Parallel Programming Constructs For Divide-And Conquer, And Branch-And-Bound Paradigms

1985 ◽  
Vol 23 (4) ◽  
pp. 403-416
Author(s):  
Jaroslav Opatrny
Keyword(s):  
Parallel Programming ◽  
Branch And Bound ◽  
Divide And Conquer

scholarly journals Investigating Parallel Programming Paradigms in HeMPS MPSoC Platform

2019 ◽  
Author(s):  
Geaninne Lopes ◽  
Aline Mello ◽  
Ewerson Carvalho ◽  
César Marcon
Keyword(s):  
Parallel Programming ◽  
Power Dissipation ◽  
Execution Time ◽  
Matrix Multiplication ◽  
Divide And Conquer ◽  
Image Manipulation ◽  
Multiprocessor System ◽  
Input Size ◽  
Programming Paradigms ◽  
The Impact

This work investigates the use of parallel programming paradigms in the development of applications targeting a Multiprocessor System-on-Chip (MPSoC). We implemented Matrix Multiplication, Image Manipulation and Advanced Encryption Standard (AES) applications in the Master-Slave, Pipeline and Divide-and-Conquer paradigms, and applied execution time and power dissipation as criteria for evaluating the performance of the applications executing according to the paradigms on an MPSoC architecture. The obtained results allowed ​us to conclude that there are optimal application-paradigm relations. Pipeline presents lower execution time and lower power dissipation for the Image Manipulation application; whereas, Master-Slave performs better for the Matrix Multiplication and AES applications. However, when the input size of the applications increases, the Divide-and-Conquer paradigm tends to minimize the execution time for Matrix Multiplication application. ​The main contributions of this work are the development of applications, considering different paradigms, and the impact evaluation of these paradigms on MPSoC architecture.

$\mathcal{HDC}$: A HIGHER-ORDER LANGUAGE FOR DIVIDE-AND-CONQUER

2000 ◽  
Vol 10 (02n03) ◽  
pp. 239-250 ◽  
Author(s):  
CHRISTOPH A. HERRMANN ◽  
CHRISTIAN LENGAUER
Keyword(s):  
Parallel Programming ◽  
Parallel Implementation ◽  
Higher Order ◽  
Divide And Conquer ◽  
Functional Language ◽  
Polynomial Multiplication ◽  
Functional Program ◽  
Design Decisions ◽  
Order Language

We propose the higher-order functional style for the parallel programming of algorithms. The functional language [Formula: see text], a subset of the language Haskell, facilitates the clean integration of skeletons into a functional program. Skeletons are predefined programming schemata with an efficient parallel implementation. We report on our compiler, which translates [Formula: see text] programs into C+MPI, especially on the design decisions we made. Two small examples, the n queens problem and Karatsuba's polynomial multiplication, are presented to demonstrate the programming comfort and the speedup one can obtain.

RANDOM SEEKING: A GENERAL, EFFICIENT, AND INFORMED RANDOMIZED SCHEME FOR DYNAMIC LOAD BALANCING

2000 ◽  
Vol 11 (02) ◽  
pp. 231-246 ◽  
Author(s):  
NIHAR R. MAHAPATRA ◽  
SHANTANU DUTT
Keyword(s):  
Artificial Intelligence ◽  
Load Balancing ◽  
Branch And Bound ◽  
Operations Research ◽  
Dynamic Load ◽  
Load Distribution ◽  
Search Algorithms ◽  
Dynamic Load Balancing ◽  
Divide And Conquer ◽  
Branch And Bound Algorithms

We propose a completely general, informed randomized dynamic load balancing method called random seeking (RS) suitable for parallel algorithms with characteristics found in many search algorithms used in artificial intelligence and operations research and many divide-and-conquer algorithms. In it, source processors randomly seek out sink processors for load balancing by flinging "probe" messages. These probes not only locate sinks, but also collect load distribution information which is used to efficiently regulate load balancing activities. We empirically compare RS with a well-known randomized dynamic load balancing method, the random communication (RC) strategy, by using them in parallel best-first branch-and-bound algorithms on up to 512 processors of a parallel system. We find that the RC execution times are more than those of RS by 16–67% when used to perform combined dynamic quantitative and qualitative load balancing, and by 9–74% when used to perform only dynamic quantitative load balancing.

CALCULATING AN OPTIMAL HOMOMORPHIC ALGORITHM FOR BRACKET MATCHING

1999 ◽  
Vol 09 (03) ◽  
pp. 335-345 ◽  
Author(s):  
ZHENJIANG HU ◽  
MASATO TAKEICHI
Keyword(s):  
Parallel Programming ◽  
Parallel Algorithm ◽  
Parallel Computation ◽  
Divide And Conquer ◽  
Recognition Problem ◽  
Language Recognition ◽  
Formal Derivation ◽  
Parallel Software ◽  
Simple Language ◽  
Compilation Techniques

It is widely recognized that a key problem of parallel computation is in the development of both efficient and correct parallel software. Although many advanced language features and compilation techniques have been proposed to alleviate the complexity of parallel programming, much effort is still required to develop parallelism in a formal and systematic way. In this paper, we intend to clarify this point by demonstrating a formal derivation of a correct but efficient homomorphic parallel algorithm for a simple language recognition problem known as bracket matching. To the best of our knowledge, our formal derivation leads to a novel divide-and-conquer parallel algorithm for bracket matching.

Research and Application of Parallel Computing under Linux

2013 ◽  
Vol 756-759 ◽  
pp. 2825-2828
Author(s):  
Xue Chun Wang ◽  
Quan Lu Zheng
Keyword(s):  
Parallel Computing ◽  
Parallel Processing ◽  
High Performance Computing ◽  
Parallel Programming ◽  
High Performance ◽  
Performance Testing ◽  
Divide And Conquer ◽  
Parallel Computer ◽  
Super Computing ◽  
Performance Computing

Parallel computing is in parallel computer system for parallel processing of data and information, often also known as the high performance computing or super computing. The content of parallel computing were introduced, the realization of parallel computing and MPI parallel programming under Linux environment were described. The parallel algorithm based on divide and conquer method to solve rectangle placemen problem was designed and implemented with two processors. Finally, Through the performance testing and comparison, we verified the efficiency of parallel computing.

A CORRECTNESS PROOF OF PARALLEL SCAN

1994 ◽  
Vol 04 (03) ◽  
pp. 329-338 ◽  
Author(s):  
JOHN T. O’DONNELL
Keyword(s):  
Parallel Programming ◽  
Formal Specification ◽  
Parallel Architecture ◽  
Divide And Conquer ◽  
Functional Language ◽  
Correctness Proof ◽  
Equational Reasoning ◽  
Parallel Scan

The parallel scan algorithm plays an important role in parallel programming, but previous explanations of it generally rely on informal methods that fail to establish its correctness. Equational reasoning in a pure functional language provides a formal vehicle for stating the parallel scan algorithm and proving that a parallel architecture executes it correctly. The two key ideas in the proof are (1) a collection of lemmas that show how folds and scans can be decomposed into smaller problems, supporting a divide-and-conquer strategy, and (2) a formal specification of the abstract parallel architecture in the same language used to specify the problem, making it possible to reason formally about how the architecture executes the algorithm.

scholarly journals PList-based Divide and Conquer Parallel Programming

2020 ◽  
Vol 16 (2) ◽  
pp. 197-206
Author(s):  
Virginia Niculescu ◽  
Darius Bufnea ◽  
Adrian Sterca
Keyword(s):  
Parallel Programming ◽  
Building Blocks ◽  
Parallel Programs ◽  
Divide And Conquer ◽  
Existing Building ◽  
New Class ◽  
Programming Framework ◽  
Data Division ◽  
New Applications ◽  
Solvable Problems

This paper details an extension of a Java parallel programming framework – JPLF. The JPLF framework is a programming framework that helps programmers build parallel programs using existing building blocks. The framework is based on {\em PowerLists} and PList Theories and it naturally supports multi-way Divide and Conquer. By using this framework, the programmer is exempted from dealing with all the complexities of writing parallel programs from scratch. This extension to the JPLF framework adds PLists support to the framework and so, it enlarges the applicability of the framework to a larger set of parallel solvable problems. Using this extension, we may apply more flexible data division strategies. In addition, the length of the input lists no longer has to be a power of two – as required by the PowerLists theory. In this paper we unveil new applications that emphasize the new class of computations that can be executed within the JPLF framework. We also give a detailed description of the data structures and functions involved in the PLists extension of the JPLF, and extended performance experiments are described and analyzed.

Sign in / Sign up

Export Citation Format

Share Document