@inproceedings{8169, abstract = {{The polynomial hierarchy plays a central role in classical complexity theory. Here, we define a quantum generalization of the polynomial hierarchy, and initiate its study. We show that not only are there natural complete problems for the second level of this quantum hierarchy, but that these problems are in fact hard to approximate. Our work thus yields the first known hardness of approximation results for a quantum complexity class. Using these techniques, we also obtain hardness of approximation for the class QCMA. Our approach is based on the use of dispersers, and is inspired by the classical results of Umans regarding hardness of approximation for the second level of the classical polynomial hierarchy (Umans 1999). We close by showing that a variant of the local Hamiltonian problem with hybrid classical-quantum ground states is complete for the second level of our quantum hierarchy.}}, author = {{Gharibian, Sevag and Kempe, Julia}}, booktitle = {{International Colloquium on Automata, Languages, and Programming (ICALP 2012)}}, editor = {{Czumaj, Artur and Mehlhorn, Kurt and Pitts, Andrew and Wattenhofer, Roger}}, isbn = {{978-3-642-31594-7}}, location = {{Warwick, UK}}, pages = {{387--398}}, publisher = {{Springer Berlin Heidelberg}}, title = {{{Hardness of Approximation for Quantum Problems}}}, doi = {{10.1007/978-3-642-31594-7_33}}, year = {{2012}}, } @article{8175, abstract = {{Approximation algorithms for classical constraint satisfaction problems are one of the main research areas in theoretical computer science. Here we define a natural approximation version of the QMA-complete local Hamiltonian problem (where QMA stands for Quantum Merlin Arthur) and initiate its study. We present two main results. The first shows that a nontrivial approximation ratio can be obtained in the class NP using product states. The second result (which builds on the first one) gives a polynomial time (classical) algorithm providing a similar approximation ratio for dense instances of the problem. The latter result is based on an adaptation of the “exhaustive sampling method” by Arora, Karger, and Karpinski [J. Comput. System Sci., 58 (1999), p. 193] to the quantum setting and might be of independent interest.}}, author = {{Gharibian, Sevag and Kempe, Julia}}, issn = {{0097-5397}}, journal = {{SIAM Journal on Computing}}, number = {{4}}, pages = {{1028--1050}}, publisher = {{Society for Industrial & Applied Mathematics (SIAM)}}, title = {{{Approximation Algorithms for QMA-Complete Problems}}}, doi = {{10.1137/110842272}}, volume = {{41}}, year = {{2012}}, } @article{8174, abstract = {{We propose a measure of non-classical correlations in bipartite quantum states based on local unitary operations. We prove the measure is non-zero if and only if the quantum discord is non-zero; this is achieved via a new characterization of zero discord states in terms of the state's correlation matrix. Moreover, our scheme can be extended to ensure the same relationship holds even with a generalized version of quantum discord in which higher-rank projective measurements are allowed. We next derive a closed form expression for our scheme in the cases of Werner states and (2 x N)-dimensional systems. The latter reveals that for (2 x N)-dimensional states, our measure reduces to the geometric discord [Dakic et al., PRL 105, 2010]. A connection to the CHSH inequality is shown. We close with a characterization of all maximally non-classical, yet separable, (2 x N)-dimensional states of rank at most two (with respect to our measure).}}, author = {{Gharibian, Sevag}}, journal = {{Physical Review A}}, pages = {{042106}}, publisher = {{American Physical Society}}, title = {{{Quantifying nonclassicality with local unitary operations}}}, doi = {{10.1103/PhysRevA.86.042106}}, volume = {{86}}, year = {{2012}}, } @inproceedings{3980, abstract = {{Paper Abstract High harmonic generation is investigated for a two-band model of a semiconductor nanostructure. Similar to an atomic two-level system, the semiconductor emits high harmonic radiation. We show how one can specifically enhance the emission for a given frequency by applying a non-trivially shaped laser pulse. Therefore, the semiconductor Bloch equations including the interband and additionally the intraband dynamics are solved numerically and the spectral shape of the input pulse is computed via an optimization algorithm. It is demonstrated that desired emission frequencies can be favored even though the overall input power is kept constant. We also suggest special metallic nano geometries to achieve enhanced localized optical fields. They are found by geometric optimization.}}, author = {{Reichelt, Matthias and Hildebrandt, Andre and Walther, Andrea and Förstner, Jens and Meier, Torsten}}, booktitle = {{Ultrafast Phenomena and Nanophotonics XVI}}, isbn = {{9780819489036 }}, keywords = {{tet_topic_shg}}, publisher = {{SPIE}}, title = {{{Engineering high harmonic generation in semiconductors via pulse shaping}}}, doi = {{10.1117/12.906338}}, volume = {{8260}}, year = {{2012}}, } @article{22953, abstract = {{The generation of specific high harmonics for an optical two-level system is elucidated. The desired emitted radiation can be induced by a carefully designed excitation pulse, which is found by a multiparameter optimization procedure. The presented mechanism can also be applied to semiconductor structures for which the calculations result in much higher emission frequencies. The optimization procedure is either performed using a genetic algorithm or a rigorous mathematical optimization technique.}}, author = {{Reichelt, Matthias and Walther, Andrea and Meier, Torsten}}, issn = {{0740-3224}}, journal = {{Journal of the Optical Society of America B}}, number = {{2}}, title = {{{Tailoring the high-harmonic emission in two-level systems and semiconductors by pulse shaping}}}, doi = {{10.1364/josab.29.000a36}}, volume = {{29}}, year = {{2012}}, } @article{15984, abstract = {{A new and promising approach to the reduction of greenhouse gas emissions is the use of improved lightweight constructions based on multi-material systems comprising sheet metal with local carbon fibre reinforced plastic (CFRP) reinforcements. The CFRP is used to reinforce highly stressed areas and can be aligned to specific load cases. The locally restricted application of CFRP means that the material costs can be effectively reduced by comparison to parts made entirely of CFRP on account of the expensive production process requiring the use of an autoclave. These parts are thus only used in high-priced products. The production of hybrid CFRP steel structures in a mass production process calls for an efficient production technology. Current research work within the scope of a collaborative research project running at the University of Paderborn is concentrating on the development of manufacturing processes for the efficient production of automotive structural components made up of sheet metal blanks with local CFRP patches. The project is focusing especially on basic research into the production of industrial components. The aim of the investigation is to create an efficient and controlled process for producing CFRP reinforced steel structures from semi-finished hybrid steel-CFRP material. This includes tool concepts and an appropriate process design to permit short process times. The basis of an efficient process design is an in-depth knowledge of the material behaviour, and hence a thorough characterisation was performed. Material parameters were determined for both simulation and forming. For this, monotonic tensile, shear and bending tests were conducted using both uncured prepregs and cured CFRP specimens. To achieve an accurate simulation of the forming process, a special material model for carbon fibre prepregs has been developed which also includes the anisotropic material behaviour resulting from fibre orientation, the viscoelastic behaviour caused by the matrix and the hardening effects that prevail during curing. Recent results show good qualitative agreement and will be presented in this paper. In order to control the properties of the hybrid components, four different tool concepts for the prepreg press technology have been developed and tested. The concepts are presented and the results of experimental investigations are discussed in this paper.}}, author = {{Schmidt, Hans Christian and Damerow, Ulf and Lauter, Christian and Gorny, Bernhard and Hankeln, Frederik and Homberg, Werner and Tröster, Thomas and Maier, Hans Jürgen and Mahnken, Rolf}}, issn = {{1662-9795}}, journal = {{Key Engineering Materials}}, pages = {{295--300}}, title = {{{Manufacturing Processes for Combined Forming of Multi-Material Structures Consisting of Sheet Metal and Local CFRP Reinforcements}}}, doi = {{10.4028/www.scientific.net/kem.504-506.295}}, year = {{2012}}, } @inproceedings{15986, author = {{Gorny, B. and Hankeln, Frederik and Lauter, Christian and Schmidt, H. C. and Damerow, U. and Mahnken, Rolf and Maier, H. J. and Tröster, Thomas and Homberg, Werner}}, location = {{Turin, Italy}}, title = {{{Simulation and manufacturing of deep drawn parts reinforced by carbon fibre prepregs}}}, year = {{2012}}, } @article{16010, author = {{Lauter, Christian and Tröster, Thomas and Brandis, Rinje and Gausemeier, Jürgen}}, issn = {{1865-4819}}, journal = {{Lightweight Design}}, pages = {{50--56}}, title = {{{Methodik für die Produktentstehung hybrider Leichtbaustrukturen}}}, doi = {{10.1365/s35725-013-0137-4}}, volume = {{5}}, 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}}, } @techreport{16012, author = {{Tröster, Thomas and Marten, Thorsten and Adelbert, Stefan and Kadim, Abdel}}, isbn = {{978-3-942541-18-3 }}, publisher = {{Abschlussberichte Forschungsvereinigung Stahlanwendung e.V., Verlag und Vertriebsgesellschaft mbH}}, title = {{{P 850 – Wirbelbetterwärmung von Platinen für das Presshärten}}}, year = {{2012}}, } @inbook{52422, author = {{Schlüter, Alexander and Rommel, Benjamin}}, booktitle = {{Energie- und klimaeffiziente Produktion: Grundlagen, Leitlinien und Praxisbeispiele}}, editor = {{Hesselbach, Jens}}, pages = {{290--314}}, publisher = {{Springer Vieweg}}, title = {{{Auf dem besten Weg zu neuen Lösungen: Kunststoffverarbeitung}}}, year = {{2012}}, } @inbook{52418, author = {{Schlüter, Alexander and Rommel, Benjamin and Bleeke, Wilhelm}}, booktitle = {{Energie- und klimaeffiziente Produktion: Grundlagen, Leitlinien und Praxisbeispiele }}, editor = {{Hesselbach, Jens}}, isbn = {{978-3-8348-0448-8}}, publisher = {{Springer Vieweg}}, title = {{{Energieströme messen}}}, year = {{2012}}, }