Recently, accelerators for extremely quantized deep neural network (DNN) inference with operand widths as low as 1-bit have gained popularity due to their ability to largely cut down energy cost per inference. In this paper, a flexible SoC with mixed-precision support is presented. Contrary to the current trend of fixed-datapath accelerators, this architecture makes use of a flexible datapath based on a Transport-Triggered Architecture (TTA). The architecture is fully programmable using C. The accelerator has a peak energy efficiency of 35/67/405 fJ/op (binary, ternary, and 8-bit precision) and a throughput of 614/307/77 GOPS, which is unprecedented for a programmable architecture.
Programmable switches have emerged as powerful and flexible alternatives to fixed-function forwarding devices. But because of the unique hardware constraints of network switches, the design and implementation of compilers targeting these devices is tedious and error prone. Despite the important role that compilers play in software development, there is a dearth of tools for testing compilers for programmable network devices. We present Druzhba, a programmable switch simulator used for testing compilers targeting programmable packet-processing substrates. We show that we can model the low-level…
This paper presents an infrastructure to test the functionality of the specific architectures output by a high-level compiler targeting dynamically reconfigurable hardware. It results in a suitable scheme to verify the architectures generated by the compiler, each time new optimization techniques are included or changes in the compiler are performed. We believe this kind of infrastructure is important to verify, by functional simulation, further research techniques, as far as compilation to Field-Programmable Gate Array (FPGA) platforms is concerned.
Image processing and machine learning applications benefit tremendously from hardware acceleration, but existing compilers target either FPGAs, which sacrifice power and performance for flexible hardware, or ASICs, which rapidly become obsolete as applications change. Programmable domain-specific accelerators have emerged as a promising middle-ground between these two extremes, but such architectures have traditionally been difficult compiler targets. The main obstacle is that these accelerators often use a different memory abstraction than CPUs and GPUs: push memories that send a data stream …
Memristor crossbars are circuits capable of performing analog matrix-vector multiplications, overcoming the fundamental energy efficiency limitations of digital logic. They have been shown to be effective in special-purpose accelerators for a limited set of neural network applications. We present the Programmable Ultra-efficient Memristor-based Accelerator (PUMA) which enhances memristor crossbars with general purpose execution units to enable the acceleration of a wide variety of Machine Learning (ML) inference workloads. PUMA's microarchitecture techniques exposed through a specialized Instr…
Modern Systems-on-Chip (SoC) designs are increasingly heterogeneous and contain specialized semi-programmable accelerators in addition to programmable processors. In contrast to the pre-accelerator era, when the ISA played an important role in verification by enabling a clean separation of concerns between software and hardware, verification of these "accelerator-rich" SoCs presents new challenges. From the perspective of hardware designers, there is a lack of a common framework for the formal functional specification of accelerator behavior. From the perspective of software developers, there …
A wide range of Internet of Things (IoT) applications require powerful, energy-efficient and flexible end-nodes to acquire data from multiple sources, process and distill the sensed data through near-sensor data analytics algorithms, and transmit it wirelessly. This work presents Arnold: a 0.5 V to 0.8 V, 46.83 uW/MHz, 600 MOPS fully programmable RISC-V Microcontroller unit (MCU) fabricated in 22 nm Globalfoundries GF22FDX (GF22FDX) technology, coupled with a stateof-the-art (SoA) microcontroller to an embedded Field Programmable Gate Array (FPGA). We demonstrate the flexibility of the System-…
Overlays have shown significant promise for field-programmable gate-arrays (FPGAs) as they allow for fast development cycles and remove many of the challenges of the traditional FPGA hardware design flow. However, this often comes with a significant performance burden resulting in very little adoption of overlays for practical applications. In this paper, we tailor an overlay to a specific application domain, and we show how we maintain its full programmability without paying for the performance overhead traditionally associated with overlays. Specifically, we introduce an overlay targeted for…
Fully Homomorphic Encryption (FHE) allows computing on encrypted data, enabling secure offloading of computation to untrusted serves. Though it provides ideal security, FHE is expensive when executed in software, 4 to 5 orders of magnitude slower than computing on unencrypted data. These overheads are a major barrier to FHE's widespread adoption. We present F1, the first FHE accelerator that is programmable, i.e., capable of executing full FHE programs. F1 builds on an in-depth architectural analysis of the characteristics of FHE computations that reveals acceleration opportunities. F1 is a wi…
In modern embedded systems, the trust in comprehensive security standards all along the product life cycle has become an increasingly important access-to-market requirement. However, these security standards rely on mandatory immunity assumptions such as the integrity and authenticity of an initial system configuration typically loaded from Non-Volatile Memory (NVM). This applies especially to FPGA-based Programmable System-on-Chip (PSoC) architectures, since object codes as well as configuration data easily exceed the capacity of a secure bootROM. In this context, an attacker could try to alt…
SU3\_Bench is a microbenchmark developed to explore performance portability across multiple programming models/methodologies using a simple, but nontrivial, mathematical kernel. This kernel has been derived from the MILC lattice quantum chromodynamics (LQCD) code. SU3\_Bench is bandwidth bound and generates regular compute and data access patterns. Therefore, on most traditional CPU and GPU-based systems, its performance is mainly determined by the achievable memory bandwidth. Although SU3\_Bench is a simple kernel, experience says its subtleties require a certain amount of tweaking to achieve…
The wide adoption of deep neural networks has been accompanied by ever-increasing energy and performance demands due to the expensive nature of training them. Numerous special-purpose architectures have been proposed to accelerate training: both digital and hybrid digital-analog using resistive RAM (ReRAM) crossbars. ReRAM-based accelerators have demonstrated the effectiveness of ReRAM crossbars at performing matrix-vector multiplication operations that are prevalent in training. However, they still suffer from inefficiency due to the use of serial reads and writes for performing the weight gr…
A new approach to designing processor accelerators is presented. A new computing model and a special kind of accelerator with dynamic (end-user programmable) architecture is suggested. The new model considers a processor, in which a newly introduced supervisor layer coordinates the job of the cores. The cores have the ability (based on the parallelization information provided by the compiler, and using the help of the supervisor) to outsource part of the job they received to some neighbouring core. The introduced changes essentially and advantageously modify the architecture and operation of t…
Manycore SoC architectures based on on-chip shared memory are preferred for flexible and programmable solutions in many application domains. However, the development of many ported memory is becoming increasingly challenging as we approach the end of Moore's Law while systems requirements demand larger shared memory and more access ports. Memory can no longer be designed simply to minimize single transaction access time, but must take into account the functionality on the SoC. In this paper we examine a common large memory usage in SoC, where the memory is used as storage for large buffers tha…
In this paper a pipelined architecture of a high speed network security processor (NSP) for SSL,TLS protocol is implemented on a system on chip (SOC) where hardware information of all encryption, hashing and key exchange algorithms are stored in flash memory in terms of bit files, in contrary to related works where all are actually implemented in hardware. The NSP finds applications in e-commerce, virtual private network (VPN) and in other fields that require data confidentiality. The motivation of the present work is to dynamically execute applications with stipulated throughput within budget…
University of Bologna（博洛尼亚大学）；ETH Zurich（苏黎世联邦理工学院）；GreenWaves Technologies
The Internet-of-Things requires end-nodes with ultra-low-power always-on capability for a long battery lifetime, as well as high performance, energy efficiency, and extreme flexibility to deal with complex and fast-evolving near-sensor analytics algorithms (NSAAs). We present Vega, an IoT end-node SoC capable of scaling from a 1.7 $\mathrmμ$W fully retentive cognitive sleep mode up to 32.2 GOPS (@ 49.4 mW) peak performance on NSAAs, including mobile DNN inference, exploiting 1.6 MB of state-retentive SRAM, and 4 MB of non-volatile MRAM. To meet the performance and flexibility requirements of N…
This paper presents the definition and implementation of a quantum computer architecture to enable creating a new computational device - a quantum computer as an accelerator In this paper, we present explicitly the idea of a quantum accelerator which contains the full stack of the layers of an accelerator. Such a stack starts at the highest level describing the target application of the accelerator. Important to realise is that qubits are defined as perfect qubits, implying they do not decohere and perform good quantum gate operations. The next layer abstracts the quantum logic outlining the a…
Deep convolutional neural networks (CNNs) obtain outstanding results in tasks that require human-level understanding of data, like image or speech recognition. However, their computational load is significant, motivating the development of CNN-specialized accelerators. This work presents NEURAghe, a flexible and efficient hardware/software solution for the acceleration of CNNs on Zynq SoCs. NEURAghe leverages the synergistic usage of Zynq ARM cores and of a powerful and flexible Convolution-Specific Processor deployed on the reconfigurable logic. The Convolution-Specific Processor embeds both …
Heterogeneous SoC Integrating an Open-Source Recurrent SNN Accelerator for Neuromorphic Edge Computing on FPGA
Department of Computer and Control Engineering（计算机与控制工程系）；Politecnico di Torino（托尼诺理工大学）；Interuniversity Department of Regional and Urban Studies and Planning（区域与城市研究和规划联合大学部门）
