Radiation Sensitivity of High Performance Computing Applications on Kepler-Based GPGPUs

Oliveira, Daniel; Lunardi, Caio; Pilla, Laércio Lima; Rech, Paolo; Navaux, Philippe O. A.; Carro, Luigi

doi:10.1109/dsn.2014.75

Cited by 6 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The program metrics listed in Table 3 are collected using with NVIDIA's CUDA (6.0) profiler, known as nvprof, on an NVIDIA GTX 560 Ti GPU [23,26]. Table 2 lists detailed specifications of our underlying hardware platform.…”

Section: Methodsmentioning

confidence: 99%

GPGPU Benchmark Suites: How Well Do They Sample the Performance Spectrum?

Ryoo

Quirem²,

LeBeane

et al. 2015

2015 44th International Conference on Parallel Processing

View full text Add to dashboard Cite

Recently, GPGPUs have positioned themselves in the mainstream processor arena with their potential to perform a massive number of jobs in parallel. At the same time, many GPGPU benchmark suites have been proposed to evaluate the performance of GPGPUs. Both academia and industry have been introducing new sets of benchmarks each year while some already published benchmarks have been updated periodically. However, some benchmark suites contain benchmarks that are duplicates of each other or use the same underlying algorithm. This results in an excess of workloads in the same performance spectrum.In this paper, we provide a methodology to obtain a set of new GPGPU benchmarks that are located in the unexplored region of the performance spectrum. Our proposal uses statistical methods to understand the performance spectrum coverage and uniqueness of existing benchmark suites. Later we show techniques to identify areas that are not explored by existing benchmarks by visually showing the performance spectrum coverage. Finding unique key metrics for future benchmarks to broaden its performance spectrum coverage is also explored using hierarchical clustering and ranking by Hotelling's T 2 method. Finally, key metrics are categorized into GPGPU performance related components to show how future benchmarks can stress each of the categorized metrics to distinguish themselves in the performance spectrum. Our methodology can serve as a performance spectrum oriented guidebook for designing future GPGPU benchmarks.

show abstract

Section: Methodsmentioning

confidence: 99%

GPGPU Benchmark Suites: How Well Do They Sample the Performance Spectrum?

Ryoo

Quirem²,

LeBeane

et al. 2015

2015 44th International Conference on Parallel Processing

View full text Add to dashboard Cite

show abstract

“…Two main techniques can be used to test the fault tolerance of computer components: radiation and fault injection [11,12]. A limited number of fault injection tools have been developed for GPUs due to the scarce information about the internal architecture of these accelerators, especially in the case of lowpower GPUs included in embedded system-on-chip (SoC) devices [6,8].…”

Section: Related Workmentioning

confidence: 99%

Evaluating the soft error sensitivity of a GPU-based SoC for matrix multiplication

León

Badía

Belloch

et al. 2020

Microelectronics Reliability

View full text Add to dashboard Cite

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.

show abstract

Damage Reduction via White-Box Failure Shaping

Jones¹,

Ackley²

2018

Search-Based Software Engineering

View full text Add to dashboard Cite

Radiation Sensitivity of High Performance Computing Applications on Kepler-Based GPGPUs

Cited by 6 publications

References 12 publications

GPGPU Benchmark Suites: How Well Do They Sample the Performance Spectrum?

GPGPU Benchmark Suites: How Well Do They Sample the Performance Spectrum?

Evaluating the soft error sensitivity of a GPU-based SoC for matrix multiplication

Damage Reduction via White-Box Failure Shaping

Contact Info

Product

Resources

About