• Publications
  • Influence
Bubble-flux: precise online QoS management for increased utilization in warehouse scale computers
TLDR
We present Bubble-Flux, an integrated dynamic interference measurement and online QoS management mechanism to provide accurate QoS control and maximize server utilization. Expand
  • 273
  • 21
  • PDF
Baymax: QoS Awareness and Increased Utilization for Non-Preemptive Accelerators in Warehouse Scale Computers
TLDR
We present Baymax, a runtime system that orchestrates the execution of compute tasks from different applications and mitigates PCI-e bandwidth contention to deliver the required QoS for user-facing applications and increase accelerator utilization. Expand
  • 53
  • 7
  • PDF
Prophet: Precise QoS Prediction on Non-Preemptive Accelerators to Improve Utilization in Warehouse-Scale Computers
TLDR
We present Prophet, an approach to precisely predict the performance degradation of latency-sensitive applications on non-preemptive accelerators due to application co-location. Expand
  • 50
  • 4
  • 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
Alliances with Optimal Relay Selection
TLDR
We extend the ALLIANCES protocol to include user location information and propose an optimal relay selection scheme based on it. Expand
  • 9
  • 3
  • PDF
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
  • 54
  • 2
Towards Efficient SpMV on Sunway Manycore Architectures
TLDR
Sparse Matrix-Vector Multiplication (SpMV) is an essential computation kernel for many data-analytic workloads running in both supercomputers and data centers. Expand
  • 19
  • 2
  • PDF
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
BigRoots: An Effective Approach for Root-Cause Analysis of Stragglers in Big Data System
TLDR
We propose BigRoots, a general method incorporating both framework and system features for root-cause analysis of stragglers in the big data system. Expand
  • 9
  • 2
  • PDF
A Spherical Self-Adaptive Gripper with shrinking of an elastic membrane
TLDR
The traditional grippers with multiple fingers are able to grip multiple objects self-adaptively. Expand
  • 16
  • 1