Results 1 
5 of
5
A framework for adaptive algorithm selection in STAPL
 IN PROC. ACM SIGPLAN SYMP. PRIN. PRAC. PAR. PROG. (PPOPP), PP 277–288
, 2005
"... Writing portable programs that perform well on multiple platforms or for varying input sizes and types can be very difficult because performance is often sensitive to the system architecture, the runtime environment, and input data characteristics. This is even more challenging on parallel and distr ..."
Abstract

Cited by 39 (8 self)
 Add to MetaCart
(Show Context)
Writing portable programs that perform well on multiple platforms or for varying input sizes and types can be very difficult because performance is often sensitive to the system architecture, the runtime environment, and input data characteristics. This is even more challenging on parallel and distributed systems due to the wide variety of system architectures. One way to address this problem is to adaptively select the best parallel algorithm for the current input data and system from a set of functionally equivalent algorithmic options. Toward this goal, we have developed a general framework for adaptive algorithm selection for use in the Standard Template Adaptive Parallel Library (STAPL). Our framework uses machine learning techniques to analyze data collected by STAPL installation benchmarks and to determine tests that will select among algorithmic options at runtime. We apply a prototype implementation of our framework to two important parallel operations, sorting and matrix multiplication, on multiple platforms and show that the framework determines runtime tests that correctly select the best performing algorithm from among several competing algorithmic options in 86100 % of the cases studied, depending on the operation and the system.
Adaptivity for Two Problems in Networks
, 1997
"... An algorithm is said to be adaptive if it is capable of taking advantage of instance easiness; that is, it requires less computational resources for easier instances of the same size for the same problem. In this paper we explore adaptive algorithms for the Minimum Spanning Tree Problem and Shortest ..."
Abstract
 Add to MetaCart
(Show Context)
An algorithm is said to be adaptive if it is capable of taking advantage of instance easiness; that is, it requires less computational resources for easier instances of the same size for the same problem. In this paper we explore adaptive algorithms for the Minimum Spanning Tree Problem and Shortest Path Problem in networks. We show that instance easiness in networks for these two problems is closely related to instance easiness in Sorting. In fact, we show that adaptivity depends on the capacity of the algorithm to adjust to ffl the density of the underlying graph, ffl the distance between the topological sorted order of the underlying graph and the order of proximity to the source node (measured by a measure of disorder), ffl the cohesiveness of the graph (approximated by the degree sequence of the nodes), and ffl the intrinsic difficulty in the network (evaluated as the number of bad cycles).
Review on Sorting Algorithms A Comparative Study
"... There are many popular problems in different practical fields of computer sciences, database applications, Networks and Artificial intelligence. One of these basic operations and problems is sorting algorithm; the sorting problem has attracted a great deal of research. A lot of sorting algorithms ha ..."
Abstract
 Add to MetaCart
(Show Context)
There are many popular problems in different practical fields of computer sciences, database applications, Networks and Artificial intelligence. One of these basic operations and problems is sorting algorithm; the sorting problem has attracted a great deal of research. A lot of sorting algorithms has been developed to enhance the performance in terms of computational complexity. there are several factors that must be taken in consideration; time complexity, stability, memory space. Information growth rapidly in our world leads to increase developing sort algorithms.a stable sorting algorithms maintain the relative order of records with equal keys This paper makes a comparison between the Grouping Comparison Sort (GCS) and conventional algorithm such as Selection sort, Quick sort, Insertion sort, Merge sort and Bubble sort with respect execution time to show how this algorithm perform reduce execution time.
Comparison of Bucket Sort and RADIX Sort
, 2014
"... Bucket sort and RADIX sort are two wellknown integer sorting algorithms. This paper measures empirically what is the time usage and memory consumption for different kinds of input sequences. The algorithms are compared both from a theoretical standpoint but also on how well they do in six differe ..."
Abstract
 Add to MetaCart
(Show Context)
Bucket sort and RADIX sort are two wellknown integer sorting algorithms. This paper measures empirically what is the time usage and memory consumption for different kinds of input sequences. The algorithms are compared both from a theoretical standpoint but also on how well they do in six different use cases using randomized sequences of numbers. The measurements provide data on how good they are in different reallife situations. It was found that bucket sort was faster than RADIX sort, but that bucket sort uses more memory in most cases. The sorting algorithms performed faster with smaller integers. The RADIX sort was not quicker with already sorted inputs, but the bucket sort was. 1