In this work we propose an effective preconditioning technique to accelerate the steady-state simulation of large-scale memristor crossbar arrays (MCAs). We exploit the structural regularity of MCAs to develop a specially-crafted preconditioner that can be efficiently evaluated utilizing tensor products and block matrix inversion. Numerical experiments demonstrate the efficacy of the proposed technique

To meet the extreme compute demands for deep learning across commercial and scientific applications, dataflow accelerators are becoming increasingly popular. While these "domain-specific" accelerators are not fully programmable like CPUs and GPUs, they retain varying levels of flexibility with respect to data orchestration, i.e., dataflow and tiling optimizations to enhance efficiency. There are several

The commercialization of autonomous machines is a thriving sector, and likely to be the next major computing demand driver, after PC, cloud computing, and mobile computing. Nevertheless, a suitable computer architecture for autonomous machines is missing, and many companies are forced to develop ad hoc computing solutions that are neither scalable nor extensible. In this article, we analyze the demands

One of the most critical aspects of integrating loosely-coupled accelerators in heterogeneous SoC architectures is orchestrating their interactions with the memory hierarchy, especially in terms of navigating the various cache-coherence options: from accelerators accessing off-chip memory directly, bypassing the cache hierarchy, to accelerators having their own private cache. By running real-size applications

Molecular similarity search has been widely used in drug discovery to identify structurally similar compounds from large molecular databases rapidly. With the increasing size of chemical libraries, there is growing interest in the efficient acceleration of large-scale similarity search. Existing works mainly focus on CPU and GPU to accelerate the computation of the Tanimoto coefficient in measuring

There is an explosive growth in the size of the input and/or intermediate data used and generated by modern and emerging applications. Unfortunately, modern computing systems are not capable of handling large amounts of data efficiently. Major concepts and components (e.g., the virtual memory system) and predominant execution models (e.g., the processor-centric execution model) used in almost all computing

Traditional graphics processing units (GPUs) suffer from the low memory capacity and demand for high memory bandwidth. To address these challenges, we propose Ohm-GPU, a new optical network based heterogeneous memory design for GPUs. Specifically, Ohm-GPU can expand the memory capacity by combing a set of high-density 3D XPoint and DRAM modules as heterogeneous memory. To prevent memory channels from

Aerial autonomous machines (Drones) has a plethora of promising applications and use cases. While the popularity of these autonomous machines continues to grow, there are many challenges, such as endurance and agility, that could hinder the practical deployment of these machines. The closed-loop control frequency must be high to achieve high agility. However, given the resource-constrained nature of

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

Machine learning algorithms have enabled computers to predict things by learning from previous data. The data storage and processing power are increasing rapidly, thus increasing machine learning and Artificial intelligence applications. Much of the work is done to improve the accuracy of the models built in the past, with little research done to determine the computational costs of machine learning

The recent breakthroughs of deep neural networks (DNNs) and the advent of billions of Internet of Things (IoT) devices have excited an explosive demand for intelligent IoT devices equipped with domain-specific DNN accelerators. However, the deployment of DNN accelerator enabled intelligent functionality into real-world IoT devices still remains particularly challenging. First, powerful DNNs often come

In this paper, we propose a practical and effective approach allowing designers to optimize multi-level cache size at the early system design phase. Our key contribution is to generalize the reuse distance analysis method and develop an effective and practical cache design optimization approach. We adopt a simple scanning search method to locate optimal cache solutions in terms of cache size, power

Deep Neural Networks (DNNs), as a subset of Machine Learning (ML) techniques, entail that real-world data can be learned and that decisions can be made in real-time. However, their wide adoption is hindered by a number of software and hardware limitations. The existing general-purpose hardware platforms used to accelerate DNNs are facing new challenges associated with the growing amount of data and

Sparse neural networks can greatly facilitate the deployment of neural networks on resource-constrained platforms as they offer compact model sizes while retaining inference accuracy. Because of the sparsity in parameter matrices, sparse neural networks can, in principle, be exploited in accelerator architectures for improved energy-efficiency and latency. However, to realize these improvements in

Quantum algorithms promise quadratic or exponential speedups for applications in cryptography, chemistry and material sciences. The topologies of today's quantum computers offer limited connectivity, leading to significant overheads for implementing such quantum algorithms. One-dimensional topology displacements that remedy these limits have been recently demonstrated for architectures based on Rydberg

In-storage computing with modern solid-state drives (SSDs) enables developers to offload programs from the host to the SSD. It has been proven to be an effective approach to alleviate the I/O bottleneck. To facilitate in-storage computing, many frameworks have been proposed. However, few of them treat the in-storage security as the first citizen. Specifically, since modern SSD controllers do not have

Traditional software development in robotics is about programming functionality in the CPU of a given robot with a pre-defined architecture and constraints. With adaptive computing, instead, building a robotic behavior is about programming an architecture. By leveraging adaptive computing, roboticists can adapt one or more of the properties of its computing systems (e.g. its determinism, power consumption

Many hardware structures in today's high-performance out-of-order processors do not scale in an efficient way. To address this, different solutions have been proposed that build execution schedules in an energy-efficient manner. Issue time prediction processors are one such solution that use data-flow dependencies and predefined instruction latencies to predict issue times of repeated instructions

We found that a second-order ideal memristor degenerates into a negative nonlinear resistor. This phenomenon is quite similar to what are observed in chemistry: a chemical element with a higher atomic number is unstable and may decay radioactively into another chemical element with a lower atomic number. After extending the above local activity to other higher-order circuit elements, we concluded that

We introduce the waveform capture device (WCD), a flexible measurement system capable of recording complex digital signals on trillionth-of-a-second (ps) time scales. The WCD is implemented via modular code on an off-the-shelf field-programmable gate-array (FPGA, Intel/Altera Cyclone V), and incorporates both time-to-digital converter (TDC) and digital storage oscilloscope (DSO) functionality. The

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

In this paper, we propose a novel memory-centric scheme based on CMOS SRAM for acceleration of data intensive applications. Our proposal aims at dynamically increasing the on-chip memory storage capacity of SRAM arrays on-demand. The proposed scheme called - Augmented Memory Computing allows an SRAM cell to operate in two different modes 1) the Normal mode and 2) the Augmented mode. In the Normal mode

Software caches optimize the performance of diverse storage systems, databases and other software systems. Existing works on software caches automatically resort to fully associative cache designs. Our work shows that limited associativity caches are a promising direction for concurrent software caches. Specifically, we demonstrate that limited associativity enables simple yet efficient realizations

Multicast is an efficient way to realize one-to-many group communications in large-scale networks such as the Internet. However, the deployment of IP multicast services over the Internet has not been as rapid as expected and needed. Excepting the fatal defects in designing IPv4 address structure. Another main reason that contributes to this slow deployment is the lack of carrier-grade multicast-enabled

Convolutional Neural Networks (CNNs) are widely used in deep learning applications, e.g. visual systems, robotics etc. However, existing software solutions are not efficient. Therefore, many hardware accelerators have been proposed optimizing performance, power and resource utilization of the implementation. Amongst existing solutions, Field Programmable Gate Array (FPGA) based architecture provides

FPGAs are increasingly common in modern applications, and cloud providers now support on-demand FPGA acceleration in data centers. Applications in data centers run on virtual infrastructure, where consolidation, multi-tenancy, and workload migration enable economies of scale that are fundamental to the provider's business. However, a general strategy for virtualizing FPGAs has yet to emerge. While

The enormous amount of code required to design modern hardware implementations often leads to critical vulnerabilities being overlooked. Especially vulnerabilities that compromise the confidentiality of sensitive data, such as cryptographic keys, have a major impact on the trustworthiness of an entire system. Information flow analysis can elaborate whether information from sensitive signals flows towards

The increasing complexity of Internet-of-Things (IoT) applications and near-sensor processing algorithms is pushing the computational power of low-power, battery-operated end-node systems. This trend also reveals growing demands for high-speed and energy-efficient inter-chip communications to manage the increasing amount of data coming from off-chip sensors and memories. While traditional micro-controller

Power efficiency is critical in high performance computing (HPC) systems. To achieve high power efficiency on application level, it is vital importance to efficiently distribute power used by application checkpoints. In this study, we analyze the relation of application checkpoints and their power consumption. The observations could guide the design of power management.

In-Memory Acceleration (IMA) promises major efficiency improvements in deep neural network (DNN) inference, but challenges remain in the integration of IMA within a digital system. We propose a heterogeneous architecture coupling 8 RISC-V cores with an IMA in a shared-memory cluster, analyzing the benefits and trade-offs of in-memory computing on the realistic use case of a MobileNetV2 bottleneck layer

Ultra-fast \& low-power superconductor single-flux-quantum (SFQ)-based CNN systolic accelerators are built to enhance the CNN inference throughput. However, shift-register (SHIFT)-based scratchpad memory (SPM) arrays prevent a SFQ CNN accelerator from exceeding 40\% of its peak throughput, due to the lack of random access capability. This paper first documents our study of a variety of cryogenic memory

Specialized accelerators have recently garnered attention as a method to reduce the power consumption of neural network inference. A promising category of accelerators utilizes nonvolatile memory arrays to both store weights and perform $\textit{in situ}$ analog computation inside the array. While prior work has explored the design space of analog accelerators to optimize performance and energy efficiency

Repeated off-chip memory accesses to DRAM drive up operating power for data-intensive applications, and SRAM technology scaling and leakage power limits the efficiency of embedded memories. Future on-chip storage will need higher density and energy efficiency, and the actively expanding field of emerging, embeddable non-volatile memory (eNVM) technologies is providing many potential candidates to satisfy

The number of parameters in deep neural networks (DNNs) is scaling at about 5$\times$ the rate of Moore's Law. To sustain the pace of growth of the DNNs, new technologies and computing architectures are needed. Photonic computing systems are promising avenues, since they can perform the dominant general matrix-matrix multiplication (GEMM) operations in DNNs at a higher throughput than their electrical

In-field test of processor-based devices is a must when considering safety-critical systems (e.g., in robotics, aerospace, and automotive applications). During in-field testing, different solutions can be adopted, depending on the specific constraints of each scenario. In the last years, Self-Test Libraries (STLs) developed by IP or semiconductor companies became widely adopted. Given the strict constraints

This work proposes a competitive scheduling approach, designed to scale to large heterogeneous multicore systems. This scheduler overcomes the challenges of (1) the high computation overhead of near-optimal schedulers, and (2) the error introduced by inaccurate performance predictions. This paper presents Agon, a neural network-based classifier that selects from a range of schedulers, from simple to

Modern processor designs use a variety of microarchitectural methods to achieve high performance. Unfortunately, new side-channels have often been uncovered that exploit these enhanced designs. One area that has received little attention from a security perspective is the processor's hard-ware prefetcher, a critical component used to mitigate DRAM latency in today's systems. Prefetchers, like branch

The widening availability of hardware-based trusted execution environments (TEEs) has been accelerating the adaptation of new applications using TEEs. Recent studies showed that a cloud application consists of multiple distributed software modules provided by mutually distrustful parties. The applications use multiple TEEs (enclaves) communicating through software-encrypted memory channels. Such execution

Processing-in-memory (PIM) seeks to eliminate computation/memory data transfer using devices that support both storage and logic. Stateful logic techniques such as IMPLY, MAGIC and FELIX can perform logic gates within memristive crossbar arrays with massive parallelism. Multiplication via stateful logic is an active field of research due to the wide implications. Recently, RIME has become the state-of-the-art

This paper describes a graph-theoretic formalism and a flow that, to a great extent, automate the design of clock trees in Sampled-Data Analog Circuits (SDACs). The current practice for clock tree design of SDACs is a manual process, which is time-consuming and error-prone. Clock tree design in digital domain, however, is fully automated and is carried out by Clock Tree Synthesis (CTS) software. In

The design of many-core neuromorphic hardware is getting more and more complex as these systems are expected to execute large machine learning models. To deal with the design complexity, a predictable design flow is needed to guarantee real-time performance such as latency and throughput without significantly increasing the buffer requirement of computing cores. Synchronous Data Flow Graphs (SDFGs)

This work presents a high throughput and energy efficient multicore (MC) successive cancellation (SC) decoder architecture for polar codes. SC is a low-complexity decoding algorithm with a set of sequential operations. The sequential processing nature of SC limits parallelism but promotes not only pipelining but also multiple copies of SC decoder with an optimized pipeline depth to achieve Tb/s throughput

Synchoros VLSI design style has been proposed as an alternative to the standard cell best design style; the word synchoros is derived from the Greek word choros for space. Synchoricity discretises space with a virtual grid, the way synchronicity discretises time with clock ticks. SiLago (Silicon Lego) blocks are atomic synchoros building blocks like Lego bricks. SiLago blocks absorb all metal layer

Large-scale graph processing has drawn great attention in recent years. Most of the modern-day datacenter workloads can be represented in the form of Graph Processing such as MapReduce etc. Consequently, a lot of designs for Domain-Specific Accelerators have been proposed for Graph Processing. Spatial Architectures have been promising in the execution of Graph Processing, where the graph is partitioned

Massively parallel systolic arrays and resource-efficient depthwise separable convolutions are two promising techniques to accelerate DNN inference on the edge. Interestingly, their combination is inefficient: Computational patterns of depthwise separable convolutions do not exhibit a rhythmic systolic flow and lack sufficient data reuse to saturate systolic arrays. We formally analyse this inefficiency

Today, Internet communication security has become more complex as technology becomes faster and more efficient, especially for resource-limited devices such as embedded devices, wireless sensors, and radio frequency identification (RFID) tags, and Internet of Things (IoT). Lightweight encryption algorithms provide security for these devices to protect data against intruders. But the limitation of using

Quantum computing is an information processing paradigm that uses quantum-mechanical properties to speedup computationally hard problems. Although promising, existing gate-based quantum computers consist of only a few dozen qubits and are not large enough for most applications. On the other hand, existing QAs with few thousand of qubits have the potential to solve some domain-specific optimization

Tiled spatial architectures have proved to be an effective solution to build large-scale DNN accelerators. In particular, interconnections between tiles are critical for high performance in these tile-based architectures. In this work, we identify the inefficiency of the widely used traditional on-chip networks and the opportunity of software-hardware co-design. We propose METRO with the basic idea

Recent years have brought microarchitectural security intothe spotlight, proving that modern CPUs are vulnerable toseveral classes of microarchitectural attacks. These attacksbypass the basic isolation primitives provided by the CPUs:process isolation, memory permissions, access checks, andso on. Nevertheless, most of the research was focused on In-tel CPUs, with only a few exceptions. As a result

Spiking neural networks (SNNs) have shown a potential for having low energy with unsupervised learning capabilities due to their biologically-inspired computation. However, they may suffer from accuracy degradation if their processing is performed under the presence of hardware-induced faults in memories, which can come from manufacturing defects or voltage-induced approximation errors. Since recent

Even with generational improvements in DRAM technology, memory access latency still remains the major bottleneck for application accelerators, primarily due to limitations in memory interface IPs which cannot fully account for variations in target applications, the algorithms used, and accelerator architectures. Since developing memory controllers for different applications is time-consuming, this

Specification mining offers a solution by automating security specification for hardware. Specification miners use a form of machine learning to specify behaviors of a system by studying a system in execution. However, specification mining was first developed for use with software. Complex hardware designs offer unique challenges for this technique. Further, specification miners traditionally capture

FPGAs are quickly becoming available in the cloud as a one more heterogeneous processing element complementing CPUs and GPUs. There are many reports in the literature showing the potential for FPGAs to accelerate a wide variety of algorithms, which combined with their growing availability, would seem to also indicate a widespread use in many applications. Unfortunately, there is not much published

Augmenting everyday surfaces with interaction sensing capability that is maintenance-free, low-cost (about $1), and in an appropriate form factor is a challenge with current technologies. MARS (Multi-channel Ambiently-powered Realtime Sensing) enables battery-free sensing and wireless communication of touch, swipe, and speech interactions by combining a nanowatt programmable oscillator with frequency-shifted

In-memory computing (IMC) on a monolithic chip for deep learning faces dramatic challenges on area, yield, and on-chip interconnection cost due to the ever-increasing model sizes. 2.5D integration or chiplet-based architectures interconnect multiple small chips (i.e., chiplets) to form a large computing system, presenting a feasible solution beyond a monolithic IMC architecture to accelerate large

3D die stacking has often been proposed to build large-scale DRAM-based caches. Unfortunately, the power and performance overheads of DRAM limit the efficiency of high-bandwidth memories. Also, DRAM is facing serious scalability challenges that make alternative technologies more appealing. This paper examines Monarch, a resistive 3D stacked memory based on a novel reconfigurable crosspoint array called

The never-ending demand for high performance and energy efficiency is pushing designers towards an increasing level of heterogeneity and specialization in modern computing systems. In such systems, creating efficient memory architectures is one of the major opportunities for optimizing modern workloads (e.g., computer vision, machine learning, graph analytics, etc.) that are extremely data-driven.

Design space exploration is an important but costly step involved in the design/deployment of custom architectures to squeeze out maximum possible performance and energy efficiency. Conventionally, optimizations require iterative sampling of the design space using simulation or heuristic tools. In this paper we investigate the possibility of learning the optimization task using machine learning and

Realizing today's cloud-level artificial intelligence functionalities directly on devices distributed at the edge of the internet calls for edge hardware capable of processing multiple modalities of sensory data (e.g. video, audio) at unprecedented energy-efficiency. AI hardware architectures today cannot meet the demand due to a fundamental "memory wall": data movement between separate compute and

Loss of every bit in traditional logic circuits involves dissipation of power in the form of heat that evolve to the environment. Reversible logic is one of the alternatives that have capabilities to mitigate this dissipation by preventing the loss of bits. It also have the potential to broaden the horizon of futuristic reckon with its applications to quantum computation. Application of testing strategies