arXiv subjects

Yanfeng Zhang

Publications and source records attributed to Yanfeng Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2025

GastCoCo: Graph Storage and Coroutine-Based Prefetch Co-Design for Dynamic Graph Processing

An efficient data structure is fundamental to meeting the growing demands in dynamic graph processing. However, the dual requirements for graph computation efficiency (with contiguous structures) and graph update efficiency (with linked list-like structures) present a conflict in the design principles of graph structures. After experimental studies of existing state-of-the-art dynamic graph structures, we observe that the overhead of cache misses accounts for a major portion of the graph computation time. This paper presents GastCoCo, a system with graph storage and coroutine-based prefetch co-design. By employing software prefetching via stackless coroutines and introducing a prefetch-friendly data structure CBList, GastCoCo significantly alleviates the performance degradation caused by cache misses. Our results show that GastCoCo outperforms state-of-the-art graph storage systems by 1.3x - 180x in graph updates and 1.4x - 41.1x in graph computation.

cs.DB↗

arXiv2025

A Topology-Aware Localized Update Strategy for Graph-Based ANN Index

The graph-based index has been widely adopted to meet the demand for approximate nearest neighbor search (ANNS) for high-dimensional vectors. However, in dynamic scenarios involving frequent vector insertions and deletions, existing systems improve update throughput by adopting a batch update method. However, a large batch size leads to significant degradation in search accuracy. This work aims to improve the performance of graph-based ANNS systems in small-batch update scenarios, while maintaining high search efficiency and accuracy. We identify two key issues in existing batch update systems for small-batch updates. First, the system needs to scan the entire index file to identify and update the affected vertices, resulting in excessive unnecessary I/O. Second, updating the affected vertices introduces many new neighbors, frequently triggering neighbor pruning. To address these issues, we propose a topology-aware localized update strategy for graph-based ANN index. We introduce a lightweight index topology to identify affected vertices efficiently and employ a localized update strategy that modifies only the affected vertices in the index file. To mitigate frequent heavy neighbor pruning, we propose a similar neighbor replacement strategy, which connects the affected vertices to only a small number (typically one) of the most similar outgoing neighbors of the deleted vertex during repair. Based on extensive experiments on real-world datasets, our update strategy achieves 2.47X-6.45X higher update throughput than the state-of-the-art system FreshDiskANN while maintaining high search efficiency and accuracy.

cs.DB↗

arXiv2025

Realizing stable zig-zag polymeric nitrogen chains in P-N compounds

The zig-zag Nitrogen (N) chain similar to the Ch-N structure has long been considered a potential high energy density structure. However, all previously predicted zig-zag N chain structures similar to Ch-N exhibit imaginary frequencies in their phonon spectra at 0 GPa. Here, we conducted a systematic investigation of P-N compounds using first-principles calculations, uncovering a series of structurally similar stable phases, C2/m-PNx (x = 6, 8, 10, 12, 14), in which N forms zig-zag N chains similar to those in Ch-N. In P-N compounds, the longest zig-zag N chain that can theoretically remain stable under ambient pressure is the N chain composed of 14 N atoms in C2/m-PN14. If the N chain continues to grow, inter-chain vibrational imaginary frequencies will arise in the system. Notably, N chains with an even number of atoms are more likely to be energetically favorable. The five C2/m-PNx phases and one metastable phase (R-PN6) exhibit both remarkable stability and excellent detonability at ambient pressure, positioning them as promising candidates for high-energy-density materials. In addition, the R-PN6 is the first structure to stabilize the N6 ring through covalent bonding, with the covalent network contributing to its high hardness (47.59 GPa).

cond-mat.mtrl-sci↗

arXiv2024

NeutronTP: Load-Balanced Distributed Full-Graph GNN Training with Tensor Parallelism

Graph neural networks (GNNs) have emerged as a promising direction. Training large-scale graphs that relies on distributed computing power poses new challenges. Existing distributed GNN systems leverage data parallelism by partitioning the input graph and distributing it to multiple workers. However, due to the irregular nature of the graph structure, existing distributed approaches suffer from unbalanced workloads and high overhead in managing cross-worker vertex dependencies. In this paper, we leverage tensor parallelism for distributed GNN training. GNN tensor parallelism eliminates cross-worker vertex dependencies by partitioning features instead of graph structures. Different workers are assigned training tasks on different feature slices with the same dimensional size, leading to a complete load balance. We achieve efficient GNN tensor parallelism through two critical functions. Firstly, we employ a generalized decoupled training framework to decouple NN operations from graph aggregation operations, significantly reducing the communication overhead caused by NN operations which must be computed using complete features. Secondly, we employ a memory-efficient task scheduling strategy to support the training of large graphs exceeding single GPU memory, while further improving performance by overlapping communication and computation. By integrating the above techniques, we propose a distributed GNN training system NeutronTP. Our experimental results on a 16-node Aliyun cluster demonstrate that NeutronTP achieves 1.29X-8.72X speedup over state-of-the-art GNN systems including DistDGL, NeutronStar, and Sancus.

cs.DC↗

arXiv2024

TRAPP: An Efficient Point-to-Point Path Planning Algorithm for Road Networks with Restrictions

Path planning is a fundamental problem in road networks, with the goal of finding a path that optimizes objectives such as shortest distance or minimal travel time. Existing methods typically use graph indexing to ensure the efficiency of path planning. However, in real-world road networks, road segments may impose restrictions in terms of height, width, and weight. Most existing works ignore these road restrictions when building indices, which results in returning infeasible paths for vehicles. To address this, a naive approach is to build separate indices for each combination of different types of restrictions. However, this approach leads to a substantial number of indices, as the number of combinations grows explosively with the increase in different restrictions on road segments. In this paper, we propose a novel path planning method, TRAPP(Traffic Restrictions Adaptive Path Planning algorithm), which utilizes traffic flow data from the road network to filter out rarely used road restriction combinations, retain frequently used road restriction combinations, and build indices for them. Additionally, we introduce two optimizations aimed at reducing redundant path information storage within the indices and enhancing the speed of index matching. Our experimental results on real-world road networks demonstrate that TRAPP can effectively reduce the computational and memory overhead associated with building indices while ensuring the efficiency of path planning.

cs.DS↗

arXiv2024

LSMGraph: A High-Performance Dynamic Graph Storage System with Multi-Level CSR

The growing volume of graph data may exhaust the main memory. It is crucial to design a disk-based graph storage system to ingest updates and analyze graphs efficiently. However, existing dynamic graph storage systems suffer from read or write amplification and face the challenge of optimizing both read and write performance simultaneously. To address this challenge, we propose LSMGraph, a novel dynamic graph storage system that combines the write-friendly LSM-tree and the read-friendly CSR. It leverages the multi-level structure of LSM-trees to optimize write performance while utilizing the compact CSR structures embedded in the LSM-trees to boost read performance. LSMGraph uses a new memory structure, MemGraph, to efficiently cache graph updates and uses a multi-level index to speed up reads within the multi-level structure. Furthermore, LSMGraph incorporates a vertex-grained version control mechanism to mitigate the impact of LSM-tree compaction on read performance and ensure the correctness of concurrent read and write operations. Our evaluation shows that LSMGraph significantly outperforms state-of-the-art (graph) storage systems on both graph update and graph analytical workloads.

cs.DB↗

arXiv2024

Broadband and Accurate Electric Tuning of On-Chip Efficient Nonlinear Parametric Conversion

On-chip nonlinear photonic conversion functions with wide and precise tunability as well as high conversion efficiency are highly desirable for a wide range of applications. Photonic crystal micro-ring resonators (PhCR) facilitate efficient nonlinear conversion and enable wavenumber-accurate selection of converted optical modes, but do not support post-fabrication reconfiguration of these operational modes. Coupled-ring resonators, on the other hand, allows post-fabrication reconfiguration but suffers from ambiguity in mode selectivity. We propose a novel segmented photonic crystal micro-ring resonator featuring half-circumference gratings that decouples the locking between the grating Bragg reflection peak and micro-ring resonance frequencies. By introducing complementary thermos-optical controllers that allow differential tuning between the grating reflection peak and the micro-ring resonance, the device supports electrically reconfigurable wavenumber-accurate optical mode selectivity, experimentally demonstrated as a voltage-tunable, power-efficient optical parametric oscillator. The device demonstrates electric tuning of signal and idler frequencies both in a per-FSR stepwise manner and in a gap-free continuous manner, achieving a broad optical frequency tuning range of > 5 THz and a conversion efficiency of >25%. The novel approach introduces unprecedented design flexibility as well as high and precise reconfigurability to integrated nonlinear photonics, providing a new pathway towards future high-performance on-chip nonlinear light sources.

physics.optics↗

arXiv2024

Fast Iterative Graph Computing with Updated Neighbor States

Enhancing the efficiency of iterative computation on graphs has garnered considerable attention in both industry and academia. Nonetheless, the majority of efforts focus on expediting iterative computation by minimizing the running time per iteration step, ignoring the optimization of the number of iteration rounds, which is a crucial aspect of iterative computation. We experimentally verified the correlation between the vertex processing order and the number of iterative rounds, thus making it possible to reduce the number of execution rounds for iterative computation. In this paper, we propose a graph reordering method, GoGraph, which can construct a well-formed vertex processing order effectively reducing the number of iteration rounds and, consequently, accelerating iterative computation. Before delving into GoGraph, a metric function is introduced to quantify the efficiency of vertex processing order in accelerating iterative computation. This metric reflects the quality of the processing order by counting the number of edges whose source precedes the destination. GoGraph employs a divide-and-conquer mindset to establish the vertex processing order by maximizing the value of the metric function. Our experimental results show that GoGraph outperforms current state-of-the-art reordering algorithms by 1.83x on average (up to 3.34x) in runtime.

cs.DC↗

arXiv2024

Comprehensive Evaluation of GNN Training Systems: A Data Management Perspective

Many Graph Neural Network (GNN) training systems have emerged recently to support efficient GNN training. Since GNNs embody complex data dependencies between training samples, the training of GNNs should address distinct challenges different from DNN training in data management, such as data partitioning, batch preparation for mini-batch training, and data transferring between CPUs and GPUs. These factors, which take up a large proportion of training time, make data management in GNN training more significant. This paper reviews GNN training from a data management perspective and provides a comprehensive analysis and evaluation of the representative approaches. We conduct extensive experiments on various benchmark datasets and show many interesting and valuable results. We also provide some practical tips learned from these experiments, which are helpful for designing GNN training systems in the future.

cs.LG↗

arXiv2024

Integrated Optical Vortex Microcomb

The explorations of physical degrees of freedom with infinite dimensionalities, such as orbital angular momentum and frequency of light, have profoundly reshaped the landscape of modern optics with representative photonic functional devices including optical vortex emitters and frequency combs. In nanophotonics, whispering gallery mode microresonators naturally support orbital angular momentum of light and have been demonstrated as on-chip emitters of monochromatic optical vortices. On the other hand, whispering gallery mode microresonators serve as a highly efficient nonlinear optical platform for producing light at different frequencies - i.e., microcombs. Here, we interlace the optical vortices and microcombs by demonstrating an optical vortex comb on an III-V integrated nonlinear microresonator. The angular-grating-dressed nonlinear microring simultaneously emits spatiotemporal light springs consisting of 50 orbital angular momentum modes that are each spectrally addressed to the frequency components (longitudinal whispering gallery modes) of the generated microcomb. We further experimentally generate optical pulses with time-varying orbital angular momenta by carefully introducing a specific intermodal phase relation to spatiotemporal light springs. This work may immediately boost the development of integrated nonlinear/quantum photonics for exploring fundamental optical physics and advancing photonic quantum technology.

physics.optics↗

arXiv2023

NeutronOrch: Rethinking Sample-based GNN Training under CPU-GPU Heterogeneous Environments

Graph Neural Networks (GNNs) have demonstrated outstanding performance in various applications. Existing frameworks utilize CPU-GPU heterogeneous environments to train GNN models and integrate mini-batch and sampling techniques to overcome the GPU memory limitation. In CPU-GPU heterogeneous environments, we can divide sample-based GNN training into three steps: sample, gather, and train. Existing GNN systems use different task orchestrating methods to employ each step on CPU or GPU. After extensive experiments and analysis, we find that existing task orchestrating methods fail to fully utilize the heterogeneous resources, limited by inefficient CPU processing or GPU resource contention. In this paper, we propose NeutronOrch, a system for sample-based GNN training that incorporates a layer-based task orchestrating method and ensures balanced utilization of the CPU and GPU. NeutronOrch decouples the training process by layer and pushes down the training task of the bottom layer to the CPU. This significantly reduces the computational load and memory footprint of GPU training. To avoid inefficient CPU processing, NeutronOrch only offloads the training of frequently accessed vertices to the CPU and lets GPU reuse their embeddings with bounded staleness. Furthermore, NeutronOrch provides a fine-grained pipeline design for the layer-based task orchestrating method, fully overlapping different tasks on heterogeneous resources while strictly guaranteeing bounded staleness. The experimental results show that compared with the state-of-the-art GNN systems, NeutronOrch can achieve up to 11.51x performance speedup.

cs.DC↗

arXiv2023

NeutronStream: A Dynamic GNN Training Framework with Sliding Window for Graph Streams

Existing Graph Neural Network (GNN) training frameworks have been designed to help developers easily create performant GNN implementations. However, most existing GNN frameworks assume that the input graphs are static, but ignore that most real-world graphs are constantly evolving. Though many dynamic GNN models have emerged to learn from evolving graphs, the training process of these dynamic GNNs is dramatically different from traditional GNNs in that it captures both the spatial and temporal dependencies of graph updates. This poses new challenges for designing dynamic GNN training frameworks. First, the traditional batched training method fails to capture real-time structural evolution information. Second, the time-dependent nature makes parallel training hard to design. Third, it lacks system supports for users to efficiently implement dynamic GNNs. In this paper, we present NeutronStream, a framework for training dynamic GNN models. NeutronStream abstracts the input dynamic graph into a chronologically updated stream of events and processes the stream with an optimized sliding window to incrementally capture the spatial-temporal dependencies of events. Furthermore, NeutronStream provides a parallel execution engine to tackle the sequential event processing challenge to achieve high performance. NeutronStream also integrates a built-in graph storage structure that supports dynamic updates and provides a set of easy-to-use APIs that allow users to express their dynamic GNNs. Our experimental results demonstrate that, compared to state-of-the-art dynamic GNN implementations, NeutronStream achieves speedups ranging from 1.48X to 5.87X and an average accuracy improvement of 3.97%.

cs.LG↗

arXiv2023

Towards Transaction as a Service

This paper argues for decoupling transaction processing from existing two-layer cloud-native databases and making transaction processing as an independent service. By building a transaction as a service (TaaS) layer, the transaction processing can be independently scaled for high resource utilization and can be independently upgraded for development agility. Accordingly, we architect an execution-transaction-storage three-layer cloud-native database. By connecting to TaaS, 1) the AP engines can be empowered with ACID TP capability, 2) multiple standalone TP engine instances can be incorporated to support multi-master distributed TP for horizontal scalability, 3) multiple execution engines with different data models can be integrated to support multi-model transactions, and 4) high performance TP is achieved through extensive TaaS optimizations and consistent evolution. Cloud-native databases deserve better architecture: we believe that TaaS provides a path forward to better cloud-native databases.

cs.DB↗

arXiv2023

GeoGauss: Strongly Consistent and Light-Coordinated OLTP for Geo-Replicated SQL Database

Multinational enterprises conduct global business that has a demand for geo-distributed transactional databases. Existing state-of-the-art databases adopt a sharded master-follower replication architecture. However, the single-master serving mode incurs massive cross-region writes from clients, and the sharded architecture requires multiple round-trip acknowledgments (e.g., 2PC) to ensure atomicity for cross-shard transactions. These limitations drive us to seek yet another design choice. In this paper, we propose a strongly consistent OLTP database GeoGauss with full replica multi-master architecture. To efficiently merge the updates from different master nodes, we propose a multi-master OCC that unifies data replication and concurrent transaction processing. By leveraging an epoch-based delta state merge rule and the optimistic asynchronous execution, GeoGauss ensures strong consistency with light-coordinated protocol and allows more concurrency with weak isolation, which are sufficient to meet our needs. Our geo-distributed experimental results show that GeoGauss achieves 7.06X higher throughput and 17.41X lower latency than the state-of-the-art geo-distributed database CockroachDB on the TPC-C benchmark.

cs.DB↗

arXiv2023

Layph: Making Change Propagation Constraint in Incremental Graph Processing by Layering Graph

Real-world graphs are constantly evolving, which demands updates of the previous analysis results to accommodate graph changes. By using the memoized previous computation state, incremental graph computation can reduce unnecessary recomputation. However, a small change may propagate over the whole graph and lead to large-scale iterative computations. To address this problem, we propose Layph, a two-layered graph framework. The upper layer is a skeleton of the graph, which is much smaller than the original graph, and the lower layer has some disjointed subgraphs. Layph limits costly global iterative computations on the original graph to the small graph skeleton and a few subgraphs updated with the input graph changes. In this way, many vertices and edges are not involved in iterative computations, significantly reducing the communication overhead and improving incremental graph processing performance. Our experimental results show that Layph outperforms current state-of-the-art incremental graph systems by 9.08X on average (up to 36.66X) in response time.

cs.DC↗

arXiv2022

Fe-assisted epitaxial growth of 4-inch single-crystal transition-metal dichalcogenides on c-plane sapphire without miscut angle

Epitaxial growth and controllable doping of wafer-scale single-crystal transition-metal dichalcogenides (TMDCs) are two central tasks for extending Moore's law beyond silicon. However, despite considerable efforts, addressing such crucial issues simultaneously under two-dimensional (2D) confinement is yet to be realized. Here we design an ingenious epitaxial strategy to synthesize record-breaking 4-inch single-crystal Fe-doped TMDCs monolayers on industry-compatible c-plane sapphire without miscut angle. In-depth characterizations and theoretical calculations reveal that the introduction of Fe significantly decreases the formation energy of parallel steps on sapphire surfaces and contributes to the edge-nucleation of unidirectional TMDCs domains (>99%). The ultrahigh electron mobility (~86 cm2 V -1 s-1) and remarkable on/off current ratio (~108) are discovered on 4-inch single-crystal Fe-MoS2 monolayers due to the ultralow contact resistance and perfect Ohmic contact with metal electrodes. This work represents a substantial leap in terms of bridging the synthesis and doping of wafer-scale single-crystal 2D semiconductors without the need for substrate miscut, which should promote the further device downscaling and extension of Moore's law.

physics.app-ph↗

arXiv2022

HyTGraph: GPU-Accelerated Graph Processing with Hybrid Transfer Management

Processing large graphs with memory-limited GPU needs to resolve issues of host-GPU data transfer, which is a key performance bottleneck. Existing GPU-accelerated graph processing frameworks reduce the data transfers by managing the active subgraph transfer at runtime. Some frameworks adopt explicit transfer management approaches based on explicit memory copy with filter or compaction. In contrast, others adopt implicit transfer management approaches based on on-demand access with zero-copy or unified-memory. Having made intensive analysis, we find that as the active vertices evolve, the performance of the two approaches varies in different workloads. Due to heavy redundant data transfers, high CPU compaction overhead, or low bandwidth utilization, adopting a single approach often results in suboptimal performance. In this work, we propose a hybrid transfer management approach to take the merits of both the two approaches at runtime, with an objective to achieve the shortest execution time in each iteration. Based on the hybrid approach, we present HytGraph, a GPU-accelerated graph processing framework, which is empowered by a set of effective task scheduling optimizations to improve the performance. Our experimental results on real-world and synthesized graphs demonstrate that HyTGraph achieves up to 10.27X speedup over existing GPU-accelerated graph processing systems including Grus, Subway, and EMOGI.

cs.DC↗

arXiv2021

MVLayoutNet:3D layout reconstruction with multi-view panoramas

We present MVLayoutNet, an end-to-end network for holistic 3D reconstruction from multi-view panoramas. Our core contribution is to seamlessly combine learned monocular layout estimation and multi-view stereo (MVS) for accurate layout reconstruction in both 3D and image space. We jointly train a layout module to produce an initial layout and a novel MVS module to obtain accurate layout geometry. Unlike standard MVSNet [33], our MVS module takes a newly-proposed layout cost volume, which aggregates multi-view costs at the same depth layer into corresponding layout elements. We additionally provide an attention-based scheme that guides the MVS module to focus on structural regions. Such a design considers both local pixel-level costs and global holistic information for better reconstruction. Experiments show that our method outperforms state-of-the-arts in terms of depth rmse by 21.7% and 20.6% on the 2D-3D-S [1] and ZInD [5] datasets. Finally, our method leads to coherent layout geometry that enables the reconstruction of an entire scene.

cs.CV↗