On Generalizing Divide and Conquer Parallel Programming Pattern

نویسندگان

چکیده

(1) Background: Structuring is important in parallel programming order to master its complexity, and this structuring could be achieved through patterns skeletons. Divide-and-conquer computation essentially defined by a recurrence relation that links the solution of problem solutions subproblems same type, but smaller sizes. This pattern allows specification different types computations, so it provide general comprises all cases. We intend prove divide-and-conquer generalized such comprise many other patterns, this, we formulation it. (2) Methods: Starting from proposed pattern, analyzed based on stages: decomposition, base-case composition. Examples are provided, execution models analyzed. (3) Results: functional provided for it, specialized parameters’ instantiating into classical patterns. Based specific stages divide-and-conquer, three classes computations emphasized. In context, an equivalent efficient bottom-up formally proved. Associated executions emphasized computations. (4) Conclusion: A more definition includes arity list decomposition degrees, level recursion, also alternative cases not trivial allow approaches (sequential or parallel) lead better performance. Together with associated analysis equivalence optimized models, provides useful both at semantic implementation level.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Parallel Divide and Conquer on Meshes

We address the problem of mapping divide-and-conquer programs to mesh connected multicomputers with wormhole or store-and-forward routing. We propose the binomial tree as an eecient model of parallel divide-and-conquer and present two mappings of the binomial tree to the 2D mesh. Our mappings exploit regularity in the communication structure of the divide-and-conquer computation and are also se...

متن کامل

Task Parallel Skeletons for Divide and Conquer

Algorithmic skeletons intend to simplify parallel programming by providing recurring forms of program structure as predefined components. We present a fully distributed task parallel skeleton for a very general class of divide and conquer algorithms for MIMD machines with distributed memory. This approach is compared to a simple masterworker design. Based on experimental results for different e...

متن کامل

Complexity for Parallel Divide - and - Conquer

This paper studies the relationship between parallel computation cost and communication cost for performing divide-and-conquer (D&C) computations on a parallel system of p processors. The parallel computation cost is the maximal number of the D&C nodes that any processor in the parallel system may expand, whereas the communication cost is the total number of cross nodes. A cross node is a node ...

متن کامل

Communication Complexity for Parallel Divide-and-Conquer

This paper studies the relationship between parallel computation cost and communication cost for performing divide-and-conquer (D&C) computations on a parallel system of p processors. The parallel computation cost is the maximal number of the D&C nodes that any processor in the parallel system may expand, whereas the communication cost is the total number of cross nodes. A cross node is a node ...

متن کامل

A Fast Parallel Squarer Based on Divide and Conquer

Fast and small squarers are needed in many applications such as image compression A new family of high performance parallel squarers based on the divide and conquer method is reported Our main result was realizing the basis cases of the divide and conquer recursion by using optimized n bit primitive squarers where n is in the range of to This method reduced the gate count and provided shorter c...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Mathematics

سال: 2022

ISSN: ['2227-7390']

DOI: https://doi.org/10.3390/math10213925