Advances in Computers ( Volume 106 )

Publication series :Volume 106

Author: Hurson   Ali R.;Milutinovic   Veljko  

Publisher: Elsevier Science‎

Publication year: 2017

E-ISBN: 9780128122310

P-ISBN(Paperback): 9780128122303

Subject: O1 Mathematics;TP301.6 algorithm theory;TP31 computer software

Keyword: 数学,计算机软件,算法理论

Language: ENG

Access to resources Favorite

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Description

Advances in Computers, Volume 106 is the latest volume in the series, which has been published since 1960. This update presents innovations in computer hardware, software, theory, design and applications, with new chapters in this volume including sections on A New Course on R&D Project Management in Computer Science and Engineering: Subjects Taught, Rationales Behind, and Lessons Learned, Advances in Dataflow Systems, Adaptation and Evaluation of the Simplex Algorithm for a Data-Flow Architecture, and Simple Operations in Memory to Reduce Data Movement. In addition, this series provides contributors with a medium to explore their subjects in greater depth than journal articles usually allow.

  • Provides in-depth surveys and tutorials on new computer technology
  • Presents well-known authors and researchers in the field
  • Contains extensive bibliographies with most chapters
  • Includes volumes that are devoted to single themes or subfields of computer science

Chapter

Chapter One: A New Course on R&D Project Management in Computer Science and Engineering: Subjects Taught, Rationales Behi ...

1. Introduction

1.1. Before the Project Starts

1.2. Immediately After the Project Starts

1.3. When the Project Is Close to Its End

1.4. Soon After the Product Ends

1.5. Soon After the Project Is Over

1.6. Long After the Project Is Over

1.7. An Introductory Remark

2. Part 1: Learn How to Create a Proposal for Horizon 2020 or NSF

3. Part 2: Learn the Essence of MBA and PhD and Learn How to Prepare for the GMAT/GRE Analytical Exam

4. Part 3: Learn CMMI

5. Part 4: Learn Project Management

6. Part 5: Learn How to Write Business Plans for Investors

7. Part 6: Learn How to Prepare a Patent Application

8. Part 7: Learn How to Write SCI Journal Papers of the Survey Type

9. Part 8: Learn How to Write SCI Journal Papers of the Research Type

10. Part 9: Learn How to Make an eShop

11. Part 10: Learn MindGenomics

12. Part 11: Learn Business Intelligence Based on DataMining

13. Part 12: Learn How to Preserve Heritage and How to Create a Brand

14. Analysis

15. Conclusion

15.1. What Was Achieved?

15.2. Who Will Benefit From the Course?

15.3. Newly Open Problems?

15.4. What Is to Remember About This Course?

Acknowledgments

References

Chapter Two: Advances in Dataflow Systems

1. Introduction

2. Parallel Processor Design

3. From Multiprocessor Software to Dataflow Computing

4. Dataflow Hardware

5. Dataflow Software

6. Dataflow System in Cloud Computing

7. Example Application One: Sequential Monte Carlo System and Its Generationa

7.1. DFE Func

7.2. CPU Func

8. Example Application Two: Sparse Linear Algebra

8.1. Challenge: Excessive On-chip Memory Usage

8.2. Challenge: Avoiding Stalls Due to Data Access Conflicts

8.3. Challenge: Effective Use of Memory Throughput

8.4. Challenge: More Effective On-chip Data Reuse

9. Other Applications

9.1. Genomics Processing

9.2. Climate Modeling

9.3. Time Series Analysis

9.4. Computer Trading Strategies

9.5. Real-Time Proximity Query

9.6. Stencil Computation

9.7. Genetic Algorithms

10. Summary

Acknowledgment

References

Chapter Three: Adaptation and Evaluation of the Simplex Algorithm for a Data-Flow Architecture

1. Introduction

2. The Maxeler Architecture

2.1. Structural Overview

2.2. Programmers View

3. Linear Programming

3.1. Problem Definition

3.2. The Standard Form

3.3. Duality

3.4. The Simplex Algorithm

4. Accelerated Simplex Algorithm

4.1. Algorithm Engineering

4.2. Streaming From the Main Memory

4.3. Concurrent Streaming From the Main Memory

4.4. Streaming From the On-chip Large Memory

4.5. Concurrent Streaming From the On-chip Large Memory

5. Experimental Evaluation

5.1. Experimental Goals

5.2. Benchmark Configuration

5.3. Host-Streamed Algorithms

5.4. LMem-Streamed Algorithms

5.5. Summary

5.6. Simplex Tableau Density

5.7. Discussion and Experimental Principles

6. Conclusions and Future Work

Acknowledgments

References

Chapter Four: Simple Operations in Memory to Reduce Data Movement

1. Introduction

2. Processing in Memory

2.1. Integrating Processing Logic in Memory

2.2. 3D-Stacked DRAM Architectures

3. Processing Using Memory

4. Background on DRAM

4.1. High-Level Organization of the Memory System

4.2. DRAM Chip

4.2.1. DRAM Cell and Sense Amplifier

4.2.2. DRAM Cell Operation: The Activate--Precharge Cycle

4.2.3. DRAM MAT/Tile: The Open Bitline Architecture

4.2.4. DRAM Bank

4.2.5. DRAM Commands: Accessing Data From a DRAM Chip

4.2.6. DRAM Timing Constraints

4.3. DRAM Module

5. RowClone

5.1. Fast Parallel Mode

5.2. Pipelined Serial Mode

5.3. Mechanism for Bulk Data Copy

5.4. Mechanism for Bulk Data Initialization

6. In-DRAM Bulk AND and OR

6.1. Mechanism

6.1.1. Triple-Row Activation

6.1.2. Challenges

6.1.3. Implementation of IDAO

6.1.4. Reliability of Our Mechanism

6.1.5. Latency Optimization

7. End-to-End System Support

7.1. ISA Support

7.2. Processor Microarchitecture Support

7.2.1. Source/Destination Alignment and Size

7.2.2. Managing On-Chip Cache Coherence

7.3. Software Support

7.3.1. Subarray-Aware Page Mapping

7.3.2. Granularity of the Operations

8. Evaluation

8.1. Latency and Energy Analysis

8.2. Applications for RowClone

8.2.1. The fork System Call

8.2.2. Copy/Initialization-Intensive Applications

8.2.3. Multicore Evaluations

8.2.4. Memory-Controller-Based DMA

8.2.5. Other Applications

8.2.5.1. Secure Deallocation

8.2.5.2. Process Checkpointing

8.2.5.3. Virtual Machine Cloning/Deduplication

8.2.5.4. Page Migration

8.2.5.5. CPU-GPU Communication

8.3. Applications for IDAO

8.4. Recent Works Building on RowClone and IDAO

9. Conclusion

References

Chapter Five: A Novel Infrastructure for Synergistic Dataflow Research, Development, Education, and Deployment: The Maxel ...

1. Introduction

2. About the Dataflow Concept

3. About the Maxeler Technologies Mission in Education

3.1. About MAX-UP

4. About the Maxeler Technologies Approach to Dataflow

4.1. About the MaxJ Language

4.2. Accessing DFE

5. About the Methods for Accelerating Applications Using Maxeler Dataflow Technology

6. Architecting the AppGallery

7. Defining the Types of the AppGallery Users

7.1. Non-Registered User

7.2. Registered User

7.3. Developer

7.4. Principal Investigator and Principal Investigator Administrator

7.5. User Administrator, Content Administrator, and Super Administrator

8. Defining the AppGallery Processes

8.1. User Registration Process

8.2. PI Registration Process

8.3. Developer Registration Process

8.4. Developer Approval Process

8.5. User & PI Approval Process

8.6. App Submission Process

8.7. App Review Process

9. Implementation Details

9.1. System Overview

9.2. Client Component

9.3. Server Component

9.4. Technologies Used

10. Success Measures

11. Conclusion

References

Back Cover

The users who browse this book also browse