-
公开(公告)号:US20180253423A1
公开(公告)日:2018-09-06
申请号:US15447262
申请日:2017-03-02
发明人: MICHEL H. T. HACK , YUFEI REN , WEI TAN , YANDONG WANG , XINGBO WU , LI ZHANG , WEI ZHANG
摘要: Computational storage techniques for distribute computing are disclosed. The computational storage server receives input from multiple clients, which is used by the server when executing one or more computation functions. The computational storage server can aggregate multiple client inputs before applying one or more computation functions. The computational storage server sets up: a first memory area for storing input received from multiple clients; a second memory area designated for storing the computation functions to be executed by the computational storage server using the input data received from the multiple clients; a client specific memory management area for storing metadata related to computations performed by the computational storage server for specific clients; and a persistent storage area for storing checkpoints associated with aggregating computations performed by the computation functions.
-
公开(公告)号:US20180075159A1
公开(公告)日:2018-03-15
申请号:US15264570
申请日:2016-09-13
发明人: CHING-YUNG LIN , YANBIN LIU , LIFENG NAI , WEI TAN , ILIE G. TANASE , YINGLONG XIA
IPC分类号: G06F17/30
CPC分类号: G06F16/9024 , G06F16/28
摘要: A data storage and retrieval system for a computer memory includes a stream graph engine extracting graph data from streaming data, the graph data occupying a sliding window and comprising a plurality of slices representing a set of contiguous graphs, and where each slice of the plurality of slices corresponds to a given graph structure and its properties at a particular time, the stream graph engine causing the computer memory to store an on-disk portion of the graph data including a key table, a timestamp table and a plurality of property files, wherein the key table comprises a plurality of pointers to corresponding entries of the timestamp table, wherein each of the entries of the timestamp table comprise a corresponding timestamp and a pointer to the properties files, wherein the properties files comprise properties of a corresponding graph of the set of contiguous graphs, an in-memory portion of the graph data having a cache data structure storing a subset of the key table, and a versioning control module storing evolving changes in the graph data in the computer memory.
-
公开(公告)号:US20170154404A1
公开(公告)日:2017-06-01
申请号:US15431986
申请日:2017-02-14
发明人: LIANGLIANG CAO , LIANA L. FONG , WEI TAN
IPC分类号: G06T1/60 , G06F12/0877 , G06T1/20 , G06F17/16
CPC分类号: G06T1/60 , G06F3/0601 , G06F3/0604 , G06F3/0659 , G06F3/0673 , G06F8/441 , G06F8/443 , G06F8/453 , G06F12/0813 , G06F12/0875 , G06F12/0877 , G06F13/16 , G06F17/16 , G06F2212/1024 , G06F2212/302 , G06F2212/454 , G06F2212/455 , G06F2212/60 , G06F2212/656 , H03M13/6566
摘要: Embodiments include method, systems and computer program products for performing memory-aware matrix factorization on a graphics processing unit. Aspects include determining one or more types of memory on the graphics processing unit and determining one or more characteristics of each of the one or more types of memory. Aspects also include assigning each of a plurality of memory accesses of a matrix factorization algorithm to one of the one or more types of memory based on the one or more characteristics and executing the matrix factorization algorithm on the graphics processing unit.
-
公开(公告)号:US20160371005A1
公开(公告)日:2016-12-22
申请号:US14967417
申请日:2015-12-14
发明人: LIANGLIANG CAO , LIANA L. FONG , WEI TAN
CPC分类号: G06T1/60 , G06F3/0601 , G06F3/0604 , G06F3/0659 , G06F3/0673 , G06F8/441 , G06F8/443 , G06F8/453 , G06F12/0813 , G06F12/0875 , G06F12/0877 , G06F13/16 , G06F17/16 , G06F2212/1024 , G06F2212/302 , G06F2212/454 , G06F2212/455 , G06F2212/60 , G06F2212/656 , H03M13/6566
摘要: Embodiments include method, systems and computer program products for performing memory-aware matrix factorization on a graphics processing unit. Aspects include determining one or more types of memory on the graphics processing unit and determining one or more characteristics of each of the one or more types of memory. Aspects also include assigning each of a plurality of memory accesses of a matrix factorization algorithm to one of the one or more types of memory based on the one or more characteristics and executing the matrix factorization algorithm on the graphics processing unit.
摘要翻译: 实施例包括用于在图形处理单元上执行存储器感知矩阵分解的方法,系统和计算机程序产品。 方面包括确定图形处理单元上的一种或多种类型的存储器并且确定一种或多种类型的存储器中的每一种的一个或多个特性。 方面还包括基于一个或多个特征将矩阵分解算法的多个存储器访问中的每一个分配给一个或多个类型的存储器中的一个,并在图形处理单元上执行矩阵分解算法。
-
公开(公告)号:US20170154405A1
公开(公告)日:2017-06-01
申请号:US15431990
申请日:2017-02-14
发明人: LIANGLIANG CAO , LIANA L. FONG , WEI TAN
IPC分类号: G06T1/60 , G06F12/0877 , G06T1/20 , G06F17/16
CPC分类号: G06T1/60 , G06F3/0601 , G06F3/0604 , G06F3/0659 , G06F3/0673 , G06F8/441 , G06F8/443 , G06F8/453 , G06F12/0813 , G06F12/0875 , G06F12/0877 , G06F13/16 , G06F17/16 , G06F2212/1024 , G06F2212/302 , G06F2212/454 , G06F2212/455 , G06F2212/60 , G06F2212/656 , H03M13/6566
摘要: Embodiments include method, systems and computer program products for performing memory-aware matrix factorization on a graphics processing unit. Aspects include determining one or more types of memory on the graphics processing unit and determining one or more characteristics of each of the one or more types of memory. Aspects also include assigning each of a plurality of memory accesses of a matrix factorization algorithm to one of the one or more types of memory based on the one or more characteristics and executing the matrix factorization algorithm on the graphics processing unit.
-
公开(公告)号:US20160371809A1
公开(公告)日:2016-12-22
申请号:US14742746
申请日:2015-06-18
发明人: LIANGLIANG CAO , LIANA L. FONG , WEI TAN
CPC分类号: G06T1/60 , G06F3/0601 , G06F3/0604 , G06F3/0659 , G06F3/0673 , G06F8/441 , G06F8/443 , G06F8/453 , G06F12/0813 , G06F12/0875 , G06F12/0877 , G06F13/16 , G06F17/16 , G06F2212/1024 , G06F2212/302 , G06F2212/454 , G06F2212/455 , G06F2212/60 , G06F2212/656 , H03M13/6566
摘要: Embodiments include method, systems and computer program products for performing memory-aware matrix factorization on a graphics processing unit. Aspects include determining one or more types of memory on the graphics processing unit and determining one or more characteristics of each of the one or more types of memory. Aspects also include assigning each of a plurality of memory accesses of a matrix factorization algorithm to one of the one or more types of memory based on the one or more characteristics and executing the matrix factorization algorithm on the graphics processing unit.
-
-
-
-
-