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

US09595074B2 Multistage collector for outputs in multiprocessor systems 有权
标题翻译：多处理器系统中的输出多级收集器
公开(公告)号：US09595074B2
公开(公告)日：2017-03-14
申请号：US13611325
申请日：2012-09-12
申请人： James Alexander McCombe , Steven John Clohset , Jason Rupert Redgrave , Luke Tilman Peterson
发明人： James Alexander McCombe , Steven John Clohset , Jason Rupert Redgrave , Luke Tilman Peterson
IPC分类号： G06F15/80 , G06T1/20 , G06T15/06
CPC分类号： G06T1/60 , G06T1/20 , G06T15/06 , G06T2210/52
摘要： Aspects include a multistage collector to receive outputs from plural processing elements. Processing elements may comprise (each or collectively) a plurality of clusters, with one or more ALUs that may perform SIMD operations on a data vector and produce outputs according to the instruction stream being used to configure the ALU(s). The multistage collector includes substituent components each with at least one input queue, a memory, a packing unit, and an output queue; these components can be sized to process groups of input elements of a given size, and can have multiple input queues and a single output queue. Some components couple to receive outputs from the ALUs and others receive outputs from other components. Ultimately, the multistage collector can output groupings of input elements. Each grouping of elements (e.g., at input queues, or stored in the memories of component) can be formed based on matching of index elements.
摘要翻译：方面包括用于接收来自多个处理元件的输出的多级收集器。处理元件可以包括（每个或集体）多个聚类，其中一个或多个ALU可以对数据向量执行SIMD操作，并根据用于配置ALU的指令流产生输出。多级收集器包括各自具有至少一个输入队列，存储器，打包单元和输出队列的取代组件; 这些组件的大小可以处理给定大小的输入元素组，并且可以具有多个输入队列和单个输出队列。一些组件耦合以接收来自ALU和其他组件的输出，从其他组件接收输出。最终，多级收集器可以输出输入元素的分组。可以基于索引元素的匹配来形成每个元素组（例如，在输入队列处或存储在组件的存储器中）。

2. 发明申请

US20130069960A1 MULTISTAGE COLLECTOR FOR OUTPUTS IN MULTIPROCESSOR SYSTEMS 有权
标题翻译：多处理器系统中的输出多级收集器
公开(公告)号：US20130069960A1
公开(公告)日：2013-03-21
申请号：US13611325
申请日：2012-09-12
申请人： James Alexander McCombe , Steven John Clohset , Jason Rupert Redgrave , Luke Tilman Peterson
发明人： James Alexander McCombe , Steven John Clohset , Jason Rupert Redgrave , Luke Tilman Peterson
IPC分类号： G06T1/20
CPC分类号： G06T1/60 , G06T1/20 , G06T15/06 , G06T2210/52
摘要： Aspects include a multistage collector to receive outputs from plural processing elements. Processing elements may comprise (each or collectively) a plurality of clusters, with one or more ALUs that may perform SIMD operations on a data vector and produce outputs according to the instruction stream being used to configure the ALU(s). The multistage collector includes substituent components each with at least one input queue, a memory, a packing unit, and an output queue; these components can be sized to process groups of input elements of a given size, and can have multiple input queues and a single output queue. Some components couple to receive outputs from the ALUs and others receive outputs from other components. Ultimately, the multistage collector can output groupings of input elements. Each grouping of elements (e.g., at input queues, or stored in the memories of component) can be formed based on matching of index elements.
摘要翻译：方面包括用于接收来自多个处理元件的输出的多级收集器。处理元件可以包括（每个或集体）多个聚类，其中一个或多个ALU可以对数据向量执行SIMD操作，并根据用于配置ALU的指令流产生输出。多级收集器包括各自具有至少一个输入队列，存储器，打包单元和输出队列的取代组件; 这些组件的大小可以处理给定大小的输入元素组，并且可以具有多个输入队列和单个输出队列。一些组件耦合以接收来自ALU和其他组件的输出，从其他组件接收输出。最终，多级收集器可以输出输入元素的分组。可以基于索引元素的匹配来形成每个元素组（例如，在输入队列处或存储在组件的存储器中）。

3. 发明授权

US08692834B2 Graphics processor with non-blocking concurrent architecture 有权
标题翻译：具有非阻塞并发架构的图形处理器
公开(公告)号：US08692834B2
公开(公告)日：2014-04-08
申请号：US13567091
申请日：2012-08-06
申请人： Luke Tilman Peterson , James Alexander McCombe , Steven John Clohset , Jason Rupert Redgrave
发明人： Luke Tilman Peterson , James Alexander McCombe , Steven John Clohset , Jason Rupert Redgrave
IPC分类号： G06F15/80 , G06F15/00 , G06T1/00
CPC分类号： G06T15/005 , G06F9/5033 , G06F9/505 , G06F9/52 , G06F15/8007 , G06T1/20 , G06T1/60 , G06T15/06 , G06T2200/28
摘要： In some aspects, systems and methods provide for forming groupings of a plurality of independently-specified computation workloads, such as graphics processing workloads, and in a specific example, ray tracing workloads. The workloads include a scheduling key, which is one basis on which the groupings can be formed. Workloads grouped together can all execute from the same source of instructions, one or more different private data elements. Such workloads can recursively instantiate other workloads that reference the same private data elements. In some examples, the scheduling key can be used to identify a data element to be used by all the workloads of a grouping. Memory conflicts to private data elements are handled through scheduling of non-conflicted workloads or specific instructions an deferring conflicted workloads instead of locking memory locations.
摘要翻译：在一些方面，系统和方法提供用于形成多个独立指定的计算工作负荷（诸如图形处理工作负载）以及在具体示例中的光线跟踪工作负载的分组。工作负载包括一个调度密钥，这是可以形成分组的一个基础。分组在一起的工作负载都可以从相同的指令来源执行，一个或多个不同的私有数据元素。这样的工作负载可以递归地实例化引用相同私有数据元素的其他工作负载。在一些示例中，调度密钥可用于标识要由分组的所有工作负载使用的数据元素。与私有数据元素的内存冲突通过调度非冲突的工作负载或特定指令来处理，推迟冲突的工作负载而不是锁定内存位置。

4. 发明授权

US09665970B2 Variable-sized concurrent grouping for multiprocessing 有权
公开(公告)号：US09665970B2
公开(公告)日：2017-05-30
申请号：US13368644
申请日：2012-02-08
申请人： Jason Rupert Redgrave , Steven John Clohset , James Alexander McCombe , Luke Tilman Peterson
发明人： Jason Rupert Redgrave , Steven John Clohset , James Alexander McCombe , Luke Tilman Peterson
IPC分类号： G06F9/44 , G06F9/45 , G06T15/00 , G06F9/48 , G06F17/50 , G06T15/06 , G06F17/30 , G06F9/30
CPC分类号： G06T15/005 , G06F8/4442 , G06F9/30036 , G06F9/4881 , G06F17/30961 , G06F17/5054 , G06T15/06 , G06T2200/16 , G06T2200/28 , G06T2210/52
摘要： Aspects include, for example, a method for interpreting information in a computer program, or profiling such a program to estimate a group size for instances of that program (program module, or portion thereof). Such a method can be used in a system that supports collecting outputs of executing instances, where those outputs can specify new program instances. Scheduling of new instances (or allocation of resources for executing such instances) can be deferred. A trigger to begin scheduling (or allocation) for a collection of instances uses a target group size for that program. Thus, different programs can have different group sizes, which can be set explicitly, or based on profiling. The profiling can occur during one or more of pre-execution and during execution. The group size estimate can be an input into an algorithm that also accounts for system state during execution.

5. 发明申请

US20120133654A1 VARIABLE-SIZED CONCURRENT GROUPING FOR MULTIPROCESSING 有权
标题翻译：可变尺寸多目标分组
公开(公告)号：US20120133654A1
公开(公告)日：2012-05-31
申请号：US13368644
申请日：2012-02-08
申请人： Jason Rupert Redgrave , Stephen John Clohset , James Alexander McCombe , Luke Tilman Peterson
发明人： Jason Rupert Redgrave , Stephen John Clohset , James Alexander McCombe , Luke Tilman Peterson
IPC分类号： G06T15/00 , G06T1/00
CPC分类号： G06T15/005 , G06F8/4442 , G06F9/30036 , G06F9/4881 , G06F17/30961 , G06F17/5054 , G06T15/06 , G06T2200/16 , G06T2200/28 , G06T2210/52
摘要： Aspects include, for example, a method for interpreting information in a computer program, or profiling such a program to estimate a group size for instances of that program (program module, or portion thereof). Such a method can be used in a system that supports collecting outputs of executing instances, where those outputs can specify new program instances. Scheduling of new instances (or allocation of resources for executing such instances) can be deferred. A trigger to begin scheduling (or allocation) for a collection of instances uses a target group size for that program. Thus, different programs can have different group sizes, which can be set explicitly, or based on profiling. The profiling can occur during one or more of pre-execution and during execution. The group size estimate can be an input into an algorithm that also accounts for system state during execution.
摘要翻译：方面包括例如用于解释计算机程序中的信息的方法，或者对这样的程序进行概要分析以估计该程序（程序模块或其一部分）的实例的组大小。这种方法可用于支持收集执行实例的输出的系统，其中这些输出可以指定新的程序实例。可以推迟新实例的调度（或用于执行此类实例的资源分配）。为一组实例开始调度（或分配）的触发器使用该程序的目标组大小。因此，不同的程序可以具有不同的组大小，可以明确设置，也可以基于分析。分析可以在一个或多个预执行期间和执行期间发生。组大小估计可以是在执行期间也考虑系统状态的算法的输入。

6. 发明授权

US08300049B2 Ray tracing system architectures and methods 有权
标题翻译：光线跟踪系统架构和方法
公开(公告)号：US08300049B2
公开(公告)日：2012-10-30
申请号：US13229566
申请日：2011-09-09
申请人： Luke Tilman Peterson , James Alexander McCombe , Ryan R. Salsbury , Steven John Clohset
发明人： Luke Tilman Peterson , James Alexander McCombe , Ryan R. Salsbury , Steven John Clohset
IPC分类号： G06T15/50
CPC分类号： G06T15/06 , G06T1/60 , G06T15/08 , G06T15/80 , G06T2215/12 , G09G5/006 , G09G5/393 , G09G2360/121 , G09G2370/10
摘要： Aspects comprise systems implementing 3-D graphics processing functionality in a multiprocessing system. Control flow structures are used in scheduling instances of computation in the multiprocessing system, where different points in the control flow structure serve as points where deferral of some instances of computation can be performed in favor of scheduling other instances of computation. In some examples, the control flow structure identifies particular tasks, such as intersection testing of a particular portion of an acceleration structure, and a particular element of shading code. In some examples, the aspects are used in 3-D graphics processing systems that can perform ray tracing based rendering.
摘要翻译：方面包括在多处理系统中实现3-D图形处理功能的系统。控制流结构用于多处理系统中的计算实例中，其中控制流结构中的不同点用作能够执行一些计算实例的延迟以有利于调度其他计算实例的点。在一些示例中，控制流结构识别特定任务，例如加速结构的特定部分的交叉测试和阴影代码的特定元素。在一些示例中，这些方面用于可以执行基于光线跟踪的呈现的3-D图形处理系统中。

7. 发明申请

US20130002672A1 RAY TRACING SYSTEM ARCHITECTURES AND METHODS 有权
标题翻译： RAY跟踪系统架构与方法
公开(公告)号：US20130002672A1
公开(公告)日：2013-01-03
申请号：US13610651
申请日：2012-09-11
申请人： Luke Tilman Peterson , James Alexander McCombe , Ryan R. Salsbury , Steven John Clohset
发明人： Luke Tilman Peterson , James Alexander McCombe , Ryan R. Salsbury , Steven John Clohset
IPC分类号： G06T15/06
CPC分类号： G06T15/06 , G06T1/60 , G06T15/08 , G06T15/80 , G06T2215/12 , G09G5/006 , G09G5/393 , G09G2360/121 , G09G2370/10
摘要： Aspects comprise systems implementing 3-D graphics processing functionality in a multiprocessing system. Control flow structures are used in scheduling instances of computation in the multiprocessing system, where different points in the control flow structure serve as points where deferral of some instances of computation can be performed in favor of scheduling other instances of computation. In some examples, the control flow structure identifies particular tasks, such as intersection testing of a particular portion of an acceleration structure, and a particular element of shading code. In some examples, the aspects are used in 3-D graphics processing systems that can perform ray tracing based rendering.
摘要翻译：方面包括在多处理系统中实现3-D图形处理功能的系统。控制流结构用于多处理系统中的计算实例中，其中控制流结构中的不同点用作能够执行一些计算实例的延迟以有利于调度其他计算实例的点。在一些示例中，控制流结构识别特定任务，例如加速结构的特定部分的交叉测试和阴影代码的特定元素。在一些示例中，这些方面用于可以执行基于光线跟踪的呈现的3-D图形处理系统中。

8. 发明授权

US08018457B2 Ray tracing system architectures and methods 有权
标题翻译：光线跟踪系统架构和方法
公开(公告)号：US08018457B2
公开(公告)日：2011-09-13
申请号：US12555766
申请日：2009-09-08
申请人： Luke Tilman Peterson , James Alexander McCombe , Ryan R. Salsbury , Steven John Clohset
发明人： Luke Tilman Peterson , James Alexander McCombe , Ryan R. Salsbury , Steven John Clohset
IPC分类号： G06T15/50
CPC分类号： G06T15/06 , G06T1/60 , G06T15/08 , G06T15/80 , G06T2215/12 , G09G5/006 , G09G5/393 , G09G2360/121 , G09G2370/10
摘要： Aspects comprise systems implementing ray tracing functionality according to example architectures. In one example, rays are collected into collections against elements of an acceleration structure, which in some cases are associated with objects composing a scene being ray traced. Indications of detected ray intersections also can be collected in an output buffer, and in some examples, the output buffer can comprise a plurality of portions, each associated with a scene object, or a common portion of code to be executed during shading. Buffer contents can be accessed in a block read. An intersection shading resource can load data to be used in shading the intersections for the identified rays, and locally storing that data for use in shading those intersections.
摘要翻译：方面包括根据示例架构实现射线跟踪功能的系统。在一个示例中，光线被收集到集合中以抵抗加速结构的元素，其在某些情况下与构成被跟踪的场景的对象相关联。检测到的射线交叉点的指示也可以被收集在输出缓冲器中，并且在一些示例中，输出缓冲器可以包括多个部分，每个部分与场景对象相关联，或者在阴影期间执行的代码的公共部分。可以在块读取中访问缓冲区内容。交叉阴影资源可以加载要用于遮蔽所识别的光线的交点处的数据，并且本地存储用于遮蔽那些交叉点的数据。

9. 发明申请

US20090322752A1 RAY TRACING SYSTEM ARCHITECTURES AND METHODS 有权
标题翻译： RAY跟踪系统架构与方法
公开(公告)号：US20090322752A1
公开(公告)日：2009-12-31
申请号：US12555766
申请日：2009-09-08
申请人： Luke Tilman Peterson , James Alexander McCombe , Ryan R. Salsbury , Steven John Clohset
发明人： Luke Tilman Peterson , James Alexander McCombe , Ryan R. Salsbury , Steven John Clohset
IPC分类号： G06T15/50
CPC分类号： G06T15/06 , G06T1/60 , G06T15/08 , G06T15/80 , G06T2215/12 , G09G5/006 , G09G5/393 , G09G2360/121 , G09G2370/10
摘要： Aspects comprise systems implementing ray tracing functionality according to example architectures. In one example, rays are collected into collections against elements of an acceleration structure, which in some cases are associated with objects composing a scene being ray traced. Indications of detected ray intersections also can be collected in an output buffer, and in some examples, the output buffer can comprise a plurality of portions, each associated with a scene object, or a common portion of code to be executed during shading. Buffer contents can be accessed in a block read. An intersection shading resource can load data to be used in shading the intersections for the identified rays, and locally storing that data for use in shading those intersections.
摘要翻译：方面包括根据示例架构实现射线跟踪功能的系统。在一个示例中，光线被收集到集合中以抵抗加速度结构的元素，这在一些情况下与构成被跟踪的场景的对象相关联。检测到的射线交叉点的指示也可以被收集在输出缓冲器中，并且在一些示例中，输出缓冲器可以包括多个部分，每个部分与场景对象相关联，或者在阴影期间执行的代码的公共部分。可以在块读取中访问缓冲区内容。交叉阴影资源可以加载要用于遮蔽所识别的光线的交点处的数据，并且本地存储用于遮蔽那些交叉点的数据。

10. 发明授权

US09478062B2 Memory allocation in distributed memories for multiprocessing 有权
标题翻译：用于多处理的分布式存储器中的内存分配
公开(公告)号：US09478062B2
公开(公告)日：2016-10-25
申请号：US13368616
申请日：2012-02-08
申请人： Stephen John Clohset , James Alexander McCombe , Luke Tilman Peterson
发明人： Stephen John Clohset , James Alexander McCombe , Luke Tilman Peterson
IPC分类号： G06T15/06 , G06T15/00
CPC分类号： G06F9/4881 , G06F9/5016 , G06T15/005 , G06T15/06 , G06T2200/28 , G06T2210/52
摘要： In some aspects, finer grained parallelism is achieved by segmenting programmatic workloads into smaller discretized portions, where a first element can be indicative both of a configuration or program to be executed, and a first data set to be used in such execution, while a second element can be indicative of a second data element or group. The discretized portions can cause program execute on distributed processors. Approaches to selecting processors, and allocating local memory associated with those processors are disclosed. In one example, discretized portions that share a program have an anti-affinity to cause dispersion, for initial execution assignment. Flags, such as programmer and compiler generated flags can be used in determining such allocations. Workloads can be grouped according to compatibility of memory usage requirements.
摘要翻译：在一些方面，通过将编程工作负载分割成更小的离散部分来实现更精细的粒度并行性，其中第一元素可指示要执行的配置或程序以及要在其中执行的第一数据集，元素可以指示第二数据元素或组。离散化部分可以使分布式处理器上的程序执行。公开了选择处理器以及分配与这些处理器相关联的本地存储器的方法。在一个示例中，共享程序的离散化部分具有反关联性以引起分散，用于初始执行分配。诸如编程器和编译器生成的标志之类的标志可用于确定这样的分配。可以根据内存使用要求的兼容性对工作负载进行分组。

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