arXiv subjects

Ming-Chang Yang

Publications and source records attributed to Ming-Chang Yang.

13 recordsLinked to original sources

arXiv2026

SieveIVF: Threshold-Aware IVF Execution for Large-Scale Training Data Deduplication

Embedding-based training data deduplication retrieves candidate duplicate edges above an application similarity threshold, but fixed-probe inverted-file (IVF) search ignores this predicate when giving every query the same partition budget. Across four Hunyuan workloads, qualifying neighbors appear early despite sharply varying search depths. We present SieveIVF, a threshold-aware IVF executor that stops after $W$ consecutive searches find no qualifying candidate. The systems challenge is to preserve partition-major batching when each query's remaining work depends on prior results. Continuous batching groups ready queries by partition. A lookahead scheduler layers on top, exposing only work committed by the stopping rule to increase concurrency without changing stopping decisions or returned results. We implement SieveIVF in Lance. At $W=8$, SieveIVF is $4.1$--$7.6\times$ faster than fixed-probe IVF on four 10M Hunyuan workloads and $6.1$--$8.4\times$ faster on two public 100M workloads under the same index and search parameters, with pooled filtered top-10 recall losses of $0.03$--$1.13$ percentage points on Hunyuan and $1.43$--$2.29$ percentage points on the public workloads. These results show how an application predicate can guide IVF work allocation without changing the index or bounded top-$k$ interface.

cs.DB↗

arXiv2026

DMG: A Scalable and Efficient Memory-Disaggregated Graph Processing System

Traditional graph processing systems are built on monolithic servers, which couple a fixed ratio of compute and memory resources but often result in resource under-utilization in data centers. Although the disaggregated memory (DM) architecture has emerged to address this inefficiency, we identify that existing graph processing systems on DM remain highly impractical. They rely on unscalable architectures that fail to scale beyond a single memory node and a single compute node, and they require compute-side caches that are orders of magnitude larger than conventional practice in DM. To this end, this paper presents DMG, the first practical graph processing system on DM, which demonstrates superior system scalability and cache efficiency while delivering high performance. To improve efficiency of graph retrieval on DM, DMG proposes a DM-friendly graph store with retrieval optimizations. To mitigate costly update propagation, DMG presents an adaptive update coordinator that coordinates compute and memory nodes to perform update propagation with low overhead. To enable fast and effective load balancing, DMG employs a two-stage workload manager that includes a coarse-grained initial partitioning and a fine-grained runtime re-scheduling. Experimental results substantiate that compared with the state-of-the-art DM-based graph processing system, DMG can elastically scale up both compute and memory resources, delivering up to 4.9X better performance and accommodating graphs with ever-increasing sizes; meanwhile, it effectively tames the compute-side cache demands by up to 18.9X, positioning itself as a DM-ready solution in practice.

cs.DB↗

arXiv2026

Black-Box Performance Evaluation of Elastic Block Storage: Contract, Rate-Limiting Model, and Software Exploration

Elastic block storage (EBS) with the storage-compute disaggregated architecture is a key component in modern cloud infrastructure. EBS offers users storage resources in the form of elastic solid-state drives (ESSDs). Nonetheless, despite recent efforts that have documented EBS architectures from the provider's perspective, how ESSDs perform differently from local SSDs and how host software should adapt accordingly have not been sufficiently studied. In this paper, we conduct a user-centric, black-box performance characterization of ESSDs from Amazon AWS and Alibaba Cloud. We make three main contributions: (1) an ESSD contract that presents four behavioral observations and five actionable implications for software adaptation, (2) a refined I/O rate-limiting model combining bandwidth-IOPS dual limiting and fine-grained token refilling to suppress latency spikes, and (3) a case study on RocksDB that derives four guidelines on cache management, I/O regulation, storage budget utilization, and compression algorithms. Collectively, we hope these contributions can serve as a practical reference for EBS users to understand and exploit the distinctive performance properties of ESSDs.

cs.PF↗

arXiv2026

Aquifer: Hierarchical Memory Pooling with CXL and RDMA for MicroVM Snapshots

Memory stranding wastes 25-35% of installed DRAM in production cloud clusters. Memory pooling over CXL and RDMA offers a remedy, but neither technology alone suffices: CXL provides low-latency, load/store-transparent access limited to a pod, while RDMA provides cluster-wide reach at higher latency with software overhead. A hierarchical architecture combining both tiers is the practical path forward, yet remains unexplored for MicroVM-based serverless computing, where snapshot restore latency is the dominant cold-start bottleneck. We present Aquifer, the first system to serve MicroVM snapshots from a hierarchical CXL+RDMA memory pool. A characterization of snapshot images reveals that the vast majority of pages are either zero or cold, enabling a hotness-based snapshot format that eliminates zero pages and places only the hot working set in the CXL pool while storing cold pages in the RDMA pool. Sharing these snapshots across hosts on CXL 2.0 multi-headed devices, which lack hardware cache coherence, requires Aquifer's ownership-based coherence protocol to ensure correctness. Finally, Aquifer uses a copy-based page serving mechanism pre-installs hot pages from CXL memory before MicroVM resume and demand-pages cold pages asynchronously from RDMA. On emulated CXL+RDMA hardware, Aquifer achieves a 2.2x geometric-mean speedup in end-to-end invocation time over Firecracker and 1.1x over the next best alternative.

cs.DC↗

arXiv2026

Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving

Long-context LLM serving is bottlenecked by the cost of attending over ever-growing KV caches. Dynamic sparse attention promises relief by accessing only a small, query-dependent subset of the KV state per decoding step and extending the KV storage to CPU memory. In practice, however, these algorithmic savings rarely translate into end-to-end system-level gains because sparse methods typically operate at different granularities and thus rely on ad hoc, per-algorithm implementations. At the same time, hierarchical KV storage introduces a new systems bottleneck: retrieving fine-grained, irregular KV subsets across the GPU-CPU boundary can easily erase the benefits of sparsity. We present SPIN, a sparse-attention-aware inference framework that co-designs the execution pipeline with hierarchical KV storage through three techniques: (1) a unified partition abstraction that maps different sparsity granularities onto a shared page-based KV substrate; (2) a locality-aware KV cache manager that dynamically sizes per-request HBM budgets and uses a GPU-friendly bucketed LRU policy to cut PCIe round-trips; and (3) a two-level hierarchical metadata layout sized to the active working set rather than the worst-case address space. Built on vLLM with three representative sparse attention algorithms, SPIN delivers 1.66-5.66x higher end-to-end throughput and 7-9x lower TTFT than vLLM, and reduces TPOT by up to 58% over the original sparse-attention implementations.

cs.LG↗

arXiv2025

Lotus: Optimizing Disaggregated Transactions with Disaggregated Locks

Disaggregated memory (DM) separates compute and memory resources, allowing flexible scaling to achieve high resource utilization. To ensure atomic and consistent data access on DM, distributed transaction systems have been adapted, where compute nodes (CNs) rely on one-sided RDMA operations to access remote data in memory nodes (MNs). However, we observe that in existing transaction systems, the RDMA network interface cards at MNs become a primary performance bottleneck. This bottleneck arises from the high volume of one-sided atomic operations used for locks, which hinders the system's ability to scale efficiently. To address this issue, this paper presents Lotus, a scalable distributed transaction system with lock disaggregation on DM. The key innovation of Lotus is to disaggregate locks from data and execute all locks on CNs, thus eliminating the bottleneck at MN RNICs. To achieve efficient lock management on CNs, Lotus employs an application-aware lock management mechanism that leverages the locality of the OLTP workloads to shard locks while maintaining load balance. To ensure consistent transaction processing with lock disaggregation, Lotus introduces a lock-first transaction protocol, which separates the locking phase as the first step in each read-write transaction execution. This protocol allows the system to determine the success of lock acquisitions early and proactively abort conflicting transactions, improving overall efficiency. To tolerate lock loss during CN failures, Lotus employs a lock-rebuild-free recovery mechanism that treats locks as ephemeral and avoids their reconstruction, ensuring lightweight recovery for CN failures. Experimental results demonstrate that Lotus improves transaction throughput by up to 2.1$\times$ and reduces latency by up to 49.4% compared to state-of-the-art transaction systems on DM.

cs.DC↗

arXiv2025

FlexKV: Flexible Index Offloading for Memory-Disaggregated Key-Value Store

Disaggregated memory (DM) is a promising data center architecture that decouples CPU and memory into independent resource pools to improve resource utilization. Building on DM, memory-disaggregated key-value (KV) stores are adopted to efficiently manage remote data. Unfortunately, existing approaches suffer from poor performance due to two critical issues: 1) the overdependence on one-sided atomic operations in index processing, and 2) the constrained efficiency in compute-side caches. To address these issues, we propose FlexKV, a memory-disaggregated KV store with index proxying. Our key idea is to dynamically offload the index to compute nodes, leveraging their powerful CPUs to accelerate index processing and maintain high-performance compute-side caches. Three challenges have to be addressed to enable efficient index proxying on DM, i.e., the load imbalance across compute nodes, the limited memory of compute nodes, and the expensive cache coherence overhead. FlexKV proposes: 1) a rank-aware hotness detection algorithm to continuously balance index load across compute nodes, 2) a two-level CN memory optimization scheme to efficiently utilize compute node memory, and 3) an RPC-aggregated cache management mechanism to reduce cache coherence overhead. The experimental results show that FlexKV improves throughput by up to 2.94$\times$ and reduces latency by up to 85.2%, compared with the state-of-the-art memory-disaggregated KV stores.

cs.DC↗

arXiv2025

The Unwritten Contract of Cloud-based Elastic Solid-State Drives

Elastic block storage (EBS) with the storage-compute disaggregated architecture stands as a pivotal piece in today's cloud. EBS furnishes users with storage capabilities through the elastic solid-state drive (ESSD). Nevertheless, despite the widespread integration into cloud services, the absence of a thorough ESSD performance characterization raises critical doubt: when more and more services are shifted onto the cloud, can ESSD satisfactorily substitute the storage responsibilities of the local SSD and offer comparable performance? In this paper, we for the first time target this question by characterizing two ESSDs from Amazon AWS and Alibaba Cloud. We present an unwritten contract of cloud-based ESSDs, encapsulating four observations and five implications for cloud storage users. Specifically, the observations are counter-intuitive and contrary to the conventional perceptions of what one would expect from the local SSD. The implications we hope could guide users in revisiting the designs of their deployed cloud software, i.e., harnessing the distinct characteristics of ESSDs for better system performance.

cs.PF↗

arXiv2025

Prefill-Decode Aggregation or Disaggregation? Unifying Both for Goodput-Optimized LLM Serving

An ongoing debate considers whether prefill-decode (PD) aggregation or disaggregation is superior for serving large language models (LLMs). This has driven optimizations for both approaches, each showing distinct advantages. This paper compares PD aggregation and disaggregation, showing that each excels under different service-level objectives (SLOs): aggregation is optimal for tight time-to-first-token (TTFT) and relaxed time-per-output-token (TPOT), while disaggregation excels for strict TPOT and relaxed TTFT. However, under balanced TTFT and TPOT SLOs, neither approach delivers optimal goodput. This paper proposes TaiChi, an LLM serving system that unifies PD disaggregation and aggregation for optimal goodput under any combination of TTFT and TPOT SLOs. TaiChi uses a unified disaggregation-aggregation architecture with differentiated-capability GPU instances: prefill-heavy (fast prefill, high-interference decode) and decode-heavy (low-interference decode, slow prefill). Three configurable sliders control the ratio between these instances and their chunk sizes. TaiChi adapts to various SLO regimes by adjusting sliders. When TTFT constraints are tight, TaiChi resembles a PD aggregation configuration; when TPOT dominates, it adapts toward PD disaggregation. Crucially, under balanced SLOs, TaiChi enables a hybrid mode for superior goodput. The key innovation behind this hybrid mode is latency shifting: selectively reallocating GPU resources from requests that meet SLOs to those at risk of violation, maximizing the number of SLO-satisfied requests. This fine-grained latency shifting is orchestrated by two scheduling mechanisms: flowing decode scheduling to control TPOTs and length-aware prefill scheduling to manage TTFTs, which jointly optimize request assignment. Our experiments show TaiChi improves goodput by up to 77% over state-of-the-art systems under balanced TTFT and TPOT SLOs.

cs.DC↗

arXiv2024

ControlNeXt: Powerful and Efficient Control for Image and Video Generation

Diffusion models have demonstrated remarkable and robust abilities in both image and video generation. To achieve greater control over generated results, researchers introduce additional architectures, such as ControlNet, Adapters and ReferenceNet, to integrate conditioning controls. However, current controllable generation methods often require substantial additional computational resources, especially for video generation, and face challenges in training or exhibit weak control. In this paper, we propose ControlNeXt: a powerful and efficient method for controllable image and video generation. We first design a more straightforward and efficient architecture, replacing heavy additional branches with minimal additional cost compared to the base model. Such a concise structure also allows our method to seamlessly integrate with other LoRA weights, enabling style alteration without the need for additional training. As for training, we reduce up to 90% of learnable parameters compared to the alternatives. Furthermore, we propose another method called Cross Normalization (CN) as a replacement for Zero-Convolution' to achieve fast and stable training convergence. We have conducted various experiments with different base models across images and videos, demonstrating the robustness of our method.

cs.CV↗

arXiv2022

Measuring and Improving the Use of Graph Information in Graph Neural Networks

Graph neural networks (GNNs) have been widely used for representation learning on graph data. However, there is limited understanding on how much performance GNNs actually gain from graph data. This paper introduces a context-surrounding GNN framework and proposes two smoothness metrics to measure the quantity and quality of information obtained from graph data. A new GNN model, called CS-GNN, is then designed to improve the use of graph information based on the smoothness values of a graph. CS-GNN is shown to achieve better performance than existing methods in different types of real graphs.

cs.LG↗

arXiv2022

A Representation Learning Framework for Property Graphs

Representation learning on graphs, also called graph embedding, has demonstrated its significant impact on a series of machine learning applications such as classification, prediction and recommendation. However, existing work has largely ignored the rich information contained in the properties (or attributes) of both nodes and edges of graphs in modern applications, e.g., those represented by property graphs. To date, most existing graph embedding methods either focus on plain graphs with only the graph topology, or consider properties on nodes only. We propose PGE, a graph representation learning framework that incorporates both node and edge properties into the graph embedding procedure. PGE uses node clustering to assign biases to differentiate neighbors of a node and leverages multiple data-driven matrices to aggregate the property information of neighbors sampled based on a biased strategy. PGE adopts the popular inductive model for neighborhood aggregation. We provide detailed analyses on the efficacy of our method and validate the performance of PGE by showing how PGE achieves better embedding results than the state-of-the-art graph embedding methods on benchmark applications such as node classification and link prediction over real-world datasets.

cs.LG↗

arXiv2019

Understanding and Improving Proximity Graph based Maximum Inner Product Search

The inner-product navigable small world graph (ip-NSW) represents the state-of-the-art method for approximate maximum inner product search (MIPS) and it can achieve an order of magnitude speedup over the fastest baseline. However, to date it is still unclear where its exceptional performance comes from. In this paper, we show that there is a strong norm bias in the MIPS problem, which means that the large norm items are very likely to become the result of MIPS. Then we explain the good performance of ip-NSW as matching the norm bias of the MIPS problem - large norm items have big in-degrees in the ip-NSW proximity graph and a walk on the graph spends the majority of computation on these items, thus effectively avoids unnecessary computation on small norm items. Furthermore, we propose the ip-NSW+ algorithm, which improves ip-NSW by introducing an additional angular proximity graph. Search is first conducted on the angular graph to find the angular neighbors of a query and then the MIPS neighbors of these angular neighbors are used to initialize the candidate pool for search on the inner-product proximity graph. Experiment results show that ip-NSW+ consistently and significantly outperforms ip-NSW and provides more robust performance under different data distributions.

cs.IR↗