Loading...
9 results
Search Results
Now showing 1 - 9 of 9
- XtokaxtikoX: a stochastic computing-based autonomous cyber-physical systemPublication . Duarte, Rui Policarpo; Neto, Horácio; Véstias, MárioThis paper presents XtokaxtikoX, a fully autonomous cyber-physical system employing only stochastic arithmetic to perform computations on its data-path. Traditional implementations of stochastic computing systems benefit from fast and compact implementation of arithmetic operators, and high tolerance to errors, but depend heavily on the conversion between stochastic bitstreams and binary to implement many parts of the system. Furthermore, if a system requires any interaction with analog electronic components it must have additional ADC/DAC conversion circuitry, which further increases the complexity of the system. Conversely, the proposed work is able to directly translate analog signals into stochastic bitstreams, process the stochastic bitstreams and finally control analog actuators relying only on the information on the stochastic bitstreams. Details on the architectures to accomplish such functionality are presented as well as other stochastic arithmetic units. This paper also presents a small stochastic computing-based autonomous cyber-physical system implemented on a Cyclone IV FPGA to carry out a proof-of-concept.
- Hybrid dot-product calculation for convolutional neural networks in FPGAPublication . Véstias, Mário; Duarte, Rui Policarpo; De Sousa, Jose; Cláudio de Campos Neto, HorácioConvolutional Neural Networks (CNN) are quite useful in edge devices for security, surveillance, and many others. Running CNNs in embedded devices is a design challenge since these models require high computing power and large memory storage. Data quantization is an optimization technique applied to CNN to reduce the computing and memory requirements. The method reduces the number of bits used to represent weights and activations, which consequently reduces the size of operands and of the memory. The method is more effective if hybrid quantization is considered in which data in different layers may have different bit widths. This article proposes a new hardware module to calculate dot-products of CNNs with hybrid quantization. The module improves the implementation of CNNs in low density FPGAs, where the same module runs dot-products of different layers with different data quantizations. We show implementation results in ZYNQ7020 and compare with state-of-the-art works. Improvements in area and performance are achieved with the new proposed module.
- Onboard processing of synthetic aperture radar backprojection algorithm in FPGAPublication . Mota, David; Cruz, Helena; Miranda, Pedro R.; Duarte, Rui Policarpo; De Sousa, Jose; Cláudio de Campos Neto, Horácio; Véstias, MárioSynthetic aperture radar is a microwave technique to extracting image information of the target. Electromagnetic waves that are reflected from the target are acquired by the aircraft or satellite receivers and sent to a ground station to be processed by applying computational demanding algorithms. Radar data streams are acquired by an aircraft or satellite and sent to a ground station to be processed in order to extract images from the data since these processing algorithms are computationally demanding. However, novel applications require real-time processing for real-time analysis and decisions and so onboard processing is necessary. Running computationally demanding algorithms on onboard embedded systems with limited energy and computational capacity is a challenge. This article proposes a configurable hardware core for the execution of the backprojection algorithm with high performance and energy efficiency. The original backprojection algorithm is restructured to expose computational parallelism and then optimized by replacing floating-point with fixed-point arithmetic. The backprojection core was integrated into a system-onchip architecture and implemented in a field-programmable gate array. The proposed solution runs the optimized backprojection algorithm over images of sizes 512 x 512 and 1024 x 1024 in 0.14 s (0.41 J) and 1.11 s (3.24 J), respectively. The architecture is 2.6x faster and consumes 13x less energy than an embedded Jetson TX2 GPU. The solution is scalable and, therefore, a tradeoff exists between performance and utilization of resources.
- Stochastic theater: stochastic datapath generation framework for fault-tolerant IoT sensorsPublication . Duarte, Rui Policarpo; Véstias, Mário; Carvalho, Carlos; Casaleiro, JoãoStochastic Computing has emerged as a competitive computing paradigm that produces fast and simple implementations of arithmetic operations, while offering high levels of parallelism, and graceful degradation of the results when in the presence of errors. IoT devices are often operate under limited power and area constraints and subjected to harsh environments, for which, traditional computing paradigms struggle to provide high availability and fault-tolerance. Stochastic Computing is based on the computation of pseudo-random sequences of bits, hence requiring only a single bit per signal, rather than a data-bus. Notwithstanding, we haven’t witnessed its inclusion in custom computing systems. In this direction, this work presents Stochastic Theater, a framework to specify, simulate, and test Stochastic Datapaths to perform computations using stochastic bitstreams targeting IoT systems. In virtue of the granularity of the bitstreams, the bit-level specification of circuits, high-performance characteristics and reconfigurable capabilities, FPGAs were adopted to implement and test such systems. The proposed framework creates Stochastic Machines from a set of user defined arithmetic expressions, and then tests them with the corresponding input values and specific fault injection patterns. Besides the support to create autonomous Stochastic Computing systems, the presented framework also provides generation of stochastic units, being able to produce estimates on performance, resources and power. A demonstration is presented targeting KLT, typical method for data compression in IoT applications.
- Energy-efficient and real-time wearable for wellbeing-monitoring IoT system based on SoC-FPGAPublication . Frutuoso, Maria Inês; Cláudio de Campos Neto, Horácio; Véstias, Mário; Duarte, Rui PolicarpoWearable devices used for personal monitoring applications have been improved over the last decades. However, these devices are limited in terms of size, processing capability and power consumption. This paper proposes an efficient hardware/software embedded system for monitoring bio-signals in real time, including a heart rate calculator using PPG and an emotion classifier from EEG. The system is suitable for outpatient clinic applications requiring data transfers to external medical staff. The proposed solution contributes with an effective alternative to the traditional approach of processing bio-signals offline by proposing a SoC-FPGA based system that is able to fully process the signals locally at the node. Two sub-systems were developed targeting a Zynq 7010 device and integrating custom hardware IP cores that accelerate the processing of the most complex tasks. The PPG sub-system implements an autocorrelation peak detection algorithm to calculate heart rate values. The EEG sub-system consists of a KNN emotion classifier of preprocessed EEG features. This work overcomes the processing limitations of microcontrollers and general-purpose units, presenting a scalable and autonomous wearable solution with high processing capability and real-time response.
- Fast convolutional neural networks in low density FPGAs using zero-skipping and weight pruningPublication . Véstias, Mário; Duarte, Rui Policarpo; De Sousa, Jose; Cláudio de Campos Neto, HorácioEdge devices are becoming smarter with the integration of machine learning methods, such as deep learning, and are therefore used in many application domains where decisions have to be made without human intervention. Deep learning and, in particular, convolutional neural networks (CNN) are more efficient than previous algorithms for several computer vision applications such as security and surveillance, where image and video analysis are required. This better efficiency comes with a cost of high computation and memory requirements. Hence, running CNNs in embedded computing devices is a challenge for both algorithm and hardware designers. New processing devices, dedicated system architectures and optimization of the networks have been researched to deal with these computation requirements. In this paper, we improve the inference execution times of CNNs in low density FPGAs (Field-Programmable Gate Arrays) using fixed-point arithmetic, zero-skipping and weight pruning. The developed architecture supports the execution of large CNNs in FPGA devices with reduced on-chip memory and computing resources. With the proposed architecture, it is possible to infer an image in AlexNet in 2.9 ms in a ZYNQ7020 and 1.0 ms in a ZYNQ7045 with less than 1% accuracy degradation. These results improve previous state-of-the-art architectures for CNN inference.
- Coarse-grained reconfigurable computing with the versat architecturePublication . D. Lopes, João; Véstias, Mário; Duarte, Rui Policarpo; Neto, Horácio C; De Sousa, JoseReconfigurable computing architectures allow the adaptation of the underlying datapath to the algorithm. The granularity of the datapath elements and data width determines the granularity of the architecture and its programming flexibility. Coarse-grained architectures have shown the right balance between programmability and performance. This paper provides an overview of coarse-grained reconfigurable architectures and describes Versat, a Coarse-Grained Reconfigurable Array (CGRA) with self-generated partial reconfiguration, presented as a case study for better understanding these architectures. Unlike most of the existing approaches, which mainly use pre-compiled configurations, a Versat program can generate and apply myriads of on-the-fly configurations. Partial reconfiguration plays a central role in this approach, as it speeds up the generation of incrementally different configurations. The reconfigurable array has a complete graph topology, which yields unprecedented programmability, including assembly programming. Besides being useful for optimising programs, assembly programming is invaluable for working around post-silicon hardware, software, or compiler issues. Results on core area, frequency, power, and performance running different codes are presented and compared to other implementations.
- Moving deep learning to the edgePublication . Véstias, Mário; Duarte, Rui Policarpo; De Sousa, Jose; Neto, Horácio CDeep learning is now present in a wide range of services and applications, replacing and complementing other machine learning algorithms. Performing training and inference of deep neural networks using the cloud computing model is not viable for applications where low latency is required. Furthermore, the rapid proliferation of the Internet of Things will generate a large volume of data to be processed, which will soon overload the capacity of cloud servers. One solution is to process the data at the edge devices themselves, in order to alleviate cloud server workloads and improve latency. However, edge devices are less powerful than cloud servers, and many are subject to energy constraints. Hence, new resource and energy-oriented deep learning models are required, as well as new computing platforms. This paper reviews the main research directions for edge computing deep learning algorithms.
- Configurable hardware core for IoT object detectionPublication . Miranda, Pedro R.; Pestana, Daniel; D. Lopes, João; Duarte, Rui Policarpo; Véstias, Mário; Neto, Horácio C; De Sousa, JoseObject detection is an important task for many applications, like transportation, security, and medical applications. Many of these applications are needed on edge devices to make local decisions. Therefore, it is necessary to provide low-cost, fast solutions for object detection. This work proposes a configurable hardware core on a field-programmable gate array (FPGA) for object detection. The configurability of the core allows its deployment on target devices with diverse hardware resources. The object detection accelerator is based on YOLO, for its good accuracy at moderate computational complexity. The solution was applied to the design of a core to accelerate the Tiny-YOLOv3, based on a CNN developed for constrained environments. However, it can be applied to other YOLO versions. The core was integrated into a full system-on-chip solution and tested with the COCO dataset. It achieved a performance from 7 to 14 FPS in a low-cost ZYNQ7020 FPGA, depending on the quantization, with an accuracy reduction from 2.1 to 1.4 points of mAP50.