Embedded Files
"PRoductivity and Energy-efficiency through Abstraction-based Parallel Programming" at University of Tromsø (UiT), funded by Research Council of Norway.
The PREAPP project aims to devise novel programming models that will form foundations for a paradigm shift from energy “blind” to energy “aware” software development. The new models will enable one order of magnitude improvement in energy efficiency in comparison with today’s multicore computing, thereby greatly advancing green computing and sustainable services. The new models will facilitate unprecedented productivity for implementing scientific big data applications that run effectively on large-scale high-performance computing (HPC) platforms, which are based on cutting-edge manycore architectures. We aim to facilitate PGAS languages, such as UPC and X10 as some accepted locality aware languages, in combination with accelerators to achieve productivity and improve performance per watt.
"Parallel Neural Network Simulator" at Federal University of ABC, founded by FAPESP; in collaboration with Indian's National Center for Biological Sciences.
We designed and developed an efficient simulation engine, Parallel Neural Network Simulator, PN2S, for spiking neural network models.
The engine provides a framework for scientist, to simply develop their model/solver and execute it on systems with multiple GPUs and CPUs
Heterogeneous model imports from host simulators, such as MOOSE, after clustering the model and creating tasks for vector processing, it facilitates non-blocking and one-way synchronization method to execute solvers on CPUs and multiple GPUs.
GENESIS initiated at 1990 at University of Colorado, Boulder, USA. So far, it's one of the main simulation tools in neuroscience and I'm responsible for its development, troubleshooting and package management.
Page updated
Google Sites
Report abuse