@inproceedings{1787, author = {{Suess, Tim and Schoenrock, Andrew and Meisner, Sebastian and Plessl, Christian}}, booktitle = {{Proc. Int. Symp. on Parallel and Distributed Processing Workshops (IPDPSW)}}, isbn = {{978-0-7695-4979-8}}, pages = {{64--73}}, publisher = {{IEEE Computer Society}}, title = {{{Parallel Macro Pipelining on the Intel SCC Many-Core Computer}}}, doi = {{10.1109/IPDPSW.2013.136}}, year = {{2013}}, } @inproceedings{2097, author = {{Kasap, Server and Redif, Soydan}}, booktitle = {{Proc. Int. Conf. on Field Programmable Technology (ICFPT)}}, pages = {{135--140}}, publisher = {{IEEE Computer Society}}, title = {{{FPGA-based design and implementation of an approximate polynomial matrix EVD algorithm}}}, doi = {{10.1109/FPT.2012.6412125}}, year = {{2012}}, } @inproceedings{2100, author = {{Kasap, Server and Redif, Soydan}}, booktitle = {{Int. Architecture and Engineering Symp. (ARCHENG)}}, title = {{{FPGA implementation of a second-order convolutive blind signal separation algorithm}}}, year = {{2012}}, } @inproceedings{2103, author = {{Wistuba, Martin and Schaefers, Lars and Platzner, Marco}}, booktitle = {{Proc. IEEE Conf. on Computational Intelligence and Games (CIG)}}, pages = {{91--99}}, publisher = {{IEEE}}, title = {{{Comparison of Bayesian Move Prediction Systems for Computer Go}}}, doi = {{10.1109/CIG.2012.6374143}}, year = {{2012}}, } @article{2172, author = {{Thielemans, Kris and Tsoumpas, Charalampos and Mustafovic, Sanida and Beisel, Tobias and Aguiar, Pablo and Dikaios, Nikolaos and W Jacobson, Matthew}}, journal = {{Physics in Medicine and Biology}}, number = {{4}}, pages = {{867--883}}, publisher = {{IOP Publishing}}, title = {{{STIR: Software for Tomographic Image Reconstruction Release 2}}}, doi = {{10.1088/0031-9155/57/4/867}}, volume = {{57}}, year = {{2012}}, } @article{2173, author = {{Redif, Soydan and Kasap, Server}}, journal = {{Int. Journal of Electronics}}, number = {{12}}, pages = {{1646--1651}}, publisher = {{Taylor & Francis}}, title = {{{Parallel algorithm for computation of second-order sequential best rotations}}}, doi = {{10.1080/00207217.2012.751343}}, volume = {{100}}, year = {{2012}}, } @article{2174, author = {{Kasap, Server and Benkrid, Khaled}}, journal = {{Journal of Computers}}, number = {{6}}, pages = {{1312--1328}}, publisher = {{Academy Publishers}}, title = {{{Parallel Processor Design and Implementation for Molecular Dynamics Simulations on a FPGA Parallel Computer}}}, volume = {{7}}, year = {{2012}}, } @phdthesis{586, abstract = {{FPGAs, systems on chip and embedded systems are nowadays irreplaceable. They combine the computational power of application specific hardware with software-like flexibility. At runtime, they can adjust their functionality by downloading new hardware modules and integrating their functionality. Due to their growing capabilities, the demands made to reconfigurable hardware grow. Their deployment in increasingly security critical scenarios requires new ways of enforcing security since a failure in security has severe consequences. Aside from financial losses, a loss of human life and risks to national security are possible. With this work I present the novel and groundbreaking concept of proof-carrying hardware. It is a method for the verification of properties of hardware modules to guarantee security for a target platform at runtime. The producer of a hardware module delivers based on the consumer's safety policy a safety proof in combination with the reconfiguration bitstream. The extensive computation of a proof is a contrast to the comparatively undemanding checking of the proof. I present a prototype based on open-source tools and an abstract FPGA architecture and bitstream format. The proof of the usability of proof-carrying hardware provides the evaluation of the prototype with the exemplary application of securing combinational and bounded sequential equivalence of reference monitor modules for memory safety.}}, author = {{Drzevitzky, Stephanie}}, pages = {{114}}, publisher = {{Universität Paderborn}}, title = {{{Proof-Carrying Hardware: A Novel Approach to Reconfigurable Hardware Security}}}, year = {{2012}}, } @misc{587, author = {{Plessl, Christian and Platzner, Marco and Agne, Andreas and Happe, Markus and Lübbers, Enno}}, publisher = {{Awareness Magazine}}, title = {{{Programming models for reconfigurable heterogeneous multi-cores}}}, year = {{2012}}, } @inproceedings{10636, author = {{Boschmann, Alexander and Platzner, Marco}}, booktitle = {{Proc. IEEE Int. Conf. Eng. Med. Biolog. (EMBC)}}, title = {{{Reducing classification accuracy degradation of pattern recognition based myoelectric control caused by electrode shift using a high density electrode array}}}, year = {{2012}}, } @misc{10650, author = {{Dridger, Denis}}, publisher = {{Paderborn University}}, title = {{{Design and Implementation of a Nanophotonics Simulation Personality for the Convey HC-1 Hybrid Core Computer}}}, year = {{2012}}, } @phdthesis{10652, abstract = {{The paradigm shift towards many-core parallelism is accompanied by two fundamental questions: how should the many processors on a single die communicate to each other and what are suitable programming models for these novel architectures? In this thesis, the author tackles both questions by reviewing the reconfigurable mesh model of massively parallel computation for many-cores. The book presents the design, implementation and evaluation of a many-core architecture that is based on the execution principles and communication infrastructure of the reconfigurable mesh. This work fundamentally rests on FPGA implementations and shows that reconfigurable mesh processors with hundreds of autonomous cores are feasible. Several case studies demonstrate the effectiveness of programming and illustrate why the reconfigurable mesh is a promising model for many-cores.}}, author = {{Giefers, Heiner}}, isbn = {{978-3-8325-3165-2}}, pages = {{159}}, publisher = {{Logos Verlag Berlin GmbH}}, title = {{{Design and Programming of Reconfigurable Mesh based Many-Cores}}}, year = {{2012}}, } @misc{10658, author = {{Graf, Tobias}}, publisher = {{Paderborn University}}, title = {{{Adaptive Playouts in der Monte-Carlo Spielbaumsuche am Anwendungsfall Go}}}, year = {{2012}}, } @misc{10667, author = {{Hangmann, Hendrik}}, publisher = {{Paderborn University}}, title = {{{Generating Adjustable Temperature Gradients on modern FPGAs}}}, year = {{2012}}, } @article{10685, author = {{Kaufmann, Paul and Glette, Kyrre and Platzner, Marco and Torresen, Jim}}, journal = {{International Journal of Adaptive, Resilient and Autonomic Systems (IJARAS)}}, number = {{4}}, pages = {{17--31}}, publisher = {{IGI Global}}, title = {{{Compensating Resource Fluctuations by Means of Evolvable Hardware: The Run-Time Reconfigurable Functional Unit Row Classifier Architecture}}}, doi = {{10.4018/jaras.2012100102}}, volume = {{3}}, year = {{2012}}, } @misc{10723, author = {{Platzner, Marco and Boschmann, Alexander and Kaufmann, Paul}}, pages = {{6--11}}, title = {{{Wieder natürlich gehen und greifen}}}, year = {{2012}}, } @misc{10734, author = {{Schmitz, Henning}}, publisher = {{Paderborn University}}, title = {{{Stereo Matching on a HC-1 Hybrid Core Computer}}}, year = {{2012}}, } @misc{10747, author = {{Topmöller, Christoph}}, publisher = {{Paderborn University}}, title = {{{Entwicklung eines Picoblaze Compilers mit dem Gentle Compiler Construction System}}}, year = {{2012}}, } @misc{10754, author = {{Wistuba, Martin}}, publisher = {{Paderborn University}}, title = {{{Analysis of Pattern Based Model Design and Learning in Computer-Go}}}, year = {{2012}}, } @misc{13462, author = {{Lewis, Peter and Platzner, Marco and Yao, Xin}}, publisher = {{Awareness Magazine}}, title = {{{An outlook for self-awareness in computing systems}}}, year = {{2012}}, } @inproceedings{2106, abstract = {{Although the benefits of FPGAs for accelerating scientific codes are widely acknowledged, the use of FPGA accelerators in scientific computing is not widespread because reaping these benefits requires knowledge of hardware design methods and tools that is typically not available with domain scientists. A promising but hardly investigated approach is to develop tool flows that keep the common languages for scientific code (C,C++, and Fortran) and allow the developer to augment the source code with OpenMPlike directives for instructing the compiler which parts of the application shall be offloaded the FPGA accelerator. In this work we study whether the promise of effective FPGA acceleration with an OpenMP-like programming effort can actually be held. Our target system is the Convey HC-1 reconfigurable computer for which an OpenMP-like programming environment exists. As case study we use an application from computational nanophotonics. Our results show that a developer without previous FPGA experience could create an FPGA-accelerated application that is competitive to an optimized OpenMP-parallelized CPU version running on a two socket quad-core server. Finally, we discuss our experiences with this tool flow and the Convey HC-1 from a productivity and economic point of view.}}, author = {{Meyer, Björn and Schumacher, Jörn and Plessl, Christian and Förstner, Jens}}, booktitle = {{Proc. Int. Conf. on Field Programmable Logic and Applications (FPL)}}, keywords = {{funding-upb-forschungspreis, funding-maxup, tet_topic_hpc}}, pages = {{189--196}}, publisher = {{IEEE}}, title = {{{Convey Vector Personalities – FPGA Acceleration with an OpenMP-like Effort?}}}, doi = {{10.1109/FPL.2012.6339370}}, year = {{2012}}, } @article{2108, author = {{Schumacher, Tobias and Plessl, Christian and Platzner, Marco}}, issn = {{0141-9331}}, journal = {{Microprocessors and Microsystems}}, keywords = {{funding-altera}}, number = {{2}}, pages = {{110--126}}, title = {{{IMORC: An Infrastructure and Architecture Template for Implementing High-Performance Reconfigurable FPGA Accelerators}}}, doi = {{10.1016/j.micpro.2011.04.002}}, volume = {{36}}, year = {{2012}}, } @inproceedings{615, abstract = {{Due to the continuously shrinking device structures and increasing densities of FPGAs, thermal aspects have become the new focus for many research projects over the last years. Most researchers rely on temperature simulations to evaluate their novel thermal management techniques. However, the accuracy of the simulations is to some extent questionable and they require a high computational effort if a detailed thermal model is used.For experimental evaluation of real-world temperature management methods, often synthetic heat sources are employed. Therefore, in this paper we investigated the question if we can create significant rises in temperature on modern FPGAs to enable future evaluation of thermal management techniques based on experiments in contrast to simulations. Therefore, we have developed eight different heat-generating cores that use different subsets of the FPGA resources. Our experimental results show that, according to the built-in thermal diode of our Xilinx Virtex-5 FPGA, we can increase the chip temperature by 134 degree C in less than 12 minutes by only utilizing about 21% of the slices.}}, author = {{Happe, Markus and Hangmann, Hendrik and Agne, Andreas and Plessl, Christian}}, booktitle = {{Proceedings of the International Conference on Reconfigurable Computing and FPGAs (ReConFig)}}, pages = {{1--8}}, publisher = {{IEEE}}, title = {{{Eight Ways to put your FPGA on Fire – A Systematic Study of Heat Generators}}}, doi = {{10.1109/ReConFig.2012.6416745}}, year = {{2012}}, } @inproceedings{591, abstract = {{One major obstacle for a wide spread FPGA usage in general-purpose computing is the development tool flow that requires much higher effort than for pure software solutions. Convey Computer promises a solution to this problem for their HC-1 platform, where the FPGAs are configured to run as a vector processor and the software source code can be annotated with pragmas that guide an automated vectorization process. We investigate this approach for a stereo matching algorithm that has abundant parallelism and a number of different computational patterns. We note that for this case study the automated vectorization in its current state doesn’t hold its productivity promise. However, we also show that using the Vector Personality can yield a significant speedups compared to CPU implementations in two of three investigated phases of the algorithm. Those speedups don’t match custom FPGA implementations, but can come with much reduced development effort.}}, author = {{Kenter, Tobias and Plessl, Christian and Schmitz, Henning}}, booktitle = {{Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig)}}, pages = {{1--8}}, publisher = {{IEEE}}, title = {{{Pragma based parallelization - Trading hardware efficiency for ease of use?}}}, doi = {{10.1109/ReConFig.2012.6416773}}, year = {{2012}}, } @inproceedings{609, abstract = {{Today's design and operation principles and methods do not scale well with future reconfigurable computing systems due to an increased complexity in system architectures and applications, run-time dynamics and corresponding requirements. Hence, novel design and operation principles and methods are needed that possibly break drastically with the static ones we have built into our systems and the fixed abstraction layers we have cherished over the last decades. Thus, we propose a HW/SW platform that collects and maintains information about its state and progress which enables the system to reason about its behavior (self-awareness) and utilizes its knowledge to effectively and autonomously adapt its behavior to changing requirements (self-expression).To enable self-awareness, our compute nodes collect information using a variety of sensors, i.e. performance counters and thermal diodes, and use internal self-awareness models that process these information. For self-awareness, on-line learning is crucial such that the node learns and continuously updates its models at run-time to react to changing conditions. To enable self-expression, we break with the classic design-time abstraction layers of hardware, operating system and software. In contrast, our system is able to vertically migrate functionalities between the layers at run-time to exploit trade-offs between abstraction and optimization.This paper presents a heterogeneous multi-core architecture, that enables self-awareness and self-expression, an operating system for our proposed hardware/software platform and a novel self-expression method.}}, author = {{Happe, Markus and Agne, Andreas and Plessl, Christian and Platzner, Marco}}, booktitle = {{Proceedings of the Workshop on Self-Awareness in Reconfigurable Computing Systems (SRCS)}}, pages = {{8--9}}, title = {{{Hardware/Software Platform for Self-aware Compute Nodes}}}, year = {{2012}}, } @inproceedings{567, abstract = {{Heterogeneous machines are gaining momentum in the High Performance Computing field, due to the theoretical speedups and power consumption. In practice, while some applications meet the performance expectations, heterogeneous architectures still require a tremendous effort from the application developers. This work presents a code generation method to port codes into heterogeneous platforms, based on transformations of the control flow into function calls. The results show that the cost of the function-call mechanism is affordable for the tested HPC kernels. The complete toolchain, based on the LLVM compiler infrastructure, is fully automated once the sequential specification is provided.}}, author = {{Barrio, Pablo and Carreras, Carlos and Sierra, Roberto and Kenter, Tobias and Plessl, Christian}}, booktitle = {{Proceedings of the International Conference on High Performance Computing and Simulation (HPCS)}}, pages = {{559--565}}, publisher = {{IEEE}}, title = {{{Turning control flow graphs into function calls: Code generation for heterogeneous architectures}}}, doi = {{10.1109/HPCSim.2012.6266973}}, year = {{2012}}, } @inproceedings{612, abstract = {{While numerous publications have presented ring oscillator designs for temperature measurements a detailed study of the ring oscillator's design space is still missing. In this work, we introduce metrics for comparing the performance and area efficiency of ring oscillators and a methodology for determining these metrics. As a result, we present a systematic study of the design space for ring oscillators for a Xilinx Virtex-5 platform FPGA.}}, author = {{Rüthing, Christoph and Happe, Markus and Agne, Andreas and Plessl, Christian}}, booktitle = {{Proceedings of the International Conference on Field Programmable Logic and Applications (FPL)}}, pages = {{559--562}}, publisher = {{IEEE}}, title = {{{Exploration of Ring Oscillator Design Space for Temperature Measurements on FPGAs}}}, doi = {{10.1109/FPL.2012.6339370}}, year = {{2012}}, } @inproceedings{2180, author = {{Beisel, Tobias and Wiersema, Tobias and Plessl, Christian and Brinkmann, André}}, booktitle = {{Proc. Workshop on Computer Architecture and Operating System Co-design (CAOS)}}, keywords = {{funding-enhance}}, title = {{{Programming and Scheduling Model for Supporting Heterogeneous Accelerators in Linux}}}, year = {{2012}}, } @article{2177, author = {{Grad, Mariusz and Plessl, Christian}}, journal = {{Int. Journal of Reconfigurable Computing (IJRC)}}, publisher = {{Hindawi Publishing Corp.}}, title = {{{On the Feasibility and Limitations of Just-In-Time Instruction Set Extension for FPGA-based Reconfigurable Processors}}}, doi = {{10.1155/2012/418315}}, year = {{2012}}, } @inproceedings{2191, author = {{Kenter, Tobias and Plessl, Christian and Platzner, Marco and Kauschke, Michael}}, booktitle = {{Intel European Research and Innovation Conference}}, keywords = {{funding-intel}}, title = {{{Estimation and Partitioning for CPU-Accelerator Architectures}}}, year = {{2011}}, } @inbook{2202, author = {{Plessl, Christian and Platzner, Marco}}, booktitle = {{Reconfigurable Embedded Control Systems: Applications for Flexibility and Agility}}, editor = {{Khalgui, Mohamed and Hanisch, Hans-Michael}}, isbn = {{978-1-60960-086-0}}, publisher = {{IGI Global}}, title = {{{Hardware Virtualization on Dynamically Reconfigurable Embedded Processors}}}, doi = {{10.4018/978-1-60960-086-0}}, year = {{2011}}, } @inproceedings{2204, author = {{Graf, Tobias and Lorenz, Ulf and Platzner, Marco and Schaefers, Lars}}, booktitle = {{Proc. European Conf. on Parallel Processing (Euro-Par)}}, publisher = {{Springer}}, title = {{{Parallel Monte-Carlo Tree Search for HPC Systems}}}, doi = {{10.1007/978-3-642-23397-5_36}}, volume = {{6853}}, year = {{2011}}, } @inproceedings{666, abstract = {{Reconfigurable systems on chip are increasingly deployed in security and safety critical contexts. When downloading and configuring new hardware functions, we want to make sure that modules adhere to certain security specifications and do not, for example, contain hardware Trojans. As a possible approach to achieving hardware security we propose and demonstrate the concept of proof-carrying hardware, a concept inspired by previous work on proof-carrying code techniques in the software domain. In this paper, we discuss the hardware trust and threat models behind proof-carrying hardware and then present our experimental setup. We detail the employed open-source tool chain for the runtime verification of combinational equivalence and our bitstream format for an abstract FPGA architecture that allows us to experimentally validate the feasibility of our approach.}}, author = {{Drzevitzky, Stephanie and Platzner, Marco}}, booktitle = {{Proceedings of the 6th International Workshop on Reconfigurable Communication-centric Systems-on-Chip (ReCoSoC)}}, pages = {{58--65}}, title = {{{Achieving Hardware Security for Reconfigurable Systems on Chip by a Proof-Carrying Code Approach}}}, doi = {{10.1109/ReCoSoC.2011.5981499}}, year = {{2011}}, } @inproceedings{10637, author = {{Boschmann, Alexander and Kaufmann, Paul and Platzner, Marco}}, booktitle = {{Proc. IEEE Int. Conf. Bioinformatics and Biomedical Technology (ICBBT)}}, title = {{{Accurate gait phase detection using surface electromyographic signals and support vector machines}}}, year = {{2011}}, } @inproceedings{10638, author = {{Boschmann, Alexander and Platzner, Marco and Robrecht, Michael and Hahn, Martin and Winkler, Michael}}, booktitle = {{Proc. MyoElectric Controls Symposium (MEC)}}, title = {{{Development of a pattern recognition-based myoelectric transhumeral prosthesis with multifunctional simultaneous control using a model-driven ppproach for mechatronic systems}}}, year = {{2011}}, } @misc{10678, author = {{Ikonomakis, Nikolaos}}, publisher = {{Paderborn University}}, title = {{{PinSim: Schnelle Simulation mit Pintools}}}, year = {{2011}}, } @misc{10680, author = {{Kassner, Hendrik}}, publisher = {{Paderborn University}}, title = {{{MPI-CUDA Codegenerierung für Nanophoton Simulationen auf Clustern}}}, year = {{2011}}, } @inbook{10687, author = {{Kaufmann, Paul and Platzner, Marco}}, booktitle = {{Organic Computing---A Paradigm Shift for Complex Systems}}, editor = {{Müller-Schloer, Christian and Schmeck, Hartmut and Ungerer, Theo}}, pages = {{193--206}}, publisher = {{Springer Basel}}, title = {{{Multi-objective Intrinsic Evolution of Embedded Systems}}}, volume = {{1}}, year = {{2011}}, } @misc{10736, author = {{Schwabe, Arne}}, publisher = {{Paderborn University}}, title = {{{Analysis of Algorithmic Approaches for Temporal Partitioning}}}, year = {{2011}}, } @inbook{10737, author = {{Sekanina, Lukas and Walker, James Alfred and Kaufmann, Paul and Plessl, Christian and Platzner, Marco}}, booktitle = {{Cartesian Genetic Programming}}, pages = {{125--179}}, publisher = {{Springer Berlin Heidelberg}}, title = {{{Evolution of Electronic Circuits}}}, year = {{2011}}, } @inbook{10748, author = {{Walker, James Alfred and Miller, Julian F. and Kaufmann, Paul and Platzner, Marco}}, booktitle = {{Cartesian Genetic Programming}}, pages = {{35--99}}, publisher = {{Springer Berlin Heidelberg}}, title = {{{Problem Decomposition in Cartesian Genetic Programming}}}, year = {{2011}}, } @misc{10750, author = {{Welp, Daniel}}, publisher = {{Paderborn University}}, title = {{{User Space Scheduling for Heterogeneous Systems}}}, year = {{2011}}, } @inproceedings{13643, author = {{Agne, Andreas and Platzner, Marco and Lübbers, Enno}}, booktitle = {{Proceedings of the International Conference on Field Programmable Logic and Applications (FPL)}}, isbn = {{9781457714849}}, pages = {{185--188}}, publisher = {{IEEE}}, title = {{{Memory Virtualization for Multithreaded Reconfigurable Hardware}}}, doi = {{10.1109/fpl.2011.42}}, year = {{2011}}, } @inproceedings{13644, author = {{Henkel, Jörg and Hedrich, Lars and Herkersdorf, Andreas and Kapitza, Rüdiger and Lohmann, Daniel and Marwedel, Peter and Platzner, Marco and Rosenstiel, Wolfgang and Schlichtmann, Ulf and Spinczyk, Olaf and Tahoori, Mehdi and Bauer, Lars and Teich, Jürgen and Wehn, Norbert and Wunderlich, Hans-Joachim and Becker, Joachim and Bringmann, Oliver and Brinkschulte, Uwe and Chakraborty, Samarjit and Engel, Michael and Ernst, Rolf and Härtig, Hermann}}, booktitle = {{Proceedings of the seventh IEEE/ACM/IFIP International Conference on Hardware/software Codesign and system synthesis - CODES+ISSS '11}}, isbn = {{9781450307154}}, title = {{{Design and architectures for dependable embedded systems}}}, doi = {{10.1145/2039370.2039384}}, year = {{2011}}, } @inproceedings{2194, author = {{Meyer, Björn and Plessl, Christian and Förstner, Jens}}, booktitle = {{Symp. on Application Accelerators in High Performance Computing (SAAHPC)}}, keywords = {{tet_topic_hpc}}, pages = {{60--63}}, publisher = {{IEEE Computer Society}}, title = {{{Transformation of scientific algorithms to parallel computing code: subdomain support in a MPI-multi-GPU backend}}}, doi = {{10.1109/SAAHPC.2011.12}}, year = {{2011}}, } @inproceedings{2193, author = {{Beisel, Tobias and Wiersema, Tobias and Plessl, Christian and Brinkmann, André}}, booktitle = {{Proc. Int. Conf. on Application-Specific Systems, Architectures, and Processors (ASAP)}}, pages = {{223--226}}, publisher = {{IEEE Computer Society}}, title = {{{Cooperative multitasking for heterogeneous accelerators in the Linux Completely Fair Scheduler}}}, doi = {{10.1109/ASAP.2011.6043273}}, year = {{2011}}, } @inproceedings{656, abstract = {{In the next decades, hybrid multi-cores will be the predominant architecture for reconfigurable FPGA-based systems. Temperature-aware thread mapping strategies are key for providing dependability in such systems. These strategies rely on measuring the temperature distribution and redicting the thermal behavior of the system when there are changes to the hardware and software running on the FPGA. While there are a number of tools that use thermal models to predict temperature distributions at design time, these tools lack the flexibility to autonomously adjust to changing FPGA configurations. To address this problem we propose a temperature-aware system that empowers FPGA-based reconfigurable multi-cores to autonomously predict the on-chip temperature distribution for pro-active thread remapping. Our system obtains temperature measurements through a self-calibrating grid of sensors and uses area constrained heat-generating circuits in order to generate spatial and temporal temperature gradients. The generated temperature variations are then used to learn the free parameters of the system's thermal model. The system thus acquires an understanding of its own thermal characteristics. We implemented an FPGA system containing a net of 144 temperature sensors on a Xilinx Virtex-6 LX240T FPGA that is aware of its thermal model. Finally, we show that the temperature predictions vary less than 0.72 degree C on average compared to the measured temperature distributions at run-time.}}, author = {{Happe, Markus and Agne, Andreas and Plessl, Christian}}, booktitle = {{Proceedings of the 2011 International Conference on Reconfigurable Computing and FPGAs (ReConFig)}}, pages = {{55--60}}, publisher = {{IEEE}}, title = {{{Measuring and Predicting Temperature Distributions on FPGAs at Run-Time}}}, doi = {{10.1109/ReConFig.2011.59}}, year = {{2011}}, } @inproceedings{2200, author = {{Kenter, Tobias and Platzner, Marco and Plessl, Christian and Kauschke, Michael}}, booktitle = {{Proc. Int. Symp. on Field-Programmable Gate Arrays (FPGA)}}, isbn = {{978-1-4503-0554-9}}, keywords = {{design space exploration, LLVM, partitioning, performance, estimation, funding-intel}}, pages = {{177--180}}, publisher = {{ACM}}, title = {{{Performance Estimation Framework for Automated Exploration of CPU-Accelerator Architectures}}}, doi = {{10.1145/1950413.1950448}}, year = {{2011}}, } @article{2201, author = {{Schumacher, Tobias and Süß, Tim and Plessl, Christian and Platzner, Marco}}, journal = {{Int. Journal of Recon- figurable Computing (IJRC)}}, keywords = {{funding-altera}}, publisher = {{Hindawi Publishing Corp.}}, title = {{{FPGA Acceleration of Communication-bound Streaming Applications: Architecture Modeling and a 3D Image Compositing Case Study}}}, doi = {{10.1155/2011/760954}}, year = {{2011}}, } @inproceedings{2198, author = {{Grad, Mariusz and Plessl, Christian}}, booktitle = {{Proc. Reconfigurable Architectures Workshop (RAW)}}, pages = {{278--285}}, publisher = {{IEEE Computer Society}}, title = {{{Just-in-time Instruction Set Extension – Feasibility and Limitations for an FPGA-based Reconfigurable ASIP Architecture}}}, doi = {{10.1109/IPDPS.2011.153}}, year = {{2011}}, } @article{10605, author = {{Drzevitzky, Stephanie and Kastens, Uwe and Platzner, Marco}}, journal = {{International Journal of Reconfigurable Computing}}, publisher = {{Hindawi Publishing Corporation}}, title = {{{Proof-Carrying Hardware: Concept and Prototype Tool Flow for Online Verification}}}, doi = {{10.1155/2010/180242}}, volume = {{2010}}, year = {{2010}}, } @misc{10614, author = {{Agne, Andreas}}, publisher = {{Paderborn University}}, title = {{{Virtuelle Speicherverwaltung für Hardware Threads in Rekonfigurierbaren Systemen}}}, year = {{2010}}, } @misc{10629, author = {{Boschmann, Alexander}}, publisher = {{Paderborn University}}, title = {{{EMG-basierte Ganganalyse}}}, year = {{2010}}, } @misc{10642, author = {{Breitlauch, Daniel}}, publisher = {{Paderborn University}}, title = {{{Evolvable Cache Controller}}}, year = {{2010}}, } @misc{10649, author = {{Dridger, Denis}}, publisher = {{Paderborn University}}, title = {{{Soft Microprocessors with tightly coupled Application-Specific Coprocessors}}}, year = {{2010}}, } @misc{10657, author = {{Graf, Tobias}}, publisher = {{Paderborn University}}, title = {{{Parallelization of the UCT Algorithm on HPC-Clusters}}}, year = {{2010}}, } @inproceedings{10683, author = {{Kaufmann, Paul and Englehart, Kevin and Platzner, Marco}}, booktitle = {{International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)}}, pages = {{6357--6360}}, publisher = {{IEEE}}, title = {{{Fluctuating EMG Signals: Investigating Long-term Effects of Pattern Matching Algorithms}}}, year = {{2010}}, } @inproceedings{10686, author = {{Kaufmann, Paul and Knieper, Tobias and Platzner, Marco}}, booktitle = {{IEEE World Congress on Computational Intelligence (WCCI), Congress on Evolutionary Computation (CEC)}}, pages = {{541--548}}, publisher = {{IEEE}}, title = {{{A Novel Hybrid Evolutionary Strategy and its Periodization with Multi-objective Genetic Optimizers}}}, year = {{2010}}, } @article{10694, author = {{Kebschull, Udo and Platzner, Marco and Teich, Jürgen}}, issn = {{1751-8601}}, journal = {{IET Computers Digital Techniques}}, number = {{3}}, pages = {{157--158}}, title = {{{Selected papers from the 18th International Conference on Field Programmable Logic and Applications, FPL 2008 (editorial)}}}, doi = {{10.1049/iet-cdt.2010.9044}}, volume = {{4}}, year = {{2010}}, } @misc{10697, author = {{Knieper, Tobias}}, publisher = {{Paderborn University}}, title = {{{Hybridization of Global Multi-Objective and Local Search Techniques}}}, year = {{2010}}, } @inproceedings{10699, author = {{Knieper, Tobias and Kaufmann, Paul and Glette, Kyrre and Platzner, Marco and Torresen, Jim}}, booktitle = {{IEEE Intl. Conf. on Evolvable Systems (ICES)}}, pages = {{250--261}}, publisher = {{Springer}}, title = {{{Coping with Resource Fluctuations: The Run-time Reconfigurable Functional Unit Row Classifier Architecture}}}, volume = {{6274}}, year = {{2010}}, } @inbook{10704, author = {{Lübbers, Enno and Platzner, Marco}}, booktitle = {{Dynamically Reconfigurable Systems: Architectures, Design Methods and Applications}}, editor = {{Platzner, Marco and Teich, Jürgen and Wehn, Norbert}}, pages = {{269--290}}, publisher = {{Springer-Verlag GmbH}}, title = {{{ReconOS: An Operating System for Dynamically Reconfigurable Hardware}}}, doi = {{10.1007/978-90-481-3485-4_13}}, year = {{2010}}, } @misc{10710, author = {{Meiche, Robert}}, publisher = {{Paderborn University}}, title = {{{FPGA/CPU Multicore-Plattform für ReconOS/eCos}}}, year = {{2010}}, } @misc{10717, author = {{Niekamp, Manuel}}, publisher = {{Paderborn University}}, title = {{{Transparente Hardwarebeschleunigung durch Shared Library Interposing}}}, year = {{2010}}, } @misc{10731, author = {{Runde, Bodo}}, publisher = {{Paderborn University}}, title = {{{A Token-Ring Network-On-Chip for Message Passing in ReconOS}}}, year = {{2010}}, } @misc{10752, author = {{Wiersema, Tobias}}, publisher = {{Paderborn University}}, title = {{{Scheduling Support for Heterogeneous Hardware Accelerators under Linux}}}, year = {{2010}}, } @book{10763, editor = {{Platzner, Marco and Teich, Jürgen and Wehn, Norbert}}, isbn = {{9048134846}}, publisher = {{Springer-Verlag GmbH}}, title = {{{Dynamically Reconfigurable Systems: Architectures, Design Methods and Applications}}}, doi = {{10.1007/978-90-481-3485-4}}, year = {{2010}}, } @inproceedings{10776, author = {{Khatir, Mehrdad and Ghasemzadeh Mohammadi, Hassan and Ejlali, Alireza}}, booktitle = {{Computer Design (ICCD), 2010 IEEE International Conference on}}, pages = {{138--144}}, publisher = {{IEEE}}, title = {{{Sub-threshold charge recovery circuits}}}, doi = {{10.1109/ICCD.2010.5647815}}, year = {{2010}}, } @inproceedings{13640, author = {{Giefers, Heiner and Platzner, Marco}}, booktitle = {{Proceedings of the 20th International Conference on Field Programmable Logic and Applications (FPL)}}, publisher = {{IEEE}}, title = {{{A Triple Hybrid Interconnect for Many-Cores: Reconfigurable Mesh, NoC and Barrier}}}, year = {{2010}}, } @inproceedings{13641, author = {{Schäfer, Wilhelm and Birattari, Mauro and Blömer, Johannes and Dorigo, Marco and Engels, Gregor and O'Grady, Rehan and Platzner, Marco and Rammig, Franz-Josef and Reif, Wolfgang and Trächtler, Ansgar}}, booktitle = {{Proceedings of the Foundations of Software Engineering (FSE) and NITR & D/SPD Working Conference on the Future of Software Engineering Research (FoSER)}}, pages = {{321--324}}, title = {{{Engineering Self-Coordinating Software Intensive Systems}}}, year = {{2010}}, } @inproceedings{13642, author = {{Giefers, Heiner and Platzner, Marco}}, booktitle = {{Proceedings of the 10th International Conference on Engineering of Reconfigurable Systems and Algorithms (ERSA)}}, publisher = {{CSREA Press}}, title = {{{A Self-Reconfigurable Lightweight Interconnect for Scalable Processor Fabrics}}}, year = {{2010}}, } @inproceedings{2223, author = {{Lübbers, Enno and Platzner, Marco and Plessl, Christian and Keller, Ariane and Plattner, Bernhard}}, booktitle = {{Proc. Int. Conf. on Engineering of Reconfigurable Systems and Algorithms (ERSA)}}, isbn = {{1-60132-140-6}}, pages = {{225--231}}, publisher = {{CSREA Press}}, title = {{{Towards Adaptive Networking for Embedded Devices based on Reconfigurable Hardware}}}, year = {{2010}}, } @inproceedings{2216, author = {{Grad, Mariusz and Plessl, Christian}}, booktitle = {{Proc. Int. Conf. on ReConFigurable Computing and FPGAs (ReConFig)}}, pages = {{67--72}}, publisher = {{IEEE Computer Society}}, title = {{{Pruning the Design Space for Just-In-Time Processor Customization}}}, doi = {{10.1109/ReConFig.2010.19}}, year = {{2010}}, } @inproceedings{2224, author = {{Grad, Mariusz and Plessl, Christian}}, booktitle = {{Proc. Int. Conf. on Engineering of Reconfigurable Systems and Algorithms (ERSA)}}, isbn = {{1-60132-140-6}}, pages = {{144--150}}, publisher = {{CSREA Press}}, title = {{{An Open Source Circuit Library with Benchmarking Facilities}}}, year = {{2010}}, } @inproceedings{2220, author = {{Andrews, David and Plessl, Christian}}, booktitle = {{Proc. Int. Conf. on Engineering of Reconfigurable Systems and Algorithms (ERSA)}}, isbn = {{1-60132-140-6}}, pages = {{165}}, publisher = {{CSREA Press}}, title = {{{Configurable Processor Architectures: History and Trends}}}, year = {{2010}}, } @proceedings{2222, editor = {{Plaks, Toomas P. and Andrews, David and DeMara, Ronald and Lam, Herman and Lee, Jooheung and Plessl, Christian and Stitt, Greg}}, isbn = {{1-60132-140-6}}, publisher = {{CSREA Press}}, title = {{{Proc. Int. Conf. on Engineering of Reconfigurable Systems and Algorithms (ERSA)}}}, year = {{2010}}, } @inproceedings{2226, author = {{Beisel, Tobias and Niekamp, Manuel and Plessl, Christian}}, booktitle = {{Proc. Int. Conf. on Application-Specific Systems, Architectures, and Processors (ASAP)}}, isbn = {{978-1-4244-6965-9}}, pages = {{65--72}}, publisher = {{IEEE Computer Society}}, title = {{{Using Shared Library Interposing for Transparent Acceleration in Systems with Heterogeneous Hardware Accelerators}}}, doi = {{10.1109/ASAP.2010.5540798}}, year = {{2010}}, } @inproceedings{2206, author = {{Keller, Ariane and Plattner, Bernhard and Lübbers, Enno and Platzner, Marco and Plessl, Christian}}, booktitle = {{Proc. IEEE Globecom Workshop on Network of the Future (FutureNet)}}, isbn = {{978-1-4244-8864-3}}, pages = {{372--376}}, publisher = {{IEEE}}, title = {{{Reconfigurable Nodes for Future Networks}}}, doi = {{10.1109/GLOCOMW.2010.5700341}}, year = {{2010}}, } @inproceedings{2228, author = {{Kenter, Tobias and Platzner, Marco and Plessl, Christian and Kauschke, Michael}}, booktitle = {{Proc. Workshop on Architectural Research Prototyping (WARP), International Symposium on Computer Architecture (ISCA)}}, editor = {{Hammami, Omar and Larrabee, Sandra}}, title = {{{Performance Estimation for the Exploration of CPU-Accelerator Architectures}}}, year = {{2010}}, } @inproceedings{10639, author = {{Boschmann, Alexander and Kaufmann, Paul and Platzner, Marco and Winkler, Michael}}, booktitle = {{Proc. Technically Assisted Rehabilitation (TAR)}}, title = {{{Towards multi-movement hand prostheses: Combining adaptive classification with high precision sockets}}}, year = {{2009}}, } @misc{10702, author = {{Kostin, Alexander}}, publisher = {{Paderborn University}}, title = {{{Evolvable Robot Controller}}}, year = {{2009}}, } @article{10703, author = {{Lübbers, Enno and Platzner, Marco}}, issn = {{1539-9087}}, journal = {{ACM Transactions on Embedded Computing Systems}}, keywords = {{Reconfigurable computing, multithreading, operating systems}}, number = {{1}}, pages = {{8:1--8:33}}, title = {{{ReconOS: Multithreaded Programming for Reconfigurable Computers}}}, doi = {{10.1145/1596532.1596540}}, volume = {{9}}, year = {{2009}}, } @misc{10746, author = {{Tofall, Martin}}, publisher = {{Paderborn University}}, title = {{{Compiler for a Custom Instruction Set CPU}}}, year = {{2009}}, } @misc{10749, author = {{Warkentin, Alexander}}, publisher = {{Paderborn University}}, title = {{{Coarse-grained CGP Model using Xilinx Virtex5 DSP48E Functional Units}}}, year = {{2009}}, } @misc{10753, author = {{Wildenhain, Benedikt}}, publisher = {{Paderborn University}}, title = {{{Implementierung von Kryptographie-Hardwarebeschleunigern für das HW/SW-Betriebssystem ReconOS}}}, year = {{2009}}, } @inproceedings{10777, author = {{Ghasemzadeh Mohammadi, Hassan and Miremadi, Seyed Ghassem and Ejlali, Alireza}}, booktitle = {{Dependable Computing (PRDC), 2009 IEEE Pacific Rim International Symposium on}}, pages = {{252--255}}, publisher = {{IEEE}}, title = {{{Signature Self Checking (SSC): A Low-Cost Reliable Control Logic for Pipelined Microprocessors}}}, doi = {{10.1109/PRDC.2009.69}}, year = {{2009}}, } @inproceedings{13632, author = {{Happe, Markus and Lübbers, Enno and Platzner, Marco}}, booktitle = {{Proceedings of the International Workshop on Applied Reconfigurable Computing (ARC)}}, publisher = {{Springer}}, title = {{{A Multithreaded Framework for Sequential Monte Carlo Methods on CPU/FPGA Platforms}}}, year = {{2009}}, } @inproceedings{13634, author = {{Giefers, Heiner and Platzner, Marco}}, booktitle = {{Proceedings of the Workshop on Many-Cores, International Conference on Architecture of Computing Systems (ARCS)}}, title = {{{Towards Models for Many-Cores: The Case for the Reconfigurable Mesh}}}, year = {{2009}}, } @inproceedings{13635, author = {{Giefers, Heiner and Platzner, Marco}}, booktitle = {{Reconfigurable Architectures Workshop (RAW), Proceedings of the International Parallel and Distributed Processing Symposium}}, publisher = {{IEEE}}, title = {{{ARMLang: A Language and Compiler for Programming Reconfigurable Mesh Many-Cores}}}, year = {{2009}}, } @inproceedings{13636, author = {{Lübbers, Enno and Platzner, Marco}}, booktitle = {{Proceedings of the 19th International Workshop on Field Programmable Logic and Applications (FPL) }}, publisher = {{IEEE}}, title = {{{Cooperative Multithreading in Dynamically Reconfigurable Systems}}}, year = {{2009}}, } @inproceedings{13637, author = {{Giefers, Heiner and Platzner, Marco}}, booktitle = {{Proceedings of the 19th International Workshop on Field Programmable Logic and Applications (FPL) }}, publisher = {{IEEE}}, title = {{{Program-driven Fine-grained Power Management for the Reconfigurable Mesh}}}, year = {{2009}}, } @inproceedings{13638, author = {{Happe, Markus and Lübbers, Enno and Platzner, Marco}}, booktitle = {{Proceedings of the 2009 International Conference on Field-Programmable Technology (FPT)}}, isbn = {{9781424443758}}, publisher = {{IEEE}}, title = {{{An adaptive Sequential Monte Carlo framework with runtime HW/SW repartitioning}}}, doi = {{10.1109/fpt.2009.5377645}}, year = {{2009}}, } @inproceedings{13639, author = {{Drzevitzky, Stephanie and Kastens, Uwe and Platzner, Marco}}, booktitle = {{Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig)}}, publisher = {{IEEE}}, title = {{{Proof-carrying Hardware: Towards Runtime Verification of Reconfigurable Modules}}}, year = {{2009}}, } @inproceedings{2350, abstract = {{Mapping applications that consist of a collection of cores to FPGA accelerators and optimizing their performance is a challenging task in high performance reconfigurable computing. We present IMORC, an architectural template and highly versatile on-chip interconnect. IMORC links provide asynchronous FIFOs and bitwidth conversion which allows for flexibly composing accelerators from cores running at full speed within their own clock domains, thus facilitating the re-use of cores and portability. Further, IMORC inserts performance counters for monitoring runtime data. In this paper, we first introduce the IMORC architectural template and the on-chip interconnect, and then demonstrate IMORC on the example of accelerating the k-th nearest neighbor thinning problem on an XD1000 reconfigurable computing system. Using IMORC's monitoring infrastructure, we gain insights into the data-dependent behavior of the application which, in turn, allow for optimizing the accelerator. }}, author = {{Schumacher, Tobias and Plessl, Christian and Platzner, Marco}}, booktitle = {{Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM)}}, isbn = {{978-1-4244-4450-2}}, keywords = {{IMORC, interconnect, performance}}, pages = {{275--278}}, publisher = {{IEEE Computer Society}}, title = {{{IMORC: Application Mapping, Monitoring and Optimization for High-Performance Reconfigurable Computing}}}, doi = {{10.1109/FCCM.2009.25}}, year = {{2009}}, } @inproceedings{2262, abstract = {{In this work we present EvoCache, a novel approach for implementing application-specific caches. The key innovation of EvoCache is to make the function that maps memory addresses from the CPU address space to cache indices programmable. We support arbitrary Boolean mapping functions that are implemented within a small reconfigurable logic fabric. For finding suitable cache mapping functions we rely on techniques from the evolvable hardware domain and utilize an evolutionary optimization procedure. We evaluate the use of EvoCache in an embedded processor for two specific applications (JPEG and BZIP2 compression) with respect to execution time, cache miss rate and energy consumption. We show that the evolvable hardware approach for optimizing the cache functions not only significantly improves the cache performance for the training data used during optimization, but that the evolved mapping functions generalize very well. Compared to a conventional cache architecture, EvoCache applied to test data achieves a reduction in execution time of up to 14.31% for JPEG (10.98% for BZIP2), and in energy consumption by 16.43% for JPEG (10.70% for BZIP2). We also discuss the integration of EvoCache into the operating system and show that the area and delay overheads introduced by EvoCache are acceptable. }}, author = {{Kaufmann, Paul and Plessl, Christian and Platzner, Marco}}, booktitle = {{Proc. NASA/ESA Conference on Adaptive Hardware and Systems (AHS)}}, keywords = {{EvoCache, evolvable hardware, computer architecture}}, pages = {{11--18}}, publisher = {{IEEE Computer Society}}, title = {{{EvoCaches: Application-specific Adaptation of Cache Mapping}}}, year = {{2009}}, } @inproceedings{2238, author = {{Schumacher, Tobias and Süß, Tim and Plessl, Christian and Platzner, Marco}}, booktitle = {{Proc. Int. Conf. on ReConFigurable Computing and FPGAs (ReConFig)}}, isbn = {{978-0-7695-3917-1}}, keywords = {{IMORC, graphics}}, pages = {{119--124}}, publisher = {{IEEE Computer Society}}, title = {{{Communication Performance Characterization for Reconfigurable Accelerator Design on the XD1000}}}, doi = {{10.1109/ReConFig.2009.32}}, year = {{2009}}, } @inproceedings{2261, author = {{Schumacher, Tobias and Plessl, Christian and Platzner, Marco}}, booktitle = {{Proc. Int. Conf. on Field Programmable Logic and Applications (FPL)}}, isbn = {{978-1-4244-3892-1}}, issn = {{1946-1488}}, keywords = {{IMORC, NOC, KNN, accelerator}}, pages = {{338--344}}, publisher = {{IEEE}}, title = {{{An Accelerator for k-th Nearest Neighbor Thinning Based on the IMORC Infrastructure}}}, year = {{2009}}, } @inproceedings{2263, abstract = {{In this paper, we introduce the Woolcano reconfigurable processor architecture. The architecture is based on the Xilinx Virtex-4 FX FPGA and leverages the Auxiliary Processing Unit (APU) as well as the partial reconfiguration capabilities to provide dynamically reconfigurable custom instructions. We also present a hardware tool flow that automatically translates software functions into custom instructions and a software tool flow that creates binaries using these instructions. While previous research on processors with reconfigurable functional units has been performed predominantly with simulation, the Woolcano architecture allows for exploring dynamic instruction set extension with commercially available hardware. Finally, we present a case study demonstrating a custom floating-point instruction generated with our approach, which achieves a 40x speedup over software-emulated floating-point operations and a 21% speedup over the Xilinx hardware floating-point unit. }}, author = {{Grad, Mariusz and Plessl, Christian}}, booktitle = {{Proc. Int. Conf. on Engineering of Reconfigurable Systems and Algorithms (ERSA)}}, isbn = {{1-60132-101-5}}, pages = {{319--322}}, publisher = {{CSREA Press}}, title = {{{Woolcano: An Architecture and Tool Flow for Dynamic Instruction Set Extension on Xilinx Virtex-4 FX}}}, year = {{2009}}, } @inproceedings{2358, author = {{Beisel, Tobias and Lietsch, Stefan and Thielemans, Kris}}, booktitle = {{IEEE Nuclear Science Symposium Conference Record (NSS)}}, pages = {{4161--4168}}, publisher = {{IEEE}}, title = {{{A method for OSEM PET reconstruction on parallel architectures using STIR}}}, doi = {{10.1109/NSSMIC.2008.4774198}}, year = {{2008}}, } @inproceedings{2365, author = {{Platzner, Marco and Döhre, Sven and Happe, Markus and Kenter, Tobias and Lorenz, Ulf and Schumacher, Tobias and Send, Andre and Warkentin, Alexander}}, booktitle = {{Proc. Int. Conf. on Engineering of Reconfigurable Systems and Algorithms (ERSA)}}, isbn = {{1-60132-064-7}}, pages = {{245--251}}, publisher = {{CSREA Press}}, title = {{{The GOmputer: Accelerating GO with FPGAs}}}, year = {{2008}}, }