Testing permanent faults in pipeline registers of GPGPUs: A multi-kernel approach

JER Condia, MS Reorda - … Symposium on On-Line Testing and …, 2019 - ieeexplore.ieee.org
In the last decade, General Purpose Graphics Processing Units (GPGPUs) have been
widely employed in high demanding data processing applications including multimedia and …

An on-line testing technique for the scheduler memory of a GPGPU

S Di Carlo, JER Condia, MS Reorda - IEEE Access, 2020 - ieeexplore.ieee.org
The highly parallel processing capabilities and reduced power performance of General
Purpose Graphics Processing Units (GPGPUs) have been crucial factors for their massive …

An effective method to identify microarchitectural vulnerabilities in gpus

JER Condia, P Rech, FF dos Santos… - … on Device and …, 2022 - ieeexplore.ieee.org
Graphics Processing Units (GPUs) are increasingly adopted in several domains where
reliability is fundamental, such as self-driving cars and autonomous systems. Unfortunately …

On the evaluation of SEU effects in GPGPUs

B Du, JER Condia, MS Reorda… - 2019 IEEE Latin …, 2019 - ieeexplore.ieee.org
General Purpose Graphic Processing Units (GPGPUs) are effective solutions for high-
demand data applications which involve multi-signal, image and video processing thanks to …

Improving GPU register file reliability with a comprehensive ISA extension

MM Goncalves, JER Condia, MS Reorda… - Microelectronics …, 2020 - Elsevier
This work proposes a comprehensive ISA extension to improve GPU reliability to transient
effects. Three additional instructions are proposed, implemented, and combined with …

Improving selective fault tolerance in gpu register files by relaxing application accuracy

MM Goncalves, IP Lamb, P Rech… - … on Nuclear Science, 2020 - ieeexplore.ieee.org
The high computing power of graphics processing units (GPUs) makes them attractive for
safety-critical applications, where reliability is a major concern. This article uses an …

Evaluating the reliability of a GPU pipeline to SEU and the impacts of software-based and hardware-based fault tolerance techniques

M Gonçalves, M Saquetti, JR Azambuja - Microelectronics Reliability, 2018 - Elsevier
This paper evaluates the reliability of a GPU pipeline upset by SEU faults and the impacts of
software-based and hardware-based fault tolerance techniques. The approach entails first …

Evaluating softcore GPU in SRAM-based FPGA under radiation-induced effects

G Braga, F Benevenuti, MM Gonçalves… - Microelectronics …, 2021 - Elsevier
This work investigates selective mitigation techniques to improve the reliability of a
configurable open-source softcore GPU implemented in an SRAM-based FPGA against …

Selective fault tolerance for register files of graphics processing units

M Goncalves, F Fernandes, I Lamb… - … on Nuclear Science, 2019 - ieeexplore.ieee.org
The high computing efficiency of graphics processing units (GPUs) makes them attractive for
both high-performance computing and safety-critical applications, such as the automotive …

Analyzing the sensitivity of gpu pipeline registers to single events upsets

JER Condia, MM Goncalves… - 2020 IEEE Computer …, 2020 - ieeexplore.ieee.org
Graphics processing units are available solutions for high-performance safety-critical
applications, such as self-driving cars. In this application domain, functional-safety and …