-
公开(公告)号：US20110080416A1
公开(公告)日：2011-04-07
申请号：US12898624
申请日：2010-10-05
IPC分类号： G06T1/20
CPC分类号： G06T1/20 , G06F9/3851 , G06F9/3887 , G06T15/005 , G06T2210/04 , G06T2210/52
摘要： One embodiment of the present invention sets forth a technique for splitting a set of vertices into a plurality of batches for processing. The method includes receiving one or more primitives each containing an associated set of vertices. For each of the one or more primitives, one or more vertices are gathered from the set of vertices, the vertices are arranged into one or more batches, the batch is routed to a processing pipeline line to process each batch as a separate primitive, and the one or more batches are processed to produce results identical to those of processing the entire primitive as a single entity.
摘要翻译： 本发明的一个实施例提出了一种用于将一组顶点分割成多个批次以进行处理的技术。 该方法包括接收一个或多个每个包含相关联的顶点集的基元。 对于一个或多个基元中的每一个，从顶点集合中收集一个或多个顶点，将顶点排列成一个或多个批次，批次被路由到处理流水线，以将每个批处理作为单独的原语处理，以及 处理一个或多个批次以产生与作为单个实体处理整个原语的结果相同的结果。
-
公开(公告)号：US20110109638A1
公开(公告)日：2011-05-12
申请号：US12897622
申请日：2010-10-04
IPC分类号： G06T1/00
CPC分类号： G06T1/20 , G06F9/3851 , G06F9/3887
摘要： One embodiment of the present invention sets forth a technique for reducing overhead associated with transmitting primitive draw commands from memory to a graphics processing unit (GPU). Command pairs comprising an end draw command and a begin draw command associated with a conventional graphics application programming interface (API) are selectively replaced with a new construct. The new construct is a reset topology index, which implements a combined function of the end draw command and begin draw command. The new construct improves efficiency by reducing total data transmitted from memory to the GPU.
摘要翻译： 本发明的一个实施例提出了一种用于减少与将图形绘制命令从存储器传输到图形处理单元（GPU）相关联的开销的技术。 包括与传统图形应用编程接口（API）相关联的结束绘制命令和开始绘制命令的命令对被选择性地替换为新构造。 新构造是复位拓扑索引，它实现了结束绘制命令和开始绘制命令的组合功能。 新的结构通过减少从内存传输到GPU的总数据来提高效率。
-
公开(公告)号：US20110084975A1
公开(公告)日：2011-04-14
申请号：US12893617
申请日：2010-09-29
申请人： Jerome F. DULUK, JR. , Thomas Roell
发明人： Jerome F. DULUK, JR. , Thomas Roell
IPC分类号： G06T1/00
CPC分类号： G06T17/00 , G06F9/3009 , G06F9/30101 , G06F9/30109 , G06F9/3851 , G06F9/3887 , G06T2210/32
摘要： One embodiment of the present invention sets forth a technique for reducing the overhead for transmitting explicit begin and explicit end commands that are needed in primitive draw command sequences. A draw method includes a header to specify an implicit begin command, an implicit end command, and instancing information for a primitive draw command sequence. The header is followed by a packet including one or more data words (dwords) that each specify a primitive topology, starting offset into a vertex or index buffer, and vertex or index count. Only a single clock cycle is consumed to transmit and process the header. The performance of graphics application programs that have many small batches of geometry (as is typical of many workstation applications) may be improved since the overhead of transmitting and processing the explicit begin and explicit end draw commands is reduced.
摘要翻译： 本发明的一个实施例提出了用于减少用于发送原始绘制命令序列中所需的显式开始和显式终止命令的开销的技术。 绘制方法包括用于指定隐式开始命令的头部，隐式结束命令和用于原始绘制命令序列的实例化信息。 标题之后是包括一个或多个数据字（dwords）的数据包，每个数据字指定原始拓扑，将偏移开始到顶点或索引缓冲区，以及顶点或索引计数。 仅消耗一个时钟周期来传输和处理标题。 可以改进具有许多小批量几何图形应用程序的性能（如许多工作站应用程序的典型），因为减少了显式开始和显式结束绘制命令的传输和处理的开销。
-
公开(公告)号：US09589310B2
公开(公告)日：2017-03-07
申请号：US12898624
申请日：2010-10-05
CPC分类号： G06T1/20 , G06F9/3851 , G06F9/3887 , G06T15/005 , G06T2210/04 , G06T2210/52
摘要： One embodiment of the present invention sets forth a technique for splitting a set of vertices into a plurality of batches for processing. The method includes receiving one or more primitives each containing an associated set of vertices. For each of the one or more primitives, one or more vertices are gathered from the set of vertices, the vertices are arranged into one or more batches, the batch is routed to a processing pipeline line to process each batch as a separate primitive, and the one or more batches are processed to produce results identical to those of processing the entire primitive as a single entity.
摘要翻译： 本发明的一个实施例提出了一种用于将一组顶点分割成多个批次以进行处理的技术。 该方法包括接收一个或多个每个包含相关联的顶点集的基元。 对于一个或多个基元中的每一个，从顶点集合中收集一个或多个顶点，将顶点排列成一个或多个批次，批次被路由到处理流水线，以将每个批处理作为单独的原语处理，以及 处理一个或多个批次以产生与作为单个实体处理整个原语的结果相同的结果。
-
公开(公告)号：US08760455B2
公开(公告)日：2014-06-24
申请号：US12897622
申请日：2010-10-04
CPC分类号： G06T1/20 , G06F9/3851 , G06F9/3887
摘要： One embodiment of the present invention sets forth a technique for reducing overhead associated with transmitting primitive draw commands from memory to a graphics processing unit (GPU). Command pairs comprising an end draw command and a begin draw command associated with a conventional graphics application programming interface (API) are selectively replaced with a new construct. The new construct is a reset topology index, which implements a combined function of the end draw command and begin draw command. The new construct improves efficiency by reducing total data transmitted from memory to the GPU.
摘要翻译： 本发明的一个实施例提出了一种用于减少与将图形绘制命令从存储器传输到图形处理单元（GPU）相关联的开销的技术。 包括与传统图形应用编程接口（API）相关联的结束绘制命令和开始绘制命令的命令对被选择性地替换为新构造。 新构造是复位拓扑索引，它实现了结束绘制命令和开始绘制命令的组合功能。 新的结构通过减少从内存传输到GPU的总数据来提高效率。
-
公开(公告)号：US08427493B2
公开(公告)日：2013-04-23
申请号：US12893617
申请日：2010-09-29
申请人： Jerome F. Duluk, Jr. , Thomas Roell
发明人： Jerome F. Duluk, Jr. , Thomas Roell
IPC分类号： G06T1/60
CPC分类号： G06T17/00 , G06F9/3009 , G06F9/30101 , G06F9/30109 , G06F9/3851 , G06F9/3887 , G06T2210/32
摘要： One embodiment of the present invention sets forth a technique for reducing the overhead for transmitting explicit begin and explicit end commands that are needed in primitive draw command sequences. A draw method includes a header to specify an implicit begin command, an implicit end command, and instancing information for a primitive draw command sequence. The header is followed by a packet including one or more data words (dwords) that each specify a primitive topology, starting offset into a vertex or index buffer, and vertex or index count. Only a single clock cycle is consumed to transmit and process the header. The performance of graphics application programs that have many small batches of geometry (as is typical of many workstation applications) may be improved since the overhead of transmitting and processing the explicit begin and explicit end draw commands is reduced.
摘要翻译： 本发明的一个实施例提出了用于减少用于发送原始绘制命令序列中所需的显式开始和显式终止命令的开销的技术。 绘制方法包括用于指定隐式开始命令的头部，隐式结束命令和用于原始绘制命令序列的实例化信息。 标题之后是包括一个或多个数据字（dwords）的数据包，每个数据字指定原始拓扑，将偏移开始到顶点或索引缓冲区，以及顶点或索引计数。 仅消耗一个时钟周期来传输和处理标题。 可以改进具有许多小批量几何图形应用程序的性能（如许多工作站应用程序的典型），因为减少了显式开始和显式结束绘制命令的传输和处理的开销。
-
-
-
-
-
搜索结果
6 条记录 (耗时 0.012 秒)
