Yingyan Lin

Cheng Wan, Youjie Li, Ang Li et al.

Graph Convolutional Networks (GCNs) have emerged as the state-of-the-art method for graph-based learning tasks. However, training GCNs at scale is still challenging, hindering both the exploration of more sophisticated GCN architectures and their applications to real-world large graphs. While it might be natural to consider graph partition and distributed training for tackling this challenge, this direction has only been slightly scratched the surface in the previous works due to the limitations of existing designs. In this work, we first analyze why distributed GCN training is ineffective and identify the underlying cause to be the excessive number of boundary nodes of each partitioned subgraph, which easily explodes the memory and communication costs for GCN training. Furthermore, we propose a simple yet effective method dubbed BNS-GCN that adopts random Boundary-Node-Sampling to enable efficient and scalable distributed GCN training. Experiments and ablation studies consistently validate the effectiveness of BNS-GCN, e.g., boosting the throughput by up to 16.2x and reducing the memory usage by up to 58%, while maintaining a full-graph accuracy. Furthermore, both theoretical and empirical analysis show that BNS-GCN enjoys a better convergence than existing sampling-based methods. We believe that our BNS-GCN has opened up a new paradigm for enabling GCN training at scale. The code is available at https://github.com/RICE-EIC/BNS-GCN.

Cheng Wan, Youjie Li, Cameron R. Wolfe et al.

Graph Convolutional Networks (GCNs) is the state-of-the-art method for learning graph-structured data, and training large-scale GCNs requires distributed training across multiple accelerators such that each accelerator is able to hold a partitioned subgraph. However, distributed GCN training incurs prohibitive overhead of communicating node features and feature gradients among partitions for every GCN layer during each training iteration, limiting the achievable training efficiency and model scalability. To this end, we propose PipeGCN, a simple yet effective scheme that hides the communication overhead by pipelining inter-partition communication with intra-partition computation. It is non-trivial to pipeline for efficient GCN training, as communicated node features/gradients will become stale and thus can harm the convergence, negating the pipeline benefit. Notably, little is known regarding the convergence rate of GCN training with both stale features and stale feature gradients. This work not only provides a theoretical convergence analysis but also finds the convergence rate of PipeGCN to be close to that of the vanilla distributed GCN training without any staleness. Furthermore, we develop a smoothing method to further improve PipeGCN's convergence. Extensive experiments show that PipeGCN can largely boost the training throughput (1.7x~28.5x) while achieving the same accuracy as its vanilla counterpart and existing full-graph training methods. The code is available at https://github.com/RICE-EIC/PipeGCN.

Huihong Shi, Haoran You, Yang Zhao et al.

Multiplication is arguably the most cost-dominant operation in modern deep neural networks (DNNs), limiting their achievable efficiency and thus more extensive deployment in resource-constrained applications. To tackle this limitation, pioneering works have developed handcrafted multiplication-free DNNs, which require expert knowledge and time-consuming manual iteration, calling for fast development tools. To this end, we propose a Neural Architecture Search and Acceleration framework dubbed NASA, which enables automated multiplication-reduced DNN development and integrates a dedicated multiplication-reduced accelerator for boosting DNNs' achievable efficiency. Specifically, NASA adopts neural architecture search (NAS) spaces that augment the state-of-the-art one with hardware-inspired multiplication-free operators, such as shift and adder, armed with a novel progressive pretrain strategy (PGP) together with customized training recipes to automatically search for optimal multiplication-reduced DNNs; On top of that, NASA further develops a dedicated accelerator, which advocates a chunk-based template and auto-mapper dedicated for NASA-NAS resulting DNNs to better leverage their algorithmic properties for boosting hardware efficiency. Experimental results and ablation studies consistently validate the advantages of NASA's algorithm-hardware co-design framework in terms of achievable accuracy and efficiency tradeoffs. Codes are available at https://github.com/GATECH-EIC/NASA.

Jyotikrishna Dass, Shang Wu, Huihong Shi et al.

Vision Transformer (ViT) has emerged as a competitive alternative to convolutional neural networks for various computer vision applications. Specifically, ViT multi-head attention layers make it possible to embed information globally across the overall image. Nevertheless, computing and storing such attention matrices incurs a quadratic cost dependency on the number of patches, limiting its achievable efficiency and scalability and prohibiting more extensive real-world ViT applications on resource-constrained devices. Sparse attention has been shown to be a promising direction for improving hardware acceleration efficiency for NLP models. However, a systematic counterpart approach is still missing for accelerating ViT models. To close the above gap, we propose a first-of-its-kind algorithm-hardware codesigned framework, dubbed ViTALiTy, for boosting the inference efficiency of ViTs. Unlike sparsity-based Transformer accelerators for NLP, ViTALiTy unifies both low-rank and sparse components of the attention in ViTs. At the algorithm level, we approximate the dot-product softmax operation via first-order Taylor attention with row-mean centering as the low-rank component to linearize the cost of attention blocks and further boost the accuracy by incorporating a sparsity-based regularization. At the hardware level, we develop a dedicated accelerator to better leverage the resulting workload and pipeline from ViTALiTy's linear Taylor attention which requires the execution of only the low-rank component, to further boost the hardware efficiency. Extensive experiments and ablation studies validate that ViTALiTy offers boosted end-to-end efficiency (e.g., $3\times$ faster and $3\times$ energy-efficient) under comparable accuracy, with respect to the state-of-the-art solution.

Tong Geng, Chunshu Wu, Yongan Zhang et al.

Graph Convolutional Networks (GCNs) have drawn tremendous attention in the past three years. Compared with other deep learning modalities, high-performance hardware acceleration of GCNs is as critical but even more challenging. The hurdles arise from the poor data locality and redundant computation due to the large size, high sparsity, and irregular non-zero distribution of real-world graphs. In this paper we propose a novel hardware accelerator for GCN inference, called I-GCN, that significantly improves data locality and reduces unnecessary computation. The mechanism is a new online graph restructuring algorithm we refer to as islandization. The proposed algorithm finds clusters of nodes with strong internal but weak external connections. The islandization process yields two major benefits. First, by processing islands rather than individual nodes, there is better on-chip data reuse and fewer off-chip memory accesses. Second, there is less redundant computation as aggregation for common/shared neighbors in an island can be reused. The parallel search, identification, and leverage of graph islands are all handled purely in hardware at runtime working in an incremental pipeline. This is done without any preprocessing of the graph data or adjustment of the GCN model structure. Experimental results show that I-GCN can significantly reduce off-chip accesses and prune 38% of aggregation operations, leading to performance speedups over CPUs, GPUs, the prior art GCN accelerators of 5549x, 403x, and 5.7x on average, respectively.

Zhenbang Du, Kejing Xia, Xinrui Zhong et al.

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive generation by enabling parallel token prediction. However, practical dLLM decoding still suffers from high inference latency, which limits deployment. In this work, we observe that a substantial part of this inefficiency comes from recurring redundancy in the decoding process, including spatial redundancy caused by confidence clusters and positional ambiguity, and temporal redundancy caused by repeatedly remasking predictions that have already stabilized. Motivated by these patterns, we propose $R^2$-dLLM, a unified framework for reducing decoding redundancy from both inference and training perspectives. At inference time, we introduce training-free decoding rules that aggregate local confidence and token predictions, and finalize temporally stable tokens to avoid redundant decoding steps. We further propose a redundancy-aware supervised fine-tuning pipeline that aligns the model with efficient decoding trajectories and reduces reliance on manually tuned thresholds. Experiments demonstrate that $R^2$-dLLM consistently reduces the number of decoding steps by up to 75% compared to existing decoding strategies, while maintaining competitive generation quality across different models and tasks. These results validate that decoding redundancy is a central bottleneck in dLLMs, and that explicitly reducing it yields substantial practical efficiency gains.

Zhongzhi Yu, Shang Wu, Yonggan Fu et al.

Despite the growing demand for tuning foundation vision transformers (FViTs) on downstream tasks, fully unleashing FViTs' potential under data-limited scenarios (e.g., few-shot tuning) remains a challenge due to FViTs' data-hungry nature. Common data augmentation techniques fall short in this context due to the limited features contained in the few-shot tuning data. To tackle this challenge, we first identify an opportunity for FViTs in few-shot tuning: pretrained FViTs themselves have already learned highly representative features from large-scale pretraining data, which are fully preserved during widely used parameter-efficient tuning. We thus hypothesize that leveraging those learned features to augment the tuning data can boost the effectiveness of few-shot FViT tuning. To this end, we propose a framework called Hint-based Data Augmentation (Hint-Aug), which aims to boost FViT in few-shot tuning by augmenting the over-fitted parts of tuning samples with the learned features of pretrained FViTs. Specifically, Hint-Aug integrates two key enablers: (1) an Attentive Over-fitting Detector (AOD) to detect over-confident patches of foundation ViTs for potentially alleviating their over-fitting on the few-shot tuning data and (2) a Confusion-based Feature Infusion (CFI) module to infuse easy-to-confuse features from the pretrained FViTs with the over-confident patches detected by the above AOD in order to enhance the feature diversity during tuning. Extensive experiments and ablation studies on five datasets and three parameter-efficient tuning techniques consistently validate Hint-Aug's effectiveness: 0.04% ~ 32.91% higher accuracy over the state-of-the-art (SOTA) data augmentation method under various low-shot settings. For example, on the Pet dataset, Hint-Aug achieves a 2.22% higher accuracy with 50% less training data over SOTA data augmentation methods.

Zhongzhi Yu, Yang Zhang, Kaizhi Qian et al.

Despite the impressive performance recently achieved by automatic speech recognition (ASR), we observe two primary challenges that hinder its broader applications: (1) The difficulty of introducing scalability into the model to support more languages with limited training, inference, and storage overhead; (2) The low-resource adaptation ability that enables effective low-resource adaptation while avoiding over-fitting and catastrophic forgetting issues. Inspired by recent findings, we hypothesize that we can address the above challenges with modules widely shared across languages. To this end, we propose an ASR framework, dubbed \METHODNS, that, \textit{for the first time}, simultaneously achieves strong multilingual scalability and low-resource adaptation ability thanks to its modularize-then-assemble strategy. Specifically, \METHOD learns a small set of generalizable sub-modules and adaptively assembles them for different languages to reduce the multilingual overhead and enable effective knowledge transfer for low-resource adaptation. Extensive experiments and visualizations demonstrate that \METHOD can effectively discover language similarity and improve multilingual and low-resource ASR performance over state-of-the-art (SOTA) methods, e.g., under multilingual-ASR, our framework achieves a 0.13$\sim$2.41 lower character error rate (CER) with 30\% smaller inference overhead over SOTA solutions on multilingual ASR and a comparable CER, with nearly 50 times fewer trainable parameters over SOTA solutions on low-resource tuning, respectively.

Zhongzhi Yu, Yonggan Fu, Jiayi Yuan et al.

Tiny deep learning has attracted increasing attention driven by the substantial demand for deploying deep learning on numerous intelligent Internet-of-Things devices. However, it is still challenging to unleash tiny deep learning's full potential on both large-scale datasets and downstream tasks due to the under-fitting issues caused by the limited model capacity of tiny neural networks (TNNs). To this end, we propose a framework called NetBooster to empower tiny deep learning by augmenting the architectures of TNNs via an expansion-then-contraction strategy. Extensive experiments show that NetBooster consistently outperforms state-of-the-art tiny deep learning solutions.

Zhongzhi Yu, Yonggan Fu, Shang Wu et al.

Low precision deep neural network (DNN) training is one of the most effective techniques for boosting DNNs' training efficiency, as it trims down the training cost from the finest bit level. While existing works mostly fix the model precision during the whole training process, a few pioneering works have shown that dynamic precision schedules help DNNs converge to a better accuracy while leading to a lower training cost than their static precision training counterparts. However, existing dynamic low precision training methods rely on manually designed precision schedules to achieve advantageous efficiency and accuracy trade-offs, limiting their more comprehensive practical applications and achievable performance. To this end, we propose LDP, a Learnable Dynamic Precision DNN training framework that can automatically learn a temporally and spatially dynamic precision schedule during training towards optimal accuracy and efficiency trade-offs. It is worth noting that LDP-trained DNNs are by nature efficient during inference. Furthermore, we visualize the resulting temporal and spatial precision schedule and distribution of LDP trained DNNs on different tasks to better understand the corresponding DNNs' characteristics at different training stages and DNN layers both during and after training, drawing insights for promoting further innovations. Extensive experiments and ablation studies (seven networks, five datasets, and three tasks) show that the proposed LDP consistently outperforms state-of-the-art (SOTA) low precision DNN training techniques in terms of training efficiency and achieved accuracy trade-offs. For example, in addition to having the advantage of being automated, our LDP achieves a 0.31\% higher accuracy with a 39.1\% lower computational cost when training ResNet-20 on CIFAR-10 as compared with the best SOTA method.

Jianghao Shen, Yonggan Fu, Yue Wang et al.

While increasingly deep networks are still in general desired for achieving state-of-the-art performance, for many specific inputs a simpler network might already suffice. Existing works exploited this observation by learning to skip convolutional layers in an input-dependent manner. However, we argue their binary decision scheme, i.e., either fully executing or completely bypassing one layer for a specific input, can be enhanced by introducing finer-grained, "softer" decisions. We therefore propose a Dynamic Fractional Skipping (DFS) framework. The core idea of DFS is to hypothesize layer-wise quantization (to different bitwidths) as intermediate "soft" choices to be made between fully utilizing and skipping a layer. For each input, DFS dynamically assigns a bitwidth to both weights and activations of each layer, where fully executing and skipping could be viewed as two "extremes" (i.e., full bitwidth and zero bitwidth). In this way, DFS can "fractionally" exploit a layer's expressive power during input-adaptive inference, enabling finer-grained accuracy-computational cost trade-offs. It presents a unified view to link input-adaptive layer skipping and input-adaptive hybrid quantization. Extensive experimental results demonstrate the superior tradeoff between computational cost and model expressive power (accuracy) achieved by DFS. More visualizations also indicate a smooth and consistent transition in the DFS behaviors, especially the learned choices between layer skipping and different quantizations when the total computational budgets vary, validating our hypothesis that layer quantization could be viewed as intermediate variants of layer skipping. Our source code and supplementary material are available at \link{https://github.com/Torment123/DFS}.

Junru Wu, Yue Wang, Zhenyu Wu et al.

The current trend of pushing CNNs deeper with convolutions has created a pressing demand to achieve higher compression gains on CNNs where convolutions dominate the computation and parameter amount (e.g., GoogLeNet, ResNet and Wide ResNet). Further, the high energy consumption of convolutions limits its deployment on mobile devices. To this end, we proposed a simple yet effective scheme for compressing convolutions though applying k-means clustering on the weights, compression is achieved through weight-sharing, by only recording $K$ cluster centers and weight assignment indexes. We then introduced a novel spectrally relaxed $k$-means regularization, which tends to make hard assignments of convolutional layer weights to $K$ learned cluster centers during re-training. We additionally propose an improved set of metrics to estimate energy consumption of CNN hardware implementations, whose estimation results are verified to be consistent with previously proposed energy estimation tool extrapolated from actual hardware measurements. We finally evaluated Deep $k$-Means across several CNN models in terms of both compression ratio and energy consumption reduction, observing promising results without incurring accuracy loss. The code is available at https://github.com/Sandbox3aster/Deep-K-Means

Xin Dong, Yonggan Fu, Shizhe Diao et al.

We propose Hymba, a family of small language models featuring a hybrid-head parallel architecture that integrates transformer attention mechanisms with state space models (SSMs) for enhanced efficiency. Attention heads provide high-resolution recall, while SSM heads enable efficient context summarization. Additionally, we introduce learnable meta tokens that are prepended to prompts, storing critical information and alleviating the "forced-to-attend" burden associated with attention mechanisms. This model is further optimized by incorporating cross-layer key-value (KV) sharing and partial sliding window attention, resulting in a compact cache size. During development, we conducted a controlled study comparing various architectures under identical settings and observed significant advantages of our proposed architecture. Notably, Hymba achieves state-of-the-art results for small LMs: Our Hymba-1.5B-Base model surpasses all sub-2B public models in performance and even outperforms Llama-3.2-3B with 1.32% higher average accuracy, an 11.67x cache size reduction, and 3.49x throughput.

Zishen Wan, Che-Kai Liu, Hanchen Yang et al.

The remarkable advancements in artificial intelligence (AI), primarily driven by deep neural networks, have significantly impacted various aspects of our lives. However, the current challenges surrounding unsustainable computational trajectories, limited robustness, and a lack of explainability call for the development of next-generation AI systems. Neuro-symbolic AI (NSAI) emerges as a promising paradigm, fusing neural, symbolic, and probabilistic approaches to enhance interpretability, robustness, and trustworthiness while facilitating learning from much less data. Recent NSAI systems have demonstrated great potential in collaborative human-AI scenarios with reasoning and cognitive capabilities. In this paper, we provide a systematic review of recent progress in NSAI and analyze the performance characteristics and computational operators of NSAI models. Furthermore, we discuss the challenges and potential future directions of NSAI from both system and architectural perspectives.

Yang Zhao, Shang Wu, Jingqun Zhang et al.

Instant on-device Neural Radiance Fields (NeRFs) are in growing demand for unleashing the promise of immersive AR/VR experiences, but are still limited by their prohibitive training time. Our profiling analysis reveals a memory-bound inefficiency in NeRF training. To tackle this inefficiency, near-memory processing (NMP) promises to be an effective solution, but also faces challenges due to the unique workloads of NeRFs, including the random hash table lookup, random point processing sequence, and heterogeneous bottleneck steps. Therefore, we propose the first NMP framework, Instant-NeRF, dedicated to enabling instant on-device NeRF training. Experiments on eight datasets consistently validate the effectiveness of Instant-NeRF.

Zhongzhi Yu, Yonggan Fu, Sicheng Li et al.

ViTs are often too computationally expensive to be fitted onto real-world resource-constrained devices, due to (1) their quadratically increased complexity with the number of input tokens and (2) their overparameterized self-attention heads and model depth. In parallel, different images are of varied complexity and their different regions can contain various levels of visual information, indicating that treating all regions/tokens equally in terms of model complexity is unnecessary while such opportunities for trimming down ViTs' complexity have not been fully explored. To this end, we propose a Multi-grained Input-adaptive Vision Transformer framework dubbed MIA-Former that can input-adaptively adjust the structure of ViTs at three coarse-to-fine-grained granularities (i.e., model depth and the number of model heads/tokens). In particular, our MIA-Former adopts a low-cost network trained with a hybrid supervised and reinforcement training method to skip unnecessary layers, heads, and tokens in an input adaptive manner, reducing the overall computational cost. Furthermore, an interesting side effect of our MIA-Former is that its resulting ViTs are naturally equipped with improved robustness against adversarial attacks over their static counterparts, because MIA-Former's multi-grained dynamic control improves the model diversity similar to the effect of ensemble and thus increases the difficulty of adversarial attacks against all its sub-models. Extensive experiments and ablation studies validate that the proposed MIA-Former framework can effectively allocate computation budgets adaptive to the difficulty of input images meanwhile increase robustness, achieving state-of-the-art (SOTA) accuracy-efficiency trade-offs, e.g., 20% computation savings with the same or even a higher accuracy compared with SOTA dynamic transformer models.

Yongan Zhang, Anton Banta, Yonggan Fu et al.

There exists a gap in terms of the signals provided by pacemakers (i.e., intracardiac electrogram (EGM)) and the signals doctors use (i.e., 12-lead electrocardiogram (ECG)) to diagnose abnormal rhythms. Therefore, the former, even if remotely transmitted, are not sufficient for doctors to provide a precise diagnosis, let alone make a timely intervention. To close this gap and make a heuristic step towards real-time critical intervention in instant response to irregular and infrequent ventricular rhythms, we propose a new framework dubbed RT-RCG to automatically search for (1) efficient Deep Neural Network (DNN) structures and then (2)corresponding accelerators, to enable Real-Time and high-quality Reconstruction of ECG signals from EGM signals. Specifically, RT-RCG proposes a new DNN search space tailored for ECG reconstruction from EGM signals, and incorporates a differentiable acceleration search (DAS) engine to efficiently navigate over the large and discrete accelerator design space to generate optimized accelerators. Extensive experiments and ablation studies under various settings consistently validate the effectiveness of our RT-RCG. To the best of our knowledge, RT-RCG is the first to leverage neural architecture search (NAS) to simultaneously tackle both reconstruction efficacy and efficiency.

Yongan Zhang, Haoran You, Yonggan Fu et al.

Graph Neural Networks (GNNs) have emerged as the state-of-the-art (SOTA) method for graph-based learning tasks. However, it still remains prohibitively challenging to inference GNNs over large graph datasets, limiting their application to large-scale real-world tasks. While end-to-end jointly optimizing GNNs and their accelerators is promising in boosting GNNs' inference efficiency and expediting the design process, it is still underexplored due to the vast and distinct design spaces of GNNs and their accelerators. In this work, we propose G-CoS, a GNN and accelerator co-search framework that can automatically search for matched GNN structures and accelerators to maximize both task accuracy and acceleration efficiency. Specifically, GCoS integrates two major enabling components: (1) a generic GNN accelerator search space which is applicable to various GNN structures and (2) a one-shot GNN and accelerator co-search algorithm that enables simultaneous and efficient search for optimal GNN structures and their matched accelerators. To the best of our knowledge, G-CoS is the first co-search framework for GNNs and their accelerators. Extensive experiments and ablation studies show that the GNNs and accelerators generated by G-CoS consistently outperform SOTA GNNs and GNN accelerators in terms of both task accuracy and hardware efficiency, while only requiring a few hours for the end-to-end generation of the best matched GNNs and their accelerators.

Mengquan Li, Zhongzhi Yu, Yongan Zhang et al.

The recent breakthroughs and prohibitive complexities of Deep Neural Networks (DNNs) have excited extensive interest in domain-specific DNN accelerators, among which optical DNN accelerators are particularly promising thanks to their unprecedented potential of achieving superior performance-per-watt. However, the development of optical DNN accelerators is much slower than that of electrical DNN accelerators. One key challenge is that while many techniques have been developed to facilitate the development of electrical DNN accelerators, techniques that support or expedite optical DNN accelerator design remain much less explored, limiting both the achievable performance and the innovation development of optical DNN accelerators. To this end, we develop the first-of-its-kind framework dubbed O-HAS, which for the first time demonstrates automated Optical Hardware Accelerator Search for boosting both the acceleration efficiency and development speed of optical DNN accelerators. Specifically, our O-HAS consists of two integrated enablers: (1) an O-Cost Predictor, which can accurately yet efficiently predict an optical accelerator's energy and latency based on the DNN model parameters and the optical accelerator design; and (2) an O-Search Engine, which can automatically explore the large design space of optical DNN accelerators and identify the optimal accelerators (i.e., the micro-architectures and algorithm-to-accelerator mapping methods) in order to maximize the target acceleration efficiency. Extensive experiments and ablation studies consistently validate the effectiveness of both our O-Cost Predictor and O-Search Engine as well as the excellent efficiency of O-HAS generated optical accelerators.

Xiaohan Chen, Yang Zhao, Yue Wang et al.

The record-breaking performance of deep neural networks (DNNs) comes with heavy parameterization, leading to external dynamic random-access memory (DRAM) for storage. The prohibitive energy of DRAM accesses makes it non-trivial to deploy DNN on resource-constrained devices, calling for minimizing the weight and data movements to improve the energy efficiency. We present SmartDeal (SD), an algorithm framework to trade higher-cost memory storage/access for lower-cost computation, in order to aggressively boost the storage and energy efficiency, for both inference and training. The core of SD is a novel weight decomposition with structural constraints, carefully crafted to unleash the hardware efficiency potential. Specifically, we decompose each weight tensor as the product of a small basis matrix and a large structurally sparse coefficient matrix whose non-zeros are quantized to power-of-2. The resulting sparse and quantized DNNs enjoy greatly reduced energy for data movement and weight storage, incurring minimal overhead to recover the original weights thanks to the sparse bit-operations and cost-favorable computations. Beyond inference, we take another leap to embrace energy-efficient training, introducing innovative techniques to address the unique roadblocks arising in training while preserving the SD structures. We also design a dedicated hardware accelerator to fully utilize the SD structure to improve the real energy efficiency and latency. We conduct experiments on both multiple tasks, models and datasets in different settings. Results show that: 1) applied to inference, SD achieves up to 2.44x energy efficiency as evaluated via real hardware implementations; 2) applied to training, SD leads to 10.56x and 4.48x reduction in the storage and training energy, with negligible accuracy loss compared to state-of-the-art training baselines. Our source codes are available online.

Sicong Liu, Junzhao Du, Kaiming Nan et al.

Recent breakthroughs in Deep Neural Networks (DNNs) have fueled a tremendously growing demand for bringing DNN-powered intelligence into mobile platforms. While the potential of deploying DNNs on resource-constrained platforms has been demonstrated by DNN compression techniques, the current practice suffers from two limitations: 1) merely stand-alone compression schemes are investigated even though each compression technique only suit for certain types of DNN layers; and 2) mostly compression techniques are optimized for DNNs' inference accuracy, without explicitly considering other application-driven system performance (e.g., latency and energy cost) and the varying resource availability across platforms (e.g., storage and processing capability). To this end, we propose AdaDeep, a usage-driven, automated DNN compression framework for systematically exploring the desired trade-off between performance and resource constraints, from a holistic system level. Specifically, in a layer-wise manner, AdaDeep automatically selects the most suitable combination of compression techniques and the corresponding compression hyperparameters for a given DNN. Thorough evaluations on six datasets and across twelve devices demonstrate that AdaDeep can achieve up to $18.6\times$ latency reduction, $9.8\times$ energy-efficiency improvement, and $37.3\times$ storage reduction in DNNs while incurring negligible accuracy loss. Furthermore, AdaDeep also uncovers multiple novel combinations of compression techniques.

Yang Zhao, Xiaohan Chen, Yue Wang et al.

We present SmartExchange, an algorithm-hardware co-design framework to trade higher-cost memory storage/access for lower-cost computation, for energy-efficient inference of deep neural networks (DNNs). We develop a novel algorithm to enforce a specially favorable DNN weight structure, where each layerwise weight matrix can be stored as the product of a small basis matrix and a large sparse coefficient matrix whose non-zero elements are all power-of-2. To our best knowledge, this algorithm is the first formulation that integrates three mainstream model compression ideas: sparsification or pruning, decomposition, and quantization, into one unified framework. The resulting sparse and readily-quantized DNN thus enjoys greatly reduced energy consumption in data movement as well as weight storage. On top of that, we further design a dedicated accelerator to fully utilize the SmartExchange-enforced weights to improve both energy efficiency and latency performance. Extensive experiments show that 1) on the algorithm level, SmartExchange outperforms state-of-the-art compression techniques, including merely sparsification or pruning, decomposition, and quantization, in various ablation studies based on nine DNN models and four datasets; and 2) on the hardware level, the proposed SmartExchange based accelerator can improve the energy efficiency by up to 6.7$\times$ and the speedup by up to 19.2$\times$ over four state-of-the-art DNN accelerators, when benchmarked on seven DNN models (including four standard DNNs, two compact DNN models, and one segmentation model) and three datasets.

Weitao Li, Pengfei Xu, Yang Zhao et al.

Resistive-random-access-memory (ReRAM) based processing-in-memory (R$^2$PIM) accelerators show promise in bridging the gap between Internet of Thing devices' constrained resources and Convolutional/Deep Neural Networks' (CNNs/DNNs') prohibitive energy cost. Specifically, R$^2$PIM accelerators enhance energy efficiency by eliminating the cost of weight movements and improving the computational density through ReRAM's high density. However, the energy efficiency is still limited by the dominant energy cost of input and partial sum (Psum) movements and the cost of digital-to-analog (D/A) and analog-to-digital (A/D) interfaces. In this work, we identify three energy-saving opportunities in R$^2$PIM accelerators: analog data locality, time-domain interfacing, and input access reduction, and propose an innovative R$^2$PIM accelerator called TIMELY, with three key contributions: (1) TIMELY adopts analog local buffers (ALBs) within ReRAM crossbars to greatly enhance the data locality, minimizing the energy overheads of both input and Psum movements; (2) TIMELY largely reduces the energy of each single D/A (and A/D) conversion and the total number of conversions by using time-domain interfaces (TDIs) and the employed ALBs, respectively; (3) we develop an only-once input read (O$^2$IR) mapping method to further decrease the energy of input accesses and the number of D/A conversions. The evaluation with more than 10 CNN/DNN models and various chip configurations shows that, TIMELY outperforms the baseline R$^2$PIM accelerator, PRIME, by one order of magnitude in energy efficiency while maintaining better computational density (up to 31.2$\times$) and throughput (up to 736.6$\times$). Furthermore, comprehensive studies are performed to evaluate the effectiveness of the proposed ALB, TDI, and O$^2$IR innovations in terms of energy savings and area reduction.

Hongjie Wang, Yang Zhao, Chaojian Li et al.

The excellent performance of modern deep neural networks (DNNs) comes at an often prohibitive training cost, limiting the rapid development of DNN innovations and raising various environmental concerns. To reduce the dominant data movement cost of training, process in-memory (PIM) has emerged as a promising solution as it alleviates the need to access DNN weights. However, state-of-the-art PIM DNN training accelerators employ either analog/mixed signal computing which has limited precision or digital computing based on a memory technology that supports limited logic functions and thus requires complicated procedure to realize floating point computation. In this paper, we propose a spin orbit torque magnetic random access memory (SOT-MRAM) based digital PIM accelerator that supports floating point precision. Specifically, this new accelerator features an innovative (1) SOT-MRAM cell, (2) full addition design, and (3) floating point computation. Experiment results show that the proposed SOT-MRAM PIM based DNN training accelerator can achieve 3.3$\times$, 1.8$\times$, and 2.5$\times$ improvement in terms of energy, latency, and area, respectively, compared with a state-of-the-art PIM based DNN training accelerator.

Yang Zhao, Chaojian Li, Yue Wang et al.

The recent breakthroughs in deep neural networks (DNNs) have spurred a tremendously increased demand for DNN accelerators. However, designing DNN accelerators is non-trivial as it often takes months/years and requires cross-disciplinary knowledge. To enable fast and effective DNN accelerator development, we propose DNN-Chip Predictor, an analytical performance predictor which can accurately predict DNN accelerators' energy, throughput, and latency prior to their actual implementation. Our Predictor features two highlights: (1) its analytical performance formulation of DNN ASIC/FPGA accelerators facilitates fast design space exploration and optimization; and (2) it supports DNN accelerators with different algorithm-to-hardware mapping methods (i.e., dataflows) and hardware architectures. Experiment results based on 2 DNN models and 3 different ASIC/FPGA implementations show that our DNN-Chip Predictor's predicted performance differs from those of chip measurements of FPGA/ASIC implementation by no more than 17.66% when using different DNN models, hardware architectures, and dataflows. We will release code upon acceptance.

Pengfei Xu, Xiaofan Zhang, Cong Hao et al.

Recent breakthroughs in Deep Neural Networks (DNNs) have fueled a growing demand for DNN chips. However, designing DNN chips is non-trivial because: (1) mainstream DNNs have millions of parameters and operations; (2) the large design space due to the numerous design choices of dataflows, processing elements, memory hierarchy, etc.; and (3) an algorithm/hardware co-design is needed to allow the same DNN functionality to have a different decomposition, which would require different hardware IPs to meet the application specifications. Therefore, DNN chips take a long time to design and require cross-disciplinary experts. To enable fast and effective DNN chip design, we propose AutoDNNchip - a DNN chip generator that can automatically generate both FPGA- and ASIC-based DNN chip implementation given DNNs from machine learning frameworks (e.g., PyTorch) for a designated application and dataset. Specifically, AutoDNNchip consists of two integrated enablers: (1) a Chip Predictor, built on top of a graph-based accelerator representation, which can accurately and efficiently predict a DNN accelerator's energy, throughput, and area based on the DNN model parameters, hardware configuration, technology-based IPs, and platform constraints; and (2) a Chip Builder, which can automatically explore the design space of DNN chips (including IP selection, block configuration, resource balancing, etc.), optimize chip design via the Chip Predictor, and then generate optimized synthesizable RTL to achieve the target design metrics. Experimental results show that our Chip Predictor's predicted performance differs from real-measured ones by < 10% when validated using 15 DNN models and 4 platforms (edge-FPGA/TPU/GPU and ASIC). Furthermore, accelerators generated by our AutoDNNchip can achieve better (up to 3.86X improvement) performance than that of expert-crafted state-of-the-art accelerators.

Yue Wang, Ziyu Jiang, Xiaohan Chen et al.

Convolutional neural networks (CNNs) have been increasingly deployed to edge devices. Hence, many efforts have been made towards efficient CNN inference in resource-constrained platforms. This paper attempts to explore an orthogonal direction: how to conduct more energy-efficient training of CNNs, so as to enable on-device training. We strive to reduce the energy cost during training, by dropping unnecessary computations from three complementary levels: stochastic mini-batch dropping on the data level; selective layer update on the model level; and sign prediction for low-cost, low-precision back-propagation, on the algorithm level. Extensive simulations and ablation studies, with real energy measurements from an FPGA board, confirm the superiority of our proposed strategies and demonstrate remarkable energy savings for training. For example, when training ResNet-74 on CIFAR-10, we achieve aggressive energy savings of >90% and >60%, while incurring a top-1 accuracy loss of only about 2% and 1.2%, respectively. When training ResNet-110 on CIFAR-100, an over 84% training energy saving is achieved without degrading inference accuracy.

Yue Wang, Jianghao Shen, Ting-Kuei Hu et al.

State-of-the-art convolutional neural networks (CNNs) yield record-breaking predictive performance, yet at the cost of high-energy-consumption inference, that prohibits their widely deployments in resource-constrained Internet of Things (IoT) applications. We propose a dual dynamic inference (DDI) framework that highlights the following aspects: 1) we integrate both input-dependent and resource-dependent dynamic inference mechanisms under a unified framework in order to fit the varying IoT resource requirements in practice. DDI is able to both constantly suppress unnecessary costs for easy samples, and to halt inference for all samples to meet hard resource constraints enforced; 2) we propose a flexible multi-grained learning to skip (MGL2S) approach for input-dependent inference which allows simultaneous layer-wise and channel-wise skipping; 3) we extend DDI to complex CNN backbones such as DenseNet and show that DDI can be applied towards optimizing any specific resource goals including inference latency or energy cost. Extensive experiments demonstrate the superior inference accuracy-resource trade-off achieved by DDI, as well as the flexibility to control such trade-offs compared to existing peer methods. Specifically, DDI can achieve up to 4 times computational savings with the same or even higher accuracy as compared to existing competitive baselines.