Compiler Optimizations for Multithreaded Multicore Network Processors

نویسنده

  • Xiaotong Zhuang
چکیده

To myself, my wife and my parents. Work hard, be good. iii ACKNOWLEDGEMENTS This dissertation would not have been possible without the tireless efforts of my advisor, Professor Santosh Pande. He has taught me how to work as an independent researcher and has been a steady source of wise discussions, cordial encouragement and support. He will be a great example throughout my professional life and I would like to express my sincere thanks to him. I am also indebted to other members in my thesis committee including Professor Profes-for their comments and help to improve this dissertation. I am extraordinarily grateful to all my friends and colleagues in the Systems Group and CERCS at College of Computing. This exceptional group of people created a collaborative environment that is friendly, well-organized, and stimulating. A number of colleagues and students, past and present, such as Weidong Shi, have helped to setup the development environment for the IXP Network Processor. It is a great pleasure to thank them here for their commitment. etc. they have made my time in graduate school a most enjoyable and memorable experience. I thank the lovely Ping Yu for her love, constant encouragement, limitless support, and patience with me while I completed this dissertation. I can no longer imagine life without her. Most of all I thank my parents for their love, sacrifice, and devotion. They have provided the foundation for all that I have accomplished and all that I ever will; I am forever in their debt. I dedicate this thesis to them. 54 Padding instruction reduction through code transformation (CSD-8). .. . 122 xi SUMMARY With advances in optical transmission technologies that offer high bandwidths and sustained growth of Internet traffic, network speed has reached a phenomenal level putting high pressure on network devices. Meanwhile, the ever-increasing requirements of network applications demand more functionalities to be fulfilled along with the packet transmission. Network processors are new types of processors with multiple threads and multiple processor cores on the same chip. The multicore design offers enormous parallel processing power to handle high speed packet streams, which are mostly independent. To expedite packet processing and provide enough programmability, network processors are designed with special features like simplified ISA and pipeline, banked register file, special functional units etc. The multithreaded chip multiprocessor design together with other architectural peculiarities raise new challenges for compiler optimizations. Moreover, the unique demands of …

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Unveiling the performance-energy trade-off in iterative linear system solvers for multithreaded processors

In this paper, we analyze the interactions occurring in the triangle performance-power-energy for the execution of a pivotal numerical algorithm, the iterative conjugate gradient (CG) method, on a diverse collection of parallel multithreaded architectures. This analysis is especially timely in a decade where the power wall has arisen as a major obstacle to build faster processors. Moreover, the...

متن کامل

Effectiveness of Compiler-Directed Prefetching on Data Mining Benchmarks

For today's increasingly power-constrained multicore systems, integrating simpler and more energy-e±cient in-order cores becomes attractive. However, since in-order processors lack complex hardware support for tolerating long-latency memory accesses, developing compiler technologies to hide such latencies becomes critical. Compiler-directed prefetching has been demonstrated e®ective on some app...

متن کامل

Hierarchical Dependency Graphs: Abstraction and Methodology for Mapping Systolic Array Designs to Multicore Processors

Systolic array designs and dependency graphs are some of the most important class of algorithms in several scientific computing areas. In this paper, we first propose an abstraction based on the fundamental principles behind designing systolic arrays. Then, based on the abstraction, we propose a methodology to map a dependency graph to a generic multicore processor. Then we present two case stu...

متن کامل

Optimizing Code by Selecting Compiler Flags using Parallel Genetic Algorithm on Multicore CPUs

The compiler optimization phase ordering not only possesses challenges to compiler developer but also for multithreaded programmer to enhance the performance of Multicore systems. Many compilers have numerous optimization techniques which are applied in predetermined ordering. These ordering of optimization techniques may not always give an optimal code further it is impossible to find a unanim...

متن کامل

Work in progress - Course development of programming for general-purpose multicore processors

This paper presents the course development activities on multicore programming at the Electrical and Computer Engineering Department of Virginia Commonwealth University. As multicore processors have become the main stream computing platform, it becomes a necessity to teach undergraduate on programming for multicore processors. This paper gives details information about the multicore programming...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2006