Basics of Data Center
Design Management
Data center overview, Real life issues
on design, Cabinets, Power, HVAC, Power sizing, cooling, Cable Management,
Safety, efficient design and planning a strategy, Collecting the heat, Heat
rejection or reuse, Energy use systems, Data Centre Metrics, Best Practices,
Fire Protection and Security Systems.
Design of HPC Cluster –
Ecosystem
Requirement Analysis, Building blocks
of HPC, Hardware and software selection process, Design of HPC Cluster, Cluster
Planning, Architecture and Cluster software, Cluster building tools, Multicore-architecture, Accelerator cards
& their configuration (CUDA Library), Latest trends
and technologies in HPC.
HPC System
Management and Monitoring
IPMI, HMC, Node resources, processor
usage, memory usage, network usage, statistics, network monitoring, Gangila,
Collecli, Graphite, Nagios
Benchmarking, theoretical peak
performance, Micro & Macro benchmarking, HPL benchmark, Tuning HPL (problem
size, block size, process grid PxQ), HPCC benchmark, OSU benchmark / IO
benchmark, HPCG benchmark, Application benchmarking and check the scalability
of the applications.
Case study of HPC solutions
like Param Shavak