Gu-Yeon Wei

Harvard University | Harvard · School of Engineering and Applied Sciences

Deploying LLMs on edge devices presents serious technical challenges. Memory elasticity is crucial for edge devices with unified memory, where memory is shared and fluctuates dynamically. Existing solutions suffer from either poor transition granularity or high storage costs. We propose FlexQuant, a novel elasticity framework that generates an ense...

Computing is at a moment of profound opportunity. Emerging applications -- such as capable artificial intelligence, immersive virtual realities, and pervasive sensor systems -- drive unprecedented demand for computer. Despite recent advances toward net zero carbon emissions, the computing industry's gross energy usage continues to rise at an alarmi...

Ideally, accelerator development should be as easy as software development. Several recent design languages/tools are working toward this goal, but actually testing early designs on real applications end-to-end remains prohibitively difficult due to the costs of building specialized compiler and simulator support. We propose a new first-in-class, m...

We present SoCProbe, a novel debug unit that enables compositional post-silicon validation of heterogeneous SoCs, particularly those featuring tiles connected by a NoC. SoCProbe, which is instantiated between each NoC router and its corresponding tile, is connected directly to the test environment with a lightweight 4-pin interface. It supports two...

Given the performance and efficiency optimizations realized by the computer systems and architecture community over the last decades, the dominating source of computing’s carbon footprint is shifting from operational emissions to embodied emissions. These embodied emissions are attributable to hardware manufacturing and infrastructure-related activ...

The Abisko project aims to develop an energy-efficient spiking neural network (SNN) computing architecture and software system capable of autonomous learning and operation. The SNN architecture explores novel neuromorphic devices that are based on resistive-switching materials, such as memristors and electrochemical RAM. Equally important, Abisko u...

We introduce a method that dramatically reduces fine-tuning VRAM requirements and rectifies quantization errors in quantized Large Language Models. First, we develop an extremely memory-efficient fine-tuning (EMEF) method for quantized models using Low-Rank Adaptation (LoRA), and drawing upon it, we construct an error-correcting algorithm designed...

Generating texts with a large language model (LLM) consumes massive amounts of memory. Apart from the already-large model parameters, the key/value (KV) cache that holds information about previous tokens in a sequence can grow to be even larger than the model itself. This problem is exacerbated in one of the current LLM serving frameworks which res...

The emergence of the Internet of Things (IoT) has resulted in a remarkable amount of data generated on edge devices, which are often processed using AI algorithms. On-device learning enables edge platforms to continually adapt the AI models to user personal data and further allows for a better service quality. However, AI training on resource-limit...

As computing hardware becomes more specialized, designing environmentally sustainable computing systems requires accounting for both hardware and software parameters. Our goal is to design low carbon computing systems while maintaining a competitive level of performance and operational efficiency. Despite previous carbon modeling efforts for comput...

We propose a new algorithm for training neural networks with binary activations and multi-level weights, which enables efficient processing-in-memory circuits with embedded nonvolatile memories (eNVM). Binary activations obviate costly DACs and ADCs. Multi-level weights leverage multi-level eNVM cells. Compared to existing algorithms, our method no...

Deep learning recommendation systems serve personalized content under diverse tail-latency targets and input-query loads. In order to do so, state-of-the-art recommendation models rely on terabyte-scale embedding tables to learn user preferences over large bodies of contents. The reliance on a fixed embedding representation of embedding tables not...

The ability to accurately predict deep neural network (DNN) inference performance metrics, such as latency, power, and memory footprint, for an arbitrary DNN on a target hardware platform is essential to the design of DNN based models. This ability is critical for the (manual or automatic) design, optimization, and deployment of practical DNNs for...

On-device machine learning (ML) inference can enable the use of private user data on user devices without remote servers. However, a pure on-device solution to private ML inference is impractical for many applications that rely on embedding tables that are too large to be stored on-device. To overcome this barrier, we propose the use of private inf...

The design of heterogeneous systems that include domain specific accelerators is a challenging and time-consuming process. While taking into account area constraints, designers must decide which parts of an application to accelerate in hardware and which to leave in software. Moreover, applications in domains such as Extended Reality (XR) offer opp...

Safety and resiliency are essential components of autonomous vehicles. In this research, we introduce ROSFI, the first robot operating system (ROS) resilience analysis methodology, to assess the effect of silent data corruption (SDC) on mission metrics. We use unmanned aerial vehicles (UAVs) as a case study to demonstrate that system-level paramete...

Graph Neural Networks (GNNs) are a class of neural networks designed to extract information from the graphical structure of data. Graph Convolutional Networks (GCNs) are a widely used type of GNN for transductive graph learning problems which apply convolution to learn information from graphs. GCN is a challenging algorithm from an architecture per...

Post-Moore’s law area-constrained systems rely on accelerators to deliver performance enhancements. Coarse-grained accelerators can offer substantial domain acceleration, but manual, ad-hoc identification of code to accelerate is prohibitively expensive. Because cycle-accurate simulators and high-level synthesis (HLS) flows are so time-consuming, t...

As the sizes and variety of training data scale over time, data prepro- cessing is becoming an important performance bottleneck for train- ing deep recommendation systems. This challenge becomes more serious when training data is stored in Solid-State Drives (SSDs). Due to the access behavior gap between recommendation systems and SSDs, unused trai...

The proliferation of personal artificial intelligence (AI) -assistant technologies with speech-based conversational AI interfaces is driving the exponential growth in the consumer Internet of Things (IoT) market. As these technologies are being applied to keyword spotting (KWS), automatic speech recognition (ASR), natural language processing (NLP),...

Systems performing scientific computing, data analysis, and machine learning tasks have a growing demand for application-specific accelerators that can provide high computational performance while meeting strict size and power requirements. However, the algorithms and applications that need to be accelerated are evolving at a rate that is incompati...

This paper proposes Impala, a new cryptographic protocol for private inference in the client-cloud setting. Impala builds upon recent solutions that combine the complementary strengths of homomorphic encryption (HE) and secure multi-party computation (MPC). A series of protocol optimizations are developed to reduce both communication and performanc...

Autonomous machines (e.g., vehicles, mobile robots, drones) require sophisticated 3D mapping to perceive the dynamic environment. However, maintaining a real-time 3D map is expensive both in terms of compute and memory requirements, especially for resource-constrained edge machines. Probabilistic OctoMap is a reliable and memory-efficient 3D dense...

Given recent algorithm, software, and hardware innovation, computing has enabled a plethora of new applications. As computing becomes increasingly ubiquitous, however, so does its environmental impact. This paper brings the issue to the attention of computer-systems researchers. Our analysis, built on industry-reported characterization, quantifies...

Multiparty computation approaches to secure neural network inference traditionally rely on garbled circuits for securely executing nonlinear activation functions. However, garbled circuits require excessive communication between server and client, impose significant storage overheads, and incur large runtime penalties. To eliminate these costs, we...

Specialized accelerators are increasingly used to meet the power-performance goals of emerging applications such as machine learning, image processing, and graph analysis. Existing accelerator programming methodologies using APIs have several limitations: (1) The application code lacks portability to other platforms and compiler frameworks; (2) the...

The design of heterogeneous systems that include domain specific accelerators is a challenging and time-consuming process. While taking into account area constraints, designers must decide which parts of an application to accelerate in hardware and which to leave in software. Moreover, applications in domains such as Extended Reality (XR) offer opp...

Edge systems are required to autonomously make real-time decisions based on large quantities of input data under strict power, performance, area, and other constraints. Meeting these constraints is only possible by specializing systems through hardware accelerators purposefully built for machine learning and data analysis algorithms. However, data...

Post-Moore's law area-constrained systems rely on accelerators to deliver performance enhancements. Coarse grained accelerators can offer substantial domain acceleration, but manual, ad-hoc identification of code to accelerate is prohibitively expensive. Because cycle-accurate simulators and high-level synthesis flows are so time-consuming, manual...

Emerging Internet of Things (IoT) devices necessitate system-on-chips (SoCs) that can scale from ultralow power always-on (AON) operation, all the way up to less frequent high-performance tasks at high energy efficiency. Specialized accelerators are essential to help meet these needs at both ends of the scale, but maintaining workload flexibility r...

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) techn...

The memory wall bottleneck is a key challenge across many data-intensive applications. Multi-level FeFET-based embedded non-volatile memories are a promising solution for denser and more energy-efficient on-chip memory. However, reliable multi-level cell storage requires careful optimizations to minimize the design overhead costs. In this work, we...

We show that aggregated model updates in federated learning may be insecure. An untrusted central server may disaggregate user updates from sums of updates across participants given repeated observations, enabling the server to recover privileged information about individual users' private training data via traditional gradient inference attacks. O...

Reliability and safety are critical in autonomous machine services, such as autonomous vehicles and aerial drones. In this paper, we first present an open-source Micro Aerial Vehicles (MAVs) reliability analysis framework, MAVFI, to characterize transient fault's impacts on the end-to-end flight metrics, e.g., flight time, success rate. Based on ou...

Silicon ferroelectric field-effect transistors (FeFETs) with low-k interfacial layer (IL) between ferroelectric gate stack and silicon channel suffers from high write voltage, limited write endurance and large read-after-write latency due to early IL breakdown and charge trapping and detrapping at the interface. We demonstrate low voltage, high spe...

Deep learning recommendation systems must provide high quality, personalized content under strict tail-latency targets and high system loads. This paper presents RecPipe, a system to jointly optimize recommendation quality and inference performance. Central to RecPipe is decomposing recommendation models into multi-stage pipelines to maintain quali...

This work analyzes how attention-based Bidirectional Long Short-Term Memory (BLSTM) models adapt to noise-augmented speech. We identify crucial components for noise adaptation in BLSTM models by freezing model components during fine-tuning. We first freeze larger model subnetworks and then pursue a fine-grained freezing approach in the encoder afte...

Building domain-specific architectures for autonomous aerial robots is challenging due to a lack of systematic methodology for designing onboard compute. We introduce a novel performance model called the F-1 roofline to help architects understand how to build a balanced computing system for autonomous aerial robots considering both its cyber (senso...

Neural personalized recommendation models are used across a wide variety of datacenter applications including search, social media, and entertainment. State-of-the-art models comprise large embedding tables that have billions of parameters requiring large memory capacities. Unfortunately, large and fast DRAM-based memories levy high infrastructure...

Transformer-based language models such as BERT provide significant accuracy improvement to a multitude of natural language processing (NLP) tasks. However, their hefty computational and memory demands make them challenging to deploy to resource-constrained edge platforms with strict latency requirements. We present EdgeBERT an in-depth and principl...

In recent years, there has been tremendous advances in hardware acceleration of deep neural networks. However, most of the research has focused on optimizing accelerator microarchitecture for higher performance and energy efficiency on a per-layer basis. We find that for overall single-batch inference latency, the accelerator may only make up 25-40...

Given recent algorithm, software, and hardware innovation, computing has enabled a plethora of new applications. As computing becomes increasingly ubiquitous, however, so does its environmental impact. This paper brings the issue to the attention of computer-systems researchers. Our analysis, built on industry-reported characterization, quantifies...

Deep learning based recommendation systems form the backbone of most personalized cloud services. Though the computer architecture community has recently started to take notice of deep recommendation inference, the resulting solutions have taken wildly different approaches - ranging from near memory processing to at-scale optimizations. To better d...