Steven J. E. Wilton

Behnam Ghavami, Mohammad Shahidzadeh, Lesley Shannon et al.

Low-precision weights and activations in deep neural networks (DNNs) outperform their full-precision counterparts in terms of hardware efficiency. When implemented with low-precision operations, specifically in the extreme case where network parameters are binarized (i.e. BNNs), the two most frequently mentioned benefits of quantization are reduced memory consumption and a faster inference process. In this paper, we introduce a third advantage of very low-precision neural networks: improved fault-tolerance attribute. We investigate the impact of memory faults on state-of-the-art binary neural networks (BNNs) through comprehensive analysis. Despite the inclusion of floating-point parameters in BNN architectures to improve accuracy, our findings reveal that BNNs are highly sensitive to deviations in these parameters caused by memory faults. In light of this crucial finding, we propose a technique to improve BNN dependability by restricting the range of float parameters through a novel deliberately uniform quantization. The introduced quantization technique results in a reduction in the proportion of floating-point parameters utilized in the BNN, without incurring any additional computational overheads during the inference stage. The extensive experimental fault simulation on the proposed BNN architecture (i.e. ZOBNN) reveal a remarkable 5X enhancement in robustness compared to conventional floating-point DNN. Notably, this improvement is achieved without incurring any computational overhead. Crucially, this enhancement comes without computational overhead. \ToolName~excels in critical edge applications characterized by limited computational resources, prioritizing both dependability and real-time performance.

Daniel H. Noronha, Bahar Salehpour, Steven J. E. Wilton

Recent work has shown that Field-Programmable Gate Arrays (FPGAs) play an important role in the acceleration of Machine Learning applications. Initial specification of machine learning applications are often done using a high-level Python-oriented framework such as Tensorflow, followed by a manual translation to either C or RTL for synthesis using vendor tools. This manual translation step is time-consuming and requires expertise that limit the applicability of FPGAs in this important domain. In this paper, we present an open-source tool-flow that maps numerical computation models written in Tensorflow to synthesizable hardware. Unlike other tools, which are often constrained by a small number of inflexible templates, our flow uses Google's XLA compiler which emits LLVM code directly from a Tensorflow specification. This LLVM code can then be used with a high-level synthesis tool to automatically generate hardware. We show that our flow allows users to generate Deep Neural Networks with very few lines of Python code.

Mohammad Shahidzadeh, Behnam Ghavami, Steve Wilton et al.

Formal Property Verification (FPV), using SystemVerilog Assertions (SVA), is crucial for ensuring the completeness of design with respect to the specification. However, writing SVA is a laborious task and has a steep learning curve. In this work, we present a large language model (LLM) -based flow to automatically generate high-quality SVA from the design specification documents, named \ToolName. We introduce a novel sub-task-focused fine-tuning approach that effectively addresses functionally incorrect assertions produced by baseline LLMs, leading to a remarkable 7.3-fold increase in the number of functionally correct assertions. Recognizing the prevalence of syntax and semantic errors, we also developed an iterative refinement method that enhances the LLM's initial outputs by systematically re-prompting it to correct identified issues. This process is further strengthened by a custom compiler that generates meaningful error messages, guiding the LLM towards improved accuracy. The experiments demonstrate a 26\% increase in the number of assertions free from syntax errors using this approach, showcasing its potential to streamline the FPV process.

Nikhil P Ghanathe, Steven J E Wilton

Uncertainty quantification (UQ) provides a resource-efficient solution for on-device monitoring of tinyML models deployed without access to true labels. However, existing UQ methods impose significant memory and compute demands, making them impractical for ultra-low-power, KB-sized TinyML devices. Prior work has attempted to reduce overhead by using early-exit ensembles to quantify uncertainty in a single forward pass, but these approaches still carry prohibitive costs. To address this, we propose QUTE, a novel resource-efficient early-exit-assisted ensemble architecture optimized for tinyML models. QUTE introduces additional output blocks at the final exit of the base network, distilling early-exit knowledge into these blocks to form a diverse yet lightweight ensemble. We show that QUTE delivers superior uncertainty quality on tiny models, achieving comparable performance on larger models with 59% smaller model sizes than the closest prior work. When deployed on a microcontroller, QUTE demonstrates a 31% reduction in latency on average. In addition, we show that QUTE excels at detecting accuracy-drop events, outperforming all prior works.

Nikhil P Ghanathe, Steven J E Wilton

TinyML models often operate in remote, dynamic environments without cloud connectivity, making them prone to failures. Ensuring reliability in such scenarios requires not only detecting model failures but also identifying their root causes. However, transient failures, privacy concerns, and the safety-critical nature of many applications-where systems cannot be interrupted for debugging-complicate the use of raw sensor data for offline analysis. We propose DEBUG-HD, a novel, resource-efficient on-device debugging approach optimized for KB-sized tinyML devices that utilizes hyper-dimensional computing (HDC). Our method introduces a new HDC encoding technique that leverages conventional neural networks, allowing DEBUG-HD to outperform prior binary HDC methods by 27% on average in detecting input corruptions across various image and audio datasets.

Behnam Ghavami, Amin Kamjoo, Lesley Shannon et al.

The imperative to deploy Deep Neural Network (DNN) models on resource-constrained edge devices, spurred by privacy concerns, has become increasingly apparent. To facilitate the transition from cloud to edge computing, this paper introduces a technique that effectively reduces the memory footprint of DNNs, accommodating the limitations of resource-constrained edge devices while preserving model accuracy. Our proposed technique, named Post-Training Intra-Layer Multi-Precision Quantization (PTILMPQ), employs a post-training quantization approach, eliminating the need for extensive training data. By estimating the importance of layers and channels within the network, the proposed method enables precise bit allocation throughout the quantization process. Experimental results demonstrate that PTILMPQ offers a promising solution for deploying DNNs on edge devices with restricted memory resources. For instance, in the case of ResNet50, it achieves an accuracy of 74.57\% with a memory footprint of 9.5 MB, representing a 25.49\% reduction compared to previous similar methods, with only a minor 1.08\% decrease in accuracy.

Nikhil Pratap Ghanathe, Vivek Seshadri, Rahul Sharma et al.

Recent breakthroughs in ML have produced new classes of models that allow ML inference to run directly on milliwatt-powered IoT devices. On one hand, existing ML-to-FPGA compilers are designed for deep neural-networks on large FPGAs. On the other hand, general-purpose HLS tools fail to exploit properties specific to ML inference, thereby resulting in suboptimal performance. We propose MAFIA, a tool to compile ML inference on small form-factor FPGAs for IoT applications. MAFIA provides native support for linear algebra operations and can express a variety of ML algorithms, including state-of-the-art models. We show that MAFIA-generated programs outperform best-performing variant of a commercial HLS compiler by 2.5x on average.

Jeffrey Goeders, Steven J. E. Wilton

High-Level Synthesis (HLS) is emerging as a mainstream design methodology, allowing software designers to enjoy the benefits of a hardware implementation. Significant work has led to effective compilers that produce high-quality hardware designs from software specifications. However, in order to fully benefit from the promise of HLS, a complete ecosystem that provides the ability to analyze, debug, and optimize designs is essential. This ecosystem has to be accessible to software designers. This is challenging, since software developers view their designs very differently than how they are physically implemented on-chip. Rather than individual sequential lines of code, the implementation consists of gates operating in parallel across multiple clock cycles. In this paper, we report on our efforts to create an ecosystem that allows software designers to debug HLS-generated circuits in a familiar manner. We have implemented our ideas in a debug framework that will be included in the next release of the popular LegUp high-level synthesis tool.