arXiv subjects

Xulong Tang

Publications and source records attributed to Xulong Tang.

36 records · Page 2Linked to original sources

arXiv2025

Pruner: A Draft-then-Verify Exploration Mechanism to Accelerate Tensor Program Tuning

Tensor program tuning is essential for the efficient deployment of deep neural networks. Search-based approaches have demonstrated scalability and effectiveness in automatically finding high-performance programs for specific hardware. However, the search process is often inefficient, taking hours or even days to discover optimal programs due to the exploration mechanisms guided by an accurate but slow-learned cost model. Meanwhile, the learned cost model trained on one platform cannot seamlessly adapt online to another, which we call cross-platform online unawareness. In this work, we propose Pruner and MoA-Pruner. Pruner is a "Draft-then-Verify" exploration mechanism that accelerates the schedule search process. Instead of applying the complex learned cost model to all explored candidates, Pruner drafts small-scale potential candidates by introducing a naive Symbol-based Analyzer (draft model), then identifies the best candidates by the learned cost model. MoA-Pruner introduces a Momentum online Adaptation strategy to address the cross-platform online unawareness. We incorporate Pruner into the TVM and conduct extensive experiments on three GPU-based platforms. Results show considerable speedup in schedule search time. In online tuning scenarios, Pruner and MoA-Pruner achieve an average speedup of $2.6 \times$ and $4.82 \times$ compared to Ansor. In offline tuning scenarios, Pruner achieves an average speedup of $4.75 \times$ and $4.05\times$ compared to TenSet and TLP, respectively. Furthermore, Pruner achieves an average speedup of $4.08 \times$ compared to MetaSchedule on TensorCore.

cs.LG↗

arXiv2024

CoheDancers: Enhancing Interactive Group Dance Generation through Music-Driven Coherence Decomposition

Dance generation is crucial and challenging, particularly in domains like dance performance and virtual gaming. In the current body of literature, most methodologies focus on Solo Music2Dance. While there are efforts directed towards Group Music2Dance, these often suffer from a lack of coherence, resulting in aesthetically poor dance performances. Thus, we introduce CoheDancers, a novel framework for Music-Driven Interactive Group Dance Generation. CoheDancers aims to enhance group dance generation coherence by decomposing it into three key aspects: synchronization, naturalness, and fluidity. Correspondingly, we develop a Cycle Consistency based Dance Synchronization strategy to foster music-dance correspondences, an Auto-Regressive-based Exposure Bias Correction strategy to enhance the fluidity of the generated dances, and an Adversarial Training Strategy to augment the naturalness of the group dance output. Collectively, these strategies enable CohdeDancers to produce highly coherent group dances with superior quality. Furthermore, to establish better benchmarks for Group Music2Dance, we construct the most diverse and comprehensive open-source dataset to date, I-Dancers, featuring rich dancer interactions, and create comprehensive evaluation metrics. Experimental evaluations on I-Dancers and other extant datasets substantiate that CoheDancers achieves unprecedented state-of-the-art performance. Code will be released.

cs.SD↗

arXiv2024

The Stabilizer Bootstrap of Quantum Machine Learning with up to 10000 qubits

Quantum machine learning is considered one of the flagship applications of quantum computers, where variational quantum circuits could be the leading paradigm both in the near-term quantum devices and the early fault-tolerant quantum computers. However, it is not clear how to identify the regime of quantum advantages from these circuits, and there is no explicit theory to guide the practical design of variational ansatze to achieve better performance. We address these challenges with the stabilizer bootstrap, a method that uses stabilizer-based techniques to optimize quantum neural networks before their quantum execution, together with theoretical proofs and high-performance computing with 10000 qubits or random datasets up to 1000 data. We find that, in a general setup of variational ansatze, the possibility of improvements from the stabilizer bootstrap depends on the structure of the observables and the size of the datasets. The results reveal that configurations exhibit two distinct behaviors: some maintain a constant probability of circuit improvement, while others show an exponential decay in improvement probability as qubit numbers increase. These patterns are termed strong stabilizer enhancement and weak stabilizer enhancement, respectively, with most situations falling in between. Our work seamlessly bridges techniques from fault-tolerant quantum computing with applications of variational quantum algorithms. Not only does it offer practical insights for designing variational circuits tailored to large-scale machine learning challenges, but it also maps out a clear trajectory for defining the boundaries of feasible and practical quantum advantages.

quant-ph↗

arXiv2024

Using Reinforcement Learning to Guide Graph State Generation for Photonic Quantum Computers

Photonic quantum computer (PQC) is an emerging and promising quantum computing paradigm that has gained momentum in recent years. In PQC, which leverages the measurement-based quantum computing (MBQC) model, computations are executed by performing measurements on photons in graph states (i.e., sets of entangled photons) that are generated before measurements. The graph state in PQC is generated deterministically by quantum emitters. The generation process is achieved by applying a sequence of quantum gates to quantum emitters. In this process, i) the time required to complete the process, ii) the number of quantum emitters used, and iii) the number of CZ gates performed between emitters greatly affect the fidelity of the generated graph state. However, prior work for determining the generation sequence only focuses on optimizing the number of quantum emitters. Moreover, identifying the optimal generation sequence has vast search space. To this end, we propose RLGS, a novel compilation framework to identify optimal generation sequences that optimize the three metrics. Experimental results show that RLGS achieves an average reduction in generation time of 31.1%, 49.6%, and 57.5% for small, medium, and large graph states compared to the baseline.

quant-ph↗

arXiv2024

Lotus: learning-based online thermal and latency variation management for two-stage detectors on edge devices

Two-stage object detectors exhibit high accuracy and precise localization, especially for identifying small objects that are favorable for various edge applications. However, the high computation costs associated with two-stage detection methods cause more severe thermal issues on edge devices, incurring dynamic runtime frequency change and thus large inference latency variations. Furthermore, the dynamic number of proposals in different frames leads to various computations over time, resulting in further latency variations. The significant latency variations of detectors on edge devices can harm user experience and waste hardware resources. To avoid thermal throttling and provide stable inference speed, we propose Lotus, a novel framework that is tailored for two-stage detectors to dynamically scale CPU and GPU frequencies jointly in an online manner based on deep reinforcement learning (DRL). To demonstrate the effectiveness of Lotus, we implement it on NVIDIA Jetson Orin Nano and Mi 11 Lite mobile platforms. The results indicate that Lotus can consistently and significantly reduce latency variation, achieve faster inference, and maintain lower CPU and GPU temperatures under various settings.

cs.CV↗

arXiv2024

Improving GPU Multi-Tenancy Through Dynamic Multi-Instance GPU Reconfiguration

Continuous learning (CL) has emerged as one of the most popular deep learning paradigms deployed in modern cloud GPUs. Specifically, CL has the capability to continuously update the model parameters (through model retraining) and use the updated model (if available) to serve overtime arriving inference requests. It is generally beneficial to co-locate the retraining and inference together to enable timely model updates and avoid model transfer overheads. This brings the need for GPU sharing among retraining and inferences. Meanwhile, multiple CL workloads can share the modern GPUs in the cloud, leading to multi-tenancy execution. In this paper, we observe that prior GPU-sharing techniques are not optimized for multi-tenancy CL workloads. Specifically, they do not coherently consider the accuracy of the retraining model and the inference service level objective (SLO) attainment. Moreover, they cannot accommodate the overtime dynamics (e.g., inference arrival intensity) in CL execution. In this paper, we propose MIGRator, a novel GPU reconfiguration runtime that dynamically performs GPU reconfiguration for multi-tenancy CL workloads. MIGRator is based on the recent NVIDIA multi-instance GPU (MIG) to mitigate resource contention and formulates the reconfiguration optimization into Integer Linear Programming (ILP) to dynamically identify, reconfigure, and allocate the GPU instances. MIGRator leverages the "Goodput" metric in the ILP objective function to consider both inference SLO attainment and model accuracy in the reconfiguration exploration. We evaluate MIGRator using representative multi-tenancy CL workloads. The results show our approach outperforms the state-of-the-art GPU sharing techniques (i.e., Ekya, Astraea, and PARIS) by 17\%, 21\%, and 20\%, respectively.

cs.DC↗

arXiv2024

Improving Multi-Instance GPU Efficiency via Sub-Entry Sharing TLB Design

NVIDIA's Multi-Instance GPU (MIG) technology enables partitioning GPU computing power and memory into separate hardware instances, providing complete isolation including compute resources, caches, and memory. However, prior work identifies that MIG does not extend to partitioning the last-level TLB (i.e., L3 TLB), which remains shared among all instances. To enhance TLB reach, NVIDIA GPUs reorganized the TLB structure with 16 sub-entries in each L3 TLB entry that have a one-to-one mapping to the address translations for 16 pages of size 64KB located within the same 1MB aligned range. Our comprehensive investigation of address translation efficiency in MIG identifies two main issues caused by L3 TLB sharing interference: (i) it results in performance degradation for co-running applications, and (ii) TLB sub-entries are not fully utilized before eviction. Based on this observation, we propose STAR to improve the utilization of TLB sub-entries through dynamic sharing of TLB entries across multiple base addresses. STAR evaluates TLB entries based on their sub-entry utilization to optimize address translation storage, dynamically adjusting between a shared and non-shared status to cater to current demand. We show that STAR improves overall performance by an average of 30.2% across various multi-tenant workloads.

cs.DC↗

arXiv2024

SmartFRZ: An Efficient Training Framework using Attention-Based Layer Freezing

There has been a proliferation of artificial intelligence applications, where model training is key to promising high-quality services for these applications. However, the model training process is both time-intensive and energy-intensive, inevitably affecting the user's demand for application efficiency. Layer freezing, an efficient model training technique, has been proposed to improve training efficiency. Although existing layer freezing methods demonstrate the great potential to reduce model training costs, they still remain shortcomings such as lacking generalizability and compromised accuracy. For instance, existing layer freezing methods either require the freeze configurations to be manually defined before training, which does not apply to different networks, or use heuristic freezing criteria that is hard to guarantee decent accuracy in different scenarios. Therefore, there lacks a generic and smart layer freezing method that can automatically perform ``in-situation'' layer freezing for different networks during training processes. To this end, we propose a generic and efficient training framework (SmartFRZ). The core proposed technique in SmartFRZ is attention-guided layer freezing, which can automatically select the appropriate layers to freeze without compromising accuracy. Experimental results show that SmartFRZ effectively reduces the amount of computation in training and achieves significant training acceleration, and outperforms the state-of-the-art layer freezing approaches.

cs.LG↗

arXiv2023

Minimizing Photonic Cluster State Depth in Measurement-Based Quantum Computing

Measurement-based quantum computing (MBQC) is a promising quantum computing paradigm that performs computation through ``one-way'' measurements on entangled quantum qubits. It is widely used in photonic quantum computing (PQC), where the computation is carried out on photonic cluster states (i.e., a 2-D mesh of entangled photons). In MBQC-based PQC, the cluster state depth (i.e., the length of one-way measurements) to execute a quantum circuit plays an important role in the overall execution time and error. Thus, it is important to reduce the cluster state depth. In this paper, we propose FMCC, a compilation framework that employs dynamic programming to efficiently minimize the cluster state depth. Experimental results on five representative quantum algorithms show that FMCC achieves 53.6%, 60.6%, and 60.0% average depth reductions in small, medium, and large qubit counts compared to the state-of-the-art MBQC compilation frameworks.

quant-ph↗

arXiv2023

BeatDance: A Beat-Based Model-Agnostic Contrastive Learning Framework for Music-Dance Retrieval

Dance and music are closely related forms of expression, with mutual retrieval between dance videos and music being a fundamental task in various fields like education, art, and sports. However, existing methods often suffer from unnatural generation effects or fail to fully explore the correlation between music and dance. To overcome these challenges, we propose BeatDance, a novel beat-based model-agnostic contrastive learning framework. BeatDance incorporates a Beat-Aware Music-Dance InfoExtractor, a Trans-Temporal Beat Blender, and a Beat-Enhanced Hubness Reducer to improve dance-music retrieval performance by utilizing the alignment between music beats and dance movements. We also introduce the Music-Dance (MD) dataset, a large-scale collection of over 10,000 music-dance video pairs for training and testing. Experimental results on the MD dataset demonstrate the superiority of our method over existing baselines, achieving state-of-the-art performance. The code and dataset will be made public available upon acceptance.

cs.SD↗

arXiv2023

SupeRBNN: Randomized Binary Neural Network Using Adiabatic Superconductor Josephson Devices

Adiabatic Quantum-Flux-Parametron (AQFP) is a superconducting logic with extremely high energy efficiency. By employing the distinct polarity of current to denote logic `0' and `1', AQFP devices serve as excellent carriers for binary neural network (BNN) computations. Although recent research has made initial strides toward developing an AQFP-based BNN accelerator, several critical challenges remain, preventing the design from being a comprehensive solution. In this paper, we propose SupeRBNN, an AQFP-based randomized BNN acceleration framework that leverages software-hardware co-optimization to eventually make the AQFP devices a feasible solution for BNN acceleration. Specifically, we investigate the randomized behavior of the AQFP devices and analyze the impact of crossbar size on current attenuation, subsequently formulating the current amplitude into the values suitable for use in BNN computation. To tackle the accumulation problem and improve overall hardware performance, we propose a stochastic computing-based accumulation module and a clocking scheme adjustment-based circuit optimization method. We validate our SupeRBNN framework across various datasets and network architectures, comparing it with implementations based on different technologies, including CMOS, ReRAM, and superconducting RSFQ/ERSFQ. Experimental results demonstrate that our design achieves an energy efficiency of approximately 7.8x10^4 times higher than that of the ReRAM-based BNN framework while maintaining a similar level of model accuracy. Furthermore, when compared with superconductor-based counterparts, our framework demonstrates at least two orders of magnitude higher energy efficiency.

cs.ET↗

arXiv2022

Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training

Recently, sparse training has emerged as a promising paradigm for efficient deep learning on edge devices. The current research mainly devotes efforts to reducing training costs by further increasing model sparsity. However, increasing sparsity is not always ideal since it will inevitably introduce severe accuracy degradation at an extremely high sparsity level. This paper intends to explore other possible directions to effectively and efficiently reduce sparse training costs while preserving accuracy. To this end, we investigate two techniques, namely, layer freezing and data sieving. First, the layer freezing approach has shown its success in dense model training and fine-tuning, yet it has never been adopted in the sparse training domain. Nevertheless, the unique characteristics of sparse training may hinder the incorporation of layer freezing techniques. Therefore, we analyze the feasibility and potentiality of using the layer freezing technique in sparse training and find it has the potential to save considerable training costs. Second, we propose a data sieving method for dataset-efficient training, which further reduces training costs by ensuring only a partial dataset is used throughout the entire training process. We show that both techniques can be well incorporated into the sparse training algorithm to form a generic framework, which we dub SpFDE. Our extensive experiments demonstrate that SpFDE can significantly reduce training costs while preserving accuracy from three dimensions: weight sparsity, layer freezing, and dataset sieving.

cs.LG↗

arXiv2022

Demystifying Arch-hints for Model Extraction: An Attack in Unified Memory System

The deep neural network (DNN) models are deemed confidential due to their unique value in expensive training efforts, privacy-sensitive training data, and proprietary network characteristics. Consequently, the model value raises incentive for adversary to steal the model for profits, such as the representative model extraction attack. Emerging attack can leverage timing-sensitive architecture-level events (i.e., Arch-hints) disclosed in hardware platforms to extract DNN model layer information accurately. In this paper, we take the first step to uncover the root cause of such Arch-hints and summarize the principles to identify them. We then apply these principles to emerging Unified Memory (UM) management system and identify three new Arch-hints caused by UM's unique data movement patterns. We then develop a new extraction attack, UMProbe. We also create the first DNN benchmark suite in UM and utilize the benchmark suite to evaluate UMProbe. Our evaluation shows that UMProbe can extract the layer sequence with an accuracy of 95% for almost all victim test models, which thus calls for more attention to the DNN security in UM system.

cs.CR↗

arXiv2022

Sustainable AI Processing at the Edge

Edge computing is a popular target for accelerating machine learning algorithms supporting mobile devices without requiring the communication latencies to handle them in the cloud. Edge deployments of machine learning primarily consider traditional concerns such as SWaP constraints (Size, Weight, and Power) for their installations. However, such metrics are not entirely sufficient to consider environmental impacts from computing given the significant contributions from embodied energy and carbon. In this paper we explore the tradeoffs of convolutional neural network acceleration engines for both inference and on-line training. In particular, we explore the use of processing-in-memory (PIM) approaches, mobile GPU accelerators, and recently released FPGAs, and compare them with novel Racetrack memory PIM. Replacing PIM-enabled DDR3 with Racetrack memory PIM can recover its embodied energy as quickly as 1 year. For high activity ratios, mobile GPUs can be more sustainable but have higher embodied energy to overcome compared to PIM-enabled Racetrack memory.

cs.AR↗

arXiv2022

A Survey of Large-Scale Deep Learning Serving System Optimization: Challenges and Opportunities

Deep Learning (DL) models have achieved superior performance in many application domains, including vision, language, medical, commercial ads, entertainment, etc. With the fast development, both DL applications and the underlying serving hardware have demonstrated strong scaling trends, i.e., Model Scaling and Compute Scaling, for example, the recent pre-trained model with hundreds of billions of parameters with ~TB level memory consumption, as well as the newest GPU accelerators providing hundreds of TFLOPS. With both scaling trends, new problems and challenges emerge in DL inference serving systems, which gradually trends towards Large-scale Deep learning Serving systems (LDS). This survey aims to summarize and categorize the emerging challenges and optimization opportunities for large-scale deep learning serving systems. By providing a novel taxonomy, summarizing the computing paradigms, and elaborating the recent technique advances, we hope that this survey could shed light on new optimization perspectives and motivate novel works in large-scale deep learning system optimization.

cs.LG↗

arXiv2021

Automated Runtime-Aware Scheduling for Multi-Tenant DNN Inference on GPU

With the fast development of deep neural networks (DNNs), many real-world applications are adopting multiple models to conduct compound tasks, such as co-running classification, detection, and segmentation models on autonomous vehicles. Such multi-tenant DNN inference cases greatly exacerbate the computational complexity and call for comprehensive collaboration for graph-level operator scheduling, runtime-level resource awareness, as well as hardware scheduler support. However, the current scheduling support for such multi-tenant inference is still relatively backward. In this work, we propose a resource-aware scheduling framework for efficient multi-tenant DNN inference on GPU, which automatically coordinates DNN computing in different execution levels. Leveraging the unified scheduling intermediate representation and the automated ML-based searching algorithm, optimal schedules could be generated to wisely adjust model concurrency and interleave DNN model operators, maintaining a continuously balanced resource utilization across the entire inference process, and eventually improving the runtime efficiency. Experiments show that we could consistently achieve 1.3-1.7x speed-up, compared to regular DNN runtime libraries (e.g., CuDNN, TVM) and particular concurrent scheduling methods (e.g., NVIDIA Multi-Stream).

cs.DC↗

arXiv2021

Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration

Weight pruning is an effective model compression technique to tackle the challenges of achieving real-time deep neural network (DNN) inference on mobile devices. However, prior pruning schemes have limited application scenarios due to accuracy degradation, difficulty in leveraging hardware acceleration, and/or restriction on certain types of DNN layers. In this paper, we propose a general, fine-grained structured pruning scheme and corresponding compiler optimizations that are applicable to any type of DNN layer while achieving high accuracy and hardware inference performance. With the flexibility of applying different pruning schemes to different layers enabled by our compiler optimizations, we further probe into the new problem of determining the best-suited pruning scheme considering the different acceleration and accuracy performance of various pruning schemes. Two pruning scheme mapping methods, one is search-based and the other is rule-based, are proposed to automatically derive the best-suited pruning regularity and block size for each layer of any given DNN. Experimental results demonstrate that our pruning scheme mapping methods, together with the general fine-grained structured pruning scheme, outperform the state-of-the-art DNN optimization framework with up to 2.48$\times$ and 1.73$\times$ DNN inference acceleration on CIFAR-10 and ImageNet dataset without accuracy loss.

cs.LG↗

arXiv2020

YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design

The rapid development and wide utilization of object detection techniques have aroused attention on both accuracy and speed of object detectors. However, the current state-of-the-art object detection works are either accuracy-oriented using a large model but leading to high latency or speed-oriented using a lightweight model but sacrificing accuracy. In this work, we propose YOLObile framework, a real-time object detection on mobile devices via compression-compilation co-design. A novel block-punched pruning scheme is proposed for any kernel size. To improve computational efficiency on mobile devices, a GPU-CPU collaborative scheme is adopted along with advanced compiler-assisted optimizations. Experimental results indicate that our pruning scheme achieves 14$\times$ compression rate of YOLOv4 with 49.0 mAP. Under our YOLObile framework, we achieve 17 FPS inference speed using GPU on Samsung Galaxy S20. By incorporating our proposed GPU-CPU collaborative scheme, the inference speed is increased to 19.1 FPS, and outperforms the original YOLOv4 by 5$\times$ speedup. Source code is at: \url{https://github.com/nightsnack/YOLObile}.

cs.CV↗