Home |  Research Labs |  Announcemnents |  People  |  Careers |  Site Map |  Picture Gallery |  Contact Us  |  Feed Back  |  Kics Mail
KICS Home >> Projects  >> Characterization, Evaluation, and Development of High Performance Network Services on Multi-core Architectures




High Performance Computing & Networking Lab


Characterization, Evaluation, and Development of High Performance Network Services on Multi-core Architectures

This project is funded by the ICT fund and the primary objective of this project is to research on multi-core processor performance characterization and evaluation of CPU-memory subsystem performance disparity for high-throughput networking applications.

Multi-core processor architectures offer unique challenges and opportunities for all types of software applications compared to traditional single core architectures. In this research, our focus is on networking applications on current and future generation of multi-core processor based systems. Multi-core processors bring the compute power of high-end parallel systems within a single chip. While this immense compute power can enable highly intelligent services within the network infrastructure, multi-core systems inherit all the challenges of traditional parallel systems. Multiple cores on a chip also enable utilizing exponentially increasing link speeds as well; however, memory access latencies are not reducing at the same rate. Our research objective is to investigate various parallel programming paradigms in terms of their suitability for network applications to be conducive for intelligent services for 1 Gbps networks. In order for this effort to be relevant for the industry, we adopt a measurement-based evaluation approach to conduct this research.
Under this project an extensible multithreaded Multicore Processor Architecture and Communication MPAC library is developed which will facilitate in development of multithreaded benchmarks for multi-core processor based systems. These benchmarks will assist in determining the baseline performance of cache/memory, processor floating point and integer units, and end-to end network. These benchmarks will facilitate in measurement based studies of multi-core systems and will provide the basis for efficiently parallelizing the network applications with memory, cache, and interconnection subsystem constraints of the target multi-core systems.
A measurement based analysis for these developed benchmarks will be performed to tune them for optimization at 1 Gbps networks using profiling tools and instrumentation systems.

Click for Project Details

MPAC Library

This development is a part of project titled “Characterization, Evaluation, and Development of High Performance Network Services on Multi-Core Architectures” which is funded by National ICT R&D Fund. MPAC Library is an absolutely free, open source library developed in C and Java.The primary objective of this project is to research on multi-core processor performance characterization and evaluation of CPU-memory subsystem performance disparity for high-throughput networking applications. It is released under the BSD License. Different API’s are provided to use this library. Some example APIs are introduced below:

latest arch.JPG


Overview of MPAC Architecture

1-Thread Manager :-
API provides the facility to Fork/Join multiple threads in a user friendly manner. Mostly, developers have to call only one function that will manage the life cycle of the whole thread pool.
2-Timing :-
API provides the functions to calculate the time and latency.
3-Resolution :-
API enables the users to calculate/determine the resolution (least count) of different timing functions
4-I/O :-
API supports TCP and UDP based network communication.
5-Statistics :-
API deals with all functionality related to statistics.
MPAC Library in a Fact Sheet
Release Milestones: 
  • MPAC library version 1.0 released on August 16th, 2008
  • MPAC library version 1.1 released on May 9th, 2009
Knowledge Sharing:

We have been introducing MPAC library and related material via different workshops and hand on short courses.  Few of them are as follows:

  • Workshop on parallel programming paradigms (May 9th, 2009)
  • A short course on parallel programming   (August 10 to 13, 2009)
The future of MPAC library:
We are working to port the code of MPAC library to PPC (on Sony’s Play Station 3) and nVidia’s graphics processors.  Both of these initiatives are in its early phases.
Technical Reports:
File:1 [.pdf]
File:2 [.pdf]

Funded By

 

Download Latest MPAC Benchmark

Total Downloads

   
Copyright © 2008 by Al-Khawarizmi Institute of Computer Science, UET, Lahore.