Multistage collector for outputs in multiprocessor systems
    1.
    发明授权
    Multistage collector for outputs in multiprocessor systems 有权
    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

    IPC分类号: G06F15/80 G06T1/20 G06T15/06

    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)。

    MULTISTAGE COLLECTOR FOR OUTPUTS IN MULTIPROCESSOR SYSTEMS
    2.
    发明申请
    MULTISTAGE COLLECTOR FOR OUTPUTS IN MULTIPROCESSOR SYSTEMS 有权
    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

    IPC分类号: G06T1/20

    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)。

    Graphics processor with non-blocking concurrent architecture
    3.
    发明授权
    Graphics processor with non-blocking concurrent architecture 有权
    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

    IPC分类号: G06F15/80 G06F15/00 G06T1/00

    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。

    Ray tracing system architectures and methods
    5.
    发明授权
    Ray tracing system architectures and methods 有权
    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

    IPC分类号: G06T15/50

    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。

    RAY TRACING SYSTEM ARCHITECTURES AND METHODS
    6.
    发明申请
    RAY TRACING SYSTEM ARCHITECTURES AND METHODS 有权
    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

    IPC分类号: G06T15/06

    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。

    Ray tracing system architectures and methods
    7.
    发明授权
    Ray tracing system architectures and methods 有权
    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

    IPC分类号: G06T15/50

    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。

    RAY TRACING SYSTEM ARCHITECTURES AND METHODS
    8.
    发明申请
    RAY TRACING SYSTEM ARCHITECTURES AND METHODS 有权
    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

    IPC分类号: G06T15/50

    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。

    Dynamic ray population control
    9.
    发明授权
    Dynamic ray population control 有权
    动态射线人口控制

    公开(公告)号:US08674987B2

    公开(公告)日:2014-03-18

    申请号:US12771408

    申请日:2010-04-30

    IPC分类号: G06T15/50

    摘要: Aspects can be for ray tracing of 3-D scenes, and include dynamically controlling a population of rays being stored in a memory, to keep the population within a target, a memory footprint or other resource usage specification. An example includes controlling the population by examining indicia associated with rays returning from intersection testing, to be shaded, the indicia correlated with behavior of shaders to be run for those rays, such that population control selects, or reorders rays for shading, to prioritize shading of rays whose shaders are expected to produce fewer rays. The indicia can include a respective weight for each ray. In an example, analyzer modules examine hints associated with shaders bound to intersected primitives. Population control aspects can influence ray diversity in memory, including encouraging a varying diversity pattern as rendering of a given scene or frame progresses, based on system resource indicia, rendering metrics and so on.

    摘要翻译: 方面可以用于3-D场景的光线跟踪,并且包括动态地控制存储在存储器中的光线数量,以将人口保持在目标内,内存覆盖区或其他资源使用规范中。 一个例子包括通过检查与从交叉点测试返回的光线相关联的标记来控制人口,以便被遮蔽,该标记与用于这些光线的着色器的行为相关联,使得人口控制选择或重新排列用于阴影的光线以优先化阴影 预计其着色器会产生较少光线的光线。 标记可以包括每个射线的相应重量。 在一个示例中,分析器模块检查与绑定到相交原语的着色器相关联的提示。 人口控制方面可以影响记忆中​​的射线多样性,其中包括根据系统资源标记,渲染度量等,鼓励在给定场景或帧的渲染过程中出现变化的多样性模式。

    DYNAMIC RAY POPULATION CONTROL
    10.
    发明申请
    DYNAMIC RAY POPULATION CONTROL 有权
    动态人口控制

    公开(公告)号:US20110032257A1

    公开(公告)日:2011-02-10

    申请号:US12771408

    申请日:2010-04-30

    IPC分类号: G06T17/00

    摘要: Aspects can be for ray tracing of 3-D scenes, and include dynamically controlling a population of rays being stored in a memory, to keep the population within a target, a memory footprint or other resource usage specification. An example includes controlling the population by examining indicia associated with rays returning from intersection testing, to be shaded, the indicia correlated with behavior of shaders to be run for those rays, such that population control selects, or reorders rays for shading, to prioritize shading of rays whose shaders are expected to produce fewer rays. The indicia can include a respective weight for each ray. In an example, analyzer modules examine hints associated with shaders bound to intersected primitives. Population control aspects can influence ray diversity in memory, including encouraging a varying diversity pattern as rendering of a given scene or frame progresses, based on system resource indicia, rendering metrics and so on.

    摘要翻译: 方面可以用于3-D场景的光线跟踪,并且包括动态地控制存储在存储器中的光线数量,以将人口保持在目标内,内存覆盖区或其他资源使用规范中。 一个例子包括通过检查与从交叉点测试返回的光线相关联的标记来控制人口,以便被遮蔽,该标记与用于这些光线的着色器的行为相关联,使得人口控制选择或重新排列用于阴影的光线以优先化阴影 预计其着色器会产生较少光线的光线。 标记可以包括每个射线的相应重量。 在一个示例中,分析器模块检查与绑定到相交原语的着色器相关联的提示。 人口控制方面可以影响记忆中​​的射线多样性,其中包括根据系统资源标记,渲染度量等,鼓励在给定场景或帧的渲染过程中出现变化的多样性模式。