CSE 225 Reading List

Updated: March 29, 2005


 

1.       Grid Computing – Vision and Realities (3 classes)

a.       Lecture 1: Vision of Wide-Area Shared Resource Environments (Grids)

·         Grids in Context (Smarr 1999)

·         What is the Grid? (Foster 2002)

·         What is Grid Computing? (IBM 2002)

·         The Grid: Past, Present, Future (Berman, Fox, Hey 2003)

b.       Lecture 2: Real Production Grids and Experiences

·         SETI@Home – A Desktop Grid (Anderson 2002) and backup Entropia: Architecture of a Desktop Grid System (Chien 2002)

·         Open Science Grid (Avery 2005);  and backup The Grid2003 Production Grid:Principles and Practice (Gardner 2004)

·         Planetlab: A Blueprint for Introducing Disruptive Technology in the Internet (Peterson 2002)

c.        Lecture 3: High Performance Distributed Applications

·         Massive Computation: Genome and Proteomics Analysis Encyclopedia of Life (Li 2004) , Protein Folding in Folding@home (Pande 2004 video)

·         Online Simulation:  

(1)    Structures and Earthquakes (Kesselman 2004) (NEESGrid Slides, Spencer 2004)

(2)    LEAD: Tornadoes and Hurricanes (Droegemeier 2005)

·         Massive Data:

(1)     High Energy Physics: Atlas on the Open Science Grid (Gardner 2005)

(2)     Medical Research:  Biogrids (Ellisman 2004), and backup Biomedical Informatics Research Network (Ellisman 2003)  

(3)     Astronomy/Astrophysics: National Virtual Observatory

·         Enterprise Computing:

(1)    IBM Grid Computing (2004)

(2)    HP’s Adaptive Enterprise (2004)

 

2.       Dynamic Applications are Resource Aware: “Beauty is in the eye of the beholder.”  (5 classes)

a.       Lecture 4:  Resource Information and Description

·         Metacomputing Directory Service

·         Globus RSL/GRAM and Redline

·         Matchmaking and Gang Matching

·         Additional: SWORD, vgDL: Virtual Grid High Level Resource Abstractions

·         Recipe-Based Service Composition

·         AI Planning Approach

b.       Lecture 5:  Resource Selection (Nut Taesombut)

·         Same Papers as Lecture 4, selection discussion

c.       Lecture 6:  Dynamic Monitoring and Resource Behavior

·         Network Weather Service

·         Desktop Grid Resource Characterization

·         Statistical Availability Modeling

·         Impact: Optimizing Makespan

d.       Lecture 7:  Challenges in Supporting Adaptive Applications: the GrADS Project

·         GrADS General Approach

·         GrADS Rescheduling

e.       Lecture 8:  Virtual Grids: Supporting Adaptive Applications

·         Virtual Grids: Describing Resource Needs (vgDL) and Robust Selection and Binding vgES Resource Selection)

·         Design of the VGrADS System (and Open Research Challenges)

(1)    Scheduling and Rescheduling (EMAN, Fault tolerance)

(2)    Integration of Dynamic Information

(3)    Monitoring

 

3.       Open Resource Sharing: “You can’t always get what you want.” (4 classes)

a.       Lecture 9: Resource Models: Asymmetric Resource Sharing in Desktop Grids

·         Condor: Hunter of Idle Workstations

·         Resource Management in the Entropia System

·         Bounding the Resources Savings of Utility Computing Models

b.       Lecture 10: Resource Models: Traditional Batch Resource Managers and Co-allocation/Reservation

·         Portable Batch System (Shareware and product web site)

·         PBS and Maui Scheduler Comparison

·         Batch Queue Wait Prediction

c.       Lecture 11: Resource Models: Best-effort Slice and Virtualization Systems; Share Scheduling

·         Planetlab Slice and info on Proportional Scheduling

·         Lottery Scheduling

·         Coscheduling

·         Optional: SHARP: Resource Exchange and Comparing Planetlab and Globus

d.       Lecture 12: Resource Allocation: Economic techniques, Stability

·         Current Resource Allocation Practice

·         Market-based Central Allocation and backup Bellagio

·         G-commerce

·         Network and Application Uncertainty: Resource Utilization and Network/Application Uncertainty

 

4.       Configurable Networks and Grids: “Communication as a first-class resource.” (4 classes)

a.       Lecture 13:  Technology (OptIPuter), and Large-scale Infrastructure (Starlight) for configurable optical networks and CANARIE/CALREN/NLR; GLIF, etc.

b.       Lecture 14:  Usage Models: Intelligent Networks, Super FTP model, Distributed Virtual Computer and Application Specification:  DVC-ISL, RSL2, ASTDL and DRAC, UCLP and backup (Canarie UCLP),

c.       Lecture 15:  Protocols for Lambda Grids: UDT, Group Transport Protocol, and Composite Endpoint Protocol

 

5.       Advanced Distributed Applications  (1 class)

a.       GriPhyN: the Grid Physics Network

b.       Biomedical Informatics Research Network  and see the BIRN Web

 

6.       Course Project Presentations – Thursday June 2, 1230-330pm, 4882 APM

 

References

 

[Gridbook 2003]            The Grid: Blueprint for a New Computing Infrastructure, Second Edition  Morgan Kaufmann  (eds. Foster, Kesselman), 2003.

 

[GridInfrastructure2003]            Grid Computing: Making the Global Infrastructure a Reality,   (eds. Fox, Berman, Hey), Wiley and Sons 2003.

 


For more information, email Professor Andrew Chien

CSE225 Home

CSAG Home

UCSD CSE Home

UCSD Home

Contact Webmaster