arXiv subjects

Yunpeng Chai

Publications and source records attributed to Yunpeng Chai.

6 recordsLinked to original sources

arXiv2026

DisagFusion: Asynchronous Pipeline Parallelism and Elastic Scheduling for Disaggregated Diffusion Serving

Diffusion-based generation is increasingly powering production content pipelines; however, deploying these models at scale remains a significant challenge. Model weights frequently exceed the memory capacity of commodity GPUs, while the encoder, diffusion transformer (DiT), and decoder stages exhibit highly imbalanced computational and memory footprints. A natural remedy is disaggregated serving-running stages as separate services on heterogeneous GPUs-yet this introduces new bottlenecks, including stage handoff overheads and fast-changing workloads that make cross-stage provisioning and scheduling brittle. This paper presents DisagFusion, enabling asynchronous pipeline parallelism and elastic scheduling for disaggregated diffusion serving. First, DisagFusion introduces asynchronous pipeline parallelism that overlaps computation and stage-to-stage communication to reduce pipeline bubbles and mitigate network jitter. Second, DisagFusion employs a hybrid instance scheduling strategy that combines lightweight performance prediction with runtime feedback to continuously rebalance instance ratio across stages under workload shifts. We implement DisagFusion and evaluate it with modern diffusion models. Compared to a monolithic baseline, DisagFusion improves throughput by 3.4x-20.5x and reduces end-to-end latency by 18.5x, while enabling flexible, cost-efficient deployment across heterogeneous GPUs.

cs.DC↗

arXiv2025

TXSQL: Lock Optimizations Towards High Contented Workloads (Extended Version)

Two-phase locking (2PL) is a fundamental and widely used concurrency control protocol. It regulates concurrent access to database data by following a specific sequence of acquiring and releasing locks during transaction execution, thereby ensuring transaction isolation. However, in strict 2PL, transactions must wait for conflicting transactions to commit and release their locks, which reduces concurrency and system throughput. We have observed this issue is exacerbated in high-contented workloads at Tencent, where lock contention can severely degrade system performance. While existing optimizations demonstrate some effectiveness in high-contention scenarios, their performance remains insufficient, as they suffer from lock contention and waiting in hotspot access. This paper presents optimizations in lock management implemented in Tencent's database, TXSQL, with a particular focus on high-contention scenarios. First, we discuss our motivations and the journey toward general lock optimization, which includes lightweight lock management, a copy-free active transaction list, and queue locking mechanisms that effectively enhance concurrency. Second, we introduce a hotspot-aware approach that enables certain highly conflicting transactions to switch to a group locking method, which groups conflicting transactions at a specific hotspot, allowing them to execute serially in an uncommitted state within a conflict group without the need for locking, thereby reducing lock contention. Our evaluation shows that under high-contented workloads, TXSQL achieves performance improvements of up to 6.5x and up to 22.3x compared to state-of-the-art methods and systems, respectively.

cs.DB↗

arXiv2024

PixelsDB: Serverless and NL-Aided Data Analytics with Flexible Service Levels and Prices

Serverless query processing has become increasingly popular due to its advantages, including automated resource management, high elasticity, and pay-as-you-go pricing. For users who are not system experts, serverless query processing greatly reduces the cost of owning a data analytic system. However, it is still a significant challenge for non-expert users to transform their complex and evolving data analytic needs into proper SQL queries and select a serverless query service that delivers satisfactory performance and price for each type of query. This paper presents PixelsDB, an open-source data analytic system that allows users who lack system or SQL expertise to explore data efficiently. It allows users to generate and debug SQL queries using a natural language interface powered by fine-tuned language models. The queries are then executed by a serverless query engine that offers varying prices for different performance service levels (SLAs). The performance SLAs are natively supported by dedicated architecture design and heterogeneous resource scheduling that can apply cost-efficient resources to process non-urgent queries. We demonstrate that the combination of a serverless paradigm, a natural-language-aided interface, and flexible SLAs and prices will substantially improve the usability of cloud data analytic systems.

cs.DB↗

arXiv2024

Serverless Query Processing with Flexible Performance SLAs and Prices

Serverless query processing has become increasingly popular due to its auto-scaling, high elasticity, and pay-as-you-go pricing. It allows cloud data warehouse (or lakehouse) users to focus on data analysis without the burden of managing systems and resources. Accordingly, in serverless query services, users become more concerned about cost-efficiency under acceptable performance than performance under fixed resources. This poses new challenges for serverless query engine design in providing flexible performance service-level agreements (SLAs) and cost-efficiency (i.e., prices). In this paper, we first define the problem of flexible performance SLAs and prices in serverless query processing and discuss its significance. Then, we envision the challenges and solutions for solving this problem and the opportunities it raises for other database research. Finally, we present PixelsDB, an open-source prototype with three service levels supported by dedicated architectural designs. Evaluations show that PixelsDB reduces resource costs by 65.5\% for near-real-world workloads generated by Cloud Analytics Benchmark (CAB) while not violating the pending time guarantees.

cs.DB↗

arXiv2024

Towards Coarse-to-Fine Evaluation of Inference Efficiency for Large Language Models

In real world, large language models (LLMs) can serve as the assistant to help users accomplish their jobs, and also support the development of advanced applications. For the wide application of LLMs, the inference efficiency is an essential concern, which has been widely studied in existing work, and numerous optimization algorithms and code libraries have been proposed to improve it. Nonetheless, users still find it challenging to compare the effectiveness of all the above methods and understand the underlying mechanisms. In this work, we perform a detailed coarse-to-fine analysis of the inference performance of various code libraries. To evaluate the overall effectiveness, we examine four usage scenarios within two practical applications. We further provide both theoretical and empirical fine-grained analyses of each module in the Transformer architecture. Our experiments yield comprehensive results that are invaluable for researchers to evaluate code libraries and improve inference strategies.

cs.CL↗

arXiv2023

SALI: A Scalable Adaptive Learned Index Framework based on Probability Models

The growth in data storage capacity and the increasing demands for high performance have created several challenges for concurrent indexing structures. One promising solution is learned indexes, which use a learning-based approach to fit the distribution of stored data and predictively locate target keys, significantly improving lookup performance. Despite their advantages, prevailing learned indexes exhibit constraints and encounter issues of scalability on multi-core data storage. This paper introduces SALI, the Scalable Adaptive Learned Index framework, which incorporates two strategies aimed at achieving high scalability, improving efficiency, and enhancing the robustness of the learned index. Firstly, a set of node-evolving strategies is defined to enable the learned index to adapt to various workload skews and enhance its concurrency performance in such scenarios. Secondly, a lightweight strategy is proposed to maintain statistical information within the learned index, with the goal of further improving the scalability of the index. Furthermore, to validate their effectiveness, SALI applied the two strategies mentioned above to the learned index structure that utilizes fine-grained write locks, known as LIPP. The experimental results have demonstrated that SALI significantly enhances the insertion throughput with 64 threads by an average of 2.04x compared to the second-best learned index. Furthermore, SALI accomplishes a lookup throughput similar to that of LIPP+.

cs.DB↗