4th Int. Workshop on New Algorithms and Programming Models for the Manycore Era, Bologna, Italien

Abbrevation

APMM

Link

http://hpcs2014.cisedu.info/

City

Bologna

Country

Italy

Deadline Paper

2014-03-11

Start Date

2014-07-21

End Date

2014-07-25

Abstract

With multi– and many–core based systems, performance increase on the microprocessor side will continue according to Moore′s Law, at least in the near future. However, the already existing performance limitations due to slow memory access are expected to get worse with multiple cores on a chip, and complex hierarchies of cache memory will make it hard for users to fully exploit the theoretically available performance. In addition, the increasingly hybrid and hierarchical design of compute clusters and high–end supercomputers, as well as the use of accelerator components (GPGPUs by AMD and NVIDIA, Intel Xeon Phi, Intel SCC, integrated GPUs etc.) add further challenges to efficient programming in HPC applications. Therefore, compute and data intensive tasks can only benefit from the hardware′s full potential, if both processor and architecture features are taken into account at all stages – from the early algorithmic design, via appropriate programming models, up to the final implementation. The APMM Workshop topics of interest include (but are not limited to) the following: – Hardware–aware, compute– and memory–intensive simulations of real–world problems in computational science and engineering (for example, from applications in electrical, mechanical, civil, or medical engineering). – Manycore–aware approaches for large–scale parallel simulations in both implementation and algorithm design, including scalability studies. – Parallelisation on HPC platforms; esp. platforms with hierarchical communication layout, multi–/many–core platforms, NUMA architectures, or accelerator components (Intel Xeon Phi, NVIDIA and AMD GPU, Tilera, FPGA, integrated GPUs (such as AMD APUs or Intel Haswell/Ivy Bridge)). – Parallelisation with appropriate programming models and tool support for multi–core and hybrid platforms. – concepts for exploiting emerging vector extensions of instruction sets – Software engineering, code optimisation, and code generation strategies for parallel systems with multi–core processors. – Tools for performance and cache behavior analysis (including cache simulation) for parallel systems with multi–core processors. – Performance modelling and performance engineering approaches for multi–thread and mutli–process applications.