TY - JOUR AB - We address the general mathematical problem of computing the inverse p-th root of a given matrix in an efficient way. A new method to construct iteration functions that allow calculating arbitrary p-th roots and their inverses of symmetric positive definite matrices is presented. We show that the order of convergence is at least quadratic and that adaptively adjusting a parameter q always leads to an even faster convergence. In this way, a better performance than with previously known iteration schemes is achieved. The efficiency of the iterative functions is demonstrated for various matrices with different densities, condition numbers and spectral radii. AU - Richters, Dorothee AU - Lass, Michael AU - Walther, Andrea AU - Plessl, Christian AU - Kühne, Thomas ID - 21 IS - 2 JF - Communications in Computational Physics TI - A General Algorithm to Calculate the Inverse Principal p-th Root of Symmetric Positive Definite Matrices VL - 25 ER - TY - JOUR AU - Platzner, Marco AU - Plessl, Christian ID - 12871 JF - Informatik Spektrum SN - 0170-6012 TI - FPGAs im Rechenzentrum ER - TY - JOUR AB - Approximate computing has shown to provide new ways to improve performance and power consumption of error-resilient applications. While many of these applications can be found in image processing, data classification or machine learning, we demonstrate its suitability to a problem from scientific computing. Utilizing the self-correcting behavior of iterative algorithms, we show that approximate computing can be applied to the calculation of inverse matrix p-th roots which are required in many applications in scientific computing. Results show great opportunities to reduce the computational effort and bandwidth required for the execution of the discussed algorithm, especially when targeting special accelerator hardware. AU - Lass, Michael AU - Kühne, Thomas AU - Plessl, Christian ID - 20 IS - 2 JF - Embedded Systems Letters SN - 1943-0663 TI - Using Approximate Computing for the Calculation of Inverse Matrix p-th Roots VL - 10 ER - TY - GEN AU - Filmwala, Tasneem ID - 5414 TI - Study Effects of Approximation on Conjugate Gradient Algorithm and Accelerate it on FPGA Platform ER - TY - GEN AU - Gadewar, Onkar ID - 5421 TI - Programmable Programs? - Designing FPGA Overlay Architectures with OpenCL ER - TY - JOUR AU - Mertens, Jan Cedric AU - Boschmann, Alexander AU - Schmidt, M. AU - Plessl, Christian ID - 6516 IS - 4 JF - Sports Engineering SN - 1369-7072 TI - Sprint diagnostic with GPS and inertial sensor fusion VL - 21 ER - TY - GEN AB - Molecular Dynamic (MD) simulations are computationally intensive and accelerating them using specialized hardware is a topic of investigation in many studies. One of the routines in the critical path of MD simulations is the three-dimensional Fast Fourier Transformation (FFT3d). The potential in accelerating FFT3d using hardware is usually bound by bandwidth and memory. Therefore, designing a high throughput solution for an FPGA that overcomes this problem is challenging. In this thesis, the feasibility of offloading FFT3d computations to FPGA implemented using OpenCL is investigated. In order to mask the latency in memory access, an FFT3d that overlaps computation with communication is designed. The implementa- tion of this design is synthesized for the Arria 10 GX 1150 FPGA and evaluated with the FFTW benchmark. Analysis shows a better performance using FPGA over CPU for larger FFT sizes, with the 643 FFT showing a 70% improvement in runtime using FPGAs. This FFT3d design is integrated with CP2K to explore the potential in accelerating molecular dynamic simulations. Evaluation of CP2K simulations using FPGA shows a 41% improvement in runtime in FFT3d computations over CPU for larger FFT3d designs. AU - Ramaswami, Arjun ID - 5417 KW - FFT: FPGA KW - CP2K KW - OpenCL TI - Accelerating Molecular Dynamic Simulations by Offloading Fast Fourier Transformations to FPGA ER - TY - CONF AB - The exploration of FPGAs as accelerators for scientific simulations has so far mostly been focused on small kernels of methods working on regular data structures, for example in the form of stencil computations for finite difference methods. In computational sciences, often more advanced methods are employed that promise better stability, convergence, locality and scaling. Unstructured meshes are shown to be more effective and more accurate, compared to regular grids, in representing computation domains of various shapes. Using unstructured meshes, the discontinuous Galerkin method preserves the ability to perform explicit local update operations for simulations in the time domain. In this work, we investigate FPGAs as target platform for an implementation of the nodal discontinuous Galerkin method to find time-domain solutions of Maxwell's equations in an unstructured mesh. When maximizing data reuse and fitting constant coefficients into suitably partitioned on-chip memory, high computational intensity allows us to implement and feed wide data paths with hundreds of floating point operators. By decoupling off-chip memory accesses from the computations, high memory bandwidth can be sustained, even for the irregular access pattern required by parts of the application. Using the Intel/Altera OpenCL SDK for FPGAs, we present different implementation variants for different polynomial orders of the method. In different phases of the algorithm, either computational or bandwidth limits of the Arria 10 platform are almost reached, thus outperforming a highly multithreaded CPU implementation by around 2x. AU - Kenter, Tobias AU - Mahale, Gopinath AU - Alhaddad, Samer AU - Grynko, Yevgen AU - Schmitt, Christian AU - Afzal, Ayesha AU - Hannig, Frank AU - Förstner, Jens AU - Plessl, Christian ID - 1588 KW - tet_topic_hpc T2 - Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM) TI - OpenCL-based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes ER - TY - CONF AB - We present the submatrix method, a highly parallelizable method for the approximate calculation of inverse p-th roots of large sparse symmetric matrices which are required in different scientific applications. Following the idea of Approximate Computing, we allow imprecision in the final result in order to utilize the sparsity of the input matrix and to allow massively parallel execution. For an n x n matrix, the proposed algorithm allows to distribute the calculations over n nodes with only little communication overhead. The result matrix exhibits the same sparsity pattern as the input matrix, allowing for efficient reuse of allocated data structures. We evaluate the algorithm with respect to the error that it introduces into calculated results, as well as its performance and scalability. We demonstrate that the error is relatively limited for well-conditioned matrices and that results are still valuable for error-resilient applications like preconditioning even for ill-conditioned matrices. We discuss the execution time and scaling of the algorithm on a theoretical level and present a distributed implementation of the algorithm using MPI and OpenMP. We demonstrate the scalability of this implementation by running it on a high-performance compute cluster comprised of 1024 CPU cores, showing a speedup of 665x compared to single-threaded execution. AU - Lass, Michael AU - Mohr, Stephan AU - Wiebeler, Hendrik AU - Kühne, Thomas AU - Plessl, Christian ID - 1590 KW - approximate computing KW - linear algebra KW - matrix inversion KW - matrix p-th roots KW - numeric algorithm KW - parallel computing SN - 978-1-4503-5891-0/18/07 T2 - Proc. Platform for Advanced Scientific Computing (PASC) Conference TI - A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices ER - TY - CONF AU - Riebler, Heinrich AU - Vaz, Gavin Francis AU - Kenter, Tobias AU - Plessl, Christian ID - 1204 KW - htrop SN - 9781450349826 T2 - Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP) TI - Automated Code Acceleration Targeting Heterogeneous OpenCL Devices ER - TY - JOUR AB - Branch and bound (B&B) algorithms structure the search space as a tree and eliminate infeasible solutions early by pruning subtrees that cannot lead to a valid or optimal solution. Custom hardware designs significantly accelerate the execution of these algorithms. In this article, we demonstrate a high-performance B&B implementation on FPGAs. First, we identify general elements of B&B algorithms and describe their implementation as a finite state machine. Then, we introduce workers that autonomously cooperate using work stealing to allow parallel execution and full utilization of the target FPGA. Finally, we explore advantages of instance-specific designs that target a specific problem instance to improve performance. We evaluate our concepts by applying them to a branch and bound problem, the reconstruction of corrupted AES keys obtained from cold-boot attacks. The evaluation shows that our work stealing approach is scalable with the available resources and provides speedups proportional to the number of workers. Instance-specific designs allow us to achieve an overall speedup of 47 × compared to the fastest implementation of AES key reconstruction so far. Finally, we demonstrate how instance-specific designs can be generated just-in-time such that the provided speedups outweigh the additional time required for design synthesis. AU - Riebler, Heinrich AU - Lass, Michael AU - Mittendorf, Robert AU - Löcke, Thomas AU - Plessl, Christian ID - 18 IS - 3 JF - ACM Transactions on Reconfigurable Technology and Systems (TRETS) KW - coldboot SN - 1936-7406 TI - Efficient Branch and Bound on FPGAs Using Work Stealing and Instance-Specific Designs VL - 10 ER - TY - CONF AB - Compared to classical HDL designs, generating FPGA with high-level synthesis from an OpenCL specification promises easier exploration of different design alternatives and, through ready-to-use infrastructure and common abstractions for host and memory interfaces, easier portability between different FPGA families. In this work, we evaluate the extent of this promise. To this end, we present a parameterized FDTD implementation for photonic microcavity simulations. Our design can trade-off different forms of parallelism and works for two independent OpenCL-based FPGA design flows. Hence, we can target FPGAs from different vendors and different FPGA families. We describe how we used pre-processor macros to achieve this flexibility and to work around different shortcomings of the current tools. Choosing the right design configurations, we are able to present two extremely competitive solutions for very different FPGA targets, reaching up to 172 GFLOPS sustained performance. With the portability and flexibility demonstrated, code developers not only avoid vendor lock-in, but can even make best use of real trade-offs between different architectures. AU - Kenter, Tobias AU - Förstner, Jens AU - Plessl, Christian ID - 1592 KW - tet_topic_hpc T2 - Proc. Int. Conf. on Field Programmable Logic and Applications (FPL) TI - Flexible FPGA design for FDTD using OpenCL ER - TY - JOUR AU - Schumacher, Jörn AU - Plessl, Christian AU - Vandelli, Wainer ID - 1589 JF - Journal of Physics: Conference Series TI - High-Throughput and Low-Latency Network Communication with NetIO VL - 898 ER - TY - CONF AB - Version Control Systems (VCS) are a valuable tool for software development and document management. Both client/server and distributed (Peer-to-Peer) models exist, with the latter (e.g., Git and Mercurial) becoming increasingly popular. Their distributed nature introduces complications, especially concerning security: it is hard to control the dissemination of contents stored in distributed VCS as they rely on replication of complete repositories to any involved user. We overcome this issue by designing and implementing a concept for cryptography-enforced access control which is transparent to the user. Use of field-tested schemes (end-to-end encryption, digital signatures) allows for strong security, while adoption of convergent encryption and content-defined chunking retains storage efficiency. The concept is seamlessly integrated into Mercurial---respecting its distributed storage concept---to ensure practical usability and compatibility to existing deployments. AU - Lass, Michael AU - Leibenger, Dominik AU - Sorge, Christoph ID - 19 KW - access control KW - distributed version control systems KW - mercurial KW - peer-to-peer KW - convergent encryption KW - confidentiality KW - authenticity SN - 978-1-5090-2054-6 T2 - Proc. 41st Conference on Local Computer Networks (LCN) TI - Confidentiality and Authenticity for Distributed Version Control Systems - A Mercurial Extension ER - TY - GEN AU - Tölke, Christian ID - 5418 TI - Sicherheit von hybriden FPGA-Systemen in der industriellen Automatisierungstechnik -- Anforderungen und Umsetzung ER - TY - GEN AU - Wüllrich, Gunnar ID - 5420 TI - Dynamic OpenCL Task Scheduling for Energy and Performance in a Heterogeneous Environment ER - TY - THES AU - Kenter, Tobias ID - 161 TI - Reconfigurable Accelerators in the World of General-Purpose Computing ER - TY - CHAP AB - In this chapter, we present an introduction to the ReconOS operating system for reconfigurable computing. ReconOS offers a unified multi-threaded programming model and operating system services for threads executing in software and threads mapped to reconfigurable hardware. By supporting standard POSIX operating system functions for both software and hardware threads, ReconOS particularly caters to developers with a software background, because developers can use well-known mechanisms such as semaphores, mutexes, condition variables, and message queues for developing hybrid applications with threads running on the CPU and FPGA concurrently. Through the semantic integration of hardware accelerators into a standard operating system environment, ReconOS allows for rapid design space exploration, supports a structured application development process and improves the portability of applications between different reconfigurable computing systems. AU - Agne, Andreas AU - Platzner, Marco AU - Plessl, Christian AU - Happe, Markus AU - Lübbers, Enno ED - Koch, Dirk ED - Hannig, Frank ED - Ziener, Daniel ID - 29 SN - 978-3-319-26406-6 T2 - FPGAs for Software Programmers TI - ReconOS ER - TY - CONF AU - Riebler, Heinrich AU - Vaz, Gavin Francis AU - Plessl, Christian AU - Trainiti, Ettore M. G. AU - Durelli, Gianluca C. AU - Bolchini, Cristiana ID - 31 T2 - Proc. HiPEAC Workshop on Reonfigurable Computing (WRC) TI - Using Just-in-Time Code Generation for Transparent Resource Management in Heterogeneous Systems ER - TY - CONF AU - Kenter, Tobias AU - Plessl, Christian ID - 24 T2 - Proc. Workshop on Heterogeneous High-performance Reconfigurable Computing (H2RC) TI - Microdisk Cavity FDTD Simulation on FPGA using OpenCL ER - TY - CONF AU - Lass, Michael AU - Kühne, Thomas AU - Plessl, Christian ID - 25 T2 - Workshop on Approximate Computing (AC) TI - Using Approximate Computing in Scientific Codes ER - TY - CONF AB - Hardware accelerators are becoming popular in academia and industry. To move one step further from the state-of-the-art multicore plus accelerator approaches, we present in this paper our innovative SAVEHSA architecture. It comprises of a heterogeneous hardware platform with three different high-end accelerators attached over PCIe (GPGPU, FPGA and Intel MIC). Such systems can process parallel workloads very efficiently whilst being more energy efficient than regular CPU systems. To leverage the heterogeneity, the workload has to be distributed among the computing units in a way that each unit is well-suited for the assigned task and executable code must be available. To tackle this problem we present two software components; the first can perform resource allocation at runtime while respecting system and application goals (in terms of throughput, energy, latency, etc.) and the second is able to analyze an application and generate executable code for an accelerator at runtime. We demonstrate the first proof-of-concept implementation of our framework on the heterogeneous platform, discuss different runtime policies and measure the introduced overheads. AU - Riebler, Heinrich AU - Vaz, Gavin Francis AU - Plessl, Christian AU - Trainiti, Ettore M. G. AU - Durelli, Gianluca C. AU - Del Sozzo, Emanuele AU - Santambrogio, Marco D. AU - Bolchini, Christina ID - 138 T2 - Proceedings of International Forum on Research and Technologies for Society and Industry (RTSI) TI - Using Just-in-Time Code Generation for Transparent Resource Management in Heterogeneous Systems ER - TY - CHAP AB - Many modern compute nodes are heterogeneous multi-cores that integrate several CPU cores with fixed function or reconfigurable hardware cores. Such systems need to adapt task scheduling and mapping to optimise for performance and energy under varying workloads and, increasingly important, for thermal and fault management and are thus relevant targets for self-aware computing. In this chapter, we take up the generic reference architecture for designing self-aware and self-expressive computing systems and refine it for heterogeneous multi-cores. We present ReconOS, an architecture, programming model and execution environment for heterogeneous multi-cores, and show how the components of the reference architecture can be implemented on top of ReconOS. In particular, the unique feature of dynamic partial reconfiguration supports self-expression through starting and terminating reconfigurable hardware cores. We detail a case study that runs two applications on an architecture with one CPU and 12 reconfigurable hardware cores and present self-expression strategies for adapting under performance, temperature and even conflicting constraints. The case study demonstrates that the reference architecture as a model for self-aware computing is highly useful as it allows us to structure and simplify the design process, which will be essential for designing complex future compute nodes. Furthermore, ReconOS is used as a base technology for flexible protocol stacks in Chapter 10, an approach for self-aware computing at the networking level. AU - Agne, Andreas AU - Happe, Markus AU - Lösch, Achim AU - Plessl, Christian AU - Platzner, Marco ID - 156 T2 - Self-aware Computing Systems TI - Self-aware Compute Nodes ER - TY - JOUR AB - A broad spectrum of applications can be accelerated by offloading computation intensive parts to reconfigurable hardware. However, to achieve speedups, the number of loop it- erations (trip count) needs to be sufficiently large to amortize offloading overheads. Trip counts are frequently not known at compile time, but only at runtime just before entering a loop. Therefore, we propose to generate code for both the CPU and the coprocessor, and defer the offloading decision to the application runtime. We demonstrate how a toolflow, based on the LLVM compiler framework, can automatically embed dynamic offloading de- cisions into the application code. We perform in-depth static and dynamic analysis of pop- ular benchmarks, which confirm the general potential of such an approach. We also pro- pose to optimize the offloading process by decoupling the runtime decision from the loop execution (decision slack). The feasibility of our approach is demonstrated by a toolflow that automatically identifies suitable data-parallel loops and generates code for the FPGA coprocessor of a Convey HC-1. We evaluate the integrated toolflow with representative loops executed for different input data sizes. AU - Vaz, Gavin Francis AU - Riebler, Heinrich AU - Kenter, Tobias AU - Plessl, Christian ID - 165 JF - Computers and Electrical Engineering SN - 0045-7906 TI - Potential and Methods for Embedding Dynamic Offloading Decisions into Application Code VL - 55 ER - TY - CONF AB - The use of heterogeneous computing resources, such as Graphic Processing Units or other specialized coprocessors, has become widespread in recent years because of their per- formance and energy efficiency advantages. Approaches for managing and scheduling tasks to heterogeneous resources are still subject to research. Although queuing systems have recently been extended to support accelerator resources, a general solution that manages heterogeneous resources at the operating system- level to exploit a global view of the system state is still missing.In this paper we present a user space scheduler that enables task scheduling and migration on heterogeneous processing resources in Linux. Using run queues for available resources we perform scheduling decisions based on the system state and on task characterization from earlier measurements. With a pro- gramming pattern that supports the integration of checkpoints into applications, we preempt tasks and migrate them between three very different compute resources. Considering static and dynamic workload scenarios, we show that this approach can gain up to 17% performance, on average 7%, by effectively avoiding idle resources. We demonstrate that a work-conserving strategy without migration is no suitable alternative. AU - Lösch, Achim AU - Beisel, Tobias AU - Kenter, Tobias AU - Plessl, Christian AU - Platzner, Marco ID - 168 T2 - Proceedings of the 2016 Design, Automation & Test in Europe Conference & Exhibition (DATE) TI - Performance-centric scheduling with task migration for a heterogeneous compute node in the data center ER - TY - CONF AU - Kenter, Tobias AU - Vaz, Gavin Francis AU - Riebler, Heinrich AU - Plessl, Christian ID - 171 T2 - Workshop on Reconfigurable Computing (WRC) TI - Opportunities for deferring application partitioning and accelerator synthesis to runtime (extended abstract) ER - TY - JOUR AU - Torresen, Jim AU - Plessl, Christian AU - Yao, Xin ID - 1772 IS - 7 JF - IEEE Computer KW - self-awareness KW - self-expression TI - Self-Aware and Self-Expressive Systems – Guest Editor's Introduction VL - 48 ER - TY - GEN AB - Demands for computational power and energy efficiency of computing devices are steadily increasing. At the same time, following classic methods to increase speed and reduce energy consumption of these devices becomes increasingly difficult, bringing alternative methods into focus. One of these methods is approximate computing which utilizes the fact that small errors in computations are acceptable in many applications in order to allow acceleration of these computations or to increase energy efficiency. This thesis develops elements of a workflow that can be followed to apply approximate computing to existing applications. It proposes a novel heuristic approach to the localization of code paths that are suitable to approximate computing based on findings in recent research. Additionally, an approach to identification of approximable instructions within these code paths is proposed and used to implement simulation of approximation. The parts of the workflow are implemented with the goal to lay the foundation for a partly automated toolflow. Evaluation of the developed techniques shows that the proposed methods can help providing a convenient workflow, facilitating the first steps into the application of approximate computing. AU - Lass, Michael ID - 1794 TI - Localization and Analysis of Code Paths Suitable for Acceleration using Approximate Computing ER - TY - CONF AB - The first year of studying has been extensively researched applying different theoretical lenses to better understand the transition into Higher Education (HE). It is of particular interest to investigate how students deal with frictions between themselves as individuals and what they perceive to be dominant features of the first-year culture of their studies. To tackle this question, a qualitative longitudinal study was conducted. Based on a sociocultural understanding of attitudes and motivations, its aim was to closely follow a relatively small but highly diverse sample of students throughout their first year at a business school in order to develop an in-depth understanding of each individual’s motivational and attitudinal development. AU - Jenert, Tobias AU - Brahm, Taiga ID - 4465 KW - Enculturation KW - first-year students KW - beginning students KW - retention KW - drop-out TI - How Do They Find Their Place? A Longitudinal Study of Management Students' Attitudes and Motivations During Their First Year at Business School ER - TY - GEN AU - Funke, Lukas ID - 5413 TI - An LLVM Based Toolchain for Transparent Acceleration of Digital Image Processing Applications using FPGA Overlay Architectures ER - TY - GEN AU - Löcke, Thomas ID - 5416 TI - Instance-Specific Computing in Hard- and Software for Faster Solving of Complex Problems ER - TY - GEN AU - Wallaschek, Felix ID - 5419 TI - Accelerating Programmable Logic Controllers with the use of FPGAs ER - TY - THES AB - The use of heterogeneous computing resources, such as graphics processing units or other specialized co-processors, has become widespread in recent years because of their performance and energy efficiency advantages. Operating system approaches that are limited to optimizing CPU usage are no longer sufficient for the efficient utilization of systems that comprise diverse resource types. Enabling task preemption on these architectures and migration of tasks between different resource types at run-time is not only key to improving the performance and energy consumption but also to enabling automatic scheduling methods for heterogeneous compute nodes. This thesis proposes novel techniques for run-time management of heterogeneous resources and enabling tasks to migrate between diverse hardware. It provides fundamental work towards future operating systems by discussing implications, limitations, and chances of the heterogeneity and introducing solutions for energy- and performance-efficient run-time systems. Scheduling methods to utilize heterogeneous systems by the use of a centralized scheduler are presented that show benefits over existing approaches in varying case studies. AU - Beisel, Tobias ID - 10624 SN - 978-3-8325-4155-2 TI - Management and Scheduling of Accelerators for Heterogeneous High-Performance Computing ER - TY - JOUR AB - FPGAs are known to permit huge gains in performance and efficiency for suitable applications but still require reduced design efforts and shorter development cycles for wider adoption. In this work, we compare the resulting performance of two design concepts that in different ways promise such increased productivity. As common starting point, we employ a kernel-centric design approach, where computational hotspots in an application are identified and individually accelerated on FPGA. By means of a complex stereo matching application, we evaluate two fundamentally different design philosophies and approaches for implementing the required kernels on FPGAs. In the first implementation approach, we designed individually specialized data flow kernels in a spatial programming language for a Maxeler FPGA platform; in the alternative design approach, we target a vector coprocessor with large vector lengths, which is implemented as a form of programmable overlay on the application FPGAs of a Convey HC-1. We assess both approaches in terms of overall system performance, raw kernel performance, and performance relative to invested resources. After compensating for the effects of the underlying hardware platforms, the specialized dataflow kernels on the Maxeler platform are around 3x faster than kernels executing on the Convey vector coprocessor. In our concrete scenario, due to trade-offs between reconfiguration overheads and exposed parallelism, the advantage of specialized dataflow kernels is reduced to around 2.5x. AU - Kenter, Tobias AU - Schmitz, Henning AU - Plessl, Christian ID - 296 JF - International Journal of Reconfigurable Computing (IJRC) TI - Exploring Tradeoffs between Specialized Kernels and a Reusable Overlay in a Stereo-Matching Case Study VL - 2015 ER - TY - CONF AB - This paper introduces Binary Acceleration At Runtime(BAAR), an easy-to-use on-the-fly binary acceleration mechanismwhich aims to tackle the problem of enabling existentsoftware to automatically utilize accelerators at runtime. BAARis based on the LLVM Compiler Infrastructure and has aclient-server architecture. The client runs the program to beaccelerated in an environment which allows program analysisand profiling. Program parts which are identified as suitable forthe available accelerator are exported and sent to the server.The server optimizes these program parts for the acceleratorand provides RPC execution for the client. The client transformsits program to utilize accelerated execution on the server foroffloaded program parts. We evaluate our work with a proofof-concept implementation of BAAR that uses an Intel XeonPhi 5110P as the acceleration target and performs automaticoffloading, parallelization and vectorization of suitable programparts. The practicality of BAAR for real-world examples is shownbased on a study of stencil codes. Our results show a speedup ofup to 4 without any developer-provided hints and 5.77 withhints over the same code compiled with the Intel Compiler atoptimization level O2 and running on an Intel Xeon E5-2670machine. Based on our insights gained during implementationand evaluation we outline future directions of research, e.g.,offloading more fine-granular program parts than functions, amore sophisticated communication mechanism or introducing onstack-replacement. AU - Damschen, Marvin AU - Plessl, Christian ID - 303 T2 - Proceedings of the 5th International Workshop on Adaptive Self-tuning Computing Systems (ADAPT) TI - Easy-to-Use On-The-Fly Binary Program Acceleration on Many-Cores ER - TY - CONF AU - Schumacher, Jörn AU - T. Anderson, J. AU - Borga, A. AU - Boterenbrood, H. AU - Chen, H. AU - Chen, K. AU - Drake, G. AU - Francis, D. AU - Gorini, B. AU - Lanni, F. AU - Lehmann-Miotto, Giovanna AU - Levinson, L. AU - Narevicius, J. AU - Plessl, Christian AU - Roich, A. AU - Ryu, S. AU - P. Schreuder, F. AU - Vandelli, Wainer AU - Vermeulen, J. AU - Zhang, J. ID - 1773 T2 - Proc. Int. Conf. on Distributed Event-Based Systems (DEBS) TI - Improving Packet Processing Performance in the ATLAS FELIX Project – Analysis and Optimization of a Memory-Bounded Algorithm ER - TY - JOUR AU - Plessl, Christian AU - Platzner, Marco AU - Schreier, Peter J. ID - 1768 IS - 5 JF - Informatik Spektrum KW - approximate computing KW - survey TI - Aktuelles Schlagwort: Approximate Computing ER - TY - CONF AB - In this paper, we study how binary applications can be transparently accelerated with novel heterogeneous computing resources without requiring any manual porting or developer-provided hints. Our work is based on Binary Acceleration At Runtime (BAAR), our previously introduced binary acceleration mechanism that uses the LLVM Compiler Infrastructure. BAAR is designed as a client-server architecture. The client runs the program to be accelerated in an environment, which allows program analysis and profiling and identifies and extracts suitable program parts to be offloaded. The server compiles and optimizes these offloaded program parts for the accelerator and offers access to these functions to the client with a remote procedure call (RPC) interface. Our previous work proved the feasibility of our approach, but also showed that communication time and overheads limit the granularity of functions that can be meaningfully offloaded. In this work, we motivate the importance of a lightweight, high-performance communication between server and client and present a communication mechanism based on the Message Passing Interface (MPI). We evaluate our approach by using an Intel Xeon Phi 5110P as the acceleration target and show that the communication overhead can be reduced from 40% to 10%, thus enabling even small hotspots to benefit from offloading to an accelerator. AU - Damschen, Marvin AU - Riebler, Heinrich AU - Vaz, Gavin Francis AU - Plessl, Christian ID - 238 T2 - Proceedings of the 2015 Conference on Design, Automation and Test in Europe (DATE) TI - Transparent offloading of computational hotspots from binary code to Xeon Phi ER - TY - JOUR AB - The ATLAS experiment at CERN is planning full deployment of a new unified optical link technology for connecting detector front end electronics on the timescale of the LHC Run 4 (2025). It is estimated that roughly 8000 GBT (GigaBit Transceiver) links, with transfer rates up to 10.24 Gbps, will replace existing links used for readout, detector control and distribution of timing and trigger information. A new class of devices will be needed to interface many GBT links to the rest of the trigger, data-acquisition and detector control systems. In this paper FELIX (Front End LInk eXchange) is presented, a PC-based device to route data from and to multiple GBT links via a high-performance general purpose network capable of a total throughput up to O(20 Tbps). FELIX implies architectural changes to the ATLAS data acquisition system, such as the use of industry standard COTS components early in the DAQ chain. Additionally the design and implementation of a FELIX demonstration platform is presented and hardware and software aspects will be discussed. AU - Anderson, J AU - Borga, A AU - Boterenbrood, H AU - Chen, H AU - Chen, K AU - Drake, G AU - Francis, D AU - Gorini, B AU - Lanni, F AU - Lehmann Miotto, G AU - Levinson, L AU - Narevicius, J AU - Plessl, Christian AU - Roich, A AU - Ryu, S AU - Schreuder, F AU - Schumacher, Jörn AU - Vandelli, Wainer AU - Vermeulen, J AU - Zhang, J ID - 1775 JF - Journal of Physics: Conference Series TI - FELIX: a High-Throughput Network Approach for Interfacing to Front End Electronics for ATLAS Upgrades VL - 664 ER - TY - CHAP AB - Im Bereich der Computersysteme ist die Festlegung der Grenze zwischen Hardware und Software eine zentrale Problemstellung. Diese Grenze hat in den letzten Jahrzehnten nicht nur die Entwicklung von Computersystemen bestimmt, sondern auch die Strukturierung der Ausbildung in den Computerwissenschaften beeinflusst und sogar zur Entstehung von neuen Forschungsrichtungen gef{\"u}hrt. In diesem Beitrag besch{\"a}ftigen wir uns mit Verschiebungen an der Grenze zwischen Hardware und Software und diskutieren insgesamt drei qualitativ unterschiedliche Formen solcher Verschiebungen. Wir beginnen mit der Entwicklung von Computersystemen im letzten Jahrhundert und der Entstehung dieser Grenze, die Hardware und Software erst als eigenst{\"a}ndige Produkte differenziert. Dann widmen wir uns der Frage, welche Funktionen in einem Computersystem besser in Hardware und welche besser in Software realisiert werden sollten, eine Fragestellung die zu Beginn der 90er-Jahre zur Bildung einer eigenen Forschungsrichtung, dem sogenannten Hardware/Software Co-design, gef{\"u}hrt hat. Im Hardware/Software Co-design findet eine Verschiebung von Funktionen an der Grenze zwischen Hardware und Software w{\"a}hrend der Entwicklung eines Produktes statt, um Produkteigenschaften zu optimieren. Im fertig entwickelten und eingesetzten Produkt hingegen k{\"o}nnen wir dann eine feste Grenze zwischen Hardware und Software beobachten. Im dritten Teil dieses Beitrags stellen wir mit selbst-adaptiven Systemen eine hochaktuelle Forschungsrichtung vor. In unserem Kontext bedeutet Selbstadaption, dass ein System Verschiebungen von Funktionen an der Grenze zwischen Hardware und Software autonom w{\"a}hrend der Betriebszeit vornimmt. Solche Systeme beruhen auf rekonfigurierbarer Hardware, einer relativ neuen Technologie mit der die Hardware eines Computers w{\"a}hrend der Laufzeit ver{\"a}ndert werden kann. Diese Technologie f{\"u}hrt zu einer durchl{\"a}ssigen Grenze zwischen Hardware und Software bzw. l{\"o}st sie die herk{\"o}mmliche Vorstellung einer festen Hardware und einer flexiblen Software damit auf. AU - Platzner, Marco AU - Plessl, Christian ED - Künsemöller, Jörn ED - Eke, Norber Otto ED - Foit, Lioba ED - Kaerlein, Timo ID - 335 SN - 978-3-7705-5730-1 T2 - Logiken strukturbildender Prozesse: Automatismen TI - Verschiebungen an der Grenze zwischen Hardware und Software ER - TY - CONF AB - In order to leverage the use of reconfigurable architectures in general-purpose computing, quick and automated methods to find suitable accelerator designs are required. We tackle this challenge in both regards. In order to avoid long synthesis times, we target a vector copro- cessor, implemented on the FPGAs of a Convey HC-1. Previous studies showed that existing tools were not able to accelerate a real-world application with low effort. We present a toolflow to automatically identify suitable loops for vectorization, generate a corresponding hardware/software bipartition, and generate coprocessor code. Where applicable, we leverage outer-loop vectorization. We evaluate our tools with a set of characteristic loops, systematically analyzing different dependency and data layout properties. AU - Kenter, Tobias AU - Vaz, Gavin Francis AU - Plessl, Christian ID - 388 T2 - Proceedings of the International Symposium on Reconfigurable Computing: Architectures, Tools, and Applications (ARC) TI - Partitioning and Vectorizing Binary Applications for a Reconfigurable Vector Computer VL - 8405 ER - TY - JOUR AB - 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, these temperature simulations require a high computational effort if a detailed thermal model is used and their accuracies are often unclear. In contrast to simulations, the use of synthetic heat sources allows for experimental evaluation of temperature management methods. In this paper we investigate the creation of significant rises in temperature on modern FPGAs to enable future evaluation of thermal management techniques based on experiments. To that end, we have developed seven different heat-generating cores that use different subsets of FPGA resources. Our experimental results show that, according to external temperature probes connected to the FPGA’s heat sink, we can increase the temperature by an average of 81 !C. This corresponds to an average increase of 156.3 !C as measured by the built-in thermal diodes of our Virtex-5 FPGAs in less than 30 min by only utilizing about 21 percent of the slices. AU - Agne, Andreas AU - Hangmann, Hendrik AU - Happe, Markus AU - Platzner, Marco AU - Plessl, Christian ID - 363 IS - 8, Part B JF - Microprocessors and Microsystems TI - Seven Recipes for Setting Your FPGA on Fire – A Cookbook on Heat Generators VL - 38 ER - TY - CONF AB - In this paper, we study how AES key schedules can be reconstructed from decayed memory. This operation is a crucial and time consuming operation when trying to break encryption systems with cold-boot attacks. In software, the reconstruction of the AES master key can be performed using a recursive, branch-and-bound tree-search algorithm that exploits redundancies in the key schedule for constraining the search space. In this work, we investigate how this branch-and-bound algorithm can be accelerated with FPGAs. We translated the recursive search procedure to a state machine with an explicit stack for each recursion level and create optimized datapaths to accelerate in particular the processing of the most frequently accessed tree levels. We support two different decay models, of which especially the more realistic non-idealized asymmetric decay model causes very high runtimes in software. Our implementation on a Maxeler dataflow computing system outperforms a software implementation for this model by up to 27x, which makes cold-boot attacks against AES practical even for high error rates. AU - Riebler, Heinrich AU - Kenter, Tobias AU - Plessl, Christian AU - Sorge, Christoph ID - 377 KW - coldboot T2 - Proceedings of Field-Programmable Custom Computing Machines (FCCM) TI - Reconstructing AES Key Schedules from Decayed Memory with FPGAs ER - TY - JOUR AB - Self-aware computing is a paradigm for structuring and simplifying the design and operation of computing systems that face unprecedented levels of system dynamics and thus require novel forms of adaptivity. The generality of the paradigm makes it applicable to many types of computing systems and, previously, researchers started to introduce concepts of self-awareness to multicore architectures. In our work we build on a recent reference architectural framework as a model for self-aware computing and instantiate it for an FPGA-based heterogeneous multicore running the ReconOS reconfigurable architecture and operating system. After presenting the model for self-aware computing and ReconOS, we demonstrate with a case study how a multicore application built on the principle of self-awareness, autonomously adapts to changes in the workload and system state. Our work shows that the reference architectural framework as a model for self-aware computing can be practically applied and allows us to structure and simplify the design process, which is essential for designing complex future computing systems. AU - Agne, Andreas AU - Happe, Markus AU - Lösch, Achim AU - Plessl, Christian AU - Platzner, Marco ID - 365 IS - 2 JF - ACM Transactions on Reconfigurable Technology and Systems (TRETS) TI - Self-awareness as a Model for Designing and Operating Heterogeneous Multicores VL - 7 ER - TY - JOUR AB - The ReconOS operating system for reconfigurable computing offers a unified multi-threaded programming model and operating system services for threads executing in software and threads mapped to reconfigurable hardware. The operating system interface allows hardware threads to interact with software threads using well-known mechanisms such as semaphores, mutexes, condition variables, and message queues. By semantically integrating hardware accelerators into a standard operating system environment, ReconOS allows for rapid design space exploration, supports a structured application development process and improves the portability of applications AU - Agne, Andreas AU - Happe, Markus AU - Keller, Ariane AU - Lübbers, Enno AU - Plattner, Bernhard AU - Platzner, Marco AU - Plessl, Christian ID - 328 IS - 1 JF - IEEE Micro TI - ReconOS - An Operating System Approach for Reconfigurable Computing VL - 34 ER - TY - CONF AU - C. Durelli, Gianluca AU - Pogliani, Marcello AU - Miele, Antonio AU - Plessl, Christian AU - Riebler, Heinrich AU - Vaz, Gavin Francis AU - D. Santambrogio, Marco AU - Bolchini, Cristiana ID - 1778 T2 - Proc. Int. Symp. on Parallel and Distributed Processing with Applications (ISPA) TI - Runtime Resource Management in Heterogeneous System Architectures: The SAVE Approach ER - TY - CONF AB - Reconfigurable architectures provide an opportunityto accelerate a wide range of applications, frequentlyby exploiting data-parallelism, where the same operations arehomogeneously executed on a (large) set of data. However, whenthe sequential code is executed on a host CPU and only dataparallelloops are executed on an FPGA coprocessor, a sufficientlylarge number of loop iterations (trip counts) is required, such thatthe control- and data-transfer overheads to the coprocessor canbe amortized. However, the trip count of large data-parallel loopsis frequently not known at compile time, but only at runtime justbefore entering a loop. Therefore, we propose to generate codeboth for the CPU and the coprocessor, and to defer the decisionwhere to execute the appropriate code to the runtime of theapplication when the trip count of the loop can be determinedjust at runtime. We demonstrate how an LLVM compiler basedtoolflow can automatically insert appropriate decision blocks intothe application code. Analyzing popular benchmark suites, weshow that this kind of runtime decisions is often applicable. Thepractical feasibility of our approach is demonstrated by a toolflowthat automatically identifies loops suitable for vectorization andgenerates code for the FPGA coprocessor of a Convey HC-1. Thetoolflow adds decisions based on a comparison of the runtimecomputedtrip counts to thresholds for specific loops and alsoincludes support to move just the required data to the coprocessor.We evaluate the integrated toolflow with characteristic loopsexecuted on different input data sizes. AU - Vaz, Gavin Francis AU - Riebler, Heinrich AU - Kenter, Tobias AU - Plessl, Christian ID - 439 T2 - Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig) TI - Deferring Accelerator Offloading Decisions to Application Runtime ER - TY - CONF AB - Stereo-matching algorithms recently received a lot of attention from the FPGA acceleration community. Presented solutions range from simple, very resource efficient systems with modest matching quality for small embedded systems to sophisticated algorithms with several processing steps, implemented on big FPGAs. In order to achieve high throughput, most implementations strongly focus on pipelining and data reuse between different computation steps. This approach leads to high efficiency, but limits the supported computation patterns and due the high integration of the implementation, adaptions to the algorithm are difficult. In this work, we present a stereo-matching implementation, that starts by offloading individual kernels from the CPU to the FPGA. Between subsequent compute steps on the FPGA, data is stored off-chip in on-board memory of the FPGA accelerator card. This enables us to accelerate the AD-census algorithm with cross-based aggregation and scanline optimization for the first time without algorithmic changes and for up to full HD image dimensions. Analyzing throughput and bandwidth requirements, we outline some trade-offs that are involved with this approach, compared to tighter integration of more kernel loops into one design. AU - Kenter, Tobias AU - Schmitz, Henning AU - Plessl, Christian ID - 406 T2 - Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig) TI - Kernel-Centric Acceleration of High Accuracy Stereo-Matching ER - TY - CONF AU - C. Durelli, Gianluca AU - Copolla, Marcello AU - Djafarian, Karim AU - Koranaros, George AU - Miele, Antonio AU - Paolino, Michele AU - Pell, Oliver AU - Plessl, Christian AU - D. Santambrogio, Marco AU - Bolchini, Cristiana ID - 1780 T2 - Proc. Int. Conf. on Reconfigurable Computing: Architectures, Tools and Applications (ARC) TI - SAVE: Towards efficient resource management in heterogeneous system architectures ER - TY - JOUR AU - Giefers, Heiner AU - Plessl, Christian AU - Förstner, Jens ID - 1779 IS - 5 JF - ACM SIGARCH Computer Architecture News KW - funding-maxup KW - tet_topic_hpc SN - 0163-5964 TI - Accelerating Finite Difference Time Domain Simulations with Reconfigurable Dataflow Computers VL - 41 ER -