Courseware - Intel® Manycore Testing Lab

Parallel Minimum Spanning Tree Algorithm

Material Type:

Article / White paper

ISN Logo

Technical Format:

PDF document

URL:

Go to URL

Location:

Go to materials

Date Added:

06/22/2011

Date Modified:

06/22/2011

Author

Xiwen Chen, York University, Toronto
Description:

In the graduate course Concurrent Object Oriented Languages, taught at York University, Toronto, students do three assignment and write a paper based on these assignments.

The objective of the first assignment is to find a nontrivial concurrent algorithm in the literature. In the second assignment, the aim is the implementation of the concurrent algorithm presented in the first assignment in Java. The focus of the third assignment is to apply tools to verify the concurrent Java program of the second assignment.

The paper should cover the material discussed in the three assignments. The paper should not be produced by simply cutting and pasting parts of the assignments (but students may reuse bits and pieces of the assignments). The paper should have an abstract, introduction, conclusion and bibliography. The rest of the paper should address the algorithm, the implementation in Java and the verification effort. The paper should be 15 pages. If necessary, the paper may be supplemented with appendices. The paper should be formatted according to Springer-Verlag Lecture Notes in Computer Science Series guidelines.

Recommended Audience:

Advanced programmers, Graduate students

Language:

English

Keywords:

minimum, spanning, tree, parallel, Java

 

Exploring AVS Video Decoder Parallelism on Intel® Manycore Testing Lab

Material Type:

Other

ISN Logo

Technical Format:

PDF document

Location:

Go to materials

Date Added:

12/23/2010

Date Modified:

12/23/2010

Author

Wu-Chun Feng, Virginia Tech
Konstantinos Krommydos, Virginia Tech
Description:

Using the Intel(R) Manycore Testing Lab researchers were able to scale investigations previously done on quad-core processors to 32 cores. Results were unexpected and open up several lines of speculation for further optimization tests in the future.

Recommended Audience:

Graduate students, Undergraduate students

Language:

English

Keywords:

Manycore, Testing, Lab, Krommydas, Feng

 

Application of the tensor analysis of network for parallel calculations of engineering systems

Material Type:

Lecture / Presentation

ISN Logo

Technical Format:

PDF document

Location:

Go to materials

Date Added:

12/07/2010

Date Modified:

12/07/2010

Author

Yuri Sohor, The Pskov state polytechnical institute
Description:

Application of the tensor diakoptics and coarray Fortran for calculation of electric circuits on manycore devices is considered.

Recommended Audience:

Graduate students, Beginning programmers, Undergraduate students

Language:

English

Keywords:

engineering systems, the tensor diakoptics, Coarray Fortran, Manycore Testing Lab

 

Using X on the Intel® Manycore Testing Lab

Material Type:

Article / White paper

ISN Logo

Technical Format:

PDF document

Location:

Go to materials

Date Added:

09/24/2010

Date Modified:

09/24/2010

Author

Jeffrey Gallagher, Intel Corporation
Mike Pearce, Intel Corporatino
Description:

Using X services on the Intel(R) Manycore Testing Lab is unsupported, yet possible. This article demonstrates in general and in detail the four necessary steps to run X on the server:

1) Make a standard, character-based connection
2) Run the required software on the server
3) Run your secure PCX server software
4) Make the connection

Two secure PCX server solutions are discussed.

Recommended Audience:

Advanced programmers

Language:

English

Keywords:

Manycore, Testing, Lab, MTL, X, Services, vncserver, Xming, VNC, Client, graphical, display, GUI

 

Pointer Jumping for Exact Inference on Manycore Systems

Material Type:

Other

ISN Logo

Technical Format:

PDF document

Location:

Go to materials

Date Added:

09/16/2010

Date Modified:

09/16/2010

Author

Nam Ma, USC
Viktor Prasanna, USC
Yinglong Xia, USC
Description:

We study the performance of a pointer jumping based exact inference algorithm for a special type of junction trees – a chain of cliques. Many traditional methods for exact inference result in unsatisfactory performance for such a type of junction trees due to limited parallelism. A pointer jumping based algorithm helps explore independent operations that can be run in parallel. Our analysis on the performance of the algorithm shows that a large number of processors with shared memory are particularly suitable for exact inference in a chain of cliques. The Intel® Manycore Testing Lab gives us an opportunity to experimentally evaluate our algorithm on a real manycore system – a 32-core Intel® Nehalem-EX based system. The experimental results show that the algorithm scales well with the number of cores, and that the algorithm achieves speedup with respect to the sequential algorithm when the number of cores is sufficiently large.

Recommended Audience:

Advanced programmers, Graduate students, Undergraduate students

Language:

English

Keywords:

PointerJumping, ExactInference, Manycore

 

Pointer Jumping for Exact Inference on Manycore Systems

Material Type:

Other

ISN Logo

Technical Format:

PDF document

Location:

Go to materials

Date Added:

09/13/2010

Date Modified:

09/13/2010

Author

Nam Ma, University of Southern California
Viktor Prasanna, University of Southern California
Yinglong Xia, University of Southern California
Description:

We study the performance of a pointer jumping based exact inference algorithm for a special type of junction trees – a chain of cliques. Many traditional methods for exact inference result in unsatisfactory performance for such a type of junction trees due to limited parallelism. A pointer jumping based algorithm helps explore independent operations that can be run in parallel. Our analysis on the performance of the algorithm shows that a large number of processors with shared memory are particularly suitable for exact inference in a chain of cliques. The Intel® Manycore Testing Lab gives us an opportunity to experimentally evaluate our algorithm on a real manycore system – a 32-core Intel® Nehalem-EX based system. The experimental results show that the algorithm scales well with the number of cores, and that the algorithm achieves speedup with respect to the sequential algorithm when the number of cores is sufficiently large.

Recommended Audience:

Advanced programmers, Beginning programmers, Graduate students, Undergraduate students

Language:

English

Keywords:

ExactInference, PointerJumping, Manycore

 

Matrix Multiplication, Performance, and Scalability in OpenMP: Student Challenge

Material Type:

Other

ISN Logo

Technical Format:

PDF document

URL:

Go to URL

Location:

Go to materials

Date Added:

09/01/2010

Date Modified:

09/01/2010

Author

Nicolas Wolovick, National University of Córdoba, Argentina
Description:

This year, a simple matrix multiplication problem was posed to the students and we set up an internal contest, to obtain the fastest serial code. Many versions were submitted, and we finally obtained 20x of improvement over the most naïve implementation. The students learned a lot about compiler optimizations, and above all, the effect of the caches in the performance of the code.

The objective of this exercise was to extrapolate this work to a massive multicore architecture. Having 32 cores to perform the matrix multiplication under the QuickPath memory communication architecture provided a complex enough scenario to explore different solutions.

Recommended Audience:

Graduate students, Beginning programmers, Secondary School students, Undergraduate students

Language:

English

Keywords:

Manycore, Testing, Lab, Wolovick, MTL

 

Computation of Automorphism Groups of q-ary Codes

Material Type:

Other

ISN Logo

Technical Format:

PDF document

Location:

Go to materials

Date Added:

08/13/2010

Date Modified:

08/13/2010

Author

Evengy Gorkunov, Novosibirsk State University
Description:

The purpose of this work is to develop and implement an effective algorithm to find automorphism groups of different algebraic and combinatorial objects in n-dimensional vector space over finite field. We use the First String Method (FSM) to deal with the automorphism groups used in cryptography and coding theory.

Recommended Audience:

Advanced programmers, Beginning programmers, Graduate students, Undergraduate students

Language:

English

Keywords:

Manycore, Testing, Lab, Gorkunov, Zhmud, MTL

 

Fast Spectral Estimation of Genetic Homology

Material Type:

Other

ISN Logo

Technical Format:

PDF document

Location:

Go to materials

Date Added:

07/01/2010

Date Modified:

07/01/2010

Author

Anton Pankratov, Moscow State University
Description:

Technical Brief- 32 Core Testing Plan Contest
Imagine if you want to view homology of all known genetic sequences at once. As one single image it would be huge indeed. To do this we could identify pixels at positions (i,j) of the image with bright red points when the estimated similarity value of corresponding i-th and j-th DNA segments is above a predefined threshold value; green points would denote inverted identities, and so on. The questions remain: how could such a huge image be generated quickly, how would a user browse over its broad plane, and how would they pull out interesting subsequences separately for additional exploration?

Recommended Audience:

Graduate students, Beginning programmers, Advanced programmers, Undergraduate students

Language:

English

Keywords:

Manycore, Testing, Lab, Pankratov, MTL, Tetuev, Pyatkov

 

Manycore Testing Lab - Getting Started Guide

Material Type:

Other

ISN Logo

Technical Format:

PDF document

Location:

Go to materials

Date Added:

03/30/2010

Date Modified:

03/30/2010

Author

Michael Pearce, ISE
Description:

This is the Getting Started Guide for the Intel(R) Manycore Testing Lab

Recommended Audience:

Beginning programmers, Graduate students, Secondary School students, Undergraduate students

Language:

English

Keywords:

Multithreading, Manycore Testing Lab, C++, PBSPro, Academic Community
有关编译器优化的更完整信息,请参阅优化通知
类别: