Simplex Parallelization in a Fully Hybrid Hardware Platform
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2017, Vol 8, Issue 4
Abstract
The simplex method has been successfully used in solving linear programming (LP) problems for many years. Parallel approaches have also extensively been studied due to the intensive computations required, especially for the solution of large LP problems. Furthermore, the rapid proliferation of multicore CPU architectures as well as the computational power provided by the massive parallelism of modern GPUs have turned CPU / GPU collaboration models increasingly into focus over the last years for better performance. In this paper, a highly scalable implementation framework of the standard full tableau simplex method is first presented, over a hybrid parallel platform which consists of multiple multicore nodes interconnected via a high-speed communication network. The proposed approach is based on the combined use of MPI and OpenMP, adopting a suitable column-based distribution scheme for the simplex tableau. The parallelization framework is then extended in such a way that it can exploit concurrently the full power of the provided resources on a multicore single-node environment with a CUDA-enabled GPU (i.e. using the CPU cores and the GPU concurrently), based on a suitable hybrid multithreading/GPU offloading scheme with OpenMP and CUDA. The corresponding experimental results show that the hybrid MPI+OpenMP based parallelization scheme leads to particularly high speed-up and efficiency values, considerably better than in other competitive approaches, and scaling well even for very large / huge linear problems. Furthermore, the performance of the hybrid multithreading/GPU offloading scheme is clearly superior to both the OpenMP-only and the GPU-only based implementations in almost all cases, which validates the worth of using both resources concurrently. The most important, when it is used in combination with MPI in a multi-node (fully hybrid) environment, it leads to substantial improvements in the speedup achieved for large and very large LP problems.
Authors and Affiliations
Basilis Mamalis, Marios Perlitis
Keywords
Related Articles
- EP ID EP258366
- DOI 10.14569/IJACSA.2017.080449
- Views 100
- Downloads 0
Testing and Analysis of Activities of Daily Living Data with Machine Learning Algorithms
It is estimated that 28% of European Union’s population will be aged 65 or older by 2060. Europe is getting older and this has a high impact on the estimated cost to be spent for older people. This is because, compared t...
SME Cloud Adoption in Botswana: Its Challenges and Successes
The standard office or business in Botswana hosts their resources in-house. This means that a company will have their hardware, software and support staff as part of their daily work operations. Technology has brought a...
Inferring of Cognitive Skill Zones in Concept Space of Knowledge Assessment
In these research zones of the knowledge, the assessed domain is identified. Explicitly, these zones are known as Verified Skills, Derived Skills and Potential Skills. In detail, the Verified Skills Zone is the set of te...
TCP- Costco Reno: New Variant by Improving Bandwidth Estimation to adapt over MANETs
The Transmission Control Protocol (TCP) is traditional, dominant and has been de facto standard protocol, used as transport agent at transport layer of TCP/IP protocol suite. Basically it is designed to provide reliabili...
Impact of Privacy Issues on Smart City Services in a Model Smart City
With the recent technological development, there is prevalent trend for smart infrastructure deployment with intention to provide smart services for inhabitants. City governments of current era are under huge pressure to...