Yongnan Li

A VM-based Resource Management Method Using Statistics

Virtualization technology is one of the key technologies in cloud computing. Proper allocation of the virtual machines onto available hosts plays an important role on the performance optimization of cloud computing. At present, many resource management methods are based on the load model to predict the resource requirements of the application. However, a variety of heterogeneous hardware environments and virtualization technologies make it hard to efficiently allocate the resources based on existing methods. To address the problem, we proposed a virtual machine allocation strategy based on statistics. And The contribution of this paper include:(1) A load-resource model for estimating the resource demand of each virtual machine, (2) An algorithm for assigning virtual machines onto the hosts among resource pool according to the resources requirement of virtual machine. Experiments show that our load-resource model can accurately estimate the resource requirements of virtual machines for physical host, and our virtual machine assigning algorithm can achieve better load balancing compared with the first-fit and best-fit algorithm.

A DNA Computing System of Modular-Multiplication over Finite Field GF(2n)

The enormous parallel computing ability and high memory density of DNA computing bring potential challenges and opportunities to traditional cryptography. Finite field GF(2n) is one of the most commonly used mathematic sets for cryptography. It is an open problem that how to implement the arithmetic operations over finite field GF(2n) based on DNA computing. Existing research has the problem that the lengths of parameters in the DNA tile assembly process could not match each other strictly. This paper proposes a parallel molecular computing system to compute the modular-multiplication, an operation combining multiplication and reduction over finite field GF(2n). The multiplication and the reduction are executed simultaneously in this system. One concrete example of

Arithmetic Computation Using Self-Assembly of DNA Tiles: Modular-Square over Finite Field GF(2n)

1100 \cdot 1001 \ mod \ 10011

Parallel Extended Basic Operations for Conic Curves Cryptography over Ring Zn

is proposed to show the details of our tile assembly system. The time complexity of this system is Θ(n) and the space complexity is Θ(n 2). This system requires 210 types of computation tiles and 17 types of boundary tiles.

Parallel molecular computation of modular-multiplication with two same inputs over finite field GF(2n) using self-assembly of DNA tiles

Tile assembly model is a highly distributed parallel model of DNA computing. This paper proposes how the tile assembly process could be used for computing the modular square, an operation combining square and reduction, over finite field GF(2n). In this molecular computing system, reduction is executed after the completion of square. The time complexity of this molecular computing system is ⊙(n) and the space complexity is ⊙(n2). This system requires 75 types of computation tiles and 9 types of boundary tiles.

Energy Aware Scheduling for Precedence Constrained Parallel Tasks in a Power-Scalable Cluster

This paper presents parallel extended operations of point-addition and point-double for cryptosystem on conic curves over ring Zn. The data dependencies are deduced by analyzing the definitions of two extended operations. Take procedure of paralleling extended point-addition as an example. We employ the Chinese Remainder Theorem to divide point-addition over ring Zn into two point-additions over finite field Fp and finite field Fq. Then the temporary values of point-addition over two finite fields are merged to get the final result of extended point-addition over ring Zn. The analysis of parallel methodology is based on our previous works about the basic parallel algorithms used in conic curves cryptosystem. Computing extended point-addition and point-double both need to execute three steps. For getting the average runtime and speedup ratio, different cases are considered in the second step. The performance evaluation demonstrates that our techniques improve the efficiencies of two extended operations. Additionally, the parallel methods introduced in this paper are also more efficient than traditional parallel algorithms.

Parallel molecular computation of modular-multiplication based on tile assembly model

Two major advantages of DNA computing - huge memory capacity and high parallelism - are being explored for large-scale parallel computing, mass data storage and cryptography. Tile assembly model is a highly distributed parallel model of DNA computing. Finite field GF(2(n)) is one of the most commonly used mathematic sets for constructing public-key cryptosystem. It is still an open question that how to implement the basic operations over finite field GF(2(n)) using DNA tiles. This paper proposes how the parallel tile assembly process could be used for computing the modular-square, modular-multiplication with two same inputs, over finite field GF(2(n)). This system could obtain the final result within less steps than another molecular computing system designed in our previous study, because square and reduction are executed simultaneously and the previous system computes reduction after calculating square. Rigorous theoretical proofs are described and specific computing instance is given after defining the basic tiles and the assembly rules. Time complexity of this system is 3n-1 and space complexity is 2n(2).

A Framework for Porting Linux OS to a cc-NUMA Server Based on Loongson Processors

Improving the energy efficiency of high performance clusters has become important research issue. We proposed a new algorithm that reduces energy consumption of precedence constrained parallel tasks in power-scalable clusters. To reduce energy consumption without increasing the schedule length, our algorithm reclaims both static and dynamic slack time and employs different frequency adjusting techniques in different slack time. The optimal frequency is obtained through analyzing the precedence constraints of parallel tasks. We conducted experiments to compare the proposed algorithm with two other existing algorithms. Simulation results show that the proposed algorithm can get better energy efficiency without increasing the make span.

High Performance Implementation of ARIA Encryption Algorithm on Graphics Processing Units

DNA computing is a new method for computation using the technology in molecular biology. The enormous parallel computing ability of DNA computing brings new opportunities and challenges to the development of cryptography. DNA cryptography is a cutting-edge sciences which combines classical cryptogram and molecular computing. Finite field GF(2n) is one of the most commonly used mathematic sets for cryptography. This paper proposes a parallel molecular computing system to compute the modular-multiplication, an operation combining multiplication and reduction, over finite field GF(2n). The operation of reduction is executed after the completion of the operation of multiplication. An instance of computing modular-multiplication is introduced to show the details of our system. The time complexity is Θ(n) and the space complexity is Θ(n2).

GPU-Accelerated Query by Humming Using Modified SPRING Algorithm

In order to make the Linux operating system available on a cache coherence NUMA (cc-NUMA) server based on Loongson processors, a family of general-purpose MIPS64 CPUs developed by the Institute of Computing Technology in China, this paper proposes a framework for porting Linux operating system to this cc-NUMA server. Researchers present the overall port scheme after analyzing the framework of the Linux kernel and the architecture of the hardware platform, and then they discuss the transplantation in details with processor-level transplantation, memory management transplantation, interrupt and trap transplantation. The performance evaluation shows that the whole system works stable and the ported operating system could reach about 30 % of the theoretical peak value of floating-point calculation. The method could port Linux OS to the target board successfully and can be used on other platforms. The research has great significance to the development of the domestic Loongson processor and the cc-NUMA platform based on Loongson processors.