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. 发明申请

US20140351827A1 APPLICATION PROGRAMMING INTERFACE TO ENABLE THE CONSTRUCTION OF PIPELINE PARALLEL PROGRAMS 有权
标题翻译：应用编程接口，实现管道平行程序的构建
公开(公告)号：US20140351827A1
公开(公告)日：2014-11-27
申请号：US13899343
申请日：2013-05-21
申请人： NVIDIA CORPORATION
发明人： Ignacio LLAMAS
IPC分类号： G06F9/48
CPC分类号： G06F9/4881
摘要： An application programming interface (API) provides various software constructs that allow a developer to assemble a processing pipeline having arbitrary structure and complexity. Once assembled, the processing pipeline is configured to include a set of interconnected pipestages. Those pipestages are associated with one or more different CTAs that may execute in parallel with one another on a parallel processing unit. The developer specifies the configuration of the pipestages, including the configuration of the different CTAs across all pipestages, as well as the different processing operations performed by each different CTA.
摘要翻译：应用程序编程接口（API）提供各种软件结构，允许开发人员组装具有任意结构和复杂性的处理管道。一旦组装，处理管道被配置为包括一组相互连接的管道。这些管道与一个或多个可在并行处理单元上彼此并行执行的不同CTA相关联。开发人员指定管道的配置，包括跨所有管道的不同CTA的配置，以及由不同CTA执行的不同处理操作。

2. 发明申请

US20140123144A1 WORK-QUEUE-BASED GRAPHICS PROCESSING UNIT WORK CREATION 有权
标题翻译：基于工作队列的图形处理单元创作
公开(公告)号：US20140123144A1
公开(公告)日：2014-05-01
申请号：US13662274
申请日：2012-10-26
申请人： NVIDIA CORPORATION
发明人： Ignacio LLAMAS , Craig Ross DUTTWEILER , Jeffrey A. BOLZ , Daniel Elliot WEXLER
IPC分类号： G06F9/54
CPC分类号： G06F9/52 , G06F9/546 , G06F2209/548
摘要： One embodiment of the present invention enables threads executing on a processor to locally generate and execute work within that processor by way of work queues and command blocks. A device driver, as an initialization procedure for establishing memory objects that enable the threads to locally generate and execute work, generates a work queue, and sets a GP_GET pointer of the work queue to the first entry in the work queue. The device driver also, during the initialization procedure, sets a GP_PUT pointer of the work queue to the last free entry included in the work queue, thereby establishing a range of entries in the work queue into which new work generated by the threads can be loaded and subsequently executed by the processor. The threads then populate command blocks with generated work and point entries in the work queue to the command blocks to effect processor execution of the work stored in the command blocks.
摘要翻译：本发明的一个实施例使得在处理器上执行的线程能够通过工作队列和命令块来本地生成和执行该处理器内的工作。设备驱动程序作为用于建立使线程本地生成和执行工作的内存对象的初始化过程，生成工作队列，并将工作队列的GP_GET指针设置为工作队列中的第一个条目。在初始化过程中，设备驱动程序还将工作队列的GP_PUT指针设置到工作队列中包含的最后一个空闲条目，从而在工作队列中建立一个可以加载线程生成的新工作的条目范围并随后由处理器执行。然后，线程将工作队列中的生成工作和点条目的命令块填充到命令块，以执行存储在命令块中的工作的处理器执行。

3. 发明公开

US20240013471A1 QUERY-SPECIFIC BEHAVIORAL MODIFICATION OF TREE TRAVERSAL 审中-公开
公开(公告)号：US20240013471A1
公开(公告)日：2024-01-11
申请号：US18471651
申请日：2023-09-21
申请人： NVIDIA CORPORATION
发明人： Samuli LAINE , Timo AILA , Tero KARRAS , Gregory MUTHLER , William P. NEWHALL, JR. , Ronald C. BABICH, JR. , Craig KOLB , Ignacio LLAMAS , John BURGESS
IPC分类号： G06T15/06 , G06T15/00 , G06T17/00
CPC分类号： G06T15/06 , G06T15/005 , G06T17/005
摘要： Methods and systems are described in some examples for changing the traversal of an acceleration data structure in a highly dynamic query-specific manner, with each query specifying test parameters, a test opcode and a mapping of test results to actions. In an example ray tracing implementation, traversal of a bounding volume hierarchy by a ray is performed with the default behavior of the traversal being changed in accordance with results of a test performed using the test opcode and test parameters specified in the ray data structure and another test parameter specified in a node of the bounding volume hierarchy. In an example implementation a traversal coprocessor is configured to perform the traversal of the bounding volume hierarchy.

4. 发明申请

US20220027280A1 METHOD FOR EFFICIENT GROUPING OF CACHE REQUESTS FOR DATAPATH SCHEDULING 有权
公开(公告)号：US20220027280A1
公开(公告)日：2022-01-27
申请号：US17483133
申请日：2021-09-23
申请人： NVIDIA Corporation
发明人： Greg MUTHLER , Timo AILA , Tero KARRAS , Samuli LAINE , William Parsons NEWHALL, JR. , Ronald Charles BABICH, JR. , John BURGESS , Ignacio LLAMAS
IPC分类号： G06F12/0875 , G06T15/06 , G06F16/901
摘要： In a ray tracer, a cache for streaming workloads groups ray requests for coherent successive bounding volume hierarchy traversal operations by sending common data down an attached data path to all ray requests in the group at the same time or about the same time. Grouping the requests provides good performance with a smaller number of cache lines.

5. 发明申请

US20220020202A1 METHOD FOR HANDLING OF OUT-OF-ORDER OPAQUE AND ALPHA RAY/PRIMITIVE INTERSECTIONS 有权
公开(公告)号：US20220020202A1
公开(公告)日：2022-01-20
申请号：US17490024
申请日：2021-09-30
申请人： NVIDIA Corporation
发明人： Samuli LAINE , Tero KARRAS , Greg MUTHLER , William Parsons NEWHALL , Ronald Charles BABICH , Ignacio LLAMAS , John BURGESS
IPC分类号： G06T15/06 , G06T1/20 , G06T15/00
摘要： A hardware-based traversal coprocessor provides acceleration of tree traversal operations searching for intersections between primitives represented in a tree data structure and a ray. The primitives may include opaque and alpha triangles used in generating a virtual scene. The hardware-based traversal coprocessor is configured to determine primitives intersected by the ray, and return intersection information to a streaming multiprocessor for further processing. The hardware-based traversal coprocessor is configured to provide a deterministic result of intersected triangles regardless of the order that the memory subsystem returns triangle range blocks for processing, while opportunistically eliminating alpha intersections that lie further along the length of the ray than closer opaque intersections.

6. 发明申请

US20200051316A1 METHOD FOR HANDLING OF OUT-OF-ORDER OPAQUE AND ALPHA RAY/PRIMITIVE INTERSECTIONS 审中-公开
公开(公告)号：US20200051316A1
公开(公告)日：2020-02-13
申请号：US16101196
申请日：2018-08-10
申请人： NVIDIA Corporation
发明人： Samuli LAINE , Tero KARRAS , Greg MUTHLER , William Parsons NEWHALL, JR. , Ronald Charles BABICH , Ignacio LLAMAS , John BURGESS
IPC分类号： G06T15/06 , G06T1/20 , G06T15/60 , G06F17/30
摘要： A hardware-based traversal coprocessor provides acceleration of tree traversal operations searching for intersections between primitives represented in a tree data structure and a ray. The primitives may include opaque and alpha triangles used in generating a virtual scene. The hardware-based traversal coprocessor is configured to determine primitives intersected by the ray, and return intersection information to a streaming multiprocessor for further processing. The hardware-based traversal coprocessor is configured to provide a deterministic result of intersected triangles regardless of the order that the memory subsystem returns triangle range blocks for processing, while opportunistically eliminating alpha intersections that lie further along the length of the ray than closer opaque intersections.

7. 发明公开

US20230410410A1 METHOD FOR HANDLING OF OUT-OF-ORDER OPAQUE AND ALPHA RAY/PRIMITIVE INTERSECTIONS 审中-公开
公开(公告)号：US20230410410A1
公开(公告)日：2023-12-21
申请号：US18239876
申请日：2023-08-30
申请人： NVIDIA Corporation
发明人： Samuli LAINE , Tero KARRAS , Greg MUTHLER , William Parsons Newhall, JR. , Ronald Charles BABACH, JR. , Ignacio LLAMAS , John BURGESS
IPC分类号： G06T15/06 , G06T1/20 , G06T15/00
CPC分类号： G06T15/06 , G06T1/20 , G06T15/005 , G06T2210/21
摘要： A hardware-based traversal coprocessor provides acceleration of tree traversal operations searching for intersections between primitives represented in a tree data structure and a ray. The primitives may include opaque and alpha triangles used in generating a virtual scene. The hardware-based traversal coprocessor is configured to determine primitives intersected by the ray, and return intersection information to a streaming multiprocessor for further processing. The hardware-based traversal coprocessor is configured to provide a deterministic result of intersected triangles regardless of the order that the memory subsystem returns triangle range blocks for processing, while opportunistically eliminating alpha intersections that lie further along the length of the ray than closer opaque intersections.

8. 发明申请

US20200160588A1 METHOD FOR CONTINUED BOUNDING VOLUME HIERARCHY TRAVERSAL ON INTERSECTION WITHOUT SHADER INTERVENTION 审中-公开
公开(公告)号：US20200160588A1
公开(公告)日：2020-05-21
申请号：US16749089
申请日：2020-01-22
申请人： NVIDIA Corporation
发明人： Greg MUTHLER , Tero KARRAS , Samuli LAINE , William Parsons NEWHALL, JR. , Ronald Charles BABICH, JR. , John BURGESS , Ignacio LLAMAS
IPC分类号： G06T15/06
摘要： A hardware-based traversal coprocessor provides acceleration of tree traversal operations searching for intersections between primitives represented in a tree data structure and a ray. The primitives may include opaque and alpha triangles used in generating a virtual scene. The hardware-based traversal coprocessor is configured to determine primitives intersected by the ray, and return intersection information to a streaming multiprocessor for further processing. The hardware-based traversal coprocessor is configured to omit reporting of one or more primitives the ray is determined to intersect. The omitted primitives include primitives which are provably capable of being omitted without a functional impact on visualizing the virtual scene.

9. 发明申请

US20200051315A1 QUERY-SPECIFIC BEHAVIORAL MODIFICATION OF TREE TRAVERSAL 审中-公开
公开(公告)号：US20200051315A1
公开(公告)日：2020-02-13
申请号：US16101180
申请日：2018-08-10
申请人： NVIDIA Corporation
发明人： Samuli Laine , Timo AILA , Tero KARRAS , Gregory MUTHLER , William Parsons NEWHALL, JR. , Ronald Charles BABICH, JR. , Craig KOLB , Ignacio LLAMAS
IPC分类号： G06T15/06 , G06T7/60 , G06T15/60 , G06F17/30
摘要： Methods and systems are described in some examples for changing the traversal of an acceleration data structure in a highly dynamic query-specific manner, with each query specifying test parameters, a test opcode and a mapping of test results to actions. In an example ray tracing implementation, traversal of a bounding volume hierarchy by a ray is performed with the default behavior of the traversal being changed in accordance with results of a test performed using the test opcode and test parameters specified in the ray data structure and another test parameter specified in a node of the bounding volume hierarchy. In an example implementation a traversal coprocessor is configured to perform the traversal of the bounding volume hierarchy.

10. 发明申请

US20200050550A1 METHOD FOR EFFICIENT GROUPING OF CACHE REQUESTS FOR DATAPATH SCHEDULING 审中-公开
公开(公告)号：US20200050550A1
公开(公告)日：2020-02-13
申请号：US16101109
申请日：2018-08-10
申请人： NVIDIA Corporation
发明人： Greg MUTHLER , Timo AILA , Tero KARRAS , Samuli LAINE , William Parsons NEWHALL , Ronald Charles BABICH , John BURGESS , Ignacio LLAMAS
IPC分类号： G06F12/0875 , G06T15/06 , G06F17/30
摘要： In a ray tracer, a cache for streaming workloads groups ray requests for coherent successive bounding volume hierarchy traversal operations by sending common data down an attached data path to all ray requests in the group at the same time or about the same time. Grouping the requests provides good performance with a smaller number of cache lines.

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