• Publications
  • Influence
swDNN: A Library for Accelerating Deep Learning Applications on Sunway TaihuLight
To explore the potential of training complex deep neural networks (DNNs) on other commercial chips rather than GPUs, we report our work on swDNN, which is a highly-efficient library for acceleratingExpand
Refactoring and Optimizing the Community Atmosphere Model (CAM) on the Sunway TaihuLight Supercomputer
  • H. Fu, Junfeng Liao, +22 authors G. Yang
  • Computer Science, Engineering
  • SC16: International Conference for High…
  • 13 November 2016
To map the large code base of CAM to the millions of cores on the Sunway system, OpenACC-based refactoring is taken as the major approach, and source-to-source translator tools are applied to exploit the most suitable parallelism for the CPE cluster. Expand
Working principles of binary differential evolution
A first fundamental analysis of the working principles of binary differential evolution (BDE) shows that unlike most other optimization paradigms, it is stable in the sense that neutral bit values are sampled with probability close to 1/2 for a long time, which enables BDE to optimize the most important bits very fast. Expand
Optimizing Convolutional Neural Networks on the Sunway TaihuLight Supercomputer
The Sunway TaihuLight supercomputer is powered by SW26010, a new 260-core processor designed with on-chip fusion of heterogeneous cores. In this article, we present our work on optimizing theExpand
Working principles of binary differential evolution
A first fundamental analysis of the working principles of binary differential evolution (BDE), an optimization heuristic for binary decision variables that was derived by Gong and Tuson (2007) from the very successful classic differential evolution for continuous optimization indicates that BDE is an interesting optimization paradigm having characteristics significantly different from the classic evolutionary algorithms or EDAs. Expand
Sharp Bounds for Genetic Drift in Estimation of Distribution Algorithms
This article gives the first tight quantification of this effect for three EDAs and one ant colony optimizer, namely, for the univariate marginal distribution algorithm, the compact genetic algorithm, population-based incremental learning, and the max–min ant system with iteration-best update. Expand
Theoretical analyses of multi-objective evolutionary algorithms on multi-modal objectives: (hot-off-the-press track at GECCO 2021)
The OneJumpZeroJump problem is proposed, a bi-objective problem with single objectives isomorphic to the classic jump function benchmark, and it is proved that the simple evolutionary multi-objectives optimizer (SEMO) cannot compute the full Pareto front. Expand
Targeted Mutation: A Novel Mutation Strategy for Differential Evolution
  • W. Zheng, H. Fu, G. Yang
  • Computer Science
  • IEEE 27th International Conference on Tools with…
  • 9 November 2015
A novel mutation strategy called Targeted Mutation is proposed that takes the determined target vector as the starting point of the differential vector and maintains the randomness of the ending point, which makes a better trade-off between the certainty and randomness in the differentialvector. Expand
From understanding genetic drift to a smart-restart parameter-less compact genetic algorithm
This work proposes a parameter-less version of the compact genetic algorithm that automatically finds a suitable population size without spending too much time in situations unfavorable due to genetic drift and proves an easy mathematical runtime guarantee for this algorithm. Expand
Sharp Bounds for Genetic Drift in EDAs
This paper proves the first sharp estimates of the boundary hitting time of the sampling frequency of a neutral bit for several univariate EDAs and proves the lower bounds implicit in these statements, including exponential tail bounds, on the times to reach a low frequency value. Expand