硬件体系结构

A key challenge in scaling shared-L1 multi-core clusters towards many-core (more than 16 cores) configurations is to ensure low-latency and efficient access to the L1 memory. In this work we demonstrate that it is possible to scale up the…

On-chip memory (usually based on Static RAMs-SRAMs) are crucial components for various computing devices including heterogeneous devices, e.g., GPUs, FPGAs, ASICs to achieve high performance. Modern workloads such as Deep Neural Networks…

In this paper, we present Ara, a 64-bit vector processor based on the version 0.5 draft of RISC-V's vector extension, implemented in GlobalFoundries 22FDX FD-SOI technology. Ara's microarchitecture is scalable, as it is composed of a set of…

Exploiting sparsity underlying neural networks has become one of the most potential methodologies to reduce the memory footprint, I/O cost, and computation workloads during inference. And the degree of sparsity one can exploit has become…

In recent years, hardware accelerators based on field-programmable gate arrays (FPGAs) have been widely adopted, thanks to FPGAs' extraordinary flexibility. However, with the high flexibility comes the difficulty in design and optimization.…

Photonic Microring Resonator (MRR) based hardware accelerators have been shown to provide disruptive speedup and energy-efficiency improvements for processing deep Convolutional Neural Networks (CNNs). However, previous MRR-based CNN…

K-nearest neighbor search is one of the fundamental tasks in various applications and the hierarchical navigable small world (HNSW) has recently drawn attention in large-scale cloud services, as it easily scales up the database while…

In Carry Propagate Adders, carry propagation is the critical delay. The most efficient scheme is to generate Cout0 (Cin=0) and Cout1(Cin=1) and multiplex the correct output according to Cin. For any radix, the carry output is always 0/1. We…

The posit representation for real numbers is an alternative to the ubiquitous IEEE 754 floating-point standard. In this work, we present PERCIVAL, an application-level posit capable RISC-V core based on CVA6 that can execute all posit…

In Carry Propagate Adders, carry propagation is the critical delay. For the 1-digit adders that they use, the most efficient scheme is to generate two intermediate carries: C$_{out0}$ ($C_{in}$=0) and $C_{out1}$($C_{in}$=1). Then multiplex…

Application virtual memory footprints are growing rapidly in all systems from servers down to smartphones. To address this growing demand, system integrators are incorporating ever larger amounts of main memory, warranting rethinking of…

FPGAs are increasingly being deployed in the cloud to accelerate diverse applications. They are to be shared among multiple tenants to improve the total cost of ownership. Partial reconfiguration technology enables multi-tenancy on FPGA by…

Approximate computing is an emerging computing paradigm that offers improved power consumption by relaxing the requirement for full accuracy. Since real-world applications may have different requirements for design accuracy, one trend of…

As the machine learning and systems communities strive to achieve higher energy-efficiency through custom deep neural network (DNN) accelerators, varied precision or quantization levels, and model compression techniques, there is a need for…

The emerging memristive Memory Processing Unit (mMPU) overcomes the memory wall through memristive devices that unite storage and logic for real processing-in-memory (PIM) systems. At the core of the mMPU is stateful logic, which is…

The attention mechanisms of transformers effectively extract pertinent information from the input sequence. However, the quadratic complexity of self-attention w.r.t the sequence length incurs heavy computational and memory burdens,…

Denizens of Silicon Valley have called Moore's Law "the most important graph in human history," and economists have found that Moore's Law-powered I.T. revolution has been one of the most important sources of national productivity growth.…

The rapid updates in error-resilient applications along with their quest for high throughput have motivated designing fast approximate functional units for Field-Programmable Gate Arrays (FPGAs). Studies that proposed imprecise functional…

Graph Neural Networks (GNNs) have drawn tremendous attention due to their unique capability to extend Machine Learning (ML) approaches to applications broadly-defined as having unstructured data, especially graphs. Compared with other…

Embedded machine learning (ML) systems have now become the dominant platform for deploying ML serving tasks and are projected to become of equal importance for training ML models. With this comes the challenge of overall efficient…