An official website of the United States government
Deep Neural Networks (DNNs) are pervasively applied in many artificial intelligence (AI) applications. The high performance of DNNs comes at the cost of larger size and higher compute complexity. Recent studies show that DNNs have much redundancy, such as the zero-value parameters and excessive numerical precision. To reduce computing complexity, many redundancy reduction techniques have been proposed, including pruning and data quantization. In this paper, we demonstrate our cooptimization of the DNN algorithm and hardware which exploits the model redundancy to accelerate DNNs.
more »
« less
Survey: Exploiting Data Redundancy for Optimization of Deep Learning
Data redundancy is ubiquitous in the inputs and intermediate results of Deep Neural Networks (DNN) . It offers many significant opportunities for improving DNN performance and efficiency and has been explored in a large body of work. These studies have scattered in many venues across several years. The targets they focus on range from images to videos and texts, and the techniques they use to detect and exploit data redundancy also vary in many aspects. There is not yet a systematic examination and summary of the many efforts, making it difficult for researchers to get a comprehensive view of the prior work, the state of the art, differences and shared principles, and the areas and directions yet to explore. This article tries to fill the void. It surveys hundreds of recent papers on the topic, introduces a novel taxonomy to put the various techniques into a single categorization framework, offers a comprehensive description of the main methods used for exploiting data redundancy in improving multiple kinds of DNNs on data, and points out a set of research opportunities for future exploration.
more »
« less
- PAR ID:
- 10417493
- Date Published:
- Journal Name:
- ACM Computing Surveys
- Volume:
- 55
- Issue:
- 10
- ISSN:
- 0360-0300
- Page Range / eLocation ID:
- 1 to 38
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Tolerating Defects in Low-Power Neural Network Accelerators Via Retraining-Free Weight Approximationnull (Ed.)Hardware accelerators are essential to the accommodation of ever-increasing Deep Neural Network (DNN) workloads on the resource-constrained embedded devices. While accelerators facilitate fast and energy-efficient DNN operations, their accuracy is threatened by faults in their on-chip and off-chip memories, where millions of DNN weights are held. The use of emerging Non-Volatile Memories (NVM) further exposes DNN accelerators to a non-negligible rate of permanent defects due to immature fabrication, limited endurance, and aging. To tolerate defects in NVM-based DNN accelerators, previous work either requires extra redundancy in hardware or performs defect-aware retraining, imposing significant overhead. In comparison, this paper proposes a set of algorithms that exploit the flexibility in setting the fault-free bits in weight memory to effectively approximate weight values, so as to mitigate defect-induced accuracy drop. These algorithms can be applied as a one-step solution when loading the weights to embedded devices. They only require trivial hardware support and impose negligible run-time overhead. Experiments on popular DNN models show that the proposed techniques successfully boost inference accuracy even in the face of elevated defect rates in the weight memory.more » « less
-
The many-body correlation function is a fundamental computation kernel in modern physics computing applications, e.g., Hadron Contractions in Lattice quantum chromodynamics (QCD). This kernel is both computation and memory intensive, involving a series of tensor contractions, and thus usually runs on accelerators like GPUs. Existing optimizations on many-body correlation mainly focus on individual tensor contractions (e.g., cuBLAS libraries and others). In contrast, this work discovers a new optimization dimension for many-body correlation by exploring the optimization opportunities among tensor contractions. More specifically, it targets general GPU architectures (both NVIDIA and AMD) and optimizes many-body correlation’s memory management by exploiting a set of memory allocation and communication redundancy elimination opportunities: first, GPU memory allocation redundancy : the intermediate output frequently occurs as input in the subsequent calculations; second, CPU-GPU communication redundancy : although all tensors are allocated on both CPU and GPU, many of them are used (and reused) on the GPU side only, and thus, many CPU/GPU communications (like that in existing Unified Memory designs) are unnecessary; third, GPU oversubscription: limited GPU memory size causes oversubscription issues, and existing memory management usually results in near-reuse data eviction, thus incurring extra CPU/GPU memory communications. Targeting these memory optimization opportunities, this article proposes MemHC, an optimized systematic GPU memory management framework that aims to accelerate the calculation of many-body correlation functions utilizing a series of new memory reduction designs. These designs involve optimizations for GPU memory allocation, CPU/GPU memory movement, and GPU memory oversubscription, respectively. More specifically, first, MemHC employs duplication-aware management and lazy release of GPU memories to corresponding host managing for better data reusability. Second, it implements data reorganization and on-demand synchronization to eliminate redundant (or unnecessary) data transfer. Third, MemHC exploits an optimized Least Recently Used (LRU) eviction policy called Pre-Protected LRU to reduce evictions and leverage memory hits. Additionally, MemHC is portable for various platforms including NVIDIA GPUs and AMD GPUs. The evaluation demonstrates that MemHC outperforms unified memory management by \( 2.18\times \) to \( 10.73\times \) . The proposed Pre-Protected LRU policy outperforms the original LRU policy by up to \( 1.36\times \) improvement. 1more » « less
-
With the rising adoption of deep neural networks (DNNs) for commercial and high-stakes applications that process sensitive user data and make critical decisions, security concerns are paramount. An adversary can undermine the confidentiality of user input or a DNN model, mislead a DNN to make wrong predictions, or even render a machine learning application unavailable to valid requests. While security vulnerabilities that enable such exploits can exist across multiple levels of the technology stack that supports machine learning applications, the hardware-level vulnerabilities can be particularly problematic. In this article, we provide a comprehensive review of the hardware-level vulnerabilities affecting domain-specific DNN inference accelerators and recent progress in secure hardware design to address these. As domain-specific DNN accelerators have a number of differences compared to general-purpose processors and cryptographic accelerators where the hardware-level vulnerabilities have been thoroughly investigated, there are unique challenges and opportunities for secure machine learning hardware. We first categorize the hardware-level vulnerabilities into three scenarios based on an adversary’s capability: 1) an adversary can only attack the off-chip components, such as the off-chip DRAM and the data bus; 2) an adversary can directly attack the on-chip structures in a DNN accelerator; and 3) an adversary can insert hardware trojans during the manufacturing and design process. For each category, we survey recent studies on attacks that pose practical security challenges to DNN accelerators. Then, we present recent advances in the defense solutions for DNN accelerators, addressing those security challenges with circuit-, architecture-, and algorithm-level techniques.more » « less
-
Drug misuse and overdose has plagued the United States over the past decades and has severely impacted several communities and families. Often, it is difficult for drug users to get the assistance they need and thus many usage cases remain undetected until it is too late. With the booming age of social media, many users often prefer to discuss their emotions through virtual environments where they can also meet others dealing with similar problems. The widespread use of social media sites creates interesting new opportunities to apply NLP techniques to analyze content and potentially help those drug users (e.g., early detection and intervention). To tap into such opportunities, we study categorization of tweets about drug usage into fine-grained categories. To facilitate the study of the proposed new problem, we create a new dataset and use this data to study the effectiveness of multiple representative categorization methods. We further analyze errors made by these methods and explore new features to improve them. We find that a new feature based on tweet tone is quite useful in improving classification scores. We further explore possible downstream applications based on this classification system and provide a set of preliminary findings.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1145/3564663
