MULTIPLE-THREAD PROCESSING METHODS AND APPARATUSES
    1.
    发明申请
    MULTIPLE-THREAD PROCESSING METHODS AND APPARATUSES 审中-公开
    多线程处理方法和设备

    公开(公告)号:US20160170799A1

    公开(公告)日:2016-06-16

    申请号:US14816265

    申请日:2015-08-03

    CPC classification number: G06F8/452

    Abstract: Multiple-thread processing apparatuses and methods are provided. The multiple-thread processing method may include searching for loops in a plurality of threads, calculating a number of repetitions of each of found loops in respective threads among the plurality of threads, determining one or more threads based on the calculated number of repetitions of each of the found loops, dividing at least one of the one or more determined threads into child threads, and processing the child threads separately from one another in the plurality of threads.

    Abstract translation: 提供多线程处理设备和方法。 多线程处理方法可以包括搜索多个线程中的循环,计算多个线程中各个线程中的每个找到的循环的重复次数,基于计算出的每个线程的重复次数来确定一个或多个线程 找到的循环,将所述一个或多个确定的线程中的至少一个划分为子线程,以及在所述多个线程中彼此分开地处理所述子线程。

    RECONFIGURABLE PROCESSOR AND METHOD FOR OPTIMIZING CONFIGURATION MEMORY

    公开(公告)号:US20150127935A1

    公开(公告)日:2015-05-07

    申请号:US14461794

    申请日:2014-08-18

    CPC classification number: G06F12/0653 G06F9/30 G06F9/44505 H03M7/30

    Abstract: A method and apparatus for optimizing a configuration memory of a reconfigurable processor is provided. The method of optimizing the configuration memory of the reconfigurable processor includes analyzing parallelism of a loop of a program code based on an architecture of the reconfigurable processor and information regarding the configuration memory, scheduling groups of function units (FUs) to be activated in each cycle of the loop based on the analyzed parallelism, generating configuration data of each cycle, and determining a memory mapping to store the generated configuration data in the configuration memory.

    RECONFIGURABLE PROCESSOR AND METHOD FOR OPTIMIZING CONFIGURATION MEMORY

    公开(公告)号:US20150127933A1

    公开(公告)日:2015-05-07

    申请号:US14296876

    申请日:2014-06-05

    CPC classification number: G06F12/0653 G06F9/30 G06F9/44505 H03M7/30

    Abstract: A method and apparatus for optimizing a configuration memory of a reconfigurable processor is provided. The method of optimizing the configuration memory of the reconfigurable processor includes analyzing parallelism of a loop of a program code based on an architecture of the reconfigurable processor and information regarding the configuration memory, scheduling groups of function units (FUs) to be activated in each cycle of the loop based on the analyzed parallelism, generating configuration data of each cycle, and determining a memory mapping to store the generated configuration data in the configuration memory.

    METHOD AND APPARATUS FOR CONTROLLING RENDERING QUALITY
    4.
    发明申请
    METHOD AND APPARATUS FOR CONTROLLING RENDERING QUALITY 有权
    控制渲染质量的方法和装置

    公开(公告)号:US20160071304A1

    公开(公告)日:2016-03-10

    申请号:US14667458

    申请日:2015-03-24

    CPC classification number: G06F3/013 G06T15/20 G06T2210/36

    Abstract: A rendering method, an apparatus for rendering an image and a rendering device are provided. The rendering method involves obtaining information about a sightline of a user, determining rendering quality based on the obtained information, and rendering a graphic image according to the determined rendering quality.

    Abstract translation: 提供了一种渲染方法,一种用于渲染图像的装置和一种渲染装置。 渲染方法包括获取关于用户的视线的信息,基于获得的信息确定渲染质量,以及根据确定的渲染质量呈现图形图像。

    RECONFIGURABLE PROCESSOR AND METHOD FOR OPTIMIZING CONFIGURATION MEMORY

    公开(公告)号:US20150127921A1

    公开(公告)日:2015-05-07

    申请号:US14461831

    申请日:2014-08-18

    CPC classification number: G06F12/0653 G06F9/30 G06F9/44505 H03M7/30

    Abstract: A method and apparatus for optimizing a configuration memory of a reconfigurable processor is provided. The method of optimizing the configuration memory of the reconfigurable processor includes analyzing parallelism of a loop of a program code based on an architecture of the reconfigurable processor and information regarding the configuration memory, scheduling groups of function units (FUs) to be activated in each cycle of the loop based on the analyzed parallelism, generating configuration data of each cycle, and determining a memory mapping to store the generated configuration data in the configuration memory.

    RECONFIGURABLE PROCESSOR AND METHOD FOR OPTIMIZING CONFIGURATION MEMORY
    6.
    发明申请
    RECONFIGURABLE PROCESSOR AND METHOD FOR OPTIMIZING CONFIGURATION MEMORY 审中-公开
    可重构处理器和优化配置存储器的方法

    公开(公告)号:US20150127934A1

    公开(公告)日:2015-05-07

    申请号:US14461718

    申请日:2014-08-18

    CPC classification number: G06F12/0653 G06F9/30 G06F9/44505 H03M7/30

    Abstract: A method and apparatus for optimizing a configuration memory of a reconfigurable processor is provided. The method of optimizing the configuration memory of the reconfigurable processor includes analyzing parallelism of a loop of a program code based on an architecture of the reconfigurable processor and information regarding the configuration memory, scheduling groups of function units (FUs) to be activated in each cycle of the loop based on the analyzed parallelism, generating configuration data of each cycle, and determining a memory mapping to store the generated configuration data in the configuration memory.

    Abstract translation: 提供了一种用于优化可重配置处理器的配置存储器的方法和装置。 优化可重配置处理器的配置存储器的方法包括基于可重构处理器的架构和关于配置存储器的信息来分析程序代码的循环的并行性,在每个周期中激活功能单元(FU)的调度组 基于分析的并行度生成循环,生成每个周期的配置数据,以及确定存储器映射以将生成的配置数据存储在配置存储器中。

    SCHEDULER AND SCHEDULING METHOD FOR RECONFIGURABLE ARCHITECTURE
    7.
    发明申请
    SCHEDULER AND SCHEDULING METHOD FOR RECONFIGURABLE ARCHITECTURE 有权
    可重构结构的调度和调度方法

    公开(公告)号:US20140259020A1

    公开(公告)日:2014-09-11

    申请号:US14197591

    申请日:2014-03-05

    CPC classification number: G06F15/7885 G06F9/4881

    Abstract: A scheduler and scheduling method perform scheduling for a reconfigurable architecture. The scheduling, performed by the scheduler, includes path information extracting including extracting direct path information and indirect path information between functional units in a reconfigurable array complying with predefined architecture requirements, based on architecture information of the reconfigurable array, command selecting including selecting a command from a data flow graph (DFG) showing commands to be executed by the reconfigurable array, and scheduling including scheduling the selected command based on the extracted direct path information and indirect path information.

    Abstract translation: 调度器和调度方法对可重构架构执行调度。 由调度器执行的调度包括路径信息提取,包括基于可重配置阵列的体系结构信息,在可重配置阵列的可重构阵列中的功能单元之间提取直接路径信息和间接路径信息,命令选择包括从 显示由可重配置阵列执行的命令的数据流图(DFG),以及包括基于所提取的直接路径信息和间接路径信息来调度所选择的命令的调度。

    COMPUTING SYSTEM AND METHOD FOR PROCESSING OPERATIONS THEREOF
    8.
    发明申请
    COMPUTING SYSTEM AND METHOD FOR PROCESSING OPERATIONS THEREOF 审中-公开
    计算机系统及其处理方法

    公开(公告)号:US20170060588A1

    公开(公告)日:2017-03-02

    申请号:US15067494

    申请日:2016-03-11

    Inventor: Yoonseo CHOI

    CPC classification number: G06F9/3881 G06F15/7821 G06F15/80 Y02D10/12 Y02D10/13

    Abstract: A computing system includes a host processor configured to process operations and a memory configured to include an internal processor and store host instructions to be processed by the host processor. The host processor offloads processing of a predetermined operation to the internal processor. The internal processor possibly provides specialized hardware designed to process the operation efficiently, improving the efficiency and performance of the computing system.

    Abstract translation: 计算系统包括被配置为处理操作的主机处理器和被配置为包括内部处理器并存储要由主处理器处理的主机指令的存储器。 主处理器将预定操作的处理卸载到内部处理器。 内部处理器可能提供专门用于高效处理操作的硬件,提高计算系统的效率和性能。

    APPARATUS AND METHOD OF CONTROLLING POWER CONSUMPTION OF GRAPHIC PROCESSING UNIT (GPU) RESOURCES
    9.
    发明申请
    APPARATUS AND METHOD OF CONTROLLING POWER CONSUMPTION OF GRAPHIC PROCESSING UNIT (GPU) RESOURCES 有权
    控制图形处理单元(GPU)资源消耗功能的装置和方法

    公开(公告)号:US20160062445A1

    公开(公告)日:2016-03-03

    申请号:US14738118

    申请日:2015-06-12

    CPC classification number: G06F1/325 G06F1/329 G06F9/3836 G06F9/46 Y02D10/24

    Abstract: A power consumption control apparatus includes a resource selecting unit configured to select resources, whose power consumption levels are to be determined, from among resources of a graphic processing unit (GPU), a resource use information acquiring unit configured to determine whether the selected resources are used from a code block which is all or part of a program executed using the GPU, and a power consumption controlling unit configured to determine a power consumption level of the selected resource based on a determination result of the resource information acquiring unit and to control the power consumption level of the selected resources based on a determined power consumption level of the selected resources.

    Abstract translation: 功率消耗控制装置包括:资源选择单元,被配置为从图形处理单元(GPU)的资源中选择要确定其功耗水平的资源;资源使用信息获取单元,被配置为确定所选择的资源是否为 从使用GPU执行的程序的全部或一部分的代码块使用的功耗控制单元,其基于资源信息取得单元的判定结果来决定所选择的资源的功耗水平,并且控制 基于所选择的资源的确定的功率消耗水平,所选择的资源的功耗水平。

    CURVE RENDERING METHOD AND APPARATUS
    10.
    发明申请
    CURVE RENDERING METHOD AND APPARATUS 有权
    曲线渲染方法和设备

    公开(公告)号:US20150228094A1

    公开(公告)日:2015-08-13

    申请号:US14518501

    申请日:2014-10-20

    CPC classification number: G06T11/203 G06T11/20 G06T11/60

    Abstract: A curve rendering method includes calculating a step size based on a length of a straight line connecting a start point and an end point among control points of a curve to be rendered, and calculating initial values of a forward differencing algorithm (FDA) based on the calculated step size and coefficient values of an equation of the curve that is determined based on the control points. The method further includes generating an FDA table based on the initial values, and calculating a coordinate value of a pixel based on the FDA table.

    Abstract translation: 曲线绘制方法包括基于在要渲染的曲线的控制点中连接开始点和终点的直线的长度来计算步长,以及基于所述前向差分算法(FDA)的初始值计算 基于控制点确定的曲线方程的计算步长和系数值。 该方法还包括基于初始值生成FDA表,并基于FDA表计算像素的坐标值。

Patent Agency Ranking