Publication: Evaluating the soft error sensitivity of a GPU-based SoC for matrix multiplication
Loading...
Identifiers
Publication date
2020-11
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Elsevier Ltd.
Impact
Export
Abstract
System-on-Chip (SoC) devices can be composed of low-power multicore processors combined with a small graphics accelerator (or GPU) which offers a trade-off between computational capacity and low-power consumption. In this work we use the LLFI-GPU fault injection tool on one of these devices to compare the sensitivity to soft errors of two different CUDA versions of matrix multiplication benchmark. Specifically, we perform fault injection campaigns on a Jetson TK1 development kit, a board equipped with a SoC including an NVIDIA 'Kepler” Graphics Processing Unit (GPU). We evaluate the effect of modifying the size of the problem and also the thread-block size on the behaviour of the algorithms. Our results show that the block version of the matrix multiplication benchmark that leverages the shared memory of the GPU is not only faster than the element-wise version, but it is also much more resilient to soft errors. We also use the cuda-gdb debugger to analyze the main causes of the crashes in the code due to soft errors. Our experiments show that most of the errors are due to accesses to invalid positions of the different memories of the GPU, which causes that the block version suffers a higher percentage of this kind of errors.
Description
Proceeding of: 31th European Symposium on Reliability of Electron Devices, Failure Physics and Analysis (ESREF 2020), Athens, Greece, 4th to 8 October 2020 (Virtual conference)
Keywords
GPU, Soft errors, Sensitivity, Fault injection
Bibliographic citation
Germán, L., et al. Evaluating the soft error sensitivity of a GPU-based SoC for matrix multiplication. Microelectronics reliability, Vol. 114, 113856 , (Special issue: Proceedings of ESREF 2020, 31th European Symposium on Reliability of Electron Devices, Failure Physics and Analysis). Elsevier, 2020, 6 p.