First three authors contributed equally. 2 pages, 6 figures, IEEE Custom Integrated Circuits Conference (CICC), April 24-27, 2022, Newport Beach, CA, USA
Simultaneous Localization and Mapping (SLAM) estimates agents' trajectories and constructs maps, and localization is a fundamental kernel in autonomous machines at all computing scales, from drones, AR, VR to self-driving cars. In this work, we present an energy-efficient and runtime-reconfigurable FPGA-based accelerator for robotic localization. We exploit SLAM-specific data locality, sparsity, reuse, and parallelism, and achieve >5x performance improvement over the state-of-the-art. Especially, our design is reconfigurable at runtime according to the environment to save power while sustaining accuracy and performance.
Floorplanning problem has been extensively explored for homogeneous FPGAs. Most modern FPGAs consist of heterogeneous resources in the form of configurable logic blocks, DSP blocks, BRAMs and more. Very little work has been done for heterogeneous FPGAs. In addition, features like partial reconfigurability allow on-the-fly changes to the executable design that can result in enhanced performance and very efficient utilization of resources. In this paper, we have designed a floorplanner for Partially Reconfigurable (PR) designs in FPGA that smartly decides one of the three proposed resource alloc…
Adaptive systems based on field programmable gate array (FPGA) architectures can greatly benefi t fro m th e high degree of flexibility offered by dynamic partial reconfiguration (DPR). By using this technique, hardware tasks can be loaded and reloaded on demand depending on the system requirements. In this paper, we propose to use the DPR for dynamic and adaptive implementation of a video cut detection application based on the MPEG-7 color structure descriptor (CSD). In the proposed implementation, different scenarios have been tested. Depending on the application and the system requirements,…
With the emerging big data applications of Machine Learning, Speech Recognition, Artificial Intelligence, and DNA Sequencing in recent years, computer architecture research communities are facing the explosive scale of various data explosion. To achieve high efficiency of data-intensive computing, studies of heterogeneous accelerators which focus on latest applications, have become a hot issue in computer architecture domain. At present, the implementation of heterogeneous accelerators mainly relies on heterogeneous computing units such as Application-specific Integrated Circuit (ASIC), Graphi…
In this treatise, my research on methods to improve efficiency, reliability, and security of reconfigurable hardware systems, i.e., FPGAs, through partial dynamic reconfiguration is outlined. The efficiency of reconfigurable systems can be improved by loading optimized data paths on-the-fly on an FPGA fabric. This technique was applied to the acceleration of SQL queries for large database applications as well as for image and signal processing applications. The focus was not only on performance improvements and resource efficiency, but also the energy efficiency has been significantly improved…
The exponential emergence of Field Programmable Gate Array (FPGA) has accelerated the research of hardware implementation of Deep Neural Network (DNN). Among all DNN processors, domain specific architectures, such as, Google's Tensor Processor Unit (TPU) have outperformed conventional GPUs. However, implementation of TPUs in reconfigurable hardware should emphasize energy savings to serve the green computing requirement. Voltage scaling, a popular approach towards energy savings, can be a bit critical in FPGA as it may cause timing failure if not done in an appropriate way. In this work, we pr…
In todays world, high-power computing applications such as image processing, digital signal processing, graphics, and robotics require enormous computing power. These applications use matrix operations, especially matrix multiplication. Multiplication operations require a lot of computational time and are also complex in design. We can use field-programmable gate arrays as low-cost hardware accelerators along with a low-cost general-purpose processor instead of a high-cost application-specific processor for such applications. In this work, we employ an efficient Strassens algorithm for matrix …
A Reconfigurable Framework for AI-FPGA Agent Integration and Acceleration
Purdue University（普渡大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Moratuwa（莫拉图瓦大学）；Stanford University（斯坦福大学）；Istinye University（伊斯提耶大学）
With the continued growth in field-programmable gate array (FPGA) capacity and their incorporation into new environments such as datacenters, we have witnessed the introduction of a new class of reconfigurable acceleration devices (RADs) that go beyond conventional FPGA architectures. These devices combine a reconfigurable fabric with coarse-grained domain-specialized accelerator blocks all connected via a high-performance packet-switched network-on-chip (NoC) for efficient system-wide communication. However, we lack the tools necessary to efficiently explore the huge design space for RADs, st…
This paper presents an FPGA runtime framework that demonstrates the feasibility of using dynamic partial reconfiguration (DPR) for time-sharing an FPGA by multiple realtime computer vision pipelines. The presented time-sharing runtime framework manages an FPGA fabric that can be round-robin time-shared by different pipelines at the time scale of individual frames. In this new use-case, the challenge is to achieve useful performance despite high reconfiguration time. The paper describes the basic runtime support as well as four optimizations necessary to achieve realtime performance given the l…
Autoencoders are unsupervised neural networks that are used to process and compress input data and then reconstruct the data back to the original data size. This allows autoencoders to be used for different processing applications such as data compression, image classification, image noise reduction, and image coloring. Hardware-wise, re-configurable architectures like Field Programmable Gate Arrays (FPGAs) have been used for accelerating computations from several domains because of their unique combination of flexibility, performance, and power efficiency. In this paper, we look at the differ…
Graduate School of Information, Production and Systems, Waseda University（早稻田大学信息生产系统研究生院）
Large-scale deep convolutional neural networks (CNNs) are widely used in machine learning applications. While CNNs involve huge complexity, VLSI (ASIC and FPGA) chips that deliver high-density integration of computational resources are regarded as a promising platform for CNN's implementation. At massive parallelism of computational units, however, the external memory bandwidth, which is constrained by the pin count of the VLSI chip, becomes the system bottleneck. Moreover, VLSI solutions are usually regarded as a lack of the flexibility to be reconfigured for the various parameters of CNNs. T…
Matrix-matrix multiplication is a key computational kernel for numerous applications in science and engineering, with ample parallelism and data locality that lends itself well to high-performance implementations. Many matrix multiplication-dependent applications can use reduced-precision integer or fixed-point representations to increase their performance and energy efficiency while still offering adequate quality of results. However, precision requirements may vary between different application phases or depend on input data, rendering constant-precision solutions ineffective. BISMO, a vecto…
In next generation wireless communication system, wireless transceivers should be able to handle wideband input signals compromising of multiple communication standards.Such multi-standard wireless communication receivers (MWCRs) need filter bank to extract the desired signal of interest from wideband input spectrum and bring it to the baseband for further signal processing tasks such as spectrum sensing, modulation classification,demodulation etc.In MWCRs,rather any wireless receivers, modulated filter banks, such as Discrete Fourier Transform Filter Banks (DFTFB), are preferred due to their …
University of Southern California（南加利福尼亚大学）；US Army Research Lab（美国陆军研究实验室）
Tensor decomposition has become an essential tool in many applications in various domains, including machine learning. Sparse Matricized Tensor Times Khatri-Rao Product (MTTKRP) is one of the most computationally expensive kernels in tensor computations. Despite having significant computational parallelism, MTTKRP is a challenging kernel to optimize due to its irregular memory access characteristics. This paper focuses on a multi-faceted memory system, which explores the spatial and temporal locality of the data structures of MTTKRP. Further, users can reconfigure our design depending on the b…
Trusted Execution Environments (TEEs) are used to protect sensitive data and run secure execution for security-critical applications, by providing an environment isolated from the rest of the system. However, over the last few years, TEEs have been proven weak, as either TEEs built upon security-oriented hardware extensions (e.g., Arm TrustZone) or resorting to dedicated secure elements were exploited multiple times. In this project, we introduce Trusted Execution Environments On-Demand (TEEOD), a novel TEE design that leverages the programmable logic (PL) in the heterogeneous system on chips …
In data communication via internet, security is becoming one of the most influential aspects. One way to support it is by classifying and filtering ethernet packets within network devices. Packet classification is a fundamental task for network devices such as routers, firewalls, and intrusion detection systems. In this paper we present architecture of fast and reconfigurable Packet Classification Engine (PCE). This engine is used in FPGA-based firewall. Our PCE inspects multi-dimensional field of packet header sequentially based on tree-based algorithm. This algorithm simplifies overall syste…
In this chapter, we study the feasibility of implementing SOR in reconfigurable hardware. We use Handel-C, a higher level design tool, to code our design, which is analyzed, synthesized, and placed and routed using the FPGAs proprietary software (DK Design Suite, Xilinx ISE 8.1i, and Quartus II 5.1). We target Virtex II Pro, Altera Stratix, and Spartan3L, which is embedded in the RC10 FPGA-based system from Celoxica. We report our timing results when targeting Virtex II Pro and compare them to software version results written in C++ and running on a general purpose processor (GPP).
Confronted with the challenge of high performance for applications and the restriction of hardware resources for field-programmable gate arrays (FPGAs), partial dynamic reconfiguration (PDR) technology is anticipated to accelerate the reconfiguration process and alleviate the device shortage. In this paper, we propose an integrated optimization framework for task partitioning, scheduling and floorplanning on partially dynamically reconfigurable FPGAs. The partitions, schedule, and floorplan of the tasks are represented by the partitioned sequence triple P-ST (PS,QS,RS), where (PS,QS) is a hybr…
The deep learning accelerator is one of the methods to accelerate deep learning network computations, which is mainly based on convolutional neural network acceleration. To address the fact that concurrent convolutional neural network accelerators are not solely open-source and the exclusiveness of platforms, FusionAccel, a scalable convolutional neural network accelerator hardware architecture with supporting software is proposed. It can adapt to different network structures and can be reconstructed before compilation and reconfigured at runtime. This paper realizes this RTL convolutional neu…
Energy harvesting is an attractive way to power future IoT devices since it can eliminate the need for battery or power cables. However, harvested energy is intrinsically unstable. While FPGAs have been widely adopted in various embedded systems, it is hard to survive unstable power since all the memory components in FPGA are based on volatile SRAMs. The emerging non-volatile memory based FPGAs provide promising potentials to keep configuration data on the chip during power outages. Few works have considered implementing efficient runtime intermediate data checkpoint on non-volatile FPGAs. To …
A Runtime-Adaptive Transformer Neural Network Accelerator on FPGAs
Department of Electrical Engineering and Computer Science, University of Arkansas（电气工程与计算机科学系，亚拉巴马大学）；Department of Computer Science and Engineering, University of South Carolina（计算机科学与工程系，南卡罗来纳大学）
FPGA overlays are commonly implemented as coarse-grained reconfigurable architectures with a goal to improve designers' productivity through balancing flexibility and ease of configuration of the underlying fabric. To truly facilitate full application acceleration, it is often necessary to also include a highly efficient processor that integrates and collaborates with the accelerators while maintaining the benefits of being implemented within the same overlay framework. This paper presents an open-source soft processor that is designed to tightly-couple with FPGA accelerators as part of an ove…
With increasing diversity in Deep Neural Network(DNN) models in terms of layer shapes and sizes, the research community has been investigating flexible/reconfigurable accelerator substrates. This line of research has opened up two challenges. The first is to determine the appropriate amount of flexibility within an accelerator array that that can trade-off the performance benefits versus the area overheads of the reconfigurability. The second is being able to determine the right configuration of the array for the current DNN model and/or layer and reconfigure the accelerator at runtime. This w…
Several embedded application domains for reconfigurable systems tend to combine frequent changes with high performance demands of their workloads such as image processing, wearable computing and network processors. Time multiplexing of reconfigurable hardware resources raises a number of new issues, ranging from run-time systems to complex programming models that usually form a Reconfigurable hardware Operating System (ROS). The Operating System performs online task scheduling and handles resource management. There are many challenges in adaptive computing and dynamic reconfigurable systems. O…
Bitwise Systolic Array Architecture for Runtime-Reconfigurable Multi-precision Quantized Multiplication on Hardware Accelerators
Dresden University of Technology, Germany（德累斯顿理工大学）；Ruhr University Bochum, Germany（博德大学）；Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI Dresden/Leipzig), Germany（可扩展数据与人工智能研究中心（ScaDS.AI 德累斯顿/莱比锡））
The use of reconfigurable computing, and FPGAs in particular, has strong potential in the field of High Performance Computing (HPC). However the traditionally high barrier to entry when it comes to programming this technology has, until now, precluded widespread adoption. To popularise reconfigurable computing with communities such as HPC, Xilinx have recently released the first version of Vitis, a platform aimed at making the programming of FPGAs much more a question of software development rather than hardware design. However a key question is how well this technology fulfils the aim, and wh…
Today, artificial neural networks are one of the major innovators pushing the progress of machine learning. This has particularly affected the development of neural network accelerating hardware. However, since most of these architectures require specialized toolchains, there is a certain amount of additional effort for developers each time they want to make use of a new deep learning accelerator. Furthermore the flexibility of the device is bound to the architecture itself, as well as to the functionality of the runtime environment. In this paper we propose a toolflow using TensorFlow as fron…
Faculty of Engineering University of Porto（波尔图大学工程学院）；INESC-TEC（INESC-TEC 研究所）
Decision trees are often preferred when implementing Machine Learning in embedded systems for their simplicity and scalability. Hoeffding Trees are a type of Decision Trees that take advantage of the Hoeffding Bound to allow them to learn patterns in data without having to continuously store the data samples for future reprocessing. This makes them especially suitable for deployment on embedded devices. In this work we highlight the features of an HLS implementation of the Hoeffding Tree. The implementation parameters include the feature size of the samples (D), the number of output classes (K…
We present Versa, an energy-efficient processor with 36 systolic ARM Cortex-M4F cores and a runtime-reconfigurable memory hierarchy. Versa exploits algorithm-specific characteristics in order to optimize bandwidth, access latency, and data reuse. Measured on a set of kernels with diverse data access, control, and synchronization characteristics, reconfiguration between different Versa modes yields median energy-efficiency improvements of 11.6x and 37.2x over mobile CPU and GPU baselines, respectively.
