arXiv subjects

Gu-Yeon Wei

Publications and source records attributed to Gu-Yeon Wei.

At least 37 records · Page 2Linked to original sources

arXiv2023

SpeedLimit: Neural Architecture Search for Quantized Transformer Models

While research in the field of transformer models has primarily focused on enhancing performance metrics such as accuracy and perplexity, practical applications in industry often necessitate a rigorous consideration of inference latency constraints. Addressing this challenge, we introduce SpeedLimit, a novel Neural Architecture Search (NAS) technique that optimizes accuracy whilst adhering to an upper-bound latency constraint. Our method incorporates 8-bit integer quantization in the search process to outperform the current state-of-the-art technique. Our results underline the feasibility and efficacy of seeking an optimal balance between performance and latency, providing new avenues for deploying state-of-the-art transformer models in latency-sensitive environments.

cs.LG↗

arXiv2023

GPU-based Private Information Retrieval for On-Device Machine Learning Inference

On-device machine learning (ML) inference can enable the use of private user data on user devices without revealing them to 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. In particular, recommendation models typically use multiple embedding tables each on the order of 1-10 GBs of data, making them impractical to store on-device. To overcome this barrier, we propose the use of private information retrieval (PIR) to efficiently and privately retrieve embeddings from servers without sharing any private information. As off-the-shelf PIR algorithms are usually too computationally intensive to directly use for latency-sensitive inference tasks, we 1) propose novel GPU-based acceleration of PIR, and 2) co-design PIR with the downstream ML application to obtain further speedup. Our GPU acceleration strategy improves system throughput by more than $20 \times$ over an optimized CPU PIR implementation, and our PIR-ML co-design provides an over $5 \times$ additional throughput improvement at fixed model quality. Together, for various on-device ML applications such as recommendation and language modeling, our system on a single V100 GPU can serve up to $100,000$ queries per second -- a $>100 \times$ throughput improvement over a CPU-based baseline -- while maintaining model accuracy.

cs.CR↗

arXiv2023

Application-Level Validation of Accelerator Designs Using a Formal Software/Hardware Interface

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, mostly automated methodology termed "3LA" to enable end-to-end testing of prototype accelerator designs on unmodified source applications. A key contribution of 3LA is the use of a formal software/hardware interface that specifies an accelerator's operations and their semantics. Specifically, we leverage the Instruction-Level Abstraction (ILA) formal specification for accelerators that has been successfully used thus far for accelerator implementation verification. We show how the ILA for accelerators serves as a software/hardware interface, similar to the Instruction Set Architecture (ISA) for processors, that can be used for automated development of compilers and instruction-level simulators. Another key contribution of this work is to show how ILA-based accelerator semantics enables extending recent work on equality saturation to auto-generate basic compiler support for prototype accelerators in a technique we term "flexible matching." By combining flexible matching with simulators auto-generated from ILA specifications, our approach enables end-to-end evaluation with modest engineering effort. We detail several case studies of 3LA, which uncovered an unknown flaw in a recently published accelerator and facilitated its fix.

cs.AR↗

arXiv2023

INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation

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 to minimize errors induced by the quantization process. Our method reduces the memory requirements by up to 5.6 times, which enables fine-tuning a 7 billion parameter Large Language Model (LLM) on consumer laptops. At the same time, we propose a Low-Rank Error Correction (LREC) method that exploits the added LoRA layers to ameliorate the gap between the quantized model and its float point counterpart. Our error correction framework leads to a fully functional INT2 quantized LLM with the capacity to generate coherent English text. To the best of our knowledge, this is the first INT2 Large Language Model that has been able to reach such a performance. The overhead of our method is merely a 1.05 times increase in model size, which translates to an effective precision of INT2.1. Also, our method readily generalizes to other quantization standards, such as INT3, INT4, and INT8, restoring their lost performance, which marks a significant milestone in the field of model quantization. The strategies delineated in this paper hold promising implications for the future development and optimization of quantized models, marking a pivotal shift in the landscape of low-resource machine learning computations.

cs.CL↗

arXiv2023

S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput

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 reserves the maximum sequence length of memory for the KV cache to guarantee generating a complete sequence as they do not know the output sequence length. This restricts us to use a smaller batch size leading to lower GPU utilization and above all, lower throughput. We argue that designing a system with a priori knowledge of the output sequence can mitigate this problem. To this end, we propose S$^{3}$, which predicts the output sequence length, schedules generation queries based on the prediction to increase device resource utilization and throughput, and handle mispredictions. Our proposed method achieves 6.49$\times$ throughput over those systems that assume the worst case for the output sequence length.

cs.AR↗

arXiv2023

Design Space Exploration and Optimization for Carbon-Efficient Extended Reality Systems

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 computing systems, there is a distinct lack of holistic design strategies to simultaneously optimize for carbon, performance, power and energy. In this work, we take a data-driven approach to characterize the carbon impact (quantified in units of CO2e) of various artificial intelligence (AI) and extended reality (XR) production-level hardware and application use-cases. We propose a holistic design exploration framework to optimize and design for carbon-efficient computing systems and hardware. Our frameworks identifies significant opportunities for carbon efficiency improvements in application-specific and general purpose hardware design and optimization. Using our framework, we demonstrate 10$\times$ carbon efficiency improvement for specialized AI and XR accelerators (quantified by a key metric, tCDP: the product of total CO2e and total application execution time), up to 21% total life cycle carbon savings for existing general-purpose hardware and applications due to hardware over-provisioning, and up to 7.86$\times$ carbon efficiency improvement using advanced 3D integration techniques for resource-constrained XR systems.

cs.AR↗

arXiv2023

MP-Rec: Hardware-Software Co-Design to Enable Multi-Path Recommendation

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 only imposes significant memory capacity and bandwidth requirements but also limits the scope of compatible system solutions. This paper challenges the assumption of fixed embedding representations by showing how synergies between embedding representations and hardware platforms can lead to improvements in both algorithmic- and system performance. Based on our characterization of various embedding representations, we propose a hybrid embedding representation that achieves higher quality embeddings at the cost of increased memory and compute requirements. To address the system performance challenges of the hybrid representation, we propose MP-Rec -- a co-design technique that exploits heterogeneity and dynamic selection of embedding representations and underlying hardware platforms. On real system hardware, we demonstrate how matching custom accelerators, i.e., GPUs, TPUs, and IPUs, with compatible embedding representations can lead to 16.65x performance speedup. Additionally, in query-serving scenarios, MP-Rec achieves 2.49x and 3.76x higher correct prediction throughput and 0.19% and 0.22% better model quality on a CPU-GPU system for the Kaggle and Terabyte datasets, respectively.

cs.AR↗

arXiv2023

MAVFI: An End-to-End Fault Analysis Framework with Anomaly Detection and Recovery for Micro Aerial Vehicles

Safety and resilience are critical for autonomous unmanned aerial vehicles (UAVs). We introduce MAVFI, the micro aerial vehicles (MAVs) resilience analysis methodology to assess the effect of silent data corruption (SDC) on UAVs' mission metrics, such as flight time and success rate, for accurately measuring system resilience. To enhance the safety and resilience of robot systems bound by size, weight, and power (SWaP), we offer two low-overhead anomaly-based SDC detection and recovery algorithms based on Gaussian statistical models and autoencoder neural networks. Our anomaly error protection techniques are validated in numerous simulated environments. We demonstrate that the autoencoder-based technique can recover up to all failure cases in our studied scenarios with a computational overhead of no more than 0.0062%. Our application-aware resilience analysis framework, MAVFI, can be utilized to comprehensively test the resilience of other Robot Operating System (ROS)-based applications and is publicly available at https://github.com/harvard-edge/MAVBench/tree/mavfi.

cs.RO↗

arXiv2023

PerfSAGE: Generalized Inference Performance Predictor for Arbitrary Deep Learning Models on Edge Devices

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 a specific hardware deployment platform. Unfortunately, these metrics are slow to evaluate using simulators (where available) and typically require measurement on the target hardware. This work describes PerfSAGE, a novel graph neural network (GNN) that predicts inference latency, energy, and memory footprint on an arbitrary DNN TFlite graph (TFL, 2017). In contrast, previously published performance predictors can only predict latency and are restricted to pre-defined construction rules or search spaces. This paper also describes the EdgeDLPerf dataset of 134,912 DNNs randomly sampled from four task search spaces and annotated with inference performance metrics from three edge hardware platforms. Using this dataset, we train PerfSAGE and provide experimental results that demonstrate state-of-the-art prediction accuracy with a Mean Absolute Percentage Error of <5% across all targets and model search spaces. These results: (1) Outperform previous state-of-art GNN-based predictors (Dudziak et al., 2020), (2) Accurately predict performance on accelerators (a shortfall of non-GNN-based predictors (Zhang et al., 2021)), and (3) Demonstrate predictions on arbitrary input graphs without modifications to the feature extractor.

cs.LG↗

arXiv2022

Architectural Implications of Embedding Dimension during GCN on CPU and GPU

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 perspective due to inherent sparsity, low data reuse, and massive memory capacity requirements. Traditional neural algorithms exploit the high compute capacity of GPUs to achieve high performance for both inference and training. The architectural decision to use a GPU for GCN inference is a question explored in this work. GCN on both CPU and GPU was characterized in order to better understand the implications of graph size, embedding dimension, and sampling on performance.

cs.LG↗

arXiv2022

Impala: Low-Latency, Communication-Efficient Private Deep Learning Inference

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 performance bottlenecks. First, we remove MPC's overwhelmingly high communication cost from the client by introducing a proxy server and developing a low-overhead key switching technique. Key switching reduces the clients bandwidth by multiple orders of magnitude, however the communication between the proxy and cloud is still excessive. Second, to we develop an optimized garbled circuit that leverages truncated secret shares for faster evaluation and less proxy-cloud communication. Finally, we propose sparse HE convolution to reduce the computational bottleneck of using HE. Compared to the state-of-the-art, these optimizations provide a bandwidth savings of over 3X and speedup of 4X for private deep learning inference.

cs.CR↗

arXiv2022

OMU: A Probabilistic 3D Occupancy Mapping Accelerator for Real-time OctoMap at the Edge

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 map model to represent the full environment, with dynamic voxel node pruning and expansion capacity. This paper presents the first efficient accelerator solution, i.e. OMU, to enable real-time probabilistic 3D mapping at the edge. To improve the performance, the input map voxels are updated via parallel PE units for data parallelism. Within each PE, the voxels are stored using a specially developed data structure in parallel memory banks. In addition, a pruning address manager is designed within each PE unit to reuse the pruned memory addresses. The proposed 3D mapping accelerator is implemented and evaluated using a commercial 12 nm technology. Compared to the ARM Cortex-A57 CPU in the Nvidia Jetson TX2 platform, the proposed accelerator achieves up to 62$\times$ performance and 708$\times$ energy efficiency improvement. Furthermore, the accelerator provides 63 FPS throughput, more than 2$\times$ higher than a real-time requirement, enabling real-time perception for 3D mapping.

cs.AR↗

arXiv2022

Trireme: Exploring Hierarchical Multi-Level Parallelism for Domain Specific Hardware Acceleration

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 opportunities for various forms of parallel execution, including loop level, task level and pipeline parallelism. To assist the design process and expose every possible level of parallelism, we present Trireme, a fully automated tool-chain that explores multiple levels of parallelism and produces domain specific accelerator designs and configurations that maximize performance, given an area budget. Experiments on demanding benchmarks from the XR domain revealed a speedup of up to 20x, as well as a speedup of up to 37x for smaller applications, compared to software-only implementations.

cs.AR↗

arXiv2022

NVMExplorer: A Framework for Cross-Stack Comparisons of Embedded Non-Volatile Memories

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 this need. Each technology proposal presents distinct trade-offs in terms of density, read, write, and reliability characteristics, and we present a comprehensive framework for navigating and quantifying these design trade-offs alongside realistic system constraints and application-level impacts. This work evaluates eNVM-based storage for a range of application and system contexts including machine learning on the edge, graph analytics, and general purpose cache hierarchy, in addition to describing a freely available (http://nvmexplorer.seas.harvard.edu/) set of tools for application experts, system designers, and device experts to better understand, compare, and quantify the next generation of embedded memory solutions.

cs.ET↗

arXiv2021

Early DSE and Automatic Generation of Coarse Grained Merged Accelerators

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 creation of high-utilization accelerators that exploit control and data flow patterns at optimal granularities is rarely successful. To address these challenges, we present AccelMerger, the first automated methodology to create coarse grained, control- and data-flow-rich, merged accelerators. AccelMerger uses sequence alignment matching to recognize similar function call-graphs and loops, and neural networks to quickly evaluate their post-HLS characteristics. It accurately identifies which functions to accelerate, and it merges accelerators to respect an area budget and to accommodate system communication characteristics like latency and bandwidth. Merging two accelerators can save as much as 99% of the area of one. The space saved is used by a globally optimal integer linear program to allocate more accelerators for increased performance. We demonstate AccelMerger's effectiveness using HLS flows without any manual effort to fine-tune the resulting designs. On FPGA-based systems, AccelMerger yields application performance improvements of up to 16.7x over software implementations, and 1.91x on average with respect to state-of-the-art early-stage design space exploration tools.

cs.AR↗

arXiv2021

Quantifying and Maximizing the Benefits of Back-End Noise Adaption on Attention-Based Speech Recognition Models

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 after identifying its importance for noise adaptation. The first encoder layer is shown to be crucial for noise adaptation, and the weights are shown to be more important than the other layers. Appreciable accuracy benefits are identified when fine-tuning on a target noisy environment from a model pretrained with noisy speech relative to fine-tuning from a model pretrained with only clean speech when tested on the target noisy environment. For this analysis, we produce our own dataset augmentation tool and it is open-sourced to encourage future efforts in exploring noise adaptation in ASR.

eess.AS↗

arXiv2021

AutoPilot: Automating SoC Design Space Exploration for SWaP Constrained Autonomous UAVs

Building domain-specific accelerators for autonomous unmanned aerial vehicles (UAVs) is challenging due to a lack of systematic methodology for designing onboard compute. Balancing a computing system for a UAV requires considering both the cyber (e.g., sensor rate, compute performance) and physical (e.g., payload weight) characteristics that affect overall performance. Iterating over the many component choices results in a combinatorial explosion of the number of possible combinations: from 10s of thousands to billions, depending on implementation details. Manually selecting combinations of these components is tedious and expensive. To navigate the {cyber-physical design space} efficiently, we introduce \emph{AutoPilot}, a framework that automates full-system UAV co-design. AutoPilot uses Bayesian optimization to navigate a large design space and automatically select a combination of autonomy algorithm and hardware accelerator while considering the cross-product effect of other cyber and physical UAV components. We show that the AutoPilot methodology consistently outperforms general-purpose hardware selections like Xavier NX and Jetson TX2, as well as dedicated hardware accelerators built for autonomous UAVs, across a range of representative scenarios (three different UAV types and three deployment environments). Designs generated by AutoPilot increase the number of missions on average by up to 2.25x, 1.62x, and 1.43x for nano, micro, and mini-UAVs respectively over baselines. Our work demonstrates the need for holistic full-UAV co-design to achieve maximum overall UAV performance and the need for automated flows to simplify the design process for autonomous cyber-physical systems.

cs.RO↗

arXiv2021

EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference

Transformer-based language models such as BERT provide significant accuracy improvement for 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 algorithm-hardware co-design for latency-aware energy optimization for multi-task NLP. EdgeBERT employs entropy-based early exit predication in order to perform dynamic voltage-frequency scaling (DVFS), at a sentence granularity, for minimal energy consumption while adhering to a prescribed target latency. Computation and memory footprint overheads are further alleviated by employing a calibrated combination of adaptive attention span, selective network pruning, and floating-point quantization. Furthermore, in order to maximize the synergistic benefits of these algorithms in always-on and intermediate edge computing settings, we specialize a 12nm scalable hardware accelerator system, integrating a fast-switching low-dropout voltage regulator (LDO), an all-digital phase-locked loop (ADPLL), as well as, high-density embedded non-volatile memories (eNVMs) wherein the sparse floating-point bit encodings of the shared multi-task parameters are carefully stored. Altogether, latency-aware multi-task NLP inference acceleration on the EdgeBERT hardware system generates up to 7x, 2.5x, and 53x lower energy compared to the conventional inference without early stopping, the latency-unbounded early exit approach, and CUDA adaptations on an Nvidia Jetson Tegra X2 mobile GPU, respectively.

cs.AR↗