Tianzheng Wang
YOU?
Author Swipe
View article: LLM Inference Scheduling: A Survey of Techniques, Frameworks, and Trade-offs
LLM Inference Scheduling: A Survey of Techniques, Frameworks, and Trade-offs Open
View article: DEX: Scalable Range Indexing on Disaggregated Memory [Extended Version]
DEX: Scalable Range Indexing on Disaggregated Memory [Extended Version] Open
Memory disaggregation can potentially allow memory-optimized range indexes such as B+-trees to scale beyond one machine while attaining high hardware utilization and low cost. Designing scalable indexes on disaggregated memory, however, is…
View article: Online Schema Evolution is (Almost) Free for Snapshot Databases
Online Schema Evolution is (Almost) Free for Snapshot Databases Open
Modern database applications often change their schemas to keep up with the changing requirements. However, support for online and transactional schema evolution remains challenging in existing database systems. Specifically, prior work of…
View article: Are updatable learned indexes ready?
Are updatable learned indexes ready? Open
Recently, numerous promising results have shown that updatable learned indexes can perform better than traditional indexes with much lower memory space consumption. But it is unknown how these learned indexes compare against each other and…
View article: Skeena: Efficient and Consistent Cross-Engine Transactions
Skeena: Efficient and Consistent Cross-Engine Transactions Open
Database systems are becoming increasingly multi-engine. In particular, a main-memory database engine may coexist with a traditional storage-centric engine in a system to support various applications. It is desirable to allow applications …
View article: APEX: A High-Performance Learned Index on Persistent Memory
APEX: A High-Performance Learned Index on Persistent Memory Open
The recently released persistent memory (PM) offers high performance, persistence, and is cheaper than DRAM. This opens up new possibilities for indexes that operate and persist data directly on the memory bus. Recent learned indexes explo…
View article: CoroBase
CoroBase Open
Data stalls are a major overhead in main-memory database engines due to the use of pointer-rich data structures. Lightweight coroutines ease the implementation of software prefetching to hide data stalls by overlapping computation and asyn…
View article: CoroBase: Coroutine-Oriented Main-Memory Database Engine
CoroBase: Coroutine-Oriented Main-Memory Database Engine Open
Data stalls are a major overhead in main-memory database engines due to the use of pointer-rich data structures. Lightweight coroutines ease the implementation of software prefetching to hide data stalls by overlapping computation and asyn…
View article: DPI: The Data Processing Interface for Modern Networks
DPI: The Data Processing Interface for Modern Networks Open
As data processing evolves towards large scale, distributed platforms, the network will necessarily play a substantial role in achieving efficiency and performance. Increasingly, switches, network cards, and protocols are becoming more fle…
View article: Erratum to: Efficiently making (almost) any concurrency control mechanism serializable
Erratum to: Efficiently making (almost) any concurrency control mechanism serializable Open
View article: Research and Application Toward the Atlas Variation Detection Technology of Soft Sensor in Substation’s State Intelligence Analysis System
Research and Application Toward the Atlas Variation Detection Technology of Soft Sensor in Substation’s State Intelligence Analysis System Open
To improve the substation’s remote monitoring capability, this system adopts the computer technology, automation technology, and atlas processing and atlas recognition technology to analyze and compare massive monitoring data, so as to i…
View article: Breaker Contact Movement State Recognition Based on Image Processing
Breaker Contact Movement State Recognition Based on Image Processing Open
This paper briefly describes a new method of breaker contact movement state recognition. This method is based on image target tracking. Particle filter algorithm can solve the non-linear processing problem, so it is better robustness and a…
View article: Be my guest
Be my guest Open
The MCS lock is one of the most prevalent queuing locks. It provides fair scheduling and high performance on massively parallel systems. However, the MCS lock mandates a bring-your-own-context policy: each lock user must provide an additio…
View article: Durable Address Translation in PCM-based Flash Storage Systems
Durable Address Translation in PCM-based Flash Storage Systems Open
Phase change memory (PCM) is a promising DRAM alternative because of its non-volatility, high density, low standby power and close-to-DRAM performance. These features make PCM an attractive solution to optimize the management of NAND flash…
View article: File system-independent block device support for storage class memory
File system-independent block device support for storage class memory Open
© 2015 IEEE. Storage class memory (SCM) modules can be placed side-by-side with DRAM on the memory bus, available to memory instructions issued by the CPU. This shift engenders a new 'DRAM-SCM' storage architecture and potentially allows n…