Guest editorial for the special issue on high-performance computing on graphics processing units for field and device modeling

Abstract This work presents a vision of future water resources hydrodynamics codes that can fully utilize the strengths of modern high-performance computing (HPC). The advances to computing power, formerly driven by the improvement of central processing unit processors, now focus on parallel computing and, in particular, the use of graphics processing units (GPUs). However, this shift to a parallel framework requires refactoring the code to make efficient use of the data as well as changing even the nature of the algorithm that solves the system of equations. These concepts along with other features such as the precision for the computations, dry regions management, and input/output data are analyzed in this paper. A 2D multi-GPU flood code applied to a large-scale test case is used to corroborate our statements and ascertain the new challenges for the next-generation parallel water resources codes.

Download Full-text

GPU-UPGMA: high-performance computing for UPGMA algorithm based on graphics processing units

Concurrency and Computation Practice and Experience ◽

10.1002/cpe.3355 ◽

2014 ◽

Vol 27 (13) ◽

pp. 3403-3414 ◽

Cited By ~ 6

Author(s):

Yu-Shiang Lin ◽

Chun-Yuan Lin ◽

Che-Lun Hung ◽

Yeh-Ching Chung ◽

Kual-Zheng Lee

Keyword(s):

High Performance Computing ◽

Graphics Processing Units ◽

High Performance ◽

Graphics Processing ◽

Performance Computing

Download Full-text

Assessment of the Impact of Sand Mining on Bottom Morphology in the Mekong River in An Giang Province, Vietnam, Using a Hydro-Morphological Model with GPU Computing

Water ◽

10.3390/w12102912 ◽

2020 ◽

Vol 12 (10) ◽

pp. 2912 ◽

Cited By ~ 1

Author(s):

Tran Thi Kim ◽

Nguyen Thi Mai Huong ◽

Nguyen Dam Quoc Huy ◽

Pham Anh Tai ◽

Sumin Hong ◽

...

Keyword(s):

Numerical Model ◽

High Performance Computing ◽

Graphics Processing Units ◽

High Performance ◽

Mekong River ◽

Computational Time ◽

Sand Mining ◽

Graphics Processing ◽

The Impact ◽

Performance Computing

Sand mining, among the many activities that have significant effects on the bed changes of rivers, has increased in many parts of the world in recent decades. Numerical modeling plays a vital role in simulation in the long term; however, computational time remains a challenge. In this paper, we propose a sand mining component integrated into the bedload continuity equation and combine it with high-performance computing using graphics processing units to boost the speed of the simulation. The developed numerical model is applied to the Mekong river segment, flowing through Tan Chau Town, An Giang Province, Vietnam. The 20 years from 1999 to 2019 is examined in this study, both with and without sand mining activities. The results show that the numerical model can simulate the bed change for the period from 1999 to 2019. By adding the sand mining component (2002–2006), the bed change in the river is modeled closely after the actual development. The Tan An sand mine in the area (2002–2006) caused the channel to deviate slightly from that of An Giang and created a slight erosion channel in 2006 (−23 m). From 2006 to 2014, although Tan An mine stopped operating, the riverbed recovered quite slowly with a small accretion rate (0.25 m/year). However, the Tan An sand mine eroded again from 2014–2019 due to a lack of sand. In 2014, in the Vinh Hoa communes, An Giang Province, the Vinh Hoa sand mine began to operate. The results of simulating with sand mining incidents proved that sand mining caused the erosion channel to move towards the sand mines, and the erosion speed was faster when there was no sand mining. Combined with high-performance computing, harnessing the power of accelerators such as graphics processing units (GPUs) can help run numerical simulations up to 23x times faster.

Download Full-text

CUDA or OpenCL

Research Advances in the Integration of Big Data and Smart Computing - Advances in Computational Intelligence and Robotics ◽

10.4018/978-1-4666-8737-0.ch015 ◽

2016 ◽

pp. 267-279

Author(s):

Mayank Bhura ◽

Pranav H. Deshpande ◽

K. Chandrasekaran

Keyword(s):

High Performance Computing ◽

Graphics Processing Units ◽

High Performance ◽

Heterogeneous Systems ◽

General Purpose ◽

Programming Environment ◽

Pros And Cons ◽

Nvidia Gpu ◽

Graphics Processing ◽

Performance Computing

Usage of General Purpose Graphics Processing Units (GPGPUs) in high-performance computing is increasing as heterogeneous systems continue to become dominant. CUDA had been the programming environment for nearly all such NVIDIA GPU based GPGPU applications. Still, the framework runs only on NVIDIA GPUs, for other frameworks it requires reimplementation to utilize additional computing devices that are available. OpenCL provides a vendor-neutral and open programming environment, with many implementations available on CPUs, GPUs, and other types of accelerators, OpenCL can thus be regarded as write once, run anywhere framework. Despite this, both frameworks have their own pros and cons. This chapter presents a comparison of the performance of CUDA and OpenCL frameworks, using an algorithm to find the sum of all possible triple products on a list of integers, implemented on GPUs.

Download Full-text

DYRE: a DYnamic REconfigurable solution to increase GPGPU’s reliability

The Journal of Supercomputing ◽

10.1007/s11227-021-03751-2 ◽

2021 ◽

Author(s):

Josie E. Rodriguez Condia ◽

Pierpaolo Narducci ◽

Matteo Sonza Reorda ◽

Luca Sterpone

Keyword(s):

Open Source ◽

High Performance Computing ◽

Graphics Processing Units ◽

High Performance ◽

General Purpose ◽

Reliability Improvement ◽

Permanent Faults ◽

Design Changes ◽

Graphics Processing ◽

Performance Computing

AbstractGeneral-purpose graphics processing units (GPGPUs) are extensively used in high-performance computing. However, it is well known that these devices’ reliability may be limited by the rising of faults at the hardware level. This work introduces a flexible solution to detect and mitigate permanent faults affecting the execution units in these parallel devices. The proposed solution is based on adding some spare modules to perform two in-field operations: detecting and mitigating faults. The solution takes advantage of the regularity of the execution units in the device to avoid significant design changes and reduce the overhead. The proposed solution was evaluated in terms of reliability improvement and area, performance, and power overhead costs. For this purpose, we resorted to a micro-architectural open-source GPGPU model (FlexGripPlus). Experimental results show that the proposed solution can extend the reliability by up to 57%, with overhead costs lower than 2% and 8% in area and power, respectively.

Download Full-text