Related papers: Bare-Metal RISC-V + NVDLA SoC for Efficient Deep L…

The RISC-V "V" extension introduces vector processing to the RISC-V architecture. Unlike most SIMD extensions, it supports long vectors which can result in significant improvement of multiple applications. In this paper, we present our…

Deployment of modern TinyML tasks on small battery-constrained IoT devices requires high computational energy efficiency. Analog In-Memory Computing (IMC) using non-volatile memory (NVM) promises major efficiency improvements in deep neural…

IoT applications are one of the driving forces in making systems energy and power-efficient, given their resource constraints. However, because of security, latency, and transmission, we advocate for local computing through multi-processor…

Recent years have witnessed impressive progress in super-resolution (SR) processing. However, its real-time inference requirement sets a challenge not only for the model design but also for the on-chip implementation. In this paper, we…

Deploying deep neural networks (DNNs) on resource-constrained IoT devices remains a challenging problem, often requiring hardware modifications tailored to individual AI models. Existing accelerator-generation tools, such as AMD's FINN, do…

Edge devices like Nvidia Jetson platforms now offer several on-board accelerators -- including GPU CUDA cores, Tensor Cores, and Deep Learning Accelerators (DLA) -- which can be concurrently exploited to boost deep neural network (DNN)…

In this paper, we propose StruM, a novel structured mixed-precision-based deep learning inference method, co-designed with its associated hardware accelerator (DPU), to address the escalating computational and memory demands of deep…

This paper focuses on the simulation of multi-die System-on-Chip (SoC) architectures using VisualSim, emphasizing chiplet-based system modeling and performance analysis. Chiplet technology presents a promising alternative to traditional…

RAPID-LLM is a unified performance modeling framework for large language model (LLM) training and inference on GPU clusters. It couples a DeepFlow-based frontend that generates hardware-aware, operator-level Chakra execution traces from an…

Large Language Model (LLM) inference requires substantial computational resources, yet CPU-based inference remains essential for democratizing AI due to the widespread availability of CPUs compared to specialized accelerators. However,…

Convolutional Neural Networks (CNNs) are rapidly gaining popularity in varied fields. Due to their increasingly deep and computationally heavy structures, it is difficult to deploy them on energy constrained mobile applications. Hardware…

The rapid growth of deep neural network (DNN) workloads has significantly increased the demand for large-capacity on-chip SRAM in machine learning (ML) applications, with SRAM arrays now occupying a substantial fraction of the total die…

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…

The evolution of 5G and the emergence of 6G wireless communication systems impose higher demands for computing capabilities and lower power consumption in the front-end and processing circuitry. Furthermore, the incorporation of Artificial…

It is a challenging task to deploy computationally and memory intensive State-of-the-art deep neural networks (DNNs) on embedded systems with limited hardware resources and power budgets. Recently developed techniques like Deep Compression…

As the increasing complexity of Neural Network(NN) models leads to high demands for computation, AMD introduces a heterogeneous programmable system-on-chip (SoC), i.e., Versal ACAP architectures featured with programmable logic (PL), CPUs,…

Deep Recommender Models (DLRMs) inference is a fundamental AI workload accounting for more than 79% of the total AI workload in Meta's data centers. DLRMs' performance bottleneck is found in the embedding layers, which perform many random…

CPU-based inference can be an alternative to off-chip accelerators, and vector architectures are a promising option due to their efficiency. However, the large design space of convolutional algorithms and hardware implementations makes it…

Embedded heterogeneous systems-on-chip (SoCs) rely on domain-specific hardware accelerators to improve performance and energy efficiency. In particular, programmable multi-core accelerators feature a cluster of processing elements and…

Neural Networks (NNs) have been widely adopted due to their outstanding efficacy and adaptability across computer vision and deep learning applications. The optimization of NNs is necessary to enable their deployment on energy constrained…