Gpu Fault Tolerance
GPU Fault Tolerance is a computational framework that ensures reliable execution of workloads on a graphics processing unit despite the occurrence of hardware or software faults, by incorporating error detection, recovery, and redundancy mechanisms specific to the parallel and heterogeneous architecture of GPUs.
95
Publications
3.8K
Citations
202
Authors
82
Institutions
Publications per year
2017–2026
50
95
GPU-Qin: A methodology for evaluating the error resilience of GPGPU applications
Bo Fang, Karthik Pattabiraman, Matei Ripeanu et al. · 2014 · 144 citations
Understanding software approaches for GPGPU reliability
Martin Dimitrov, Mike Mantor, Huiyang Zhou · 2009 · 117 citations · Full text
1–5 of 95
202
19
h-index
15
h-index
Universidade Federal do Rio Grande do Sul, Brazil
12 publications · 582 citations
12
h-index
8
h-index
7
h-index
1–5 of 202
82
Universidade Federal do Rio Grande do Sul
Porto Alegre, Brazil
19 h-index
95 publications
5K citations
Politecnico di Torino
Turin, Italy
10 h-index
24 publications
554 citations
Northeastern University
Boston, United States
8 h-index
25 publications
762 citations

University of British Columbia
Vancouver, Canada
7 h-index
16 publications
928 citations
William & Mary
Williamsburg, United States
5 h-index
17 publications
690 citations

Oak Ridge National Laboratory
Oak Ridge, United States
4 h-index
18 publications
1.8K citations
Nvidia (United States)
Santa Clara, United States
4 h-index
20 publications
479 citations
Los Alamos National Laboratory
Los Alamos, United States
4 h-index
5 publications
288 citations
1–8 of 82
8 publications · 257 citations
8
h-index
6 publications · 92 citations
6
h-index
3 publications · 162 citations
3
h-index
TACO · 2 publications · 47 citations
2
h-index
Conference · 2 publications · 52 citations
2
h-index
1–5