High Performance computing

Learning Outcomes: 
After learning the course the students should be able to:
 Understand the role of HPC in science and engineering.
 Use HPC platforms and parallel programming models.
 Able to measure, analyse and assess the performance of HPC applications and their supporting hardware.
 Able to administration, scheduling, code portability and data management in an HPC environment, with particular reference to Grid Computing.
 Analyse the suitability of different HPC solutions to common problems found in Computational Science.
Unit NoTopics


Introduction to high performance computing, Requirement for high performance computing, need of  high performance computing, grid computing, cluster computing,


Cluster Computing:

Introduction to Cluster Computing, Scalable Parallel Computer Architectures, Cluster Computer and its Architecture, Classifications, Components for Clusters, Cluster Middleware and Single System Image, Resource Management and Scheduling, Programming Environments and Tools, Applications, Representative Cluster Systems, Heterogeneous Clusters, Security, Resource Sharing, Locality, Dependability, Cluster Architectures, Detecting and Masking Faults, Recovering from Faults, Condor, Evolution of Meta computing.


Load Sharing and Balancing:

Evolution, Job and Resource Management Systems, State-of-the Art in RMS and Job, Rigid Jobs with Process Migration, Communication-Based Scheduling, Batch Scheduling, Fault Tolerance, Scheduling Problem for Network Computing, Algorithm ISH, MCP and ETF, Dynamic Load Balancing, Mapping and Scheduling, Task Granularity and Partitioning, Static and Dynamic Scheduling


Grid Computing:

Introduction to Grid Computing, Virtual Organizations, Architecture, Applications, Computational, Data, Desktop and Enterprise Grids, Data-intensive Applications, High-Performance Commodity Computing, High-Performance Schedulers, Grid Middleware: Connectivity, Resource and Collective Layer, Globus Toolkit, GSI, GRAM, LDAP, GridFTP, GIIS, Heterogeneous Computing Systems, Mapping Heuristics: Immediate and Batch Mode, Immediate: MCT, MET, Switching Algorithm, KPB and OLB, Batch: Min-Min, Max-Min, Sufferage, Duplex, GA, SA, GSA, Tabu and A*, Expected Time to Compute Matrix, Makespan, Heterogeneity: Consistent, Inconsistent and Partially-Consistent, QoS Guided Min-Min, Selective Algorithm, Grid Computing Security, Introduction to GridSim, Architecture, Grid Resource Broker, Grid Referral Service


Cloud Computing:

Introduction to Cloud Computing, Types: Deployment and Service Models, Characteristics, Applications, Service-Level Agreement, Virtualization, High-Throughput Computing: Task Computing and Task-based Application Models, Market-Based Management of Clouds, Energy-Efficient and Green Cloud Computing Architecture, Resource Allocation, Leases, Task Scheduling: RR, CLS and CMMS, Workflow Scheduling, Montage, Epigenomics, SIPHT, LIGO, CyberShake, Task Consolidation, Introduction to CloudSim, Cloudlet, Virtual Machine and its Provisioning, Time and Space-shared Provisioning.

Text Books: 
Name : 
High Performance Cluster Computing: Architectures and Systems
by Raj kumarBuyya
Reference Books: 
Grid and Cluster Computing
PHI Publication
Building Linux Clusters
by David H.M
Willey Publication
Syllabus PDF: