METHOD AND PROCESSOR FOR IMPLEMENTING THREAD AND RECORDING MEDIUM THEREOF
    11.
    发明申请
    METHOD AND PROCESSOR FOR IMPLEMENTING THREAD AND RECORDING MEDIUM THEREOF 有权
    用于执行螺纹和记录介质的方法和处理器

    公开(公告)号:US20160335125A1

    公开(公告)日:2016-11-17

    申请号:US15146044

    申请日:2016-05-04

    CPC classification number: G06F9/5038 G06F9/46

    Abstract: A processor and corresponding method are described including cores having a thread set allocated based on a pre-set implementation order, and a controller configured to receive scheduling information determined based on an implementation pattern regarding the allocated thread set from one of the cores and transmit the scheduling information to another of the cores. The one of cores determines the scheduling information according to characteristics of an application when implementation of the thread set is completed. Each of the cores re-determines an implementation order regarding the allocated thread set based on the determined scheduling information.

    Abstract translation: 描述了一种处理器和相应的方法,其包括具有基于预设实现顺序分配的线程集的核心,以及控制器,被配置为接收基于从一个核心分配的线程集合的实现模式确定的调度信息,并发送 将信息调度到另一个核心。 当线程集合的实现完成时,核心之一根据应用的特性确定调度信息。 每个核心基于所确定的调度信息重新确定关于所分配的线程组的实现顺序。

    METHOD AND SYSTEM FOR TRANSCEIVING DATA OVER ON-CHIP NETWORK
    12.
    发明申请
    METHOD AND SYSTEM FOR TRANSCEIVING DATA OVER ON-CHIP NETWORK 审中-公开
    用于在片上网络上收发数据的方法和系统

    公开(公告)号:US20160205042A1

    公开(公告)日:2016-07-14

    申请号:US14950490

    申请日:2015-11-24

    CPC classification number: H04L49/102 H04L45/16

    Abstract: A method of transceiving data over an on-chip network includes determining whether a packet is received by a first router among a plurality of first routers constituting a ring network; determining a transmission destination of the packet received by the first router; and transmitting the packet to a second router among a plurality of second routers constituting a bus network connected to the first router in response to the determined transmission destination being located on the bus network connected to the first router.

    Abstract translation: 一种通过片上网络收发数据的方法包括:确定构成环网的多个第一路由器中的第一路由器是否接收到分组; 确定由第一路由器接收的分组的传输目的地; 以及响应于所确定的发送目的地位于连接到所述第一路由器的总线网络上,将构成连接到所述第一路由器的总线网络的多个第二路由器中的所述分组发送到第二路由器。

    APPARATUS AND METHOD FOR RENDERING
    13.
    发明申请
    APPARATUS AND METHOD FOR RENDERING 有权
    设备和渲染方法

    公开(公告)号:US20160163087A1

    公开(公告)日:2016-06-09

    申请号:US14962648

    申请日:2015-12-08

    Abstract: A tile-based rendering method includes performing binning of a current frame; generating an identification code of binning information or property information of a tile to be rendered in the current frame; comparing the identification code of the tile to be rendered to an identification code of a previous tile, wherein a location of the previous tile in a previous frame is the same as a location of the tile to be rendered in the current frame; and rendering the current frame by either re-using an image stored in a frame buffer or performing pixel processing of the tile to be rendered depending on a result of the comparing.

    Abstract translation: 基于瓦片的呈现方法包括执行当前帧的合并; 生成要在当前帧中呈现的瓦片的合并信息或属性信息的识别码; 将要渲染的瓦片的识别码与先前瓦片的识别码进行比较,其中先前帧中的前一瓦片的位置与当前帧中要渲染的瓦片的位置相同; 以及通过重新使用存储在帧缓冲器中的图像或者根据比较的结果执行要渲染的图块的像素处理来渲染当前帧。

    CURVE RENDERING METHOD AND APPARATUS
    14.
    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。

    METHOD AND APPARATUS FOR PROCESSING DATA USING CALCULATORS HAVING DIFFERENT DEGREES OF ACCURACY
    17.
    发明申请
    METHOD AND APPARATUS FOR PROCESSING DATA USING CALCULATORS HAVING DIFFERENT DEGREES OF ACCURACY 审中-公开
    使用具有不同精确度的计算器处理数据的方法和装置

    公开(公告)号:US20160147515A1

    公开(公告)日:2016-05-26

    申请号:US14730915

    申请日:2015-06-04

    CPC classification number: G06F8/456 G06F7/483 G06F8/41 G06F8/447

    Abstract: A method of processing data includes classifying input data into first data and second data, the second data being different from the first data, separately compiling the first data and the second data, and providing the compiled first data and the compiled second data to a first operator and a second operator, respectively, in which the first operator performs an operation different from an operation performed by the second operator.

    Abstract translation: 处理数据的方法包括将输入数据分类为第一数据和第二数据,第二数据与第一数据不同,分别编译第一数据和第二数据,并将编译的第一数据和编译的第二数据提供给第一数据 操作者和第二操作者,其中第一操作者执行与第二操作者执行的操作不同的操作。

    RENDERING APPARATUS AND METHOD
    18.
    发明申请
    RENDERING APPARATUS AND METHOD 有权
    渲染设备和方法

    公开(公告)号:US20160086340A1

    公开(公告)日:2016-03-24

    申请号:US14803754

    申请日:2015-07-20

    CPC classification number: G06T7/40 G06T15/405

    Abstract: Provided are a rendering method and a rendering apparatus performing the rendering method. The rendering method includes receiving a request to output a hierarchical depth value stored in a hierarchical depth buffer, outputting the hierarchical depth value from the hierarchical depth buffer, storing the hierarchical depth value, in response to the request, and performing rendering using the stored hierarchical depth value.

    Abstract translation: 提供了一种渲染方法和一种执行渲染方法的渲染装置。 渲染方法包括:接收请求,输出存储在分层深度缓冲器中的层次深度值,响应于该请求从分层深度缓冲器输出层次深度值,存储分层深度值,并使用存储的分层 深度值。

    METHOD AND APPARATUS FOR RENDERING
    19.
    发明申请
    METHOD AND APPARATUS FOR RENDERING 审中-公开
    用于渲染的方法和装置

    公开(公告)号:US20160078637A1

    公开(公告)日:2016-03-17

    申请号:US14801108

    申请日:2015-07-16

    CPC classification number: G06T1/60 G06T15/04 G06T2210/36

    Abstract: A rendering method includes generating mipmap images of some levels with respect to texture and storing the generated mipmap images in a storage, receiving a request for the texture, calculating a level of a mipmap requested for the texture, determining whether the stored mipmap images include the mipmap image of the calculated level, and performing rendering by using at least one of the stored mipmap images, based on a result of the determining.

    Abstract translation: 渲染方法包括生成关于纹理的一些级别的mipmap图像,并将生成的mipmap图像存储在存储器中,接收对纹理的请求,计算对纹理请求的mipmap的级别,确定所存储的mipmap图像是否包括 mipmap图像,并且基于确定的结果,通过使用所存储的mipmap图像中的至少一个来执行渲染。

    CACHE MEMORY SYSTEM AND OPERATING METHOD THEREOF
    20.
    发明申请
    CACHE MEMORY SYSTEM AND OPERATING METHOD THEREOF 有权
    缓存记忆系统及其操作方法

    公开(公告)号:US20160077969A1

    公开(公告)日:2016-03-17

    申请号:US14692828

    申请日:2015-04-22

    Abstract: A cache memory apparatus includes a tag comparator configured to compare upper bits of each of pieces of tag data included in a set indicated by a set address that is received with upper bits of a tag address that is received, compare other bits of each of the pieces of the tag data with other bits of the tag address, and determine whether there is a cache hit or a cache miss based on results of the comparisons, and an update controller configured to, in response to the cache miss being determined, determine, as an update candidate, a piece among pieces of cache data included in the set and corresponding to the pieces of the tag data, based on the result of the comparison of the upper bits of each of the pieces of the tag data and the upper bits of the tag address, and update the update candidate with new data.

    Abstract translation: 高速缓冲存储器装置包括:标签比较器,被配置为比较由接收到的设定地址所指定的集合中包含的每个标签数据的高位,比较接收到的标签地址的高位, 标签数据与标签地址的其他位的片段,并且基于比较的结果来确定是否存在高速缓存命中或高速缓存未命中;以及更新控制器,被配置为响应于所确定的高速缓存未命中, 作为更新候选者,基于每个标签数据的高位和高位之间的比较结果,包括在集合中并与标签数据相对应的多条高速缓存数据中的一条 的标签地址,并用新数据更新更新候选。

Patent Agency Ranking