scholarly journals Scientific Programming with High Performance Fortran: A Case Study Using the xHPF Compiler

1997 ◽  
Vol 6 (1) ◽  
pp. 127-152
Author(s):  
Eric De Sturler ◽  
Volker Strumpen
Keyword(s):  
High Performance ◽  
Parallel Implementation ◽  
Gaussian Elimination ◽  
Primary Objective ◽  
Matrix Product ◽  
Dense Matrix ◽  
High Performance Fortran ◽  
Partial Pivoting ◽  
Intel Paragon

Recently, the first commercial High Performance Fortran (HPF) subset compilers have appeared. This article reports on our experiences with the xHPF compiler of Applied Parallel Research, version 1.2, for the Intel Paragon. At this stage, we do not expect very High Performance from our HPF programs, even though performance will eventually be of paramount importance for the acceptance of HPF. Instead, our primary objective is to study how to convert large Fortran 77 (F77) programs to HPF such that the compiler generates reasonably efficient parallel code. We report on a case study that identifies several problems when parallelizing code with HPF; most of these problems affect current HPF compiler technology in general, although some are specific for the xHPF compiler. We discuss our solutions from the perspective of the scientific programmer, and presenttiming results on the Intel Paragon. The case study comprises three programs of different complexity with respect to parallelization. We use the dense matrix-matrix product to show that the distribution of arrays and the order of nested loops significantly influence the performance of the parallel program. We use Gaussian elimination with partial pivoting to study the parallelization strategy of the compiler. There are various ways to structure this algorithm for a particular data distribution. This example shows how much effort may be demanded from the programmer to support the compiler in generating an efficient parallel implementation. Finally, we use a small application to show that the more complicated structure of a larger program may introduce problems for the parallelization, even though all subroutines of the application are easy to parallelize by themselves. The application consists of a finite volume discretization on a structured grid and a nested iterative solver. Our case study shows that it is possible to obtain reasonably efficient parallel programs with xHPF, although the compiler needs substantial support from the programmer.

scholarly journals Performance Issues in High Performance Fortran Implementations of Sensor-Based Applications

1997 ◽  
Vol 6 (1) ◽  
pp. 59-72 ◽  
Author(s):  
David R. O'hallaron ◽  
Jon Webb ◽  
Jaspal Subhlok
Keyword(s):  
High Performance ◽  
Parallel Machines ◽  
Radar Imaging ◽  
Synthetic Aperture ◽  
Application Domain ◽  
Resonance Imaging ◽  
High Performance Fortran ◽  
Intel Paragon ◽  
Independent Loops ◽  
Tracking Radar

Applications that get their inputs from sensors are an important and often overlooked application domain for High Performance Fortran (HPF). Such sensor-based applications typically perform regular operations on dense arrays, and often have latency and through put requirements that can only be achieved with parallel machines. This article describes a study of sensor-based applications, including the fast Fourier transform, synthetic aperture radar imaging, narrowband tracking radar processing, multibaseline stereo imaging, and medical magnetic resonance imaging. The applications are written in a dialect of HPF developed at Carnegie Mellon, and are compiled by the Fx compiler for the Intel Paragon. The main results of the study are that (1) it is possible to realize good performance for realistic sensor-based applications written in HPF and (2) the performance of the applications is determined by the performance of three core operations: independent loops (i.e., loops with no dependences between iterations), reductions, and index permutations. The article discusses the implications for HPF implementations and introduces some simple tests that implementers and users can use to measure the efficiency of the loops, reductions, and index permutations generated by an HPF compiler.

A HIGH PERFORMANCE PARALLEL STRASSEN IMPLEMENTATION

1996 ◽  
Vol 06 (01) ◽  
pp. 3-12 ◽  
Author(s):  
BRIAN GRAYSON ◽  
ROBERT VAN DE GEIJN
Keyword(s):  
Execution Time ◽  
High Performance ◽  
Parallel Implementation ◽  
Matrix Multiplication ◽  
Intel Paragon ◽  
Strassen’S Algorithm ◽  
Strassen's Algorithm

In this paper, we give a practical high performance parallel implementation of Strassen’s algorithm for matrix multiplication. We show how under restricted conditions, this algorithm can be implemented plug compatible with standard parallel matrix multiplication algorithms. Results obtained on a large Intel Paragon system show a 10– 20% reduction in execution time compared to what we believe to be the fastest standard parallel matrix multiplication implementation available at this time.

LU decomposition

2020 ◽  
pp. 74-133
Author(s):  
Rob H. Bisseling
Keyword(s):  
Cost Analysis ◽  
Linear Systems ◽  
High Performance ◽  
Gaussian Elimination ◽  
Collective Communication ◽  
Dense Matrix ◽  
Lu Decomposition ◽  
Two Phase ◽  
Matrix Computations ◽  
Communication Method

This chapter discusses parallel dense matrix computations, in particular the solution of linear systems by LU decomposition with partial row pivoting. It first presents a general Cartesian scheme for the distribution of matrices. Based on BSP cost analysis, the square cyclic distribution is proposed as particularly suitable for matrix computations such as LU decomposition and Gaussian elimination. The chapter introduces two-phase broadcasting of vectors, which is a useful collective-communication method for sending copies of matrix rows or columns to a group of processors. It also discusses how to achieve high performance by delaying rank-1 matrix updates to create a multiple-rank update, which can be carried out by multiplying tall-and-skinny matrices in a cache-friendly manner. The high-performance parallel LU decomposition is tested on a top-ranking supercomputer, and its performance is analysed with respect to computation, communication, and synchronization.

THE USE OF CASE STUDY METHOD IN TEACHING THE TERMINOLOGY IN THE FIELD OF AGRICULTURAL MACHINERY

2019 ◽  
pp. 123-130
Keyword(s):  
Case Studies ◽  
High Performance ◽  
Mechanical Engineering ◽  
The United States ◽  
Machine Building ◽  
Soil Tillage ◽  
Case Study Method ◽  
Agricultural Machine ◽  
Manufacturing Machine

The scientific research works concerning the field of mechanical engineering such as, manufacturing machine slate, soil tillage, sowing and harvesting based on the requirements for the implementation of agrotechnical measures for the cultivation of plants in its transportation, through the development of mastering new types of high-performance and energy-saving machines in manufacturing machine slate, creation of multifunctional machines, allowing simultaneous soil cultivation, by means of several planting operations, integration of agricultural machine designs are taken into account in manufacturing of the local universal tractor designed basing on high ergonomic indicators. For this reason, this article explores the use of case studies in teaching agricultural terminology by means analyzing the researches in machine building. Case study method was firstly used in 1870 in Harvard University of Law School in the United States. Also in the article, we give the examples of agricultural machine-building terms, teaching terminology and case methods, case study process and case studies method itself. The research works in the field of mechanical engineering and the use of case studies in teaching terminology have also been analyzed. In addition, the requirements for the development of case study tasks are given in their practical didactic nature. We also give case study models that allow us analyzing and evaluating students' activities.

Design of water allocation model: efficiency and risk aspects

2005 ◽  
Vol 5 (3-4) ◽  
pp. 9-16
Author(s):  
C. Kim ◽  
D. Han
Keyword(s):  
Water Allocation ◽  
Primary Objective ◽  
Allocation Model ◽  
Proportional Allocation ◽  
Model Efficiency ◽  
Service Sectors ◽  
Expected Benefits ◽  
Water Allocation Model ◽  
Allocation Methods

The primary objective of this study is to improve the methodology for water allocation focused on efficiency and risk aspects. To attain the primary objective, this study sets up an objective function to maximize social expected benefits, and considers three types of allocation methods. Three types of allocation methods are optimal, proportional, and fixed allocation between regions and service sectors. The results of case study area shows that the fixed allocation method is preferred to the proportional allocation in most cases except that the variance of flow is small with respect to efficiency. Also, efficient and less-risky allocation is simultaneously obtained in some cases, while efficiency and risk show the relation of trade-off in other cases.

scholarly journals Neighborhood Energy Modeling and Monitoring: A Case Study

Energies ◽  
2021 ◽  
Vol 14 (12) ◽  
pp. 3716
Author(s):  
Francesco Causone ◽  
Rossano Scoccia ◽  
Martina Pelle ◽  
Paola Colombo ◽  
Mario Motta ◽  
...  
Keyword(s):  
High Performance ◽  
High Efficiency ◽  
Early Stage ◽  
Energy Performance ◽  
Monitoring Plan ◽  
Performance Targets ◽  
Carrier Energy ◽  
Zero Carbon ◽  
Energy Grid

Cities and nations worldwide are pledging to energy and carbon neutral objectives that imply a huge contribution from buildings. High-performance targets, either zero energy or zero carbon, are typically difficult to be reached by single buildings, but groups of properly-managed buildings might reach these ambitious goals. For this purpose we need tools and experiences to model, monitor, manage and optimize buildings and their neighborhood-level systems. The paper describes the activities pursued for the deployment of an advanced energy management system for a multi-carrier energy grid of an existing neighborhood in the area of Milan. The activities included: (i) development of a detailed monitoring plan, (ii) deployment of the monitoring plan, (iii) development of a virtual model of the neighborhood and simulation of the energy performance. Comparisons against early-stage energy monitoring data proved promising and the generation system showed high efficiency (EER equal to 5.84), to be further exploited.

Hardware Accelerator Integration Tradeoffs for High-Performance Computing: A Case Study of GEMM Acceleration in N-Body Methods

2021 ◽  
Vol 32 (8) ◽  
pp. 2035-2048
Author(s):  
Mochamad Asri ◽  
Dhairya Malhotra ◽  
Jiajun Wang ◽  
George Biros ◽  
Lizy K. John ◽  
...  
Keyword(s):  
High Performance Computing ◽  
High Performance ◽  
Hardware Accelerator ◽  
Performance Computing
Sign in / Sign up

Export Citation Format

Share Document