利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

9 条记录 (耗时 0.028 秒)

    System and method for transferring data between unrelated API contexts on one or more GPUs
    6.
    发明授权
    System and method for transferring data between unrelated API contexts on one or more GPUs 有权
    用于在一个或多个GPU上的不相关的API上下文之间传送数据的系统和方法

    公开(公告)号：US08223159B1

    公开(公告)日：2012-07-17

    申请号：US11471154

    申请日：2006-06-20

    申请人： Franck R. Diard ,  Barthold B. Lichtenbelt ,  Mark J. Harris ,  Simon G. Green

    发明人： Franck R. Diard ,  Barthold B. Lichtenbelt ,  Mark J. Harris ,  Simon G. Green

    IPC分类号： G06T1/00

    CPC分类号： G06T1/20

    摘要： One embodiment of the present invention sets forth a system configured for transferring data between independent application programming interface (API) contexts on one or more graphics processing units (GPUs). Each API context may derive from an arbitrary API. Data is pushed from one API context to another API context using a peer-to-peer buffer “blit” operation executed between buffers allocated in the source and target API context memory spaces. The source and target API context memory spaces may be located within the frame buffers of the source and target GPUs, respectively, or located within the frame buffer of a single GPU. The data transfers between the API contexts are synchronized using semaphore operator pairs inserted in push buffer commands that are executed by the one or more GPUs.

    摘要翻译： 本发明的一个实施例阐述了一种被配置为在一个或多个图形处理单元（GPU）上的独立应用编程接口（API）上下文之间传送数据的系统。 每个API上下文都可以从任意的API派生。 使用在源和目标API上下文存储空间中分配的缓冲区之间执行的对等缓冲区“blit”操作，将数据从一个API上下文推送到另一个API上下文。 源API和目标API上下文存储器空间可以分别位于源GPU和目标GPU的帧缓冲器内，或者位于单个GPU的帧缓冲器内。 使用由一个或多个GPU执行的推送缓冲区命令中插入的信号量操作符对，使API上下文之间的数据传输同步。

    System, method and computer program product for performing a scan operation
    7.
    发明授权
    System, method and computer program product for performing a scan operation 有权
    用于执行扫描操作的系统，方法和计算机程序产品

    公开(公告)号：US08996846B2

    公开(公告)日：2015-03-31

    申请号：US11862938

    申请日：2007-09-27

    申请人： Samuli M. Laine ,  Timo O. Aila ,  Mark J. Harris

    发明人： Samuli M. Laine ,  Timo O. Aila ,  Mark J. Harris

    IPC分类号： G06F9/38 ,  G06F9/52 ,  G06F9/30 ,  G06F17/30

    CPC分类号： G06F9/52 ,  G06F9/3001 ,  G06F9/30029 ,  G06F9/30036 ,  G06F9/3851 ,  G06F9/3885 ,  G06F9/522 ,  G06F17/30988

    摘要： A system, method, and computer program product are provided for efficiently performing a scan operation. In use, an array of elements is traversed by utilizing a parallel processor architecture. Such parallel processor architecture includes a plurality of processors each capable of physically executing a predetermined number of threads in parallel. For efficiency purposes, the predetermined number of threads of at least one of the processors may be executed to perform a scan operation involving a number of the elements that is a function (e.g. multiple, etc.) of the predetermined number of threads.

    摘要翻译： 提供了一种用于有效执行扫描操作的系统，方法和计算机程序产品。 在使用中，通过使用并行处理器架构遍历元素数组。 这种并行处理器架构包括多个处理器，每个处理器能够并行地物理地执行预定数量的线程。 为了效率目的，可以执行至少一个处理器的预定数量的线程以执行涉及作为预定线程数的函数（例如，多个等）的多个元素的扫描操作。

    SYSTEM, METHOD AND COMPUTER PROGRAM PRODUCT FOR PERFORMING A SCAN OPERATION
    8.
    发明申请
    SYSTEM, METHOD AND COMPUTER PROGRAM PRODUCT FOR PERFORMING A SCAN OPERATION 有权
    用于执行扫描操作的系统，方法和计算机程序产品

    公开(公告)号：US20090089542A1

    公开(公告)日：2009-04-02

    申请号：US11862938

    申请日：2007-09-27

    申请人： Samuli M. Laine ,  Timo O. Aila ,  Mark J. Harris

    发明人： Samuli M. Laine ,  Timo O. Aila ,  Mark J. Harris

    IPC分类号： G06F15/80 ,  G06F9/02

    CPC分类号： G06F9/52 ,  G06F9/3001 ,  G06F9/30029 ,  G06F9/30036 ,  G06F9/3851 ,  G06F9/3885 ,  G06F9/522 ,  G06F17/30988

    摘要： A system, method, and computer program product are provided for efficiently performing a scan operation. In use, an array of elements is traversed by utilizing a parallel processor architecture. Such parallel processor architecture includes a plurality of processors each capable of physically executing a predetermined number of threads in parallel. For efficiency purposes, the predetermined number of threads of at least one of the processors may be executed to perform a scan operation involving a number of the elements that is a function (e.g. multiple, etc.) of the predetermined number of threads.

    摘要翻译： 提供了一种用于有效执行扫描操作的系统，方法和计算机程序产品。 在使用中，通过使用并行处理器架构遍历元素数组。 这种并行处理器架构包括多个处理器，每个处理器能够并行地物理地执行预定数量的线程。 为了效率目的，可以执行至少一个处理器的预定数量的线程以执行涉及作为预定线程数的函数（例如，多个等）的多个元素的扫描操作。

    Spark plug with platinum tip partially embedded in an electrode
    9.
    发明授权
    Spark plug with platinum tip partially embedded in an electrode 失效
    具有部分嵌入电极中的铂尖端的火花塞

    公开(公告)号：US5558575A

    公开(公告)日：1996-09-24

    申请号：US441095

    申请日：1995-05-15

    申请人： Randolph K. Chiu ,  Mark J. Harris

    发明人： Randolph K. Chiu ,  Mark J. Harris

    IPC分类号： H01T21/02

    CPC分类号： H01T21/02

    摘要： Generally, the invention include a spark plug with a platinum tip partially embedded in one of the spark plug's electrodes. A spark plug according to the present invention may be prepared by first heating the area of the electrode where the platinum tip is to be attached to a temperature such that the platinum tip may be pushed into and embedded in the electrode. Thereafter the platinum tip is welded to the electrode. Heating the electrode allows the platinum tip to penetrate deeper into the electrode material. This deeper penetration or embedment will reduce the operating temperature at the weld interface (junction) which will in turn reduce the thermal stress and hence prevent cracking of the platinum tip. This deeper penetration or embedment will also reduce the rate of oxidation at the platinum tip near the weld junction and hence prevent cracking of the platinum tip.

    摘要翻译： 通常，本发明包括具有部分地嵌入火花塞电极之一中的铂尖端的火花塞。 根据本发明的火花塞可以通过首先将铂尖端附着的电极的区域加热到使得铂尖端可以被推入并嵌入电极的温度来制备。 此后，铂尖端焊接到电极。 加热电极允许铂尖端深入电极材料。 这种较深的穿透或嵌入会降低焊接界面（结）处的工作温度，从而降低热应力，从而防止铂尖端开裂。 这种更深的穿透或嵌入也将降低在焊接接头附近的铂尖端的氧化速率，并且因此防止铂尖端的开裂。