1 Dong Lu, Peter A. Dinda Prescience Laboratory Computer Science Department Northwestern University Virtualized.

Slides:



Advertisements
Similar presentations
1 Scoped and Approximate Queries in a Relational Grid Information Service Dong Lu, Peter A. Dinda, Jason A. Skicewicz Prescience Lab, Dept. of Computer.
Advertisements

Nondeterministic Queries in a Relational Grid Information Service Peter A. Dinda Dong Lu Prescience Lab Department of Computer Science Northwestern University.
A Prediction-based Real-time Scheduling Advisor Peter A. Dinda Carnegie Mellon University.
Listening Tests and Evaluation of Simulated Sound Fields Using VibeStudio Designer Wersényi György Hesham Fouad SZÉCHENYI ISTVÁN UNIVERSITY, Hungary VRSonic,
Institute of Computer Science Foundation for Research and Technology – Hellas Greece Computer Architecture and VLSI Systems Laboratory Exploiting Spatial.
A system Performance Model Instructor: Dr. Yanqing Zhang Presented by: Rajapaksage Jayampthi S.
A SYSTEM PERFORMANCE MODEL CSC 8320 Advanced Operating Systems Georgia State University Yuan Long.
Self-Adapting Scheduling for Tasks with Dependencies in Stochastic Environments Ioannis Riakiotakis, Florina M. Ciorba, Theodore Andronikos and George.
Module 8: Concepts of a Network Load Balancing Cluster
1 Virtual Machine Resource Monitoring and Networking of Virtual Machines Ananth I. Sundararaj Department of Computer Science Northwestern University July.
Host Load Trace Replay Peter A. Dinda Thesis Seminar 11/23/98.
An Adaptable Benchmark for MPFS Performance Testing A Master Thesis Presentation Yubing Wang Advisor: Prof. Mark Claypool.
Towards Virtual Networks for Virtual Machine Grid Computing Ananth I. Sundararaj Peter A. Dinda Prescience Lab Department of Computer Science Northwestern.
Virtualized Audio as a Distributed Interactive Application Peter A. Dinda Northwestern University Access Grid Retreat, 1/30/01.
An Introduction to the Prescience Lab Peter A. Dinda Prescience Lab Department of Computer Science Northwestern University
Project Presentation: March 9, 2006
1 Introduction to Load Balancing: l Definition of Distributed systems. Collection of independent loosely coupled computing resources. l Load Balancing.
Dynamic Topology Adaptation of Virtual Networks of Virtual Machines Ananth I. Sundararaj Ashish Gupta Peter A. Dinda Prescience Lab Department of Computer.
Efficient Parallelization for AMR MHD Multiphysics Calculations Implementation in AstroBEAR.
A Prediction-based Approach to Distributed Interactive Applications Peter A. Dinda Jason Skicewicz Dong Lu Prescience Lab Department of Computer Science.
The Measured Network Traffic of Compiler Parallelized Programs Peter A. Dinda Northwestern University, Computer Science
Online Prediction of the Running Time Of Tasks Peter A. Dinda Department of Computer Science Northwestern University
Exploiting Packet Header Redundancy for Zero Cost Dissemination of Dynamic Resource Information Peter A. Dinda Prescience Lab Department of Computer Science.
Peter Dinda Department of Computer Science Northwestern University Beth Plale Department.
A Prediction-based Approach to Distributed Interactive Applications Peter A. Dinda Department of Computer Science Northwestern University
Binaural Sound Localization and Filtering By: Dan Hauer Advisor: Dr. Brian D. Huggins 6 December 2005.
A Prediction-based Real-time Scheduling Advisor Peter A. Dinda Prescience Lab Department of Computer Science Northwestern University
Dynamic Topology Adaptation of Virtual Networks of Virtual Machines Ananth I. Sundararaj Ashish Gupta Peter A. Dinda Prescience Lab Department of Computer.
Inferring the Topology and Traffic Load of Parallel Programs in a VM environment Ashish Gupta Peter Dinda Department of Computer Science Northwestern University.
Realistic CPU Workloads Through Host Load Trace Playback Peter A. Dinda David R. O’Hallaron Carnegie Mellon University.
23 September 2004 Evaluating Adaptive Middleware Load Balancing Strategies for Middleware Systems Department of Electrical Engineering & Computer Science.
Design and Implementation of a Single System Image Operating System for High Performance Computing on Clusters Christine MORIN PARIS project-team, IRISA/INRIA.
PROOF: the Parallel ROOT Facility Scheduling and Load-balancing ACAT 2007 Jan Iwaszkiewicz ¹ ² Gerardo Ganis ¹ Fons Rademakers ¹ ¹ CERN PH/SFT ² University.
Abstract Load balancing in the cloud computing environment has an important impact on the performance. Good load balancing makes cloud computing more.
OpenFlow-Based Server Load Balancing GoneWild Author : Richard Wang, Dana Butnariu, Jennifer Rexford Publisher : Hot-ICE'11 Proceedings of the 11th USENIX.
Authors: Tong Li, Dan Baumberger, David A. Koufaty, and Scott Hahn [Systems Technology Lab, Intel Corporation] Source: 2007 ACM/IEEE conference on Supercomputing.
Dynamic Resource Allocation Using Virtual Machines for Cloud Computing Environment.
EmNet: Satisfying The Individual User Through Empathic Home Networks J. Scott Miller, John R. Lange & Peter A. Dinda Department of Electrical Engineering.
1 Distributed Process Scheduling: A System Performance Model Vijay Jain CSc 8320, Spring 2007.
1 Distributed Energy-Efficient Scheduling for Data-Intensive Applications with Deadline Constraints on Data Grids Cong Liu and Xiao Qin Auburn University.
On Distinguishing the Multiple Radio Paths in RSS-based Ranging Dian Zhang, Yunhuai Liu, Xiaonan Guo, Min Gao and Lionel M. Ni College of Software, Shenzhen.
Performance Prediction for Random Write Reductions: A Case Study in Modelling Shared Memory Programs Ruoming Jin Gagan Agrawal Department of Computer and.
Timo Haapsaari Laboratory of Acoustics and Audio Signal Processing April 10, 2007 Two-Way Acoustic Window using Wave Field Synthesis.
Audio Systems Survey of Methods for Modelling Sound Propagation in Interactive Virtual Environments Ben Tagger Andriana Machaira.
An IP Address Based Caching Scheme for Peer-to-Peer Networks Ronaldo Alves Ferreira Joint work with Ananth Grama and Suresh Jagannathan Department of Computer.
1 CMPE 511 HIGH PERFORMANCE COMPUTING CLUSTERS Dilek Demirel İşçi.
Computer Science and Engineering Parallelizing Defect Detection and Categorization Using FREERIDE Leonid Glimcher P. 1 ipdps’05 Scaling and Parallelizing.
Computing Resources at Vilnius Gediminas Technical University Dalius Mažeika Parallel Computing Laboratory Vilnius Gediminas Technical University
Scalable Multi-core Sonar Beamforming with Computational Process Networks Motivation Sonar beamforming requires significant computation and input/output.
11 CLUSTERING AND AVAILABILITY Chapter 11. Chapter 11: CLUSTERING AND AVAILABILITY2 OVERVIEW  Describe the clustering capabilities of Microsoft Windows.
Rassul Ayani 1 Performance of parallel and distributed systems  What is the purpose of measurement?  To evaluate a system (or an architecture)  To compare.
3-D Sound and Spatial Audio MUS_TECH 348. Stereo Loudspeaker Reproduction.
A Grid-enabled Multi-server Network Game Architecture Tianqi Wang, Cho-Li Wang, Francis C.M.Lau Department of Computer Science and Information Systems.
CERN - IT Department CH-1211 Genève 23 Switzerland t High Availability Databases based on Oracle 10g RAC on Linux WLCG Tier2 Tutorials, CERN,
High Performance LU Factorization for Non-dedicated Clusters Toshio Endo, Kenji Kaneda, Kenjiro Taura, Akinori Yonezawa (University of Tokyo) and the future.
GridNets 2006 – October 1 st Grid Resource Management by means of Ant Colony Optimization Gustavo Sousa Pavani and Helio Waldman Optical Networking Laboratory.
Some Design Idea of Red5 Clustering Scalable –Server’s capacity is enlarged when more hardwares are added Failover –Client will not notice the server node.
Cluster computing. 1.What is cluster computing? 2.Need of cluster computing. 3.Architecture 4.Applications of cluster computing 5.Advantages of cluster.
08/10/ High Performance Parallel Implementation of Adaptive Beamforming Using Sinusoidal Dithers High Performance Embedded Computing Workshop Peter.
1 A Grid-Based Middleware’s Support for Processing Distributed Data Streams Liang Chen Advisor: Gagan Agrawal Computer Science & Engineering.
Introduction to Load Balancing:
Performance Evaluation of Adaptive MPI
Distributed Process Scheduling: 5.1 A System Performance Model
Department of Computer Science Northwestern University
CLUSTER COMPUTING.
Characteristics of Reconfigurable Hardware
DotSlash: An Automated Web Hotspot Rescue System
Hybrid Programming with OpenMP and MPI
Computer Systems Performance Evaluation
L. Glimcher, R. Jin, G. Agrawal Presented by: Leo Glimcher
Presentation transcript:

1 Dong Lu, Peter A. Dinda Prescience Laboratory Computer Science Department Northwestern University Virtualized Audio: A Highly Adaptive Interactive High Performance Computing Application

2 Overview Virtualized Audio: Immersive, listener-centric audio system based on high performance computing User-driven HPC exposes new challenges How to exploit many adaptation mechanisms to achieve responsiveness Concepts and initial results introduced here

3 Outline Limitations of traditional audio Virtualized audio Interactive source separation and auralization Structure of interactive auralization Adaptation mechanisms Initial performance evaluation Conclusions

4 Performer Microphones Performance Room Mixer Amp Listening Room Listener Sound Field 1 Sound Field 2 Loudspeakers Headphones Traditional Audio

5 Performer Microphones Performance Room Mixer Amp Listening Room Listener Sound Field 1 Sound Field 2 Loudspeakers Headphones Limitations of Traditional Audio Microphones capture performance room as well as performer Mixing process destroys recorded information

6 Virtualized Audio: Source Separation Performer Microphones Performance Room Separation Sound Field 1 Performer Recording process results in only the performer Not currently implemented, not the subject of this talk

7 Performer Microphones Performance Room Mixer Amp Listening Room Listener Sound Field 1 Sound Field 2 Loudspeakers Headphones Limitations of Traditional Audio Playback ignores listening room and listener Playback does not adjust as listener moves

8 Virtualized Audio: Interactive Auralization Listener at Virtual Location Headphones Auralization Sound Field 2 Virtual Performer HRTF ListenerPerformerRoom Virtual Listening Room Auralization injects performer into listener’s space Auralization adapts as listener moves or room changes Subject of this talk

9 Architecture of Interactive Auralization Client Scalable Real-time Simulation Server Master filtering server Mixing server Filtering server Streaming Audio Service Source 1 Source 2 Source 3 Source 4 Filtering server Source n Filter configuration Left Channel Right Channel Scalable Audio Filtering Service Parallel FD Simulation Filter generation Binaural Audio Output Current Spatial Model and source/sink positions User-driven Immersive Audio Client Impulse response filters characterize listening room

10 Architecture of Interactive Auralization Client Scalable Real-time Simulation Server Master filtering server Mixing server Filtering server Streaming Audio Service Source 1 Source 2 Source 3 Source 4 Filtering server Source n Filter configuration Left Channel Right Channel Scalable Audio Filtering Service Parallel FD Simulation Filter generation Binaural Audio Output Current Spatial Model and source/sink positions User-driven Immersive Audio Client

11 Finite Difference Simulation of Wave Equation Compute impulse response by injecting impulse and then iterating simulation “snap fingers and record” Captures nuances by simulating the physics Stencil computation on distributed array  2 p/  2 t =  2 p/  2 x +  2 p/  2 y +  2 p/  2 z

12 Simulation Server Simple stateless request/response protocol Block-distributed simulation arrays Extensible/Modifiable Built with C++ and PVM

13 Computation requirements 8x6x3 meter room 2 second impulse response O(xyz(kf) 4 t/c 3 ) Current Resource Limit

14 Adaptation Mechanisms for Simulation Service O(xyz(kf) 4 t/c 3 ) stencil operations f=peak frequency to be resolved x,y,z=dimensions of simulated space k=grid points per wavelength (2..10 typical) c=speed of sound in medium t=length of the impulse response Peak frequency f is key “knob” Impulse response length t Server or site selection Traditional load-balancing

15 Adaptation Mechanisms for Filtering Service O((kf) 2 t) ops/second per stream Using impulse response as FIR filter Peak frequency f is key “knob” Impulse response length t IIR approximations for impulse response filter Server or site selection

16 Simulation Server Evaluation Scalability Appropriateness of SMP Initial results on server selection

17 Experimental Environment (Cluster) 8 nodes (16 processors) –Dual 866 MHz Pentium 3 –1 GB RAM –RH Linux 7.1 Switched gigabit Ethernet

18 Simulation Server Scales Well to 16 Processors

19 Efficiency Is Reasonable

20 SMP Is Useful (Not Memory-limited)

21 Server Selection Experiments Choose from several sequential servers Small problem size –500 Hz, 8x6x3, 2 seconds –~15 second task Four server selection algorithms –Random –Load measurement –Load prediction –Real-time Scheduling Advisor (RTSA) RPS

22 Evaluation Methodology 100 repetitions, random arrivals Host load trace playback for dynamic load –Traces from production PSC cluster Metrics: mean and variance of task slowdown –Seek to minimize both

23 Experiment 0: No Challenge Choose from 4 hosts with no load SchedulerMean Slowdown StdDev Slowdown Random Load Measure Load Predict RTSA All algorithms have low overhead

24 Experiment 1: Static Challenge 2 hosts with no load, 2 with high static load SchedulerMean Slowdown StdDev Slowdown Random Load Measure Load Predict RTSA All algorithms respond well with to static load challenge

25 Experiment 2: Dynamic Challenge SchedulerMean Slowdown StdDev Slowdown Random Load Measure Load Predict RTSA host with high dynamic load, 1 with low dynamic load Prediction leads to enhanced performance here Challenging case but resource are often available

26 Experiment 3: More dynamic load SchedulerMean Slowdown StdDev Slowdown Random Load Measure Load Predict RTSA hosts, each with different low to high dynamic load All algorithms respond well

27 Experiment 4: All Dynamic High Load SchedulerMean Slowdown StdDev Slowdown Random Load Measure Load Predict RTSA hosts, each with high dynamic load Algorithms behave similarly Most challenging scenario – few resource available

28 Conclusion & Future Work Introduced Virtualized Audio as an HPC application Described application structure Identified adaptation mechanisms Evaluated scalability of one component Showed early server selection results Future Work –Dynamic load balancing of simulation service in non-dedicated environments and Grids –Dynamic load balancing with real-time constraints –Continue development of application

29 For More Information Resource Prediction System (RPS) Toolkit PlayLoad Prescience Lab