相关论文: FUSE: Fusing STT-MRAM into GPUs to Alleviate Off-C…

Emerging spin-torque (ST) phenomena may lead to ultra-low-voltage, high-speed nano-magnetic switches. Such current-based-switches can be attractive for designing low swing global-interconnects, like, clocking-networks and databuses. In this…

The increasing adoption of large language models (LLMs) necessitates inference serving systems that can deliver both high throughput and low latency. Deploying LLMs with hundreds of billions of parameters on memory-constrained GPUs exposes…

As an emerging post-CMOS Field Effect Transistor, Magneto-Electric FETs (MEFETs) offer compelling design characteristics for logic and memory applications, such as high-speed switching, low power consumption, and non-volatility. In this…

The Mixture of Experts (MoE) architecture has emerged as a key technique for scaling Large Language Models by activating only a subset of experts per query. Deploying MoE on consumer-grade edge hardware, however, is constrained by limited…

Spin-Orbit Torque (SOT) Magnetic Random-Access Memory (MRAM) devices offer improved power efficiency, nonvolatility, and performance compared to static RAM, making them ideal, for instance, for cache memory applications. Efficient…

In long-context large language model (LLM) inference, the prefill stage dominates computation due to self-attention over the complete input context. Sparse attention significantly reduces self-attention computation by limiting each token's…

Rendering large-scale 3D Gaussian Splatting (3DGS) model faces significant challenges in achieving real-time, high-fidelity performance on consumer-grade devices. Fully realizing the potential of 3DGS in applications such as virtual reality…

Searches for signals at low signal-to-noise ratios frequently involve the Fast Fourier Transform (FFT). For high-throughput searches, we here consider FFT on the homogeneous mesh of Processing Elements (PEs) of a wafer-scale engine (WSE).…

In this dissertation, we propose a memory and computing coordinated methodology to thoroughly exploit the characteristics and capabilities of the GPU-based heterogeneous system to effectively optimize applications' performance and privacy.…

Scalability issue plays a crucial role in productionizing modern recommender systems. Even lightweight architectures may suffer from high computational overload due to intermediate calculations, limiting their practicality in real-world…

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…

Today's high-performance architectures are increasingly constrained by data movement latency and energy overhead, as the slowdown of single-core performance scaling coincides with the rise of highly data-intensive workloads. In-memory…

3D Gaussian Splatting (3DGS) based Simultaneous Localization and Mapping (SLAM) systems can largely benefit from 3DGS's state-of-the-art rendering efficiency and accuracy, but have not yet been adopted in resource-constrained edge devices…

As one of the most promising emerging non-volatile memory (NVM) technologies, spin-transfer torque magnetic random access memory (STT-MRAM) has attracted significant research attention due to several features such as high density, zero…

There is an urgent and pressing need to optimize usage of Graphical Processing Units (GPUs), which have arguably become one of the most expensive and sought after IT resources. To help with this goal, several of the current generation of…

Many key electronic technologies (e.g., large-scale computing, machine learning, and superconducting electronics) require new memories that are fast, reliable, energy-efficient, and of low-impedance at the same time, which has remained a…

This paper presents the Neural Cache architecture, which re-purposes cache structures to transform them into massively parallel compute units capable of running inferences for Deep Neural Networks. Techniques to do in-situ arithmetic in…

The steeply growing performance demands for highly power- and energy-constrained processing systems such as end-nodes of the internet-of-things (IoT) have led to parallel near-threshold computing (NTC), joining the energy-efficiency…

Deep learning recommendation models (DLRMs) have been widely applied in Internet companies. The embedding tables of DLRMs are too large to fit on GPU memory entirely. We propose a GPU-based software cache approaches to dynamically manage…

Graph analytics are vital in fields such as social networks, biomedical research, and graph neural networks (GNNs). However, traditional CPUs and GPUs struggle with the memory bottlenecks caused by large graph datasets and their…