公开(公告)号：US20070139422A1

公开(公告)日：2007-06-21

申请号：US11300705

申请日：2005-12-15

申请人： Dehai Kong ,  Wen-Chung Chen ,  Ping Chen ,  Irene Cheng ,  Tatsang Mak ,  Xi Liu ,  Li Zhang ,  Li Sun ,  Chenggang Liu

发明人： Dehai Kong ,  Wen-Chung Chen ,  Ping Chen ,  Irene Cheng ,  Tatsang Mak ,  Xi Liu ,  Li Zhang ,  Li Sun ,  Chenggang Liu

IPC分类号： G06F15/16

CPC分类号： G09G5/363

摘要： A system and method for supporting multiple graphics processing units (GPUs) includes a first communication path coupled to a root complex device and a first connection point of a first GPU. A second communication path is coupled to the root complex device and a first set of switches. The first set of switches is configured to route communications between the root complex device to either a second connection point of the first GPU via a second set of switches or to a first connection point of a second GPU. The second set of switches is coupled to a second connection point of the first GPU. The second set of switches is configured to route communications to and from the second connection point of the first GPU and to either the root complex device via the first set of switches or to a second connection point of the second GPU.

摘要翻译： 用于支持多个图形处理单元（GPU）的系统和方法包括耦合到根复杂设备的第一通信路径和第一GPU的第一连接点。 第二通信路径耦合到根复合设备和第一组交换机。 第一组交换机被配置为将根复合设备之间的通信经由第二组交换机或第二GPU的第一连接点路由到第一GPU的第二连接点。 第二组开关耦合到第一GPU的第二连接点。 第二组交换机被配置为将通信路由到第一GPU的第二连接点和从第一组交换机的根复合设备到第二GPU的第二连接点的通信。

公开(公告)号：US20070139423A1

公开(公告)日：2007-06-21

申请号：US11300980

申请日：2005-12-15

申请人： Dehai Kong ,  Wen-Chung Chen ,  Ping Chen ,  Irene (Chih-Yiieh) Cheng ,  Tatsang Mak ,  Xi Liu ,  Li Zhang ,  Li Sun ,  Chenggang Liu

发明人： Dehai Kong ,  Wen-Chung Chen ,  Ping Chen ,  Irene (Chih-Yiieh) Cheng ,  Tatsang Mak ,  Xi Liu ,  Li Zhang ,  Li Sun ,  Chenggang Liu

IPC分类号： G06F15/16

CPC分类号： G09G5/363

摘要： Supporting multiple graphics processing units (GPUs) comprises a first path coupled to a north bridge device (or a root complex device) and a first GPU, which may include a portion of the first GPU's total communication lanes. A second communication path may be coupled to the north bridge device and a second GPU and may include a portion of the second GPU's total communication lanes. A third communication path may be coupled between the first and second GPUs directly or through one or more switches that can be configured for single or multiple GPU operations. The third communication path may include some or all of the remaining communication lanes for the first and second GPUs. As a nonlimiting example, the first and second GPUs may each utilize an 8-lane PCI express communication path with the north bridge device and an 8-lane PCI express communication path with each other.

摘要翻译： 支持多个图形处理单元（GPU）包括耦合到北桥设备（或根复杂设备）的第一路径和可以包括第一GPU总通信线路的一部分的第一GPU。 第二通信路径可以耦合到北桥设备和第二GPU，并且可以包括第二GPU的总通信线路的一部分。 第三通信路径可以直接地耦合在第一和第二GPU之间，或者通过一个或多个可以被配置用于单个或多个GPU操作的交换机。 第三通信路径可以包括用于第一和第二GPU的剩余通信线路中的一些或全部。 作为非限制性示例，第一和第二GPU可以各自利用与北桥设备的8通道PCI快速通信路径和彼此之间的8通道PCI快速通信路径。

公开(公告)号：US07325086B2

公开(公告)日：2008-01-29

申请号：US11300980

申请日：2005-12-15

申请人： Roy (Dehai) Kong ,  Wen-Chung Chen ,  Ping Chen ,  Irene (Chih-Yiieh) Cheng ,  Tatsang Mak ,  Xi Liu ,  Li Zhang ,  Li Sun ,  Chenggang Liu

发明人： Roy (Dehai) Kong ,  Wen-Chung Chen ,  Ping Chen ,  Irene (Chih-Yiieh) Cheng ,  Tatsang Mak ,  Xi Liu ,  Li Zhang ,  Li Sun ,  Chenggang Liu

IPC分类号： G06F13/40

CPC分类号： G09G5/363

摘要： Supporting multiple graphics processing units (GPUs) comprises a first path coupled to a north bridge device (or a root complex device) and a first GPU, which may include a portion of the first GPU's total communication lanes. A second communication path may be coupled to the north bridge device and a second GPU and may include a portion of the second GPU's total communication lanes. A third communication path may be coupled between the first and second GPUs directly or through one or more switches that can be configured for single or multiple GPU operations. The third communication path may include some or all of the remaining communication lanes for the first and second GPUs. As a nonlimiting example, the first and second GPUs may each utilize an 8-lane PCI express communication path with the north bridge device and an 8-lane PCI express communication path with each other.

摘要翻译： 支持多个图形处理单元（GPU）包括耦合到北桥设备（或根复杂设备）的第一路径和可以包括第一GPU总通信线路的一部分的第一GPU。 第二通信路径可以耦合到北桥设备和第二GPU，并且可以包括第二GPU的总通信线路的一部分。 第三通信路径可以直接地耦合在第一和第二GPU之间，或者通过一个或多个可以被配置用于单个或多个GPU操作的交换机。 第三通信路径可以包括用于第一和第二GPU的剩余通信线路中的一些或全部。 作为非限制性示例，第一和第二GPU可以各自利用与北桥设备的8通道PCI快速通信路径和彼此之间的8通道PCI快速通信路径。

公开(公告)号：US07340557B2

公开(公告)日：2008-03-04

申请号：US11300705

申请日：2005-12-15

申请人： Dehai Kong ,  Wen-Chung Chen ,  Ping Chen ,  Irene Chih-Yiieh Cheng ,  Tatsang Mak ,  Xi Liu ,  Li Zhang ,  Li Sun ,  Chenggang Liu

发明人： Dehai Kong ,  Wen-Chung Chen ,  Ping Chen ,  Irene Chih-Yiieh Cheng ,  Tatsang Mak ,  Xi Liu ,  Li Zhang ,  Li Sun ,  Chenggang Liu

IPC分类号： G06F13/00 ,  G06F13/36

CPC分类号： G09G5/363

摘要： A system and method for supporting multiple graphics processing units (GPUs) includes a first communication path coupled to a root complex device and a first connection point of a first GPU. A second communication path is coupled to the root complex device and a first set of switches. The first set of switches is configured to route communications between the root complex device to either a second connection point of the first GPU via a second set of switches or to a first connection point of a second GPU. The second set of switches is coupled to a second connection point of the first GPU. The second set of switches is configured to route communications to and from the second connection point of the first GPU and to either the root complex device via the first set of switches or to a second connection point of the second GPU.

摘要翻译： 用于支持多个图形处理单元（GPU）的系统和方法包括耦合到根复杂设备的第一通信路径和第一GPU的第一连接点。 第二通信路径耦合到根复合设备和第一组交换机。 第一组交换机被配置为将根复合设备之间的通信经由第二组交换机或第二GPU的第一连接点路由到第一GPU的第二连接点。 第二组开关耦合到第一GPU的第二连接点。 第二组交换机被配置为将通信路由到第一GPU的第二连接点和从第一组交换机的根复合设备到第二GPU的第二连接点的通信。

公开(公告)号：US09460549B2

公开(公告)日：2016-10-04

申请号：US13382765

申请日：2010-04-01

申请人： Chenggang Liu

发明人： Chenggang Liu

IPC分类号： G06T15/20 ,  G06T7/00 ,  G06K9/00 ,  G06T7/20 ,  G06T7/60

CPC分类号： G06T15/20 ,  G06K9/00791 ,  G06K9/00798 ,  G06T7/60 ,  G06T2207/10012

摘要： A method and device for generating a perspective image are provided, which are related to multimedia technology. The method comprises the following steps: acquiring the length, height and vanishing point of a required perspective image and the length and height of an original image; for each pixel point (x′, y′) in the perspective image, determining the coordinate (x, y) of a pixel point in the original image corresponding to said pixel point; copying the pixel point at the coordinate (x, y) in the original image to the position corresponding to the coordinate (x′, y′) in said perspective image. The invention utilizes a principle that perspective image is smaller than original image, and employs a form of inverse transform, thereby the calculated pixel points are reduced, and compared with forward calculation, the calculation is greatly reduced, which improves the speed of perspective image generating and saves central processing unit (CPU) resources.

摘要翻译： 提供了一种与多媒体技术相关的用于产生透视图像的方法和装置。 该方法包括以下步骤：获取所需视角图像的长度，高度和消失点以及原始图像的长度和高度; 对于透视图像中的每个像素点（x'，y'），确定对应于所述像素点的原始图像中的像素点的坐标（x，y）; 将原始图像中的坐标（x，y）处的像素点复制到与所述透视图像中的坐标（x'，y'）相对应的位置。 本发明利用透视图像小于原始图像的原理，并采用逆变换的形式，从而减少计算出的像素点，并与正向计算相比，大大减少了计算，提高了透视图像生成速度 并节省中央处理单元（CPU）资源。

公开(公告)号：US20120113114A1

公开(公告)日：2012-05-10

申请号：US13382765

申请日：2010-04-01

申请人： Chenggang Liu

发明人： Chenggang Liu

IPC分类号： G06T15/00

CPC分类号： G06T15/20 ,  G06K9/00791 ,  G06K9/00798 ,  G06T7/60 ,  G06T2207/10012

摘要： A method and device for generating a perspective image are provided, which are related to multimedia technology. The method comprises the following steps: acquiring the length, height and vanishing point of a required perspective image and the length and height of an original image; for each pixel point (x′, y′) in the perspective image, determining the coordinate (x, y) of a pixel point in the original image corresponding to said pixel point; copying the pixel point at the coordinate (x, y) in the original image to the position corresponding to the coordinate (x′, y′) in said perspective image. The invention utilizes a principle that perspective image is smaller than original image, and employs a form of inverse transform, thereby the calculated pixel points are reduced, and compared with forward calculation, the calculation is greatly reduced, which improves the speed of perspective image generating and saves central processing unit (CPU) resources.

摘要翻译： 提供了一种与多媒体技术相关的用于产生透视图像的方法和装置。 该方法包括以下步骤：获取所需视角图像的长度，高度和消失点以及原始图像的长度和高度; 对于透视图像中的每个像素点（x'，y'），确定对应于所述像素点的原始图像中的像素点的坐标（x，y）; 将原始图像中的坐标（x，y）处的像素点复制到与所述透视图像中的坐标（x'，y'）相对应的位置。 本发明利用透视图像小于原始图像的原理，并采用逆变换的形式，从而减少计算出的像素点，并与正向计算相比，大大减少了计算，提高了透视图像生成速度 并节省中央处理单元（CPU）资源。

公开(公告)号：US09091602B2

公开(公告)日：2015-07-28

申请号：US13520341

申请日：2011-03-18

申请人： Bolin Cao ,  Chengzhang Tan ,  Rui Cao ,  Chenggang Liu

发明人： Bolin Cao ,  Chengzhang Tan ,  Rui Cao ,  Chenggang Liu

IPC分类号： G01K15/00 ,  G01N3/00 ,  G01J5/52 ,  G01J5/00

CPC分类号： G01K15/005 ,  G01J5/522 ,  G01J2005/0048

摘要： The present invention provides a quantum theory correction method for improving the accuracy of temperature measurement of radiation thermometer and a radiation thermometer system. The invention is related to the radiation thermometer in the field of instrumentation. The present invention acquires parameters reflecting energy level structure by adopting effective physical model to process data and using keyboard input or data transmission. The temperature of the object to be measured is finally acquired and displayed on the displayer. The quantum theory correction method and radiation thermometer system effectively overcome the difficulty that the value of radiance ε(λ·T) cannot be accurately measured in the event that radiance correction method is used to improve the accuracy of radiation thermometer. Thus, the accuracy of thermometer is improved significantly.

摘要翻译： 本发明提供了一种用于提高辐射温度计和辐射温度计系统的温度测量精度的量子理论校正方法。 本发明涉及仪表领域的辐射温度计。 本发明通过采用有效的物理模型来处理数据和使用键盘输入或数据传输来获取反映能级结构的参数。 最终获取待测物体的温度并显示在显示器上。 量子理论校正方法和辐射温度计系统有效克服了使用辐射校正方法提高辐射温度计精度的情况下无法精确测量辐射值（λ·T）的值。 因此，温度计的精度明显提高。

公开(公告)号：US20130148688A1

公开(公告)日：2013-06-13

申请号：US13520341

申请日：2011-03-18

申请人： Bolin Cao ,  Chengzhang Tan ,  Rui Cao ,  Chenggang Liu

发明人： Bolin Cao ,  Chengzhang Tan ,  Rui Cao ,  Chenggang Liu

IPC分类号： G01K15/00

CPC分类号： G01K15/005 ,  G01J5/522 ,  G01J2005/0048

摘要： The present invention provides a quantum theory correction method for improving the accuracy of temperature measurement of radiation thermometer and a radiation thermometer system. The invention is related to the radiation thermometer in the field of instrumentation. The present invention acquires parameters reflecting energy level structure by adopting effective physical model to process data and using keyboard input or data transmission. The temperature of the object to be measured is finally acquired and displayed on the displayer. The quantum theory correction method and radiation thermometer system effectively overcome the difficulty that the value of radiance ε(λ·T) cannot be accurately measured in the event that radiance correction method is used to improve the accuracy of radiation thermometer. Thus, the accuracy of thermometer is improved significantly.

摘要翻译： 本发明提供了一种用于提高辐射温度计和辐射温度计系统的温度测量精度的量子理论校正方法。 本发明涉及仪表领域的辐射温度计。 本发明通过采用有效的物理模型来处理数据和使用键盘输入或数据传输来获取反映能级结构的参数。 最终获取待测物体的温度并显示在显示器上。 量子理论校正方法和辐射温度计系统有效地克服了使用辐射校正方法提高辐射温度计精度的情况下难以准确测量辐射ε（λ·T）值的难度。 因此，温度计的精度明显提高。