Programme Overview thematic CSC 2013

Overall description

Do you have what it takes to squeeze out a modern computer like a lemon? This weeklong intensive training is an advanced dive into software, tools and techniques for exploiting current computing hardware.
Core topics include practical use of relevant software methodologies for parallelization, efficient use of compilers, performance optimization, controlled floating point calculations – all coupled with hands-on exercises.
In addition to the core teaching material, a range of supplementary topics is offered, such as select aspects of supercomputing, accelerated processing and others.
Finally, perspectives on cutting edge software and hardware will be presented, along with a vision of projected developments and their possible consequences.

Efficient computing

Data oriented design

Memory programming

Parallelism

Acceleration

Overview
Architecture refresher: x86, ARM, Atom, MIC, GPU

Designing for data

Data-intensive applications

Vectorization

Memory effects in hardware: prefetching, false sharing, caches

Threads, thread pools, creation, overheads, pthreads

Principles of programming for accelerators

Direct,  Offload,  Symmetric mode, MIC

Advanced performance monitoring and tuning

Choosing data structures
Non-uniform memory

Parallelization technologies and environments: OpenMP, Cilk, TBB

Compilers and  their strengths /  weaknesses

Accurate and efficient Floating Point

Lectures            4
Exercises          3

Lectures            1
Exercises          1

Lectures            1
Exercises          1

Lectures            3
Exercises          3

Lectures            1
Exercises          2