
{  
   "types" : {
      "Bookmark" : {
         "pluralLabel" : "Bookmarks"
      },
      "Publication" : {
         "pluralLabel" : "Publications"
      },
      "GoldStandardPublication" : {
         "pluralLabel" : "GoldStandardPublications"
      },
      "GoldStandardBookmark" : {
         "pluralLabel" : "GoldStandardBookmarks"
      },
      "Tag" : {
         "pluralLabel" : "Tags"
      },
      "User" : {
         "pluralLabel" : "Users"
      },
      "Group" : {
         "pluralLabel" : "Groups"
      },
      "Sphere" : {
         "pluralLabel" : "Spheres"
      }
   },
   
   "properties" : {
      "count" : {
         "valueType" : "number"
      },
      "date" : {
         "valueType" : "date"
      },
      "changeDate" : {
         "valueType" : "date"
      },
      "url" : {
         "valueType" : "url"
      },
      "id" : {
         "valueType" : "url"
      },
      "tags" : {
         "valueType" : "item"
      },
      "user" : {
         "valueType" : "item"
      }      
   },
   
   "items" : [
   	  
      {
         "type" : "Publication",
         "id"   : "https://puma.ub.uni-stuttgart.de/bibtex/278feed56c1636b8fcbfd657450c145bd/clausbraun",         
         "tags" : [
            "ABFT","GPGPU","GPU","SimTech","algebra","algorithm-based","error","error-detection","fault","fault-tolerance","linear","matrix-operations","myown","simulation"
         ],
         
         "intraHash" : "78feed56c1636b8fcbfd657450c145bd",
         "interHash" : "f4aa6bff08e99d1685a2218270cadc80",
         "label" : "Algorithm-based fault tolerance for matrix operations on graphics processing units: analysis and extension to autonomous operation.",
         "user" : "clausbraun",
         "description" : "",
         "date" : "2018-03-19 16:42:05",
         "changeDate" : "2018-03-19 15:42:05",
         "count" : 3,
         "pub-type": "phdthesis",
         
         "year": "2015", 
         "url": "", 
         
         "author": [ 
            "Claus Braun"
         ],
         "authors": [
         	
            	{"first" : "Claus",	"last" : "Braun"}
         ],
         
         "ee" : "http://d-nb.info/1075190916",
         
         "bibtexKey": "phd/dnb/Braun15"

      }
,
      {
         "type" : "Publication",
         "id"   : "https://puma.ub.uni-stuttgart.de/bibtex/2a6dcd392b900956871dd3cfde89cd481/clausbraun",         
         "tags" : [
            "ABFT","GPGPU","GPU","SimTech","adaptivity","algebra","algorithm-based","autonompous","error","error-correction","error-detection","fault-tolerance","linear","matrix","matrix-multiplication","metric","myown","rounding","rounding-error"
         ],
         
         "intraHash" : "a6dcd392b900956871dd3cfde89cd481",
         "interHash" : "f672f35af5f6b825bda005ca703be294",
         "label" : "A-ABFT: Autonomous Algorithm-Based Fault Tolerance for Matrix Multiplications on Graphics Processing Units",
         "user" : "clausbraun",
         "description" : "",
         "date" : "2018-03-19 16:15:07",
         "changeDate" : "2018-03-19 15:37:08",
         "count" : 7,
         "pub-type": "inproceedings",
         "booktitle": "Proceedings of the 44th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN'14)",
         "year": "2014", 
         "url": "", 
         
         "author": [ 
            "Claus Braun","Sebastian Halder","Hans-Joachim Wunderlich"
         ],
         "authors": [
         	
            	{"first" : "Claus",	"last" : "Braun"},
            	{"first" : "Sebastian",	"last" : "Halder"},
            	{"first" : "Hans-Joachim",	"last" : "Wunderlich"}
         ],
         "pages": "443--454","abstract": "Graphics processing units (GPUs) enable large-scale scientific applications and simulations on the desktop. To allow scientific computing on GPUs with high performance and reliability requirements, the application of software-based fault tolerance is attractive. Algorithm-Based Fault Tolerance (ABFT) protects important scientific operations like matrix multiplications. However, the application to floating-point operations necessitates the runtime classification of errors into inevitable rounding errors, allowed compute errors in the magnitude of such rounding errors, and into critical errors that are larger than those and not tolerable. Hence, an ABFT scheme needs suitable rounding error bounds to detect errors reliably. The determination of such error bounds is a highly challenging task, especially since it has to be integrated tightly into the algorithm and executed autonomously with low performance overhead.\r\n In this work, A-ABFT for matrix multiplications on GPUs is introduced, which is a new, parallel ABFT scheme that determines rounding error bounds autonomously at runtime with low performance overhead and high error coverage.",
         "file" : "http://www.iti.uni-stuttgart.de/fileadmin/rami/files/publications/2014/DSN_BraunHH2014.pdf",
         
         "doi" : "http://dx.doi.org/10.1109/DSN.2014.48",
         
         "bibtexKey": "BraunHW2014"

      }
,
      {
         "type" : "Publication",
         "id"   : "https://puma.ub.uni-stuttgart.de/bibtex/28c90a682adda1e125eb007f0c70bd70a/clausbraun",         
         "tags" : [
            "ABFT","CG","PCG","SimTech","conjugate","error","error-correction","error-detection","fault","fault-tolerance","gradient","linear","myown","preconditioned","solver","sparse","system"
         ],
         
         "intraHash" : "8c90a682adda1e125eb007f0c70bd70a",
         "interHash" : "d133c0d9eda7017c266a9d01721a9c91",
         "label" : "Low-Overhead Fault-Tolerance for the Preconditioned Conjugate Gradient Solver",
         "user" : "clausbraun",
         "description" : "",
         "date" : "2018-03-19 16:15:07",
         "changeDate" : "2018-03-19 15:33:36",
         "count" : 6,
         "pub-type": "inproceedings",
         "booktitle": "Proceedings of the International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT'15)",
         "year": "2015", 
         "url": "", 
         
         "author": [ 
            "Alexander Schöll","Claus Braun","Michael A. Kochte","Hans-Joachim Wunderlich"
         ],
         "authors": [
         	
            	{"first" : "Alexander",	"last" : "Schöll"},
            	{"first" : "Claus",	"last" : "Braun"},
            	{"first" : "Michael A.",	"last" : "Kochte"},
            	{"first" : "Hans-Joachim",	"last" : "Wunderlich"}
         ],
         "pages": "60-65","abstract": "Linear system solvers are an integral part for many different compute-intensive applications and they benefit from the compute power of heterogeneous computer architectures. However, the growing spectrum of reliability threats for such nano-scaled CMOS devices makes the integration of fault tolerance mandatory. The preconditioned conjugate gradient (PCG) method is one widely used solver as it finds solutions typically faster compared to direct methods. Although this iterative approach is able to tolerate certain errors, latest research shows that the PCG solver is still vulnerable to transient effects. Even single errors, for instance, caused by marginal hardware, harsh environments, or particle radiation, can considerably affect execution times, or lead to silent data corruption. In this work, a novel fault-tolerant PCG solver with extremely low runtime overhead is proposed. Since the error detection method does not involve expensive operations, it scales very well with increasing problem sizes. In case of errors, the method selects between three different correction methods according to the identified error. Experimental results show a runtime overhead for error detection ranging only from 0.04% to 1.70%.",
         "file" : "http://www.iti.uni-stuttgart.de/fileadmin/rami/files/publications/2015/DFTS_SchoeBKW2015.pdf",
         
         "doi" : "http://dx.doi.org/10.1109/DFT.2015.7315136",
         
         "bibtexKey": "SchoeBKW2015a"

      }
	  
   ]
}
