Systems and methods for caching compute kernels for an application running on a parallel-processing computer system
    42.
    发明申请
    Systems and methods for caching compute kernels for an application running on a parallel-processing computer system 有权
    用于缓存运行在并行处理计算机系统上的应用程序的计算内核的系统和方法

    公开(公告)号:US20070294682A1

    公开(公告)日:2007-12-20

    申请号:US11714480

    申请日:2007-03-05

    IPC分类号: G06F9/45

    CPC分类号: G06F8/45

    摘要: A runtime system implemented in accordance with the present invention provides an application platform for parallel-processing computer systems. Such a runtime system enables users to leverage the computational power of parallel-processing computer systems to accelerate/optimize numeric and array-intensive computations in their application programs. This enables greatly increased performance of high-performance computing (HPC) applications.

    摘要翻译: 根据本发明实现的运行时系统提供了一种用于并行处理计算机系统的应用平台。 这样的运行时系统使用户能够利用并行处理计算机系统的计算能力来加速/优化其应用程序中的数字和阵列密集型计算。 这样可以大大提高高性能计算(HPC)应用的性能。

    Systems and methods for dynamically choosing a processing element for a compute kernel
    43.
    发明申请
    Systems and methods for dynamically choosing a processing element for a compute kernel 有权
    用于动态选择计算内核的处理元素的系统和方法

    公开(公告)号:US20070294512A1

    公开(公告)日:2007-12-20

    申请号:US11714654

    申请日:2007-03-05

    IPC分类号: G06F9/30

    摘要: A runtime system implemented in accordance with the present invention provides an application platform for parallel-processing computer systems. Such a runtime system enables users to leverage the computational power of parallel-processing computer systems to accelerate/optimize numeric and array-intensive computations in their application programs. This enables greatly increased performance of high-performance computing (HPC) applications.

    摘要翻译: 根据本发明实现的运行时系统提供了一种用于并行处理计算机系统的应用平台。 这样的运行时系统使用户能够利用并行处理计算机系统的计算能力来加速/优化其应用程序中的数字和阵列密集型计算。 这样可以大大提高高性能计算(HPC)应用的性能。

    Gamma-corrected texel storage in a graphics memory
    44.
    发明授权
    Gamma-corrected texel storage in a graphics memory 有权
    Gamma校正的纹理存储器存储在图形存储器中

    公开(公告)号:US07289126B1

    公开(公告)日:2007-10-30

    申请号:US10445144

    申请日:2003-05-23

    IPC分类号: G09G5/00 G06T15/50 G06T15/00

    摘要: Methods, circuits, and apparatus for handling gamma-corrected texels stored in a graphics memory. On-the-fly gamma-to-linear and linear-to-gamma conversions are performed such that gamma-corrected texels are provided to circuits that are able to process them, while linear valued texels are supplied where needed. In various embodiments, these conversions are done by lookup tables, software instructions, or dedicated hardware. Gamma-corrected texels may be tracked by a shader program, pipeline states, or driver instructions, and may be identified by header or flag information, or by part of a texture descriptor.

    摘要翻译: 用于处理存储在图形存储器中的伽马校正的纹素的方法,电路和装置。 执行即时伽马对线性和线性到伽马转换,使得伽马校正的纹素提供给能够处理它们的电路,而在需要时提供线性值纹理。 在各种实施例中,这些转换通过查找表,软件指令或专用硬件完成。 伽马校正的纹素可以由着色器程序,流水线状态或驱动器指令来跟踪,并且可以由标题或标志信息或纹理描述符的一部分来标识。

    Multiple data buffers for processing graphics data

    公开(公告)号:US07015914B1

    公开(公告)日:2006-03-21

    申请号:US10732730

    申请日:2003-12-10

    IPC分类号: G06T1/20 G09G5/36

    CPC分类号: G06T1/20

    摘要: Multiple output buffers are supported in a graphics processor. Each output buffer has a unique identifier and may include data represented in a variety of fixed and floating-point formats (8-bit, 16-bit, 32-bit, 64-bit and higher). A fragment program executed by the graphics processor can access (read or write any of the output buffers. Each of the output buffers may be read from and used to process graphics data by a fragment shader within the graphics processor. Likewise, each output buffer may be written to by the graphics processor, storing graphics data such as lighting parameters, indices, color, and depth.

    Parallel pseudorandom number generation
    47.
    发明授权
    Parallel pseudorandom number generation 有权
    并行伪随机数生成

    公开(公告)号:US08756264B2

    公开(公告)日:2014-06-17

    申请号:US11716379

    申请日:2007-03-09

    IPC分类号: G06F1/02

    CPC分类号: G06F7/582

    摘要: A method of generating pseudo-random numbers on a parallel processing system comprises generating a plurality of sub-streams of pseudo-random numbers, wherein the sub-streams are generated in parallel by one or more co-processors, and providing the plurality of sub-streams to respective processing elements, wherein the respective processing elements employ the plurality of sub-streams to execute an application.

    摘要翻译: 一种在并行处理系统上产生伪随机数的方法包括产生多个伪随机数子流,其中所述子流由一个或多个协处理器并行产生,并且提供所述多个子流 流到相应的处理元件,其中相应的处理元件使用多个子流来执行应用。

    Systems and methods for caching compute kernels for an application running on a parallel-processing computer system
    48.
    发明授权
    Systems and methods for caching compute kernels for an application running on a parallel-processing computer system 有权
    用于缓存运行在并行处理计算机系统上的应用程序的计算内核的系统和方法

    公开(公告)号:US08448156B2

    公开(公告)日:2013-05-21

    申请号:US13406447

    申请日:2012-02-27

    IPC分类号: G06F9/45 G06F9/46

    CPC分类号: G06F8/45

    摘要: A runtime system implemented in accordance with the present invention provides an application platform for parallel-processing computer systems. Such a runtime system enables users to leverage the computational power of parallel-processing computer systems to accelerate/optimize numeric and array-intensive computations in their application programs. This enables greatly increased performance of high-performance computing (HPC) applications.

    摘要翻译: 根据本发明实现的运行时系统提供了一种用于并行处理计算机系统的应用平台。 这样的运行时系统使用户能够利用并行处理计算机系统的计算能力来加速/优化其应用程序中的数字和阵列密集型计算。 这样可以大大提高高性能计算(HPC)应用的性能。

    Systems and methods for profiling an application running on a parallel-processing computer system
    49.
    发明授权
    Systems and methods for profiling an application running on a parallel-processing computer system 有权
    用于分析在并行处理计算机系统上运行的应用程序的系统和方法

    公开(公告)号:US08375368B2

    公开(公告)日:2013-02-12

    申请号:US11716508

    申请日:2007-03-09

    IPC分类号: G06F9/44

    摘要: A runtime system implemented in accordance with the present invention provides an application platform for parallel-processing computer systems. Such a runtime system enables users to leverage the computational power of the parallel-processing computer systems to accelerate/optimize numeric and array-intensive computations in their application programs. A profiling tool is used to collect, analyze, and visualize the performance data of an application in connection with its execution on a parallel-processing computer system through the runtime system. This profiling tool greatly enhances an application developer's ability to understand how an application is executed on the parallel-processing computer system and fine-tune the application to achieve high performance.

    摘要翻译: 根据本发明实现的运行时系统提供了一种用于并行处理计算机系统的应用平台。 这样的运行时系统使得用户能够利用并行处理计算机系统的计算能力来加速/优化其应用程序中的数字和阵列密集型计算。 分析工具用于收集,分析和可视化与通过运行时系统在并行处理计算机系统上执行相关的应用程序的性能数据。 此分析工具大大提高了应用程序开发人员了解应用程序在并行处理计算机系统上的执行情况,并调整应用程序以实现高性能的能力。

    Digital image compositing using a programmable graphics processor
    50.
    发明授权
    Digital image compositing using a programmable graphics processor 有权
    使用可编程图形处理器的数字图像合成

    公开(公告)号:US07928997B2

    公开(公告)日:2011-04-19

    申请号:US10442331

    申请日:2003-05-21

    IPC分类号: G09G5/00 G06F15/00

    CPC分类号: G06T11/60

    摘要: Digital Image compositing using a programmable graphics processor is described. The programmable graphics processor supports high-precision data formats and can be programmed to complete a plurality of compositing operations in a single pass through a fragment processing pipeline within the programmable graphics processor. Source images for one or more compositing operations are stored in graphics memory, and a resulting composited image is output or stored in graphics memory. More-complex compositing operations, such as blur, warping, morphing, and the like, can be completed in multiple passes through the fragment processing pipeline. A composited image produced during a pass through the fragment processing pipeline is stored in graphics memory and is available as a source image for a subsequent pass.

    摘要翻译: 描述使用可编程图形处理器的数字图像合成。 可编程图形处理器支持高精度数据格式,并且可以被编程为在可编程图形处理器内的片段处理流水线的单次传递中完成多个合成操作。 用于一个或多个合成操作的源图像存储在图形存储器中,并且所得到的合成图像被输出或存储在图形存储器中。 更复杂的合成操作,如模糊,翘曲,变形等,可以通过片段处理流水线进行多次遍历。 在通过片段处理流水线期间产生的合成图像被存储在图形存储器中,并且可用作后续通过的源图像。