Seminars and Workshop Presentations by Peter Strazdins

• Exaflop Computing panel discussion, ISPA'08, Sydney, Dec 2008.
• How much energy can you save with a multicore computer for web applications? , GICT2008, Canberra, Nov 2008
• Combining Parallelism, Virtualization, Heterogeneity and Reliability, U. Toronto, Platform Computing, Google (video), SunLabs, Oct 2008
• The HPNumSOA Project: Research Themes, Platform Computing, Toronto, Oct 2008
• Applying the Community of Practice Approach to Individual IT Projects, Australasian Computing Education Conference, Jan 2008

• Computer Science Project Courses: Learning, Assessment and Workload Issues, DCS Retreat, Dec 2007
• Applying the Community of Practice Approach to Postgraduate IT Projects, CECS Deans Awards Presentations, Nov 2007
• Approaches to Performance Evaluation On Shared Memory and Cluster Architectures, VaST, Syndey, Sep 2007
• Research-Based Education in Computer Science at the ANU: Challenges and Opportunities, DCS ANU Seminar, June 2007
• A Survey of `Best Practice' in Computer Science Teaching, DCS ANU Seminar, May 2007
• Efficient Cycle-Accurate Simulation of the UltraSPARC III CPU , ACSC'07, Ballarat, Jan 2007

• Performance Enhancement of SMP Clusters with Multiple Network Interfaces using Virtualization, XenHPC'06, Sorrento, Dec 2006
• Approaches to Performance Evaluation On Shared Memory and Cluster Architectures, Deakin, Nov 2006
• Performance Evaluation / Modelling and Infrastructure Support in Heterogeneous Clusters , Deakin, Nov 2006
• Parallel Matrix Computations: from Systolic Arrays to Supercomputers, Symposium on Mathematics and Computer Science (RP60), ANU, April 2006

• Cycle Accurate Memory Modelling: A Case-Study in Validation MASCOTS'05, Sep 2005
• Approaches to Performance Evaluation On Shared Memory-Supporting Architectures, HPCS Lab, Tsukuba University, Sep 2005

• A Comparison of Local and Gang Scheduling on a Beowulf Cluster (12 pages), Cluster 2004, Sep 2004 (click here for paper)
• High Performance Computing: Architecture, Applications, and SE Issues,
  BSEng seminar, ANU, May 2004

• The COMP1120 Experiment in 'Fast-track' First Year CS Teaching, DCS Seminar, Nov 03
• Simulation Techniques for NUMA Architectures, SunLabs/Berkeley, Aug 03
• A Cluster-Aware Distributed Java Virtual Machine written in Java, SunLabs, Aug 03
• Co-chair in the WoPLA'03 Workshop on Parallel Linear Algebra , Melbourne, June 03
• Issues in the Design of Scalable Out-of-core Dense Symmetric Indefinite Factorization Algorithms, WoPLA'03/ICCS 2003, June 03

• Extending the Sparc-Sulima Computer Simulator: talk given for a COMP4510 lecture (Mar 03) and for a COMP3800 seminar (Oct 02), ANU
• The Analysis and Optimization of Collective Communications on a Beowulf Cluster , ICPADS2002, NCU, Taiwan, Dec 02
• Experiences in Developing the Sparc-Sulima Complete Machine Simulator, DCS Seminar, ANU, Jun 02

• Challenges in Large-scale Electromagnetic Compatabilitty Analysis , Advcom Series, ANU, Dec 2001
• Parallel Data Mining on a Beowulf Cluster, HPCAsia'01, Gold Cost, Sep 2001
• High Performance Dense Linear Systems Solution on a Beowulf Cluster, HPCAsia'01, Gold Cost, Sep 2001
• An Efficient And Stable Method for Parallel Factorization of Dense Symmetric Indefinite Matrices , HPCAsia'01, Gold Cost, Sep 2001
• Towards a Parallel Data Mining Toolbox, PDDM'2001 Workshop, SF, Apr 2001
• Frequency Interpolation Methods for Accelerating Parallel EMC Analysis , PDSECA-01 workshop, SF, Apr 2001

• Stability and Parallelization Issues in Solving General Symmetric Linear Systems , seminar at DCS ANU, Nov 2000
• An Overview of Complete Machine Simulation of Shared Memory Computers , seminar at UNSW/UTS, May 2000
• The Emergence of the Cluster, Canberra Linux Users Group, Feb 2000

• Optimizing User-Level Communication Patterns on the Fujitsu AP3000, IWCC conf. presentation, Dec 1999
• Parallelizing Dense Symmetric Indefinite Solvers, PART'99 conf. presentation, Dec 1999
  (also DCS ANU seminar, Jun 1999)
• Parallel Dense Linear Algebra Libraries: Useability and Performance Issues , workshop at CTAC'99, Sep 1999
• Accelerated Methods for Performing the LDLT Decomposition , CTAC'99 conf. presentation, Sep 1999
• High Performance Computing: Architecture, Applications, and Software Engineering Issues,
  seminar given to COMP1800, Department of Computer Science, ANU, Sep 1999

• Optimal Load Balancing Techniques for Block-Cyclic Decompositions for Matrix Factorization , PDCN'98 conf. presentation, Dec 1998
• Lookahead and Algorithmic Blocking Techniques Compared for Parallel Matrix Factorization , PDCS'98 conf. presentation, Oct 1998 (also DCS ANU seminar, Jun 1998)
• Enhanced Parallel Matrix Factorization Routines, seminar at the Department of Computer Science, University of Tennessee Knoxville, Oct 1998. Software Overhead and Blocking Issues in Parallel BLAS, presented to the ScaLAPACK Conference (teleconference), Department of Computer Science, University of Tennessee Knoxville, Mar 1998.

• Reducing Software Overheads in Parallel Linear Algebra Libraries, PART'97 conf. presentation, Sep 1997
  (also DCS ANU seminar, Oct 1997)