Advance Computer Architect: Parallelism, Scalability, Programmability

This book deals with advanced computer architecture and parallel programming techniques. It offers a balanced treatment of theory, technology architecture and software used by advanced computer systems. It presents state-of-the-art principles and techniques for designing and programming parallel, vector, and scalable computer systems. The emphasis on parallelism, scalability and programmability lends an added flavour to this text. The new chapter on - Instruction Level Parallelism describes the basic techniques of instruction level parallelism, and discusses relevant system design and performance issues which place a limit on its successful exploitation. While another newly added chapter on Recent Advancements in Computer Architecture discusses the technological advances which have had a major impact on computer architecture, and details some recently introduced processors, systems, and multi-core systems-on-a-chip.

Salient Features:
-Learning objective based teaching methodology
-Emphasizes on parallelism, scalability and programmability aspects related to computer architecture
-Discusses case-studies of real systems- IBM, Hitachi, Cray, Intel, UltraSparc, Blue Gene (from IBM), Cray XT series, XT5 and XMT, Fujitsu, DEC, MasPar, Tera, Stardent, etc.

Part 1: Theory of Parallelism

1. Parallel Computer Models
2. Program and Network Properties
3. Principles of Scalable Performance
Part 2: Hardware Technologies

4. Processors and Memory Hierarchy
5. Bus, Cache, and Shared Memory
6. Pipelining and Superscalar Techniques
Part 3: Parallel and Scalable Architectures

7. Multiprocessors and Multicomputer
8. Multivector and SIMD Computers
9. Scalable, Multithreaded, and Dataflow Architectures
Part 4: Software for parallel programming

10. Parallel Models, Languages, and Compilers
11. Parallel Program Development and Environments
Part V Instruction and System Level Parallelism
12. Instruction Level Parallelism
13. T rends in Parallel Systems