DQA: An Efficient Method for Deep Quantization of Deep Neural Network Activations

Quantization of Deep Neural Network (DNN) activations is a commonly used technique to reduce compute and memory demands during DNN inference, which can be particularly beneficial on resource-constrained devices. To achieve high accuracy, existing methods for quantizing activations rely on complex mathematical computations or perform extensive searches for the best hyper-parameters. However, these expensive operations are impractical on devices with limited computation capabilities, memory capacities, and energy budgets. Furthermore, many existing methods do not focus on sub-6-bit (or deep) quantization. To fill these gaps, in this paper we propose DQA (Deep Quantization of DNN Activations), a new method that focuses on sub-6-bit quantization of activations and leverages simple shifting-based operations and Huffman coding to be efficient and achieve high accuracy. We evaluate DQA with 3, 4, and 5-bit quantization levels and three different DNN models for two different tasks, image classification and image segmentation, on two different datasets. DQA shows significantly better accuracy (up to 29.28%) compared to the direct quantization method and the state-of-the-art NoisyQuant for sub-6-bit quantization.

Accelerating PoT Quantization on Edge Devices

Non-uniform quantization, such as power-of-two (PoT) quantization, matches data distributions better than uniform quantization, which reduces the quantization error of Deep Neural Networks (DNNs). PoT quantization also allows bit-shift operations to replace multiplications, but there are limited studies on the efficiency of shift-based accelerators for PoT quantization. Furthermore, existing pipelines for accelerating PoT-quantized DNNs on edge devices are not open-source. In this paper, we first design shift-based processing elements (shift-PE) for different PoT quantization methods and evaluate their efficiency using synthetic benchmarks. Then we design a shift-based accelerator using our most efficient shift-PE and propose PoTAcc, an open-source pipeline for end-to-end acceleration of PoT-quantized DNNs on resource-constrained edge devices. Using PoTAcc, we evaluate the performance of our shift-based accelerator across three DNNs. On average, it achieves a 1.23x speedup and 1.24x energy reduction compared to a multiplier-based accelerator, and a 2.46x speedup and 1.83x energy reduction compared to CPU-only execution. Our code is available at https://github.com/gicLAB/PoTAcc

Designing Efficient LLM Accelerators for Edge Devices

The increase in open-source availability of Large Language Models (LLMs) has enabled users to deploy them on more and more resource-constrained edge devices to reduce reliance on network connections and provide more privacy. However, the high computation and memory demands of LLMs make their execution on resource-constrained edge devices challenging and inefficient. To address this issue, designing new and efficient edge accelerators for LLM inference is crucial. FPGA-based accelerators are ideal for LLM acceleration due to their reconfigurability, as they enable model-specific optimizations and higher performance per watt. However, creating and integrating FPGA-based accelerators for LLMs (particularly on edge devices) has proven challenging, mainly due to the limited hardware design flows for LLMs in existing FPGA platforms. To tackle this issue, in this paper we first propose a new design platform, named SECDA-LLM, that utilizes the SECDA methodology to streamline the process of designing, integrating, and deploying efficient FPGA-based LLM accelerators for the llama.cpp inference framework. We then demonstrate, through a case study, the potential benefits of SECDA-LLM by creating a new MatMul accelerator that supports block floating point quantized operations for LLMs. Our initial accelerator design, deployed on the PYNQ-Z1 board, reduces latency 1.7 seconds per token or ~2 seconds per word) by 11x over the dual-core Arm NEON-based CPU execution for the TinyLlama model.

Fix-Con: Automatic Fault Localization and Repair of Deep Learning Model Conversions

Converting deep learning models between frameworks is a common step to maximize model compatibility across devices and leverage optimization features that may be exclusively provided in one deep learning framework. However, this conversion process may be riddled with bugs, making the converted models either undeployable or problematic, considerably degrading their prediction correctness. We propose an automated approach for fault localization and repair, Fix-Con, during model conversion between deep learning frameworks. Fix-Con is capable of detecting and fixing faults introduced in model input, parameters, hyperparameters, and the model graph during conversion. Fix-Con uses a set of fault types mined from surveying conversion issues raised to localize potential conversion faults in the converted target model, and then repairs them appropriately, e.g. replacing the parameters of the target model with those from the source model. This is done iteratively for every image in the dataset with output label differences between the source model and the converted target model until all differences are resolved. We evaluate the effectiveness of Fix-Con in fixing model conversion bugs of three widely used image recognition models converted across four different deep learning frameworks. Overall, Fix-Con was able to either completely repair, or significantly improve the performance of 14 out of the 15 erroneous conversion cases.

DLAS: An Exploration and Assessment of the Deep Learning Acceleration Stack

Deep Neural Networks (DNNs) are extremely computationally demanding, which presents a large barrier to their deployment on resource-constrained devices. Since such devices are where many emerging deep learning applications lie (e.g., drones, vision-based medical technology), significant bodies of work from both the machine learning and systems communities have attempted to provide optimizations to accelerate DNNs. To help unify these two perspectives, in this paper we combine machine learning and systems techniques within the Deep Learning Acceleration Stack (DLAS), and demonstrate how these layers can be tightly dependent on each other with an across-stack perturbation study. We evaluate the impact on accuracy and inference time when varying different parameters of DLAS across two datasets, seven popular DNN architectures, four DNN compression techniques, three algorithmic primitives with sparse and dense variants, untuned and auto-scheduled code generation, and four hardware platforms. Our evaluation highlights how perturbations across DLAS parameters can cause significant variation and across-stack interactions. The highest level observation from our evaluation is that the model size, accuracy, and inference time are not guaranteed to be correlated. Overall we make 13 key observations, including that speedups provided by compression techniques are very hardware dependent, and that compiler auto-tuning can significantly alter what the best algorithm to use for a given configuration is. With DLAS, we aim to provide a reference framework to aid machine learning and systems practitioners in reasoning about the context in which their respective DNN acceleration solutions exist in. With our evaluation strongly motivating the need for co-design, we believe that DLAS can be a valuable concept for exploring the next generation of co-designed accelerated deep learning solutions.

MutateNN: Mutation Testing of Image Recognition Models Deployed on Hardware Accelerators

With the research advancement of Artificial Intelligence in the last years, there are new opportunities to mitigate real-world problems and advance technologically. Image recognition models in particular, are assigned with perception tasks to mitigate complex real-world challenges and lead to new solutions. Furthermore, the computational complexity and demand for resources of such models has also increased. To mitigate this, model optimization and hardware acceleration has come into play, but effectively integrating such concepts is a challenging and error-prone process. In order to allow developers and researchers to explore the robustness of deep learning image recognition models deployed on different hardware acceleration devices, we propose MutateNN, a tool that provides mutation testing and analysis capabilities for that purpose. To showcase its capabilities, we utilized 21 mutations for 7 widely-known pre-trained deep neural network models. We deployed our mutants on 4 different devices of varying computational capabilities and observed discrepancies in mutants related to conditional operations, as well as some unstable behaviour with those related to arithmetic types.

Fault Localization for Framework Conversions of Image Recognition Models

When deploying Deep Neural Networks (DNNs), developers often convert models from one deep learning framework to another (e.g., TensorFlow to PyTorch). However, this process is error-prone and can impact target model accuracy. To identify the extent of such impact, we perform and briefly present a differential analysis against three DNNs used for image recognition (MobileNetV2, ResNet101, and InceptionV3), converted across four well-known deep learning frameworks (PyTorch, Keras, TensorFlow (TF), and TFLite), which revealed numerous model crashes and output label discrepancies of up to 100%. To mitigate such errors, we present a novel approach towards fault localization and repair of buggy deep learning framework conversions, focusing on pre-trained image recognition models. Our technique consists of four primary stages of analysis: 1) conversion tools, 2) model parameters, 3) model hyperparameters, and 4) graph representation. In addition, we propose a number of strategies towards fault repair of the faults detected. We implement our technique on top of Apache TVM deep learning compiler, and we test it by conducting a preliminary fault localization analysis for the conversion of InceptionV3, from TF to TFLite. Our approach detected that the tf2onnx tool used in the conversion process introduced precision errors to model weights for convolutional layers in particular, which negatively affected the model accuracy. We then repaired the target model by replacing the affected weights with those from source model.

A Differential Testing Framework to Evaluate Image Recognition Model Robustness

Image recognition tasks typically use deep learning and require enormous processing power, thus relying on hardware accelerators like GPUs and TPUs for fast, timely processing. Failure in real-time image recognition tasks can occur due to sub-optimal mapping on hardware accelerators during model deployment, which may lead to timing uncertainty and erroneous behavior. Mapping on hardware accelerators is done through multiple software components like deep learning frameworks, compilers, device libraries, that we refer to as the computational environment. Owing to the increased use of image recognition tasks in safety-critical applications like autonomous driving and medical imaging, it is imperative to assess their robustness to changes in the computational environment, as the impact of parameters like deep learning frameworks, compiler optimizations, and hardware devices on model performance and correctness is not well understood. In this paper we present a differential testing framework, which allows deep learning model variant generation, execution, differential analysis and testing for a number of computational environment parameters. Using our framework, we conduct an empirical study of robustness analysis of three popular image recognition models using the ImageNet dataset, assessing the impact of changing deep learning frameworks, compiler optimizations, and hardware devices. We report the impact in terms of misclassifications and inference time differences across different settings. In total, we observed up to 72% output label differences across deep learning frameworks, and up to 82% unexpected performance degradation in terms of inference time, when applying compiler optimizations. Using the analysis tools in our framework, we also perform fault analysis to understand the reasons for the observed differences.

Improving Robustness Against Adversarial Attacks with Deeply Quantized Neural Networks

Reducing the memory footprint of Machine Learning (ML) models, particularly Deep Neural Networks (DNNs), is essential to enable their deployment into resource-constrained tiny devices. However, a disadvantage of DNN models is their vulnerability to adversarial attacks, as they can be fooled by adding slight perturbations to the inputs. Therefore, the challenge is how to create accurate, robust, and tiny DNN models deployable on resource-constrained embedded devices. This paper reports the results of devising a tiny DNN model, robust to adversarial black and white box attacks, trained with an automatic quantizationaware training framework, i.e. QKeras, with deep quantization loss accounted in the learning loop, thereby making the designed DNNs more accurate for deployment on tiny devices. We investigated how QKeras and an adversarial robustness technique, Jacobian Regularization (JR), can provide a co-optimization strategy by exploiting the DNN topology and the per layer JR approach to produce robust yet tiny deeply quantized DNN models. As a result, a new DNN model implementing this cooptimization strategy was conceived, developed and tested on three datasets containing both images and audio inputs, as well as compared its performance with existing benchmarks against various white-box and black-box attacks. Experimental results demonstrated that on average our proposed DNN model resulted in 8.3% and 79.5% higher accuracy than MLCommons/Tiny benchmarks in the presence of white-box and black-box attacks on the CIFAR-10 image dataset and a subset of the Google Speech Commands audio dataset respectively. It was also 6.5% more accurate for black-box attacks on the SVHN image dataset.

Exploring Effects of Computational Parameter Changes to Image Recognition Systems

Image recognition tasks typically use deep learning and require enormous processing power, thus relying on hardware accelerators like GPUs and FPGAs for fast, timely processing. Failure in real-time image recognition tasks can occur due to incorrect mapping on hardware accelerators, which may lead to timing uncertainty and incorrect behavior. Owing to the increased use of image recognition tasks in safety-critical applications like autonomous driving and medical imaging, it is imperative to assess their robustness to changes in the computational environment as parameters like deep learning frameworks, compiler optimizations for code generation, and hardware devices are not regulated with varying impact on model performance and correctness. In this paper we conduct robustness analysis of four popular image recognition models (MobileNetV2, ResNet101V2, DenseNet121 and InceptionV3) with the ImageNet dataset, assessing the impact of the following parameters in the model's computational environment: (1) deep learning frameworks; (2) compiler optimizations; and (3) hardware devices. We report sensitivity of model performance in terms of output label and inference time for changes in each of these environment parameters. We find that output label predictions for all four models are sensitive to choice of deep learning framework (by up to 57%) and insensitive to other parameters. On the other hand, model inference time was affected by all environment parameters with changes in hardware device having the most effect. The extent of effect was not uniform across models.