Michael Lim, Mark S. Daskin, Achal Bassamboo, Sunil Chopra
2009 Naval Research Logistics  
In this paper, we study the facility reliability problem: how to design a reliable supply chain network in the presence of random facility disruptions with the option of hardening selected facilities.  ...  We consider a facility location problem incorporating two types of facilities, one that is unreliable and another that is reliable (which is not subject to disruption, but is more expensive).  ...  Acknowledgments The research was supported in part by the National Science Foundation (DMI-0457503) and the Office of Naval Research (N00014-05-1-0190). This support is gratefully appreciated.  ... 
doi:10.1002/nav.20385 fatcat:xxb6oxrx2zh4hojurrurfr6rbi

Reliability-based coded modulation with low-density parity-check codes

R.D. Maddock, A.H. Banihashemi
2006 IEEE Transactions on Communications  
In this letter, we consider the interleaver design in bit-interleaved coded modulation (BICM) with low-density parity-check (LDPC) codes.  ...  The design paradigm is to provide more coding protection through iterative decoding to bits that are less protected by modulation (and are thus less reliable at the output of demodulator).  ...  The application of low-density parity-check (LDPC) codes [2] in BICM framework was studied in [3] ,  ... 
doi:10.1109/tcomm.2006.869865 fatcat:2kj6anqmzvbbhceiywoqp2xm4m

An Information Theoretical Framework for Analysis and Design of Nanoscale Fault-Tolerant Memories Based on Low-Density Parity-Check Codes

B. Vasic, S.K. Chilappagari
2007 IEEE Transactions on Circuits and Systems Part 1: Regular Papers  
The equivalence of the restoration phase in the TK method and faulty Gallager B algorithm enabled us to establish a theoretical framework for solving problems in reliable storage on unreliable media using  ...  In this paper, we develop a theoretical framework for the analysis and design of fault-tolerant memory architectures.  ...  algorithms have not been exploited so far to improve reliability of memory systems.  ... 
doi:10.1109/tcsi.2007.902611 fatcat:wqcjktxr4beehnyxceju3t2unu

Data mapping for unreliable memories

Christoph Roth, Christian Benkeser, Christoph Studer, Georgios Karakonstantis, Andreas Burg
2012 2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton)  
In this paper, we address this issue by investigating the impact of unreliable memories on general DSP systems.  ...  Future digital signal processing (DSP) systems must provide robustness on algorithm and application level to the presence of reliability issues that come along with corresponding implementations in modern  ...  , provided that the corresponding algorithms and system architectures are designed to take such hardware errors into account [10] - [13] .  ... 
doi:10.1109/allerton.2012.6483283 dblp:conf/allerton/RothBSKB12 fatcat:sxceesnwtfcgdflzycpdvourzm

Analysis of the Signal Reliability Measure and an Evaluation Procedure

Koren
1979 IEEE transactions on computers  
This is approximately half the n-I E 2n"i = 2(2" -1) i=O computation steps required by the algorithm in [1].  ...  In order to generate the 2" elements of S. the algorithm based on (8), (9), and (10) requires 2" computation steps.  ...  Employing the functional reliability measure results in a less accurate reliability comparison of different designs of a digital circuit.  ... 
doi:10.1109/tc.1979.1675326 fatcat:cpdls2nzwve5vi7fmyeu5q54mi

Data fusion without knowledge of the ground truth using Tseltin-like Automata

Anis Yazidi, Frode Eika Sandnes
2016 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC)  
By virtue of the limited memory requirement of our devised LA, we achieve adaptive behavior at the cost of negligible loss in the accuracy.  ...  Our approach leverages a Random Walk (RW) inspired by Tsetlin LA so that to gradually learn the identity of the reliable and unreliable sensors.  ...  Our solution can adaptively and in an on-line manner distinguish between reliable sensors and unreliable senors using finite memory.  ... 
doi:10.1109/smc.2016.7844941 dblp:conf/smc/YazidiS16 fatcat:i5pidml2rjhojhiuwguskfc47e

Performance analysis of faulty Gallager-B decoding of QC-LDPC codes with applications

Al Omran, Srdjan Brkic, Predrag Ivanis, Bane Vasic
2014 Telfor Journal  
One possible application of the presented analysis in designing memory architecture with unreliable components is considered.  ...  In this paper we evaluate the performance of Gallager-B algorithm, used for decoding low-density paritycheck (LDPC) codes, under unreliable message computation.  ...  Furthermore, the application of the described algorithm in the design of memory architecture with unreliable components is considered.  ... 
doi:10.5937/telfor1401007o fatcat:5d33ediqhjemhorl26nqaqiove
« Previous Showing results 1 — 15 out of 32,601 results