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

US09304730B2 Direct communication between GPU and FPGA components 有权
标题翻译： GPU与FPGA组件之间的直接通信
公开(公告)号：US09304730B2
公开(公告)日：2016-04-05
申请号：US13593129
申请日：2012-08-23
申请人： Ray Bittner , Erik S. Ruf
发明人： Ray Bittner , Erik S. Ruf
IPC分类号： G06F13/14 , G06F3/14 , G09G5/36
CPC分类号： G06T1/20 , G06F3/14 , G06T1/60 , G06T2200/28 , G09G5/363 , G09G2360/06 , G09G2360/08
摘要： A system may include a Graphics Processing Unit (GPU) and a Field Programmable Gate Array (FPGA). The system may further include a bus interface that is external to the FPGA, and that is configured to transfer data directly between the GPU and the FPGA without storing the data in a memory of a central processing unit (CPU) as an intermediary operation.
摘要翻译：系统可以包括图形处理单元（GPU）和现场可编程门阵列（FPGA）。该系统还可以包括在FPGA外部的总线接口，并且被配置为直接在GPU和FPGA之间传送数据，而不将数据存储在中央处理单元（CPU）的存储器中作为中介操作。

2. 发明申请

US20140055467A1 DIRECT COMMUNICATION BETWEEN GPU AND FPGA COMPONENTS 有权
标题翻译： GPU与FPGA组件之间的直接通信
公开(公告)号：US20140055467A1
公开(公告)日：2014-02-27
申请号：US13593129
申请日：2012-08-23
申请人： Ray Bittner , Erik S. Ruf
发明人： Ray Bittner , Erik S. Ruf
IPC分类号： G06F13/14
CPC分类号： G06T1/20 , G06F3/14 , G06T1/60 , G06T2200/28 , G09G5/363 , G09G2360/06 , G09G2360/08
摘要： A system may include a Graphics Processing Unit (GPU) and a Field Programmable Gate Array (FPGA). The system may further include a bus interface that is external to the FPGA, and that is configured to transfer data directly between the GPU and the FPGA without storing the data in a memory of a central processing unit (CPU) as an intermediary operation.
摘要翻译：系统可以包括图形处理单元（GPU）和现场可编程门阵列（FPGA）。该系统还可以包括在FPGA外部的总线接口，并且被配置为直接在GPU和FPGA之间传送数据，而不将数据存储在中央处理单元（CPU）的存储器中作为中介操作。

3. 发明授权

US09830172B2 Implementing functional kernels using compiled code modules 有权
公开(公告)号：US09830172B2
公开(公告)日：2017-11-28
申请号：US13539349
申请日：2012-06-30
申请人： Erik S. Ruf
发明人： Erik S. Ruf
IPC分类号： G06F9/45 , G06F9/445
CPC分类号： G06F9/44521
摘要： A framework is set forth herein that uses a composition mechanism to produce function data that describes a kernel. The composition mechanism may then send the function data to an execution mechanism. The execution mechanism uses the function data to dynamically execute pre-compiled code modules, which are identified by the function data. According to another aspect, the framework provides different mechanisms for implementing the kernel, depending on the native capabilities of the execution mechanism.

4. 发明授权

US07398484B2 Memory efficient array transposition via multi pass tiling 有权
标题翻译：通过多通道平铺来记忆高效的阵列转置
公开(公告)号：US07398484B2
公开(公告)日：2008-07-08
申请号：US11116628
申请日：2005-04-27
申请人： Erik S. Ruf
发明人： Erik S. Ruf
IPC分类号： G06F17/50 , G06F12/00 , G06F13/00 , G06F13/28
CPC分类号： G06F12/0897 , G06F12/0864
摘要： A schedule can be generated for physically transposing an array such that when the array is transferred from a first memory type to a second memory type, the number of block transfers performed is minimized. The array can be rearranged to ensure that most or all data elements in any block read into internal memory are used before that block's internal storage is reused. The algorithm can compute an offline schedule and then execute that schedule. The method can assemble the schedule during one or more passes with an algorithm. Scheduling passes can apply a permutation to a representation of the array's structure and then tile the representation to ensure efficient use of internal memory. Tiling may alter the permutation, so the algorithm can be reinvoked and run on the tiled representation. The algorithm can be run on successively retiled representations until no additional tiling is required. Optimizations for schedule generation and/or execution include: simplification of the data structure representing the array; alteration of the order in which tiles are accessed; inversion of permutations; processing non-canonical input; and the production of stream output. The method can also be modified for specialized architectures, including: block I/O architecture; fully associative caches; set-associative caches; and multi-level memory hierarchies.
摘要翻译：可以生成用于物理地转置阵列的调度，使得当阵列从第一存储器类型传送到第二存储器类型时，执行的块传送的数量被最小化。该阵列可以重新排列，以确保在该块的内部存储被重新使用之前，使用任何块中读取到内部存储器中的大部分或全部数据元素。该算法可以计算离线计划，然后执行该计划。该方法可以在一次或多次通过期间使用算法组装计划。调度传递可以将排列应用于数组结构的表示，然后平铺表示以确保内部存储器的有效使用。平铺可能会改变排列，因此可以在平铺表示中激活并运行该算法。该算法可以在连续的隐藏表示上运行，直到不需要额外的平铺。调度生成和/或执行的优化包括：简化表示数组的数据结构; 更改访问瓦片的顺序; 排列倒置; 处理非规范输入; 和流量输出的生产。该方法还可以针对专门的架构进行修改，包括：块I / O架构; 完全关联缓存; 集合关联缓存; 和多级内存层次结构。

5. 发明申请

US20140007116A1 IMPLEMENTING FUNCTIONAL KERNELS USING COMPILED CODE MODULES 有权
标题翻译：使用编码代码模块实现功能性的KERNELS
公开(公告)号：US20140007116A1
公开(公告)日：2014-01-02
申请号：US13539349
申请日：2012-06-30
申请人： Erik S. Ruf
发明人： Erik S. Ruf
IPC分类号： G06F9/46
CPC分类号： G06F9/44521
摘要： A framework is set forth herein that uses a composition mechanism to produce function data that describes a kernel. The composition mechanism may then send the function data to an execution mechanism. The execution mechanism uses the function data to dynamically execute pre-compiled code modules, which are identified by the function data. According to another aspect, the framework provides different mechanisms for implementing the kernel, depending on the native capabilities of the execution mechanism.
摘要翻译：本文阐述了使用组合机制来生成描述内核的功能数据的框架。然后，组合机构可以将功能数据发送到执行机构。执行机制使用功能数据动态执行由功能数据识别的预编译代码模块。根据另一方面，该框架提供了不同的实现内核的机制，这取决于执行机制的本机能力。

6. 发明申请

US20130018636A1 QUADRATIC APPROXIMATE OFFSET CURVES FOR QUADRATIC CURVE SEGMENTS 审中-公开
标题翻译：四分之一曲线段的四次近似偏移曲线
公开(公告)号：US20130018636A1
公开(公告)日：2013-01-17
申请号：US13182453
申请日：2011-07-14
申请人： Erik S. Ruf
发明人： Erik S. Ruf
IPC分类号： G06F17/17
CPC分类号： G06F17/17 , G06T11/203
摘要： A system is described herein that produces at least one approximate offset curve that is separated by an original curve segment So by at least a distance d, thus defining a bounding region between the original curve segment So and the approximate offset curve. The original curve segment So and the approximate offset curve both have a quadratic form. In view of this quadratic form, the system can represent the approximate offset curve in an efficient manner (e.g., using three control points). Further, the system can perform calculations with respect to the approximate offset curve in an efficient manner.
摘要翻译：本文描述了一种系统，其产生至少一个由原始曲线段So分开至少一个距离d的近似偏移曲线，从而限定了原始曲线段So和近似偏移曲线之间的边界区域。原始曲线段So和近似偏移曲线均具有二次形式。鉴于这种二次形式，系统可以以有效的方式（例如，使用三个控制点）来表示近似偏移曲线。此外，系统可以以有效的方式执行关于近似偏移曲线的计算。

7. 发明申请

US20100117931A1 FUNCTIONAL IMAGE REPRESENTATION 审中-公开
标题翻译：功能图像表示
公开(公告)号：US20100117931A1
公开(公告)日：2010-05-13
申请号：US12267628
申请日：2008-11-10
申请人： J. Turner Whitted , James Thomas Kajiya , Erik S. Ruf , Ray A. Bittner, JR.
发明人： J. Turner Whitted , James Thomas Kajiya , Erik S. Ruf , Ray A. Bittner, JR.
IPC分类号： G09G3/20
CPC分类号： G09G5/363 , G06F3/1446 , G09G3/2088 , G09G5/20 , G09G2300/026 , G09G2360/10
摘要： A display apparatus described herein includes a display screen and a display processor. The display processor includes a plurality of function units that comprise functions that are representative of data that is desirably displayed on the display screen. The display processor is configured to receive configurations, compositions, and/or parameters for the plurality of function units. In addition, the display processor displays data on the display screen based at least in part upon output of the plurality of function units.
摘要翻译：本文所述的显示装置包括显示屏和显示处理器。显示处理器包括多个功能单元，其包括表示希望显示在显示屏上的数据的功能。显示处理器被配置为接收多个功能单元的配置，组合和/或参数。此外，显示处理器至少部分地基于多个功能单元的输出在显示屏幕上显示数据。

8. 发明授权

US07028293B2 Constant return optimization transforming indirect calls to data fetches 有权
公开(公告)号：US07028293B2
公开(公告)日：2006-04-11
申请号：US09822535
申请日：2001-03-30
申请人： Erik S. Ruf
发明人： Erik S. Ruf
IPC分类号： G06F9/45
CPC分类号： G06F8/4441
摘要： Indirect method invocation of methods that only return constant values is optimized using fetching operations and return constant tables. Such method calls can be optimized if all possible method calls via the call site instruction return a constant value and have no side effects. Each constant return value is loaded from a return constant table, and method invocation is eliminated. If all possible target methods in a program result in a constant return value and have no side effects, an associated virtual function dispatch table (vtable) may be used as the return constant table. Furthermore, control operation optimization may be applied to identify type constraints, based on one or more possible type-dependent constant return values from an indirect method invocation. An optimizer identifies and maps between a restricted set of values and an associated restricted set of types on which execution code may operate relative to a given control operation. The type constraints are used to optimize the associated execution code by filtering propagation of runtime type approximations for optimization.

9. 发明授权

US5793374A Specialized shaders for shading objects in computer generated images 失效
标题翻译：用于计算机生成图像中阴影物体的专用着色器
公开(公告)号：US5793374A
公开(公告)日：1998-08-11
申请号：US508710
申请日：1995-07-28
申请人： Brian K. Guenter , Todd B. Knoblock , Erik S. Ruf
发明人： Brian K. Guenter , Todd B. Knoblock , Erik S. Ruf
IPC分类号： G06T15/50 , G06T15/80 , G06T11/40
CPC分类号： G06T15/80 , G06T15/50
摘要： A computer-implemented shading system includes a geometric renderer which renders a computer generated image to produce geometric image information for an object in a scene, and a user interface which permits a user to selectively vary a designated parameter(s) to affect how that object is shaded. The system also includes a specialized shader to shade the object in the scene according to the designated parameter(s) and other shading parameters. The specialized shader is created from the user's original shader. The specialized shader has a cache loader which contains all of the terms of the user's original shader, plus load operations to load values from computations that do not depend from the designated parameter(s). The specialized shader also has a cache reader which contains a reduced set of terms from the original shader that depend on the designated parameter(s), plus read operations to read the values of the non-variant terms from the cache. When the user designates a parameter(s), the cache loader is executed once to compute the values that will not change when the user varies the designated parameter(s). The cache reader is then executed each time the user alters the value of the designated parameter(s). In this manner, only the computations that are dependent on the designated parameter(s) are recomputed for each alteration, thereby streamlining operation of the entire shading process.
摘要翻译：计算机实现的着色系统包括几何渲染器，其呈现计算机生成的图像以产生场景中的对象的几何图像信息，以及允许用户选择性地改变指定参数以影响该对象的用户界面有阴影该系统还包括专用着色器，以根据指定的参数和其他着色参数来遮蔽场景中的对象。专用着色器是从用户的原始着色器创建的。专用着色器具有一个缓存加载器，其中包含用户原始着色器的所有术语，以及从不依赖于指定参数的计算中加载值的加载操作。专用着色器还具有一个高速缓存读取器，其中包含一组取决于指定参数的原始着色器的术语集，以及从缓存中读取非变体项的值的读取操作。当用户指定参数时，执行一次高速缓存加载器以计算当用户改变指定参数时不改变的值。每当用户改变指定参数的值时，执行缓存读取器。以这种方式，仅针对每个改变重新计算依赖于指定参数的计算，从而精简整个阴影处理的操作。

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