专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US07663635B2 Multiple video processor unit (VPU) memory mapping 有权
标题翻译：多视频处理器单元（VPU）存储映射
公开(公告)号：US07663635B2
公开(公告)日：2010-02-16
申请号：US11139917
申请日：2005-05-27
申请人： Philip J. Rogers , Jeffrey Gongxian Cheng , Dmitry Semiannikov , Raja Koduri
发明人： Philip J. Rogers , Jeffrey Gongxian Cheng , Dmitry Semiannikov , Raja Koduri
IPC分类号： G06F12/10 , G06F15/16
CPC分类号： G06T1/20
摘要： A system and method for memory mapping in a multiple video processor (multi VPU) system is described. In various embodiments, rendering tasks are shared among multiple VPUs in parallel to provide improved performance and capability with minimal increased cost. In various embodiments, multiple VPUs in a system access each other's local memories to facilitate cooperative video processing. In one embodiment, each VPU in the system has the local memories of each other VPU mapped to its own graphics aperture relocation table (GART) table to facilitate access via a virtual addressing scheme. Each VPU uses the same virtual addresses for this mapping to other VPU local memories. This allows the driver to send exactly the same write commands to each VPU, including the numeric value of the destination address for operations such as writing rendered data. Thus, unique addresses need not be generated for each VPU.
摘要翻译：描述了在多视频处理器（多VPU）系统中的存储器映射的系统和方法。在各种实施例中，并行地在多个VPU之间共享呈现任务，以最小的成本提供改善的性能和能力。在各种实施例中，系统中的多个VPU访问彼此的本地存储器以促进协作视频处理。在一个实施例中，系统中的每个VPU具有映射到其自己的图形孔径重定位表（GART）表的彼此VPU的本地存储器，以便于经由虚拟寻址方案的访问。每个VPU使用相同的虚拟地址来映射到其他VPU本地存储器。这允许驱动程序向每个VPU发送完全相同的写入命令，包括用于诸如编写渲染数据的操作的目标地址的数值。因此，不需要为每个VPU生成唯一的地址。

2. 发明申请

US20120147021A1 GRAPHICS COMPUTE PROCESS SCHEDULING 有权
标题翻译：图形计算过程调度
公开(公告)号：US20120147021A1
公开(公告)日：2012-06-14
申请号：US13289260
申请日：2011-11-04
申请人： Jeffrey Gongxian CHENG , Paul BLINZER , Mark HUMMEL , Leendert Peter VAN DOORN
发明人： Jeffrey Gongxian CHENG , Paul BLINZER , Mark HUMMEL , Leendert Peter VAN DOORN
IPC分类号： G06T1/00
CPC分类号： G06F9/545 , G06F2209/509
摘要： A method, system, and computer program product are disclosed for providing improved access to accelerated processing device compute resources to user mode applications. The functionality disclosed allows user mode applications to provide commands to an accelerated processing device without the need for kernel mode transitions in order to access a unified ring buffer. Instead, applications are each provided with their own buffers, which the accelerated processing device hardware can access to process commands. With full operating system support, user mode applications are able to utilize the accelerated processing device in much the same way as a CPU.
摘要翻译：公开了一种方法，系统和计算机程序产品，用于提供对用户模式应用的加速处理设备计算资源的改进访问。所公开的功能允许用户模式应用程序向加速处理设备提供命令，而不需要内核模式转换以便访问统一的环形缓冲区。相反，应用程序各自提供有自己的缓冲区，加速处理设备硬件可以访问进程命令。通过完整的操作系统支持，用户模式应用程序能够以与CPU相同的方式利用加速处理设备。

3. 发明授权

US09176794B2 Graphics compute process scheduling 有权
标题翻译：图形计算过程调度
公开(公告)号：US09176794B2
公开(公告)日：2015-11-03
申请号：US13289260
申请日：2011-11-04
申请人： Jeffrey Gongxian Cheng , Paul Blinzer , Mark Hummel , Leendert Peter Van Doorn
发明人： Jeffrey Gongxian Cheng , Paul Blinzer , Mark Hummel , Leendert Peter Van Doorn
IPC分类号： G06F12/02 , G06T1/00 , G06T15/00 , G06F9/54
CPC分类号： G06F9/545 , G06F2209/509
摘要： A method, system, and computer program product are disclosed for providing improved access to accelerated processing device compute resources to user mode applications. The functionality disclosed allows user mode applications to provide commands to an accelerated processing device without the need for kernel mode transitions in order to access a unified ring buffer. Instead, applications are each provided with their own buffers, which the accelerated processing device hardware can access to process commands. With full operating system support, user mode applications are able to utilize the accelerated processing device in much the same way as a CPU.
摘要翻译：公开了一种方法，系统和计算机程序产品，用于提供对用户模式应用的加速处理设备计算资源的改进访问。所公开的功能允许用户模式应用程序向加速处理设备提供命令，而不需要内核模式转换以便访问统一的环形缓冲区。相反，应用程序各自提供有自己的缓冲区，加速处理设备硬件可以访问进程命令。通过完整的操作系统支持，用户模式应用程序能够以与CPU相同的方式利用加速处理设备。

4. 发明授权

US07657897B2 Methods and apparatus for communicating between multiple levels of software components 有权
标题翻译：用于在多级软件组件之间进行通信的方法和装置
公开(公告)号：US07657897B2
公开(公告)日：2010-02-02
申请号：US11121545
申请日：2005-05-04
申请人： Zheng Huang , Efim Neiman , Jae Chong , Velodymyr Stempen , Jeffrey Gongxian Cheng , Vladimir F. Giemborek , Andrej Zdravkovic
发明人： Zheng Huang , Efim Neiman , Jae Chong , Velodymyr Stempen , Jeffrey Gongxian Cheng , Vladimir F. Giemborek , Andrej Zdravkovic
IPC分类号： G06F3/00 , G06F13/00
CPC分类号： G06F9/545
摘要： The present application discloses a method for communicating between at least two different levels of software components. The method includes establishing a command set common to the at least two different levels of software components. Additionally, the method includes providing a command decoder operable by both of the at least two levels of software components, the command decoder configured to decode the command set. By providing a common command set between different levels of software components, such as a software driver and a BIOS, where the commands within the command table are interpreted and executed by an identical command decoder that interprets and executes the same command tables, this ensures that the same features or functions are implemented or executed in the same way across different levels of the software components. Accordingly, redundant implementation of the same functions by different software components is eliminated. Additionally, when modification of the BIOS, for example, is performed, this modification only needs to be done in one place (i.e., the command table) rather than in each software component.
摘要翻译：本申请公开了一种用于在至少两个不同级别的软件组件之间进行通信的方法。该方法包括建立至少两个不同级别的软件组件共同的命令集。此外，该方法包括提供由至少两个级别的软件组件可操作的命令解码器，命令解码器被配置为对命令集进行解码。通过在不同级别的软件组件（例如软件驱动程序和BIOS）之间提供通用命令集，其中命令表中的命令由解释和执行相同命令表的相同命令解码器解释和执行，这确保了以相同的方式在不同级别的软件组件中实现或执行相同的特征或功能。因此，消除了不同软件组件对相同功能的冗余实现。此外，例如，当执行BIOS的修改时，仅在一个位置（即，命令表）而不是每个软件组件中进行该修改。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式