• Publications
  • Influence
ERMS: An Elastic Replication Management System for HDFS
TLDR
The Hadoop Distributed File System (HDFS) is a distributed storage system that stores large-scale data sets reliably and streams those data sets to applications at high bandwidth. Expand
  • 76
  • 7
  • PDF
iMeter: An integrated VM power model based on performance profiling
TLDR
We propose an integrated VM power model called iMeter, which overcomes the drawbacks of overpresumption and overapproximation in segregated power models used in previous studies. Expand
  • 32
  • 3
MapReduce Workload Modeling with Statistical Approach
TLDR
We apply principal component analysis and cluster analysis to 45 different metrics, which derive relationships between workload characteristics and corresponding performance under different Hadoop configurations. Expand
  • 55
  • 2
Virtual machine mapping policy based on load balancing in private cloud environment
TLDR
This paper presents a virtual machine mapping policy based on multi-resource load balancing, which resolves the load balancing conflicts of each independent resource caused by different demand for resources of cloud applications. Expand
  • 48
  • 2
Statistics-based Workload Modeling for MapReduce
TLDR
We propose a statistic analysis approach to identify the relationships among workload characteristics, Hadoop configurations and workload performance. Expand
  • 21
  • 2
Energy Prediction for MapReduce Workloads
TLDR
We identify several workload metrics that have strong correlations with energy consumption. Expand
  • 18
  • 1
GPU Acceleration of Dock6’s Amber Scoring Computation
TLDR
Dressing the problem of virtual screening is a long-term goal in the drug discovery field, which if properly solved, can significantly shorten new drugs’ R&D cycle. Expand
  • 13
  • 1
Scheduling Tasks with Mixed Timing Constraints in GPU-Powered Real-Time Systems
TLDR
In this paper, (1) we propose resource-aware non-uniform slack distribution to enhance the schedulability ofRT tasks (the total amount of work of RT tasks whose deadlines can be satisfied on a given amount of resources) in GPU-enabled systems; we propose deadline-aware dynamic GPU partitioning to allow RT and BE tasks to run on a GPU simultaneously. Expand
  • 16
  • 1
Operator placement with QoS constraints for distributed stream processing
TLDR
We formalize the operator placement problem with network usage as the optimization objective and use two resource allocation related QoS metrics: throughput and end-to-end delay. Expand
  • 13
  • 1
  • PDF
swTVM: Exploring the Automated Compilation for Deep Learning on Sunway Architecture
TLDR
We propose swTVM that extends the original TVM to support ahead-of-time compilation for architecture requiring cross-compilation such as Sunway. Expand
  • 3
  • 1
  • PDF