Performance Assessment Of Parallel Techniques
Free (open access)
T. Grytsenko & A. Peratta
The goal of this work is to evaluate and compare the computational performance of the most common parallel libraries such as Message Passing Interface (MPI), High Performance Fortran (HPF), OpenMP and DVM for further implementations. Evaluation is based on NAS Parallel benchmark suite (NPB) which includes simulated applications BT, SP, LU and kernel benchmarks FT, CG and MG. A brief introduction of the four parallel techniques under study: MPI, HPF, OpenMP and DVM, as well as their models is provided together with benchmarks used and the test results. Finally, corresponding recommendations are given for the different approaches depending on the number of processors. Keywords: MPI, HPL, DVM, OpenMP, parallel programming, performance, parallel calculations. 1 Introduction This section provides a brief introduction of the four parallel techniques under study: MPI, HPF, OpenMP and DVM, as well as their models. 1.1 The Message-Passing Information programming model (MPI) Programming models are generally categorised according to the way in which how memory is used. In the shared memory model each process accesses a shared address space, while in the message passing model an application runs as a collection of autonomous processes, each with its own local memory. In the message passing model processes communicate with other processes by sending and receiving messages (see Figure 1). When data is passed in a message, the sending and receiving processes must work to transfer the data from the local memory of one to the local memory of the other.
MPI, HPL, DVM, OpenMP, parallel programming, performance, parallel calculations.