CGUW: A system software for heterogeneous IPC mechanism in grid computing environments

Interprocess communication mechanisms, one of the effective factors for response time in High performance computing. Existing standards for interprocess communication between a heterogeneous operating systems such as MPI implementation at library level lead to lower performance and Increase response time compared to implementation at the operating system kernel level. We propose an approach to enable the use of IPC in heterogeneous distributed systems such as grid computing. This mechanism uses distributed shared memory for communication between Linux and Windows operating systems. Windows IPC mechanism uses shared memory and remote procedural call. Linux Inter-process communication (IPC) converting Windows remote procedure call (RPC) to Proportional System V shared memory in kernel level. We propose wrapper for the use of our mechanism with distributed application.

[1]  Mohsen Sharifi,et al.  A platform independent distributed IPC mechanism in support of programming heterogeneous distributed systems , 2010, The Journal of Supercomputing.

[2]  Alan L. Cox,et al.  TreadMarks: Distributed Shared Memory on Standard Workstations and Operating Systems , 1994, USENIX Winter.

[3]  Dhabaleswar K. Panda,et al.  Virtual machine aware communication libraries for high performance computing , 2007, Proceedings of the 2007 ACM/IEEE Conference on Supercomputing (SC '07).

[4]  Peng Wu,et al.  MPI-Based Heterogeneous Cluster Construction Technology , 2012, 2012 11th International Symposium on Distributed Computing and Applications to Business, Engineering & Science.

[5]  Ibad Kureshi,et al.  Hybrid Computer Cluster with High Flexibility , 2012, 2012 IEEE International Conference on Cluster Computing Workshops.

[6]  Jyh-Biau Chang,et al.  A grid-enabled software distributed shared memory system on a wide area network , 2007, Future Gener. Comput. Syst..

[7]  S. Shah,et al.  Resource optimization in a LAN environment using SMIG-shared memory integrated with grid , 2011, ICWET.

[8]  S.L. Mirtaheri,et al.  A Case for Kernel Level Implementation of Inter Process Communication Mechanisms , 2008, 2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications.

[9]  Bastien Chopard,et al.  MUSCLE-HPC: A new high performance API to couple multiscale parallel applications , 2017, Future Gener. Comput. Syst..

[10]  John B. Carter,et al.  Design of the Munin Distributed Shared Memory System , 1995, J. Parallel Distributed Comput..

[11]  V. Chaudhary,et al.  TECHNIQUES FOR MIGRATING COMPUTATIONS ON THE GRID , 2005 .

[12]  Brian A. Coghlan,et al.  SMG : SHARED MEMORY FOR GRIDS , 2022 .

[13]  Brian N. Bershad,et al.  The Midway distributed shared memory system , 1993, Digest of Papers. Compcon Spring.

[14]  L ScottMichael,et al.  Shared memory computing on clusters with symmetric multiprocessors and system area networks , 2005 .

[15]  Weisong Shi,et al.  JIAJIA: A Software DSM System Based on a New Cache Coherence Protocol , 1999, HPCN Europe.

[16]  Andreas Hammar.  Analysis and Design of High Performance Inter-core Process Communication for Linux , 2014 .

[17]  Galen C. Hunt,et al.  Shared memory computing on clusters with symmetric multiprocessors and system area networks , 2005, TOCS.

[18]  Kenli Li,et al.  A Fast RPC System for Virtual Machines , 2013, IEEE Transactions on Parallel and Distributed Systems.

[19]  Jameleddine Hassine,et al.  Segmenting large traces of inter-process communication with a focus on high performance computing systems , 2016, J. Syst. Softw..

[20]  Mohsen Sharifi,et al.  An Efficient Live Process Migration Approach for High Performance Cluster Computing Systems , 2011 .

[21]  Weisong Shi,et al.  Evaluation of the JIAJIA software DSM system on high performance computer architectures , 1999, Proceedings of the 32nd Annual Hawaii International Conference on Systems Sciences. 1999. HICSS-32. Abstracts and CD-ROM of Full Papers.

[22]  Dhabaleswar K. Panda,et al.  Designing high performance communication runtime for GPU managed memory: early experiences , 2016, GPGPU@PPoPP.

[23]  Kai Li,et al.  IVY: A Shared Virtual Memory System for Parallel Computing , 1988, ICPP.