A Generalized Scheme for Mapping Parallel Algorithms
نویسندگان
چکیده
The mapping problem arises when the dependency structure of a parallel algorithm differs from the processor interconnection of the parallel computer or when the number of processes generated by the algorithm exceeds the number of processors available. The mapping problem (also known as task allocation) has been widely studied. We propose a new generalized mapping strategy that uses a combination of graph theory, mathematical programming, and heuristics. The key difference between our strategy and those proposed previously is the interdependence between the algorithm and the architecture. We use the knowledge from the given algorithm and the architecture to guide the mapping. The approach begins with a graphical representation of the parallel algorithm (problem graph) and the parallel computer (host graph). Using these representations, we generate a new graphical representation (extended host graph) on which the problem graph is mapped. We use an accurate characterization of the communication overhead in our objective functions to evaluate the optimality of the mapping. An efficient mapping scheme is developed which uses two levels of optimization procedures. The objective functions include minimizing the communication overhead and minimizing the total execution time which includes both computation and communication times. The mapping scheme is tested by simulation and further confirmed by mapping a real world application onto actual distributed environments.
منابع مشابه
An Iterative Scheme for Generalized Equilibrium, Variational Inequality and Fixed Point Problems Based on the Extragradient Method
The problem ofgeneralized equilibrium problem is very general in the different subjects .Optimization problems, variational inequalities, Nash equilibrium problem and minimax problems are as special cases of generalized equilibrium problem. The purpose of this paper is to investigate the problem of approximating a common element of the set of generalized equilibrium problem, variational inequal...
متن کاملImproved Schemes for Mapping Arbitrary Algorithms Onto Processor Meshes
We address the problem of eecient schemes for mapping arbitrary parallel algorithms onto distributed memory message passing multiprocessors with mesh topologies. We analyze a particular mapping scheme, nd the reasons for its low eeciency, and show that mapped algorithms tend to be both wider and higher than necessary. As a result, they generally execute too slow while at the same time occupying...
متن کاملHigh speed Radix-4 Booth scheme in CNTFET technology for high performance parallel multipliers
A novel and robust scheme for radix-4 Booth scheme implemented in Carbon Nanotube Field-Effect Transistor (CNTFET) technology has been presented in this paper. The main advantage of the proposed scheme is its improved speed performance compared with previous designs. With the help of modifications applied to the encoder section using Pass Transistor Logic (PTL), the corresponding capacitances o...
متن کاملKinematic Mapping and Forward Kinematic Problem of a 5-DOF (3T2R) Parallel Mechanism with Identical Limb Structures
The main objective of this paper is to study the Euclidean displacement of a 5-DOF parallel mechanism performing three translation and two independent rotations with identical limb structures-recently revealed by performing the type synthesis-in a higher dimensional projective space, rather than relying on classical recipes, such as Cartesian coordinates and Euler angles. In this paper, Study's...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- IEEE Trans. Parallel Distrib. Syst.
دوره 4 شماره
صفحات -
تاریخ انتشار 1993