X
Xuehai Qian
Researcher at University of Southern California
Publications - 121
Citations - 4172
Xuehai Qian is an academic researcher from University of Southern California. The author has contributed to research in topics: Computer science & Speedup. The author has an hindex of 25, co-authored 107 publications receiving 2537 citations. Previous affiliations of Xuehai Qian include Rutgers University & Chinese Academy of Sciences.
Papers
More filters
Journal ArticleDOI
Distributed Graph Processing System and Processing-in-memory Architecture with Precise Loop-carried Dependency Guarantee
Youwei Zhuo,Jingji Chen,Gengyu Rao,Qinyi Luo,Yanzhi Wang,Hailong Yang,Depei Qian,Xuehai Qian +7 more
TL;DR: In this paper, the authors propose a distributed graph processing framework for distributed system and Processing-in-memory (PIM) architecture that precisely enforces loop-carried dependency, i.e., when a condition is satisfied by a neighbor, all following neighbors can be skipped.
Posted Content
An Efficient Framework for Implementing Persist Data Structures on Remote NVM.
TL;DR: It is demonstrated that the proposed rNVM can achieve comparable performance as symmetric deployment while enjoying the benefits of the large data size not limited by local memory, high availability and shared data structures.
Journal ArticleDOI
Improving multiprocessor performance with fine-grain coherence bypass
TL;DR: A novel hardware approach to dynamically identify the shared memory blocks at the cache block level, and bypass the coherence procedure for the private memory blocks is proposed, which increases the effectiveness of the directory-based approach and therefore improves the system performance.
Posted Content
Low-Cost Floating-Point Processing in ReRAM for Scientific Computing
TL;DR: ReFloat enables the principled local fine-tuning of floating-point representation and reconciles the conflicting goals by storing the exponent offsets from a common base among matrix values in a block, which is the granularity of computation in ReRAM.
Posted Content
IntersectX: An Efficient Accelerator for Graph Mining
TL;DR: IntersectX as discussed by the authors is a graph pattern mining accelerator with stream instruction set extension and architectural support based on a conventional processor, which can be considered as a natural extension to the traditional instructions that operate on scalar values.