On June 17, 2013, MilkyWay-2 (Tianhe-2) supercomputer was crowned as the fastest supercomputer in the world on the 41th TOP500 list. This paper provides an overview of the MilkyWay-2 project and describes the design...
详细信息
On June 17, 2013, MilkyWay-2 (Tianhe-2) supercomputer was crowned as the fastest supercomputer in the world on the 41th TOP500 list. This paper provides an overview of the MilkyWay-2 project and describes the design of hardware and software systems. The key architecture features of MilkyWay-2 are highlighted, including neo-heterogeneous compute nodes integrating commodity- off-the-shelf processors and accelerators that share similar instruction set architecture, powerful networks that employ proprietary interconnection chips to support the massively parallel message-passing communications, proprietary 16- core processor designed for scientific computing, efficient software stacks that provide high performance file system, emerging programming model for heterogeneous systems, and intelligent system administration. We perform extensive evaluation with wide-ranging applications from LINPACK and Graph500 benchmarks to massively parallel software deployed in the system.
Interconnection network plays an important role in scalable high performance computer (HPC) systems. The TH Express-2 interconnect has been used in MilkyWay-2 system to provide high-bandwidth and low-latency interpr...
详细信息
Interconnection network plays an important role in scalable high performance computer (HPC) systems. The TH Express-2 interconnect has been used in MilkyWay-2 system to provide high-bandwidth and low-latency interprocessot communications, and continuous efforts are devoted to the development of our proprietary interconnect. This paper describes the state-of-the-art of our proprietary interconnect, especially emphasizing on the design of network interface. Several key features are introduced, such as user-level communication, remote direct memory access, offload collective operation, and hardware reliable end-to-end communication, etc. The design of a low level message passing infrastructures and an upper message passing services are also proposed. The preliminary performance results demonstrate the efficiency of the TH interconnect interface.
Edge extraction is an indispensable task in digital image processing. With the sharp increase in the image data, real-time problem has become a limitation of the state of the art of edge extraction *** this paper, QSo...
详细信息
Edge extraction is an indispensable task in digital image processing. With the sharp increase in the image data, real-time problem has become a limitation of the state of the art of edge extraction *** this paper, QSobel, a novel quantum image edge extraction algorithm is designed based on the flexible representation of quantum image(FRQI) and the famous edge extraction algorithm Sobel. Because FRQI utilizes the superposition state of qubit sequence to store all the pixels of an image, QSobel can calculate the Sobel gradients of the image intensity of all the pixels simultaneously. It is the main reason that QSobel can extract edges quite fast. Through designing and analyzing the quantum circuit of QSobel, we demonstrate that QSobel can extract edges in the computational complexity of O(n2) for a FRQI quantum image with a size of2 n × 2n. Compared with all the classical edge extraction algorithms and the existing quantum edge extraction algorithms, QSobel can utilize quantum parallel computation to reach a significant and exponential ***, QSobel would resolve the real-time problem of image edge extraction.
A novel framework for parallel subgraph isomorphism on GPUs is proposed, named GPUSI, which consists of GPU region exploration and GPU subgraph matching. The GPUSI iteratively enumerates subgraph instances and solves ...
详细信息
A novel framework for parallel subgraph isomorphism on GPUs is proposed, named GPUSI, which consists of GPU region exploration and GPU subgraph matching. The GPUSI iteratively enumerates subgraph instances and solves the subgraph isomorphism in a divide-and-conquer fashion. The framework completely relies on the graph traversal, and avoids the explicit join operation. Moreover, in order to improve its performance, a task-queue based method and the virtual-CSR graph structure are used to balance the workload among warps, and warp-centric programming model is used to balance the workload among threads in a warp. The prototype of GPUSI is implemented, and comprehensive experiments of various graph isomorphism operations are carried on diverse large graphs. The experiments clearly demonstrate that GPUSI has good scalability and can achieve speed-up of 1.4–2.6 compared to the state-of-the-art solutions.
This paper presents a novel algorithm to detect null pointer dereference errors. The algorithm utilizes both of the must and may alias information in a compact way to improve the precision of the detection. Using may ...
详细信息
We consider the maximal vector problem on uncertain data, which has been recently posed by the study on processing skyline queries over a probabilistic data stream in the database context. Let D n be a set of n points...
详细信息
We consider the maximal vector problem on uncertain data, which has been recently posed by the study on processing skyline queries over a probabilistic data stream in the database context. Let D n be a set of n points in a d-dimensional space and q (0 < q 1) be a probability threshold; each point in D n has a probability to occur. Our problem is concerned with how to estimate the expected size of the probabilistic skyline, which consists of all the points that are not dominated by any other point in D n with a probability not less than q. We prove that the upper bound of the expected size is O(min{n, (- ln q)(ln n) d-1 }) under the assumptions that the value distribution on each dimension is independent and the values of the points along each dimension are distinct. The main idea of our proof is to find a recurrence about the expected size and solve it. Our results reveal the relationship between the probability threshold q and the expected size of the probabilistic skyline, and show that the upper bound is poly-logarithmic when q is not extremely small.
GPGPUs are increasingly being used to as performance accelerators for HPC (High Performance Computing) applications in CPU/GPU heterogeneous computing systems, including TianHe-1A, the world's fastest supercomputer...
详细信息
GPGPUs are increasingly being used to as performance accelerators for HPC (High Performance Computing) applications in CPU/GPU heterogeneous computing systems, including TianHe-1A, the world's fastest supercomputer in the TOP500 list, built at NUDT (national University of Defense Technology) last year. However, despite their performance advantages, GPGPUs do not provide built-in fault-tolerant mechanisms to offer reliability guarantees required by many HPC applications. By analyzing the SIMT (single-instruction, multiple-thread) characteristics of programs running on GPGPUs, we have developed PartialRC, a new checkpoint-based compiler-directed partial recomputing method, for achieving efficient fault recovery by leveraging the phenomenal computing power of GPGPUs. In this paper, we introduce our PartialRC method that recovers from errors detected in a code region by partially re-computing the region, describe a checkpoint-based faulttolerance framework developed on PartialRC, and discuss an implementation on the CUDA platform. Validation using a range of representative CUDA programs on NVIDIA GPGPUs against FullRC (a traditional full-recomputing Checkpoint-Rollback-Restart fault recovery method for CPUs) shows that PartialRC reduces significantly the fault recovery overheads incurred by FullRC, by 73.5% when errors occur earlier during execution and 74.6% when errors occur later on average. In addition, PartialRC also reduces error detection overheads incurred by FullRC during fault recovery while incurring negligible performance overheads when no fault happens.
Searchable encryption allows cloud users to outsource the massive encrypted data to the remote cloud and to search over the data without revealing the sensitive information. Many schemes have been proposed to support ...
详细信息
Searchable encryption allows cloud users to outsource the massive encrypted data to the remote cloud and to search over the data without revealing the sensitive information. Many schemes have been proposed to support the keyword search in a public cloud. However,they have some potential limitations. First,most of the existing schemes only consider the scenario with the single data owner. Second,they need secure channels to guarantee the secure transmission of secret keys from the data owner to data users. Third,in some schemes,the data owner should be online to help data users when data users intend to perform the search,which is *** this paper,we propose a novel searchable scheme which supports the multi-owner keyword search without secure channels. More than that,our scheme is a non-interactive solution,in which all the users only need to communicate with the cloud server. Furthermore,the analysis proves that our scheme can guarantee the security even without secure channels. Unlike most existing public key encryption based searchable schemes,we evaluate the performance of our scheme,which shows that our scheme is practical.
Test oracles are widely used to verify whether a system under test is running as desired. Since the correctness of real-time systems depends on the logical results of the computation and the time when results are prod...
详细信息
Barrier synchronization and reduction are global operations used frequently in large scale OpenMP programs. To improve OpenMP performance, we present two new directives BARRIER(0) and ALLREDUCTION to extend BARRIER an...
详细信息
暂无评论