In this work we show that the size versus accuracy trade-off of neural network quantization can be significantly improved by increasing the quantization dimensionality. We propose the GPTVQ method, a new fast method for post-training vector quantization (VQ) that scales well to Large Language Models (LLMs). Our method interleaves quantization of one or more columns with updates to the remaining unquantized weights, using information from the Hessian of the per-layer output reconstruction MSE. Quantization codebooks are initialized using an efficient data-aware version of the EM algorithm. The codebooks are then updated, and further compressed by using integer quantization and SVD-based compression. GPTVQ establishes a new state-of-the art in the size vs accuracy trade-offs on a wide range of LLMs such as Llama-v2 and Mistral. Furthermore, our method is efficient: on a single H100 it takes between 3 and 11 hours to process a Llamav2-70B model, depending on quantization setting. Lastly, with on-device timings for VQ decompression on a mobile CPU we show that VQ leads to improved latency compared to using a 4-bit integer format.
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.
As Deep Neural Networks (DNNs) are increasingly deployed in safety critical and privacy sensitive applications such as autonomous driving and biometric authentication, it is critical to understand the fault-tolerance nature of DNNs. Prior work primarily focuses on metrics such as Failures In Time (FIT) rate and the Silent Data Corruption (SDC) rate, which quantify how often a device fails. Instead, this paper focuses on quantifying the DNN accuracy given that a transient error has occurred, which tells us how well a network behaves when a transient error occurs. We call this metric Resiliency Accuracy (RA). We show that existing RA formulation is fundamentally inaccurate, because it incorrectly assumes that software variables (model weights/activations) have equal faulty probability under hardware transient faults. We present an algorithm that captures the faulty probabilities of DNN variables under transient faults and, thus, provides correct RA estimations validated by hardware. To accelerate RA estimation, we reformulate RA calculation as a Monte Carlo integration problem, and solve it using importance sampling driven by DNN specific heuristics. Using our lightweight RA estimation method, we show that transient faults lead to far greater accuracy degradation than what todays DNN resiliency tools estimate. We show how our RA estimation tool can help design more resilient DNNs by integrating it with a Network Architecture Search framework.
Is it possible to restructure the non-linear activation functions in a deep network to create hardware-efficient models? To address this question, we propose a new paradigm called Restructurable Activation Networks (RANs) that manipulate the amount of non-linearity in models to improve their hardware-awareness and efficiency. First, we propose RAN-explicit (RAN-e) -- a new hardware-aware search space and a semi-automatic search algorithm -- to replace inefficient blocks with hardware-aware blocks. Next, we propose a training-free model scaling method called RAN-implicit (RAN-i) where we theoretically prove the link between network topology and its expressivity in terms of number of non-linear units. We demonstrate that our networks achieve state-of-the-art results on ImageNet at different scales and for several types of hardware. For example, compared to EfficientNet-Lite-B0, RAN-e achieves a similar accuracy while improving Frames-Per-Second (FPS) by 1.5x on Arm micro-NPUs. On the other hand, RAN-i demonstrates up to 2x reduction in #MACs over ConvNexts with a similar or better accuracy. We also show that RAN-i achieves nearly 40% higher FPS than ConvNext on Arm-based datacenter CPUs. Finally, RAN-i based object detection networks achieve a similar or higher mAP and up to 33% higher FPS on datacenter CPUs compared to ConvNext based models.
Emerging Internet-of-things (IoT) applications are driving deployment of neural networks (NNs) on heavily constrained low-cost hardware (HW) platforms, where accuracy is typically limited by memory capacity. To address this TinyML challenge, new HW platforms like neural processing units (NPUs) have support for model compression, which exploits aggressive network quantization and unstructured pruning optimizations. The combination of NPUs with HW compression and compressible models allows more expressive models in the same memory footprint. However, adding optimizations for compressibility on top of conventional NN architecture choices expands the design space across which we must make balanced trade-offs. This work bridges the gap between NPU HW capability and NN model design, by proposing a neural architecture search (NAS) algorithm to efficiently search a large design space, including: network depth, operator type, layer width, bitwidth, sparsity, and more. Building on differentiable NAS (DNAS) with several key improvements, we demonstrate Unified DNAS for Compressible models (UDC) on CIFAR100, ImageNet, and DIV2K super resolution tasks. On ImageNet, we find Pareto dominant compressible models, which are 1.9x smaller or 5.76% more accurate.
Autonomous systems are highly vulnerable to a variety of adversarial attacks on Deep Neural Networks (DNNs). Training-free model-agnostic defenses have recently gained popularity due to their speed, ease of deployment, and ability to work across many DNNs. To this end, a new technique has emerged for mitigating attacks on image classification DNNs, namely, preprocessing adversarial images using super resolution -- upscaling low-quality inputs into high-resolution images. This defense requires running both image classifiers and super resolution models on constrained autonomous systems. However, super resolution incurs a heavy computational cost. Therefore, in this paper, we investigate the following question: Does the robustness of image classifiers suffer if we use tiny super resolution models? To answer this, we first review a recent work called Super-Efficient Super Resolution (SESR) that achieves similar or better image quality than prior art while requiring 2x to 330x fewer Multiply-Accumulate (MAC) operations. We demonstrate that despite being orders of magnitude smaller than existing models, SESR achieves the same level of robustness as significantly larger networks. Finally, we estimate end-to-end performance of super resolution-based defenses on a commercial Arm Ethos-U55 micro-NPU. Our findings show that SESR achieves nearly 3x higher FPS than a baseline while achieving similar robustness.
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 (sensor rate, compute performance) and physical components (body-dynamics) that affect the performance of the machine. We use F-1 to characterize commonly used learning-based autonomy algorithms with onboard platforms to demonstrate the need for cyber-physical co-design. To navigate the cyber-physical design space automatically, we subsequently introduce AutoPilot. This push-button framework automates the co-design of cyber-physical components for aerial robots from a high-level specification guided by the F-1 model. AutoPilot uses Bayesian optimization to automatically co-design the autonomy algorithm and hardware accelerator while considering various cyber-physical parameters to generate an optimal design under different task level complexities for different robots and sensor framerates. As a result, designs generated by AutoPilot, on average, lower mission time up to 2x over baseline approaches, conserving battery energy.
Point cloud analytics is poised to become a key workload on battery-powered embedded and mobile platforms in a wide range of emerging application domains, such as autonomous driving, robotics, and augmented reality, where efficiency is paramount. This paper proposes Mesorasi, an algorithm-architecture co-designed system that simultaneously improves the performance and energy efficiency of point cloud analytics while retaining its accuracy. Our extensive characterizations of state-of-the-art point cloud algorithms show that, while structurally reminiscent of convolutional neural networks (CNNs), point cloud algorithms exhibit inherent compute and memory inefficiencies due to the unique characteristics of point cloud data. We propose delayed-aggregation, a new algorithmic primitive for building efficient point cloud algorithms. Delayed-aggregation hides the performance bottlenecks and reduces the compute and memory redundancies by exploiting the approximately distributive property of key operations in point cloud algorithms. Delayed-aggregation let point cloud algorithms achieve 1.6x speedup and 51.1% energy reduction on a mobile GPU while retaining the accuracy (-0.9% loss to 1.2% gains). To maximize the algorithmic benefits, we propose minor extensions to contemporary CNN accelerators, which can be integrated into a mobile Systems-on-a-Chip (SoC) without modifying other SoC components. With additional hardware support, Mesorasi achieves up to 3.6x speedup.
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%, with the rest spent on data movement and in the deep learning software framework. Thus far, it has been very difficult to study end-to-end DNN performance during early stage design (before RTL is available) because there are no existing DNN frameworks that support end-to-end simulation with easy custom hardware accelerator integration. To address this gap in research infrastructure, we present SMAUG, the first DNN framework that is purpose-built for simulation of end-to-end deep learning applications. SMAUG offers researchers a wide range of capabilities for evaluating DNN workloads, from diverse network topologies to easy accelerator modeling and SoC integration. To demonstrate the power and value of SMAUG, we present case studies that show how we can optimize overall performance and energy efficiency for up to 1.8-5x speedup over a baseline system, without changing any part of the accelerator microarchitecture, as well as show how SMAUG can tune an SoC for a camera-powered deep learning pipeline.