检索结果-内蒙古大学图书馆

multi-gpu parallelization of the NAS multi-Zone Parallel Benchmarks

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 2021年第1期32卷 229-241页

作者： Gonzalez, Marc Morancho, Enric Univ Politecn Cataluna Comp Architecture Dept Barcelona Tech Barcelona 08034 Spain

gpu-based computing systems have become a widely accepted solution for the high-performance-computing (HPC) domain. gpus have shown highly competitive performance-per-watt ratios and can exploit an astonishing level of parallelism. However, exploiting the peak performance of such devices is a challenge, mainly due to the combination of two essential aspects of multi-gpu execution. On one hand, the workload should be distributed evenly among the gpus. On the other hand, communications between gpu devices are costly and should be minimized. Therefore, a trade-of between work-distribution schemes and communication overheads will condition the overall performance of parallel applications run on multi-gpu systems. In this article we present a multi-gpu implementation of NAS multi-Zone Parallel Benchmarks (which execution alternate communication and computational phases). We propose several work-distribution strategies that try to evenly distribute the workload among the gpus. Our evaluations show that performance is highly sensitive to this distribution strategy, as the the communication phases of the applications are heavily affected by the work-distribution schemes applied in computational phases. In particular, we consider Static, Dynamic, and Guided schedulers to find a trade-off between both phases to maximize the overall performance. In addition, we compare those schedulers with an optimal scheduler computed offline using IBM CPLEX. On an evaluation environment composed of 2 x IBM Power9 8335-GTH and 4 x gpu NVIDIA V100 (Volta), our multi-gpu parallelization outperforms single-gpu execution from 1.48x to 1.86x (2 gpus) and from 1.75x to 3.54x (4 gpus). This article analyses these improvements in terms of the relationship between the computational and communication phases of the applications as the number of gpus is increased. We prove that Guided schedulers perform at similar level as optimal schedulers.

关键词： Benchmark testing Graphics processing units Parallel processing Dynamic scheduling Performance evaluation Optimal scheduling Load management multi-gpu parallelization load balancing static dynamic guided schedulings

来源：评论

学校读者我要写书评

暂无评论

parallelization Efficiency of multi-gpu In-Core LU-Decomposition of Dense Matrices

Parallelization Efficiency of Multi-GPU In-Core LU-Decomposi...

引用

USNC-URSI Radio Science Meeting / IEEE International Symposium on Antennas and Propagation (AP-S)

作者： Teneh, Nimrod Mrdakovic, Branko Lj Kostic, Milan M. Olcan, Dragan, I Kolundzija, Branko M. Elta Syst Ltd Grp & Subsidiary IAI Ltd Airborne Syst & Radars Div Ashdod Israel WIPL Ddoo Gandijeva 7-32 Belgrade 11073 Serbia Univ Belgrade Dept Elect Engn King Alexander Blvd 73 Belgrade 11120 Serbia

ISBN: (纸本)9781728106922

Acceleration of in-core LU decomposition of a dense MoM matrix by using multiple gpus in parallel, is presented in this paper. Results for nonsymmetrical and symmetrical matrices are shown. Limitations for further increasing the parallelization efficiency and the ways for overcoming these limitations are discussed. The achieved acceleration efficiency is high (about 65%), but remains limited by the speed of data transfers between CPU RAM and gpus VRAM.

关键词： in-core LU decomposition non-symmetrical and symmetrical matrix multi-gpu parallelization parallelization efficiency

来源：评论

学校读者我要写书评

暂无评论

Development of multi-gpu-Based Smoothed Particle Hydrodynamics Code for Nuclear Thermal Hydraulics and Safety: Potential and Challenges

引用

FRONTIERS IN ENERGY RESEARCH 2020年 8卷

作者： Park, So-Hyun Jo, Young Beom Ahn, Yelyn Choi, Hae Yoon Choi, Tae Soo Park, Su-San Yoo, Hee Sang Kim, Jin Woo Kim, Eung Soo Seoul Natl Univ Dept Nucl Engn Seoul South Korea

Advanced modeling and analysis are always essential for the development of safe and reliable nuclear systems. Traditionally, the numerical analysis codes used for nuclear thermal hydraulics and safety are mostly based on mesh-based (or grid-based) methods, which are very mature for well-defined and fixed domains, both mathematically and numerically. In support of their robustness and efficiency, they have been well-fit into many nuclear applications for the last several decades. However, the recent nuclear safety issues encountered in natural disasters and severe accidents are associated with much more complex physical/chemical phenomena, and they are frequently accompanied by highly non-linear deformations. Sometimes, this means that the conventional methods encounter many difficult technical challenges. In this sense, the recent advancement in the Lagrangian-based CFD method shows great potential as a good alternative. This paper summarizes recent activities in the development of the SOPHIA code using Smoothed Particle Hydrodynamics (SPH), a well-known Lagrangian numerical method. This code incorporates the basic conservation equations (mass, momentum, and energy) and various physical models, including heat transfer, turbulence, multi-phase flow, surface tension, diffusion, etc. Additionally, the code newly formulates density and continuity equations in terms of a normalized density in order to handle multi-phase, multi-component, and multi-resolution problems. The code is parallelized using multiple graphical process units (gpus) through multi-threading and multi-streaming in order to reduce the high computational cost. In the course of the optimization of the algorithm, the computational performance is improved drastically, allowing large-scale simulations. For demonstration of its applicability, this study performs three benchmark simulations related to nuclear safety: (1) water jet breakup of FCI, (2) LMR core melt sloshing, and (3) bubble lift force. The simu

关键词： Lagrangian CFD Smoothed Particle Hydrodynamics multi-gpu parallelization severe accident Fuel Coolant Interaction LMR core sloshing

来源：评论

学校读者我要写书评

暂无评论

In-Core LU-Decomposition of Symmetrical Dense MoM Matrix in WIPL-D multi-gpu Solver

In-Core LU-Decomposition of Symmetrical Dense MoM Matrix in ...

引用

IEEE Indian Conference on Antennas and Propogation (InCAP)

作者： Mrdakovic, Branko Lj. Kostic, Milan M. Olcan, Dragan I. Kolundzija, Branko M. WIPL D Doo Gandijeva 7-32 Belgrade 11073 Serbia Univ Belgrade Dept Elect Engn Bul King Alexander 73 Belgrade 11120 Serbia

ISBN: (纸本)9781538670606

Acceleration of in-core LU decomposition of symmetrical dense MoM matrices by using multiple gpus in parallel is presented in this paper. Memory limitations of gpus are overcome by using block LU decomposition, where the entire system matrix is stored in CPU RAM, while only processed blocks are stored in gpu VRAM. The presented algorithm for LU decomposition enables highly efficient utilization of an arbitrary number of gpus. Comparison of performance of up to 4 GTX 680 gpus and up to 4 GTX 1080 Ti gpus is shown. Presented results show that a symmetrical dense MoM matrix with 100 000 complex unknowns in single precision can be LU decomposed in about 3.5 minutes, on a personal computer equipped with 4 GTX 1080 Ti gpus.

关键词： MoM SIE in core LU decomposition symmetrical matrix gpu multi-gpu parallelization

来源：评论

学校读者我要写书评

暂无评论

New Generation of WIPL-D In-Core multi-gpu Solver

New Generation of WIPL-D In-Core Multi-GPU Solver

引用

IEEE-Antennas-and-Propagation-Society International Symposium on Antennas and Propagation / USNC/URSI National Radio Science Meeting

作者： Mrdakovic, Branko Lj. Kostic, Milan M. Olcan, Dragan I. Kolundzija, Branko M. WIPL Ddoo Gandijeva 7-32 Belgrade 11073 Serbia Univ Belgrade Dept Elect Engn Bul King Alexander 73 Belgrade 11120 Serbia

ISBN: (纸本)9781538671023

Acceleration of in-core LU decomposition by using multiple gpus in parallel and comparison of performance of two different gpu types, is presented in this paper. The presented algorithm for LU decomposition enables highly efficient utilization of an arbitrary number of gpus. Comparison of performance of up to 8 GTX 680 gpus and up to 4 GTX 1080 Ti gpus is shown. The results presented show that a dense MoM matrix with 100 000 complex unknowns in single precision can be LU decomposed in 3.7 minutes, on a personal computer equipped with 4 GTX 1080 Ti gpus.

关键词： in-core LU decomposition gpu multi-gpu parallelization

来源：评论

学校读者我要写书评

暂无评论

Low-effort task distribution of stencil computation on heterogeneous multi-gpus: simulating graphene superlattices 26

Low-effort task distribution of stencil computation on heter...

引用

26th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP)

作者： Rodrigues, M. Fernandes, D. Silveirinha, M. Falcao, G. Univ Coimbra Inst Telecomunicacoes Dept Elect & Comp Engn P-3030290 Coimbra Portugal Univ Lsiboa Inst Super Tecn Ave Rovisco Pais 1 P-1049001 Lisbon Portugal

ISBN: (纸本)9781538649756

This paper proposes a low-cost workload distribution technique for the compute-intensive simulation of electron waves propagating in graphene superlattices, by fully exploiting the compute resources of heterogeneous gpus concurrently. As old gpus start failing and new ones are launched in the market, we equip our labs with more recent hardware, creating a variety of distinct gpu families that have non-negligent processing power available, but sometimes unused. Here we show how to exploit them with reduced parallel programming effort of the workload distribution on heterogeneous multi-gpu systems. The speedups obtained when comparing execution against uniform workload distribution (i.e. the same workload on each gpu) range from 1.2x up to 1.8x.

关键词： Electron wave simulation Graphene superlattice Stencil computation High-performance computing Dynamic workload distribution multi-gpu parallelization

来源：评论

学校读者我要写书评

暂无评论

Acceleration of In-Core LU-Decomposition of Dense MoM Matrix by Parallel usage of multiple gpus

Acceleration of In-Core LU-Decomposition of Dense MoM Matrix...

引用

IEEE International Conference on Microwaves, Antennas, Communications and Electronic Systems (COMCAS)

作者： Mrdakovic, Branko Lj. Kostic, Milan M. Olcan, Dragan I. Kolundzija, Branko M. WIPL D Doo Gandijeva 7-32 Belgrade 11073 Serbia Univ Belgrade Sch Elect Engn King Alexanders Blvd 73 Belgrade 11120 Serbia

ISBN: (纸本)9781538631690

Acceleration of in-core LU decomposition by using multiple gpus in parallel is presented in this paper. Memory limitations of gpus are overcome by using block LU decomposition, where the entire system matrix is stored in CPU RAM, while only currently processed blocks are stored in gpu VRAM. The presented algorithm for LU decomposition enables utilization of an arbitrary number of gpus. High efficiency of the parallelization is achieved by specifically tailored load balancing over the gpus in the most time consuming parts of the block LU decomposition. Presented results show that a dense MoM matrix with 100 000 complex unknowns in single precision can be LU decomposed in about 8 minutes, on a personal computer equipped with 8 low-cost GTX 680 gpus.

关键词： MoM SIE in-core LU decomposition gpu multi-gpu parallelization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：