Book Chapter10.1007/978-3-642-04818-0_2
Parallel Computer Architecture
Thomas Rauber,Gudula Rünger +1 more
- 01 Jan 2010
- pp 7-91
7
TL;DR: This chapter gives an overview of the general structure of parallel computers which determines how computations of a program can be mapped to the available resources, such that a parallel execution is obtained.
read more
Abstract: The possibility for a parallel execution of computations strongly depends on the architecture of the execution platform. This chapter gives an overview of the general structure of parallel computers which determines how computations of a program can be mapped to the available resources, such that a parallel execution is obtained. Section 2.1 gives a short overview of the use of parallelism within a single processor or processor core. Using the available resources within a single processor core at instruction level can lead to a significant performance increase. Sections 2.2 and 2.3 describe the control and data organization of parallel platforms. Based on this, Sect.2.4 presents an overview of the architecture of multicore processors and describes the use of thread-based parallelism for simultaneous multithreading.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A novel scalability metric about iso-area of performance for parallel computing
TL;DR: A novel scalability metric about iso-area of performance for parallel computing is proposed and the relationship between the new metric and the traditional ones is analyzed and is significant to improve parallel computing architecture and to tune parallel algorithm design.
8
Performance metrics for hybrid multi-tasking systems
Kyle Rupnow,Jacob Adriaens,Wenyin Fu,Katherine Compton +3 more
- 29 Sep 2009
TL;DR: Performance evaluation of hybrid (heterogeneous ISA) computing systems faces three major challenges: hybrid execution, multi-tasking, and system-level simulation variation; metrics that address them are presented.
3
Parallel Implementation in Case-based Reasoning Bankruptcy Prediction System
Dyah Sulistyowati Rahayu,Heru Suhartanto +1 more
- 17 Oct 2020
TL;DR: This research shows how to speed up the computational time by parallelizing CBR calculations while maintaining accuracy in a bankruptcy prediction system and proves the strategy of parallelization success without reducing much of the classification performance.
3
The Evolution of Supercomputer Architecture: A Historical Perspective
Bao Li,Pingjing Lu +1 more
- 18 Oct 2015
TL;DR: The trend of current supercomputer architecture design is analyzed and Perspectives are given on how supercomputers have evolved thru time.
1
The Design and Implementation of Crossbar in SMP Symmetrical Multi-processor System
Li Qingbao,Niu Xiaopeng,Zeng GuangYu +2 more
- 20 Dec 2008
TL;DR: The correctness and scalability of the design with an actual subject, a crossbar for SMP application system is shown, and the concept of require priority is brought forward and a scheduling algorithm in considering of the priority of each processor is designed.
References
•Book
Introduction to Parallel Algorithms and Architectures: Arrays, Trees, Hypercubes
F. Thomson Leighton
- 01 Sep 1991
TL;DR: This chapter discusses sorting on a Linear Array with a Systolic and Semisystolic Model of Computation, which automates the very labor-intensive and therefore time-heavy and expensive process of manually sorting arrays.
3.1K
How to Make a Multiprocessor Computer That Correctly Executes Multiprocess Programs
TL;DR: Many large sequential computers execute operations in a different order than is specified by the program, and a correct execution by each processor does not guarantee the correct execution of the entire program.
Deadlock-Free Message Routing in Multiprocessor Interconnection Networks
TL;DR: In this article, a deadlock-free routing algorithm for arbitrary interconnection networks using the concept of virtual channels is presented, where the necessary and sufficient condition for deadlock free routing is the absence of cycles in a channel dependency graph.
Some Computer Organizations and Their Effectiveness
TL;DR: A hierarchical model of computer organizations is developed, based on a tree model using request/service type resources as nodes, which indicates that saturation develops when the fraction of task time spent locked out approaches 1/n, where n is the number of processors.
2.1K