Marek Blazewicz

RNA FRABASE version 1.0: an engine with a database to search for the three-dimensional fragments within RNA structures

The RNA FRABASE is a web-accessible engine with a relational database, which allows for the automatic search of user-defined, 3D RNA fragments within a set of RNA structures. This is a new tool to search and analyse RNA structures, directed at the 3D structure modelling. The user needs to input either RNA sequence(s) and/or secondary structure(s) given in a ‘dot-bracket’ notation. The algorithm searching for the requested 3D RNA fragments is very efficient. As of August 2007, the database contains: (i) RNA sequences and secondary structures, in the ‘dot-bracket’ notation, derived from 1065 protein data bank (PDB)-deposited RNA structures and their complexes, (ii) a collection of atom coordinates of unmodified and modified nucleotide residues occurring in RNA structures, (iii) calculated RNA torsion angles and sugar pucker parameters and (iv) information about base pairs. Advanced query involves filters sensitive to: modified residue contents, experimental method used and limits of conformational parameters. The output list of query-matching RNA fragments gives access to their coordinates in the PDB-format files, ready for direct download and visualization, conformational parameters and information about base pairs. The RNA FRABASE is automatically, monthly updated and is freely accessible at http://rnafrabase.ibch.poznan.pl (mirror at http://cerber.cs.put.poznan.pl/rnadb).

From physics model to results: An optimizing framework for cross-architecture code generation

Starting from a high-level problem description in terms of partial differential equations using abstract tensor notation, the Chemora framework discretizes, optimizes, and generates complete high performance codes for a wide range of compute architectures. Chemora extends the capabilities of Cactus, facilitating the usage of large-scale CPU/GPU systems in an efficient manner for complex applications, without low-level code tuning. Chemora achieves parallelism through MPI and multi-threading, combining OpenMP and CUDA. Optimizations include high-level code transformations, efficient loop traversal strategies, dynamically selected data and instruction cache usage strategies, and JIT compilation of GPU code tailored to the problem characteristics. The discretization is based on higher-order finite differences on multi-block domains. Chemoras capabilities are demonstrated by simulations of black hole collisions. This problem provides an acid test of the framework, as the Einstein equations contain hundreds of variables and thousands of terms.

CaKernel --A parallel application programming framework for heterogenous computing architectures

With the recent advent of new heterogeneous computing architectures there is still a lack of parallel problem solving environments that can help scientists to use easily and efficiently hybrid supercomputers. Many scientific simulations that use structured grids to solve partial differential equations in fact rely on stencil computations. Stencil computations have become crucial in solving many challenging problems in various domains, e.g., engineering or physics. Although many parallel stencil computing approaches have been proposed, in most cases they solve only particular problems. As a result, scientists are struggling when it comes to the subject of implementing a new stencil-based simulation, especially on high performance hybrid supercomputers. In response to the presented need we extend our previous work on a parallel programming framework for CUDA --CaCUDA that now supports OpenCL. We present CaKernel --a tool that simplifies the development of parallel scientific applications on hybrid systems. CaKernel is built on the highly scalable and portable Cactus framework. In the CaKernel framework, Cactus manages the inter-process communication via MPI while CaKernel manages the code running on Graphics Processing Units GPUs and interactions between them. As a non-trivial test case we have developed a 3D CFD code to demonstrate the performance and scalability of the automatically generated code.

Using GPU's to accelerate stencil-based computation kernels for the development of large scale scientific applications on heterogeneous systems

We present CaCUDA - a GPGPU kernel abstraction and a parallel programming framework for developing highly efficient large scale scientific applications using stencil computations on hybrid CPU/GPU architectures. CaCUDA is built upon the Cactus computational toolkit, an open source problem solving environment designed for scientists and engineers. Due to the flexibility and extensibility of the Cactus toolkit, the addition of a GPGPU programming framework required no changes to the Cactus infrastructure, guaranteeing that existing features and modules will continue to work without modification. CaCUDA was tested and benchmarked using a 3D CFD code based on a finite difference discretization of Navier-Stokes equations.

Two-Dimensional discrete wavelet transform on large images for hybrid computing architectures: GPU and CELL

The Discrete Wavelet Transform (DWT) has gained the momentum in signal processing and image compression over the last decade bringing the concept up to the level of new image coding standard JPEG2000. Thanks to many added values in DWT, in particular inherent multi-resolution nature, wavelet-coding schemes are suitable for various applications where scalability and tolerable degradation are relevant. Moreover, as we demonstrate in this paper, it can be used as a perfect benchmarking procedure for more sophisticated data compression and multimedia applications using General Purpose Graphical Processor Units (GPGPUs). Thus, in this paper we show and compare experiments performed on reference implementations of DWT on Cell Broadband Engine Architecture (Cell B.E) and nVidia Graphical Processing Units (GPUs). The achieved results show clearly that although both GPU and Cell B.E. are being considered as representatives of the same hybrid architecture devices class they differ greatly in programming style and optimization techniques that need to be taken into account during the development. In order to show the speedup, the parallel algorithm has been compared to sequential computation performed on the x86 architecture.

Vitrall: web-based distributed visualization system for creation of collaborative working environments

Advanced parallel computing solutions using GPU for general purpose processing are becoming more and more popular. Applications like CFD or weather modeling take an extensive speed up using GPU-based clusters. Still, original purpose of graphic processing units --- visualization, is not exploited as much as it could be in such powerful processing centres. Main reason of that situation is their fundamental difference from classic desktop configurations: being a structure remote and hidden from the actual viewer. Already existing GPU-based architectures consisting of many processing units may be used for visualization of complex issues from many points of view and in resolutions that are not accessible for single GPUs in real-time. Visualization is a very efficient way of collaboration, especially when collaborators can interact with presented content in a natural way, for example using multi-touch devices. Vitrall embraces these methods by introducing possibility of linkage between modern interfaces and complex visualizations. This paper will begin with summary of several researches that where conducted to establish actual concept of the Vitrall system. Next, proposed architecture of Vitrall will be introduced, following main and secondary usage scenarios. Finally, some of Vitralls specific configurations will be shown, like real-time stereoscopic visualization.

Chemora: A PDE-Solving Framework for Modern High-Performance Computing Architectures

Modern HPC architectures consist of heterogeneous multicore, many-node systems with deep memory hierarchies. Modern applications employ ever more advanced discretization methods to study multiphysics problems. Developing such applications that explore cutting-edge physics on cutting-edge HPC systems has become a complex task that requires significant HPC knowledge and experience. Unfortunately, this combined knowledge is currently out of reach for all but a few groups of application developers. Chemora is a framework for solving systems of partial differential equations (PDEs) that targets modern HPC architectures. Chemora is based on Cactus, which sees prominent usage in the computational relativistic astrophysics community. In Chemora, PDEs are expressed either in high-level LaTeX-like languages or in Mathematica. The authors use Chemora in the Einstein Toolkit to implement the Einstein equations on CPUs and on accelerators, and study astrophysical systems such as black hole binaries, neutron stars, and core-collapse supernovae.