6 Şubat 2020 Dergi makalesi Açık Erişim

Cini, Nevin; Yalcin, Gülay

Citation Style Language JSON

{
  "DOI": "10.1145/3372790", 
  "abstract": "<p>Today, GPUs are widely used as coprocessors/accelerators in High-Performance Heterogeneous Computing<br>\ndue to their many advantages. However, many researches emphasize that GPUs are not as reliable as desired<br>\nyet. Despite the fact that GPUs are more vulnerable to hardware errors than CPUs, the use of GPUs in HPCs<br>\nis increasing more and more. Moreover, due to native reliability problems of GPUs, combining a great number<br>\nof GPUs with CPUs can significantly increase HPCs&rsquo; failure rates. For this reason, analyzing the reliability<br>\ncharacteristics of GPU-based HPCs has become a very important issue. Therefore, in this study we evaluate<br>\nthe reliability of GPU-based HPCs. For this purpose, we first examined field data analysis studies for GPU-<br>\nbased and CPU-based HPCs and identified factors that could increase systems failure/error rates. We then<br>\ncompared GPU-based HPCs with CPU-based HPCs in terms of reliability with the help of these factors in<br>\norder to point out reliability challenges of GPU-based HPCs. Our primary goal is to present a study that can<br>\nguide the researchers in this field by indicating the current state of GPU-based heterogeneous HPCs and<br>\nrequirements for the future, in terms of reliability. Our second goal is to offer a methodology to compare the<br>\nreliability of GPU-based HPCs and CPU-based HPCs. To the best of our knowledge, this is the first survey<br>\nstudy to compare the reliability of GPU-based and CPU-based HPCs in a systematic manner.</p>", 
  "author": [
    {
      "family": "Cini", 
      "given": " Nevin"
    }, 
    {
      "family": "Yalcin", 
      "given": " G\u00fclay"
    }
  ], 
  "container_title": "ACM Computing Surveys", 
  "id": "273917", 
  "issue": "No. 1", 
  "issued": {
    "date-parts": [
      [
        2020, 
        2, 
        6
      ]
    ]
  }, 
  "language": "eng", 
  "page": "Article 22", 
  "title": "A Methodology for Comparing the Reliability of GPU-Based and CPU-Based HPCs", 
  "type": "article-journal", 
  "volume": "Vol. 53"
}