Robert Limas Sierra
11 Papers
3 Citations
Robert Limas Sierra is an academic researcher. The author has contributed to research in topics: Computer science. The author has an hindex of 2, co-authored 6 publications.
Chat about Author
Papers
Reliability Assessment of Neural Networks in GPUs: A Framework For Permanent Faults Injections
Juan David Guerrero-Balaguera,Luigi Galasso,Robert Limas Sierra,Matteo Sonza Reorda +3 more
- 24 May 2022
TL;DR: This paper intends to propose a framework, resorting to a binary instrumentation tool to perform fault injection campaigns, targeting different components inside the GPU, such as the register files and the functional units, that allows for the first time assessing the reliability of CNNs deployed on a GPU considering the presence of permanent faults.
8
Analyzing the Impact of Different Real Number Formats on the Structural Reliability of TCUs in GPUs
Robert Limas Sierra,Juan David Guerrero-Balaguera,Josie E. Rodriguez Condia,Matteo Sonza Reorda +3 more
- 16 Oct 2023
TL;DR: This work for the first time quantitatively evaluates the effects of hardware faults arising in TCU structures when using two different formats for real number representation, and demonstrates that the Posit formats are less affected by faults than Floating-Point formats by up to one order of magnitude.
7
Evaluating the impact of Permanent Faults in a GPU running a Deep Neural Network
Juan David Guerrero-Balaguera,Luigi Galasso,Robert Limas Sierra,Ernesto Sanchez,Matteo Sonza Reorda +4 more
- 01 Aug 2022
TL;DR: In this article , the authors present an environment allowing for the first time a more detailed experimental evaluation of the impact of permanent faults in a GPU on the reliability of a DNN running on it, based on considering faults at the architectural level.
2
Analyzing the Architectural Impact of Transient Fault Effects in SFUs of GPUs
Josie E. Rodriguez Condia,Juan David Guerrero-Balaguera,Robert Limas Sierra,Matteo Sonza Reorda +3 more
- 21 Mar 2023
TL;DR: In this paper , the authors evaluate the impact of transient faults in the hardware structures of Special Function Unit (SFU) cores on GPU workloads and show that modular SFUs are less vulnerable to transient faults than fused SFUs.
1
Effective fault simulation of GPU’s permanent faults for reliability estimation of CNNs
Juan David Guerrero-Balaguera,Robert Limas Sierra,Matteo Sonza Reorda +2 more
- 12 Sep 2022
TL;DR: This work introduces a more elaborated experimental evaluation of the impact of GPU’s permanent faults on the reliability of a CNN by resorting to a Software-Implemented Fault Injection(SWIFI) strategy, considering faults at the hardware level.
1