Abstract: Homemade HPC clusters are widely used in many small labs, because they are easy to build and cost-effective. Even though incremental growth is an advantage of clusters, it results in heterogeneous systems anyhow. Instead of adding new nodes to the cluster, we can extend clusters to include some other Internet servers working independently on the same LAN, so that we can make use of their idle times, especially during the night. However extension across a firewall raises some security problems with NFS. In this paper, we propose a method to solve such a problem using SSH tunneling, and suggest a modified structure of the cluster that implements it.
Abstract: In this paper we present the PC cluster built at R.V.
College of Engineering (with great help from the Department of
Computer Science and Electrical Engineering). The structure of the
cluster is described and the performance is evaluated by rendering of
complex 3D Persistence of Vision (POV) images by the Ray-Tracing
algorithm. Here, we propose an unexampled method to render such
images, distributedly on a low cost scalable.
Abstract: The rapid improvement of the microprocessor and network has made it possible for the PC cluster to compete with conventional supercomputers. Lots of high throughput type of applications can be satisfied by using the current desktop PCs, especially for those in PC classrooms, and leave the supercomputers for the demands from large scale high performance parallel computations. This paper presents our development on enabling an automated deployment mechanism for cluster computing to utilize the computing power of PCs such as reside in PC classroom. After well deployment, these PCs can be transformed into a pre-configured cluster computing resource immediately without touching the existing education/training environment installed on these PCs. Thus, the training activities will not be affected by this additional activity to harvest idle computing cycles. The time and manpower required to build and manage a computing platform in geographically distributed PC classrooms also can be reduced by this development.
Abstract: This paper proposes a new approach to offer a private
cloud service in HPC clusters. In particular, our approach relies on
automatically scheduling users- customized environment request as a
normal job in batch system. After finishing virtualization request jobs,
those guest operating systems will dismiss so that compute nodes will
be released again for computing. We present initial work on the
innovative integration of HPC batch system and virtualization tools
that aims at coexistence such that they suffice for meeting the
minimizing interference required by a traditional HPC cluster. Given
the design of initial infrastructure, the proposed effort has the potential
to positively impact on synergy model. The results from the
experiment concluded that goal for provisioning customized cluster
environment indeed can be fulfilled by using virtual machines, and
efficiency can be improved with proper setup and arrangements.