Ana Balevic & Ivan Dimkovic – DigiCortex
Ana Balevic started with parallel programming and GPU acceleration in 2007. She has experience with design and development of parallel algorithms for accelerators in wide-range of fields, such as electromagnetic simulations, multimedia codecs, streaming applications and bioinformatics.
Ana initiated and successfully lead development of CUJ2K in 2009, which resulted in the world’s first open source CUDA JPEG2000 Encoder entirely running on the GPU. From 2009-2012, Ana has been working with Leiden University, Compaan Design and ACE Compiler Experts on compile-time transformations and parallelization techniques for streaming applications. Her research work culminated in a PhD including a novel methodology for multi-level parallelization that enables custom-tailored code generation for heterogeneous platforms. Since 2013, Ana assists Leiden University Medical Center in accelerating bioinformatics algorithms as a GPU consultant. Ana is passionate about acceleration of real-world applications and open for new high performance computing challenges.
Ivan Dimkovic is a software developer who became known in late 90s for having developed the PsyTEL AAC Encoder – an encoding scheme for digital audio files. The stereo mode of this format had the best quality available in its day. In 2002, PsyTEL AAC Encoder was acquired by Nero AG and Ivan moved to Germany to lead the development of MPEG-4 technologies at Nero. In 2008, with founders of Nero, Ivan co-founded Cinemo GmbH, a multimedia automotive software spin-off of Nero, for which he acquired the lead customer and has been responsible for overseeing the product development ever since. In 2013, Cinemo’s automotive entertainment solution was launched in 2013 BMW 7 Series and 2013 Daimler S Class. Ivan is highly interested in computational neuroscience with the vision of developing a high performance biological neural networks simulation and in-silico experimentation tool for next generation medical research that could help cure brain diseases.
Together, Ivan & Ana develop DigiCortex project – the advanced massively parallel simulator of biological neural networks. The DigiCortex engine leverages the computational power of massively parallel accelerators to deliver large and fast biological neural network simulations on desktop supercomputers.
Digicortex @ Artificialbrains.com
Interview @ GTC2013 (insideHPC)
Talk at GPGPU-day 2013 (Ana & Ivan): DigiCortex – A Hybrid (CPU/GPU) Acceleration of Biological Spiking Neural Networks on Desktop Supercomputers
Talk at GPGPU-day 2012 (Ana): Mapping Streaming Multimedia Applications onto Heterogeneous Platforms with Accelerators