Pasar al contenido principal

TECNICAS DE ENDURECIMIENTO HARDWARE E HIBRIDAS PARA SOCS HETEROGENEOS EN APLICACIONES ESPACIALES

PID2019-106455GB-C21

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2019
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD CARLOS III DE MADRID

Resultados relacionados

Resultados totales (Incluyendo duplicados): 4
Encontrada(s) 1 página(s)

RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Hybrid Lockstep Technique for Soft Error Mitigation

  • Peña-Fernández, Manuel
  • Serrano-Cases, Alejandro
  • Lindoso, Almudena
  • Cuenca-Asensi, Sergio
  • Entrena, Luis
  • Morilla, Yolanda
  • Martín-Holgado, Pedro
  • Martínez-Álvarez, Antonio
  • Cuenca-Asensi, Sergio|||/items/d56854c0-2895-4166-acfe-e7d4dea6f7e2
  • Martínez-Álvarez, Antonio|||/items/7fa5031e-e6d5-42cf-9f49-ae853d04cda9
  • Serrano-Cases, Alejandro|||/items/09bc6bdc-e4fd-4043-835a-48fee62ed569
This work presents the evaluation of a new dualcore lockstep hybrid approach aimed to improve the fault tolerance in microprocessors. Our approach takes advantage of modern multicore processor resources to combine a software-based lockstep with a custom hardware observer. The first is used to duplicate data and instruction flows; meanwhile, the second is in charge of the control-flow monitoring. The proposal has been implemented in a dualcore ARM microprocessor and validated with low energy proton irradiation and emulated fault injection campaigns. The results show an improvement of one order of magnitude in the cross-section of the benchmarks tested, even considering the worst-case scenario.
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Analyzing scaled reduced precision redundancy for error mitigation under proton irradiation

  • García-Astudillo, Luis A.
  • Lindoso, Almudena
  • Entrena, Luis A.
  • Martín, Honorio
  • García-Valderas, Mario
  • Martín Holgado, Pedro
Reduced precision redundancy (RPR) is an alternative to triple modular redundancy (TMR) that reduces the area overhead at the expense of minor accuracy loss in case of error. In this work, we propose a Scaled RPR approach for multistage circuits and analyze the error mitigation tradeoffs. As a case study, several fast Fourier transform designs were tested with low-energy protons and fault injection. Experimental results show that the proposed approach achieves error mitigation with good accuracy, while significantly reducing the area overhead with respect to a full precision TMR approach., Grant Number: PID2019-106455GB-C21. Community of Madrid: Grant Number: 49.520608.9.18, Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Hybrid lockstep technique for soft error mitigation

  • Peña-Fernandez, M.
  • Serrano-Cases, A.
  • Lindoso, Almudena
  • Cuenca-Asensi, Sergio
  • Entrena, Luis A.
  • Morilla, Yolanda
  • Martín Holgado, Pedro
  • Martínez-Álvarez, A.
This work presents the evaluation of a new dual-core lockstep hybrid approach aimed to improve the fault tolerance in microprocessors. Our approach takes advantage of modern multicore processor resources to combine software-based lockstep with a custom hardware observer. The first is used to duplicate data and instruction flows; meanwhile, the second is in charge of the control-flow monitoring. The proposal has been implemented in a dual-core ARM microprocessor and validated with low-energy proton irradiation and emulated fault injection campaigns. The results show an improvement of one order of magnitude in the cross section of the benchmarks tested, even considering the worst case scenario., 10.13039/501100004837-Ministerio de Ciencia e Innovación (Grant Number: PID2019-106455GB-C22 and PID2019-106455GB-C21). 10.13039/100012818-Comunidad de Madrid (Grant Number: IND2017/TIC-7776), Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Reliability evaluation of LU decomposition on GPU-accelerated system-on-chip under proton irradiation

  • Badía, José M.
  • León, Germán
  • Belloch, Jose A.
  • Lindoso, Almudena
  • García-Valderas, Mario
  • Morilla, Yolanda
  • Entrena, Luis A.
Graphic processing units (GPUs) have become a basic accelerator both in high-performance nodes and low-power system-on-chip (SoC). They provide massive data parallelism and very high performance per watt. However, their reliability in harsh environments is an important issue to take into account, especially for safety-critical applications. In this article, we evaluate the influence of the parallelization strategy on the reliability of lower–upper (LU) decomposition on a GPU-accelerated SoC under proton irradiation. Specifically, we compare a memory bound and a compute bound implementation of the decomposition on a K20A GPU embedded on a Tegra K1 (TK1) SoC. We leverage the GPU and CPU clock frequencies both to highlight the radiation sensitivity of the GPU where we are running the benchmark and also to apply both algorithms to solve problems with the same size when exposed to the same radiation dose. Results show that more intensive use of the resources of the GPU increases the cross section. We also observed that most of the radiation-induced errors hang the operating system and even the rebooting process. Finally, we present a preliminary study of the error propagation of the LU decomposition algorithms., 10.13039/501100003359-Valencian Regional Government (Grant Number: PROMETEO/2019/109). Jaume I University (Grant Number: UJIB2019-36) 10.13039/501100004837-Spanish Ministry of Science and Innovation (Grant Number: PID2019-106455GB-C21 and PID2020-113656RB-C21 (MCIN/AEI/10.13039/501100011033)). 10.13039/501100010774-Regional Government of Madrid (Grant Number: MIMACUHSPACE-CM-UC3M (2022/00024/001)), Peer reviewed