公开(公告)号：US20150097847A1

公开(公告)日：2015-04-09

申请号：US14046064

申请日：2013-10-04

Applicant: NVIDIA CORPORATION

Inventor： Jonathan DUNAISKY ,  Henry Packard MORETON ,  Jeffrey A. BOLZ ,  Yury Y. URALSKY ,  James Leroy DEMING ,  Rui M. BASTOS ,  Patrick R. BROWN ,  Amanpreet GREWAL ,  Christian AMSINCK ,  Poornachandra RAO ,  Jerome F. DULUK, JR. ,  Andrew J. TAO

IPC: G09G5/39 ,  G06T1/60

CPC classification number: G09G5/39 ,  G06F12/0897 ,  G06F12/1027 ,  G06T1/60

Abstract: One embodiment of the present invention includes a memory management unit (MMU) that is configured to manage sparse mappings. The MMU processes requests to translate virtual addresses to physical addresses based on page table entries (PTEs) that indicate a sparse status. If the MMU determines that the PTE does not include a mapping from a virtual address to a physical address, then the MMU responds to the request based on the sparse status. If the sparse status is active, then the MMU determines the physical address based on whether the type of the request is a write operation and, subsequently, generates an acknowledgement of the request. By contrast, if the sparse status is not active, then the MMU generates a page fault. Advantageously, the disclosed embodiments enable the computer system to manage sparse mappings without incurring the performance degradation associated with both page faults and conventional software-based sparse mapping management.

Abstract translation: 本发明的一个实施例包括被配置为管理稀疏映射的存储器管理单元（MMU）。 MMU根据指示稀疏状态的页表项（PTE）处理将虚拟地址转换为物理地址的请求。 如果MMU确定PTE不包括从虚拟地址到物理地址的映射，则MMU将根据稀疏状态对该请求进行响应。 如果稀疏状态为活动状态，则MMU将根据请求的类型是否为写入操作确定物理地址，然后生成请求的确认。 相比之下，如果稀疏状态不活动，则MMU会生成页面错误。 有利地，所公开的实施例使得计算机系统能够管理稀疏映射，而不会引起与页面故障和常规的基于软件的稀疏映射管理相关联的性能下降。

公开(公告)号：US20140354634A1

公开(公告)日：2014-12-04

申请号：US13907711

申请日：2013-05-31

Applicant: Nvidia Corporation

Inventor： Christian AMSINCK ,  Eric B. LUM ,  Barry RODGERS ,  Tony LOUCA ,  Christian ROUET ,  Jonathan DUNAISKY

IPC: G06T17/10

CPC classification number: G06T15/405

Abstract: Updating depth related graphics data is described. Geometric primitives are processed. Pixels are generated from the primitives based on the processing, each of which has at least one corresponding depth value. Culling is performed on a first group of the pixels, based on a representation of the at least one depth related value corresponding to each. Pixels may be discarded based on the culling and upon which a second group of pixels remain. A depth related raster operations function is performed, in which data is transacted with a depth buffer. The culling function is updated in relation to the transacting. The updating is performed on the basis of a granularity, which characterizes the culling function.

Abstract translation: 描述更新深度相关图形数据。 几何图元被处理。 基于这些处理，从基元生成像素，每个处理具有至少一个对应的深度值。 基于对应于每个像素的至少一个深度相关值的表示，对第一组像素执行剔除。 可以基于剔除而丢弃像素，并且保留第二组像素。 执行深度相关的光栅操作功能，其中数据与深度缓冲器进行交互。 剔除功能与交易相关更新。 基于粒度来进行更新，其特征在于剔除功能。

公开(公告)号：US20150084975A1

公开(公告)日：2015-03-26

申请号：US14038599

申请日：2013-09-26

Applicant: NVIDIA CORPORATION

Inventor： Steven J. HEINRICH ,  Eric T. ANDERSON ,  Jeffrey A. BOLZ ,  Jonathan DUNAISKY ,  Ramesh JANDHYALA ,  Joel MCCORMACK ,  Alexander L. MINKIN ,  Bryon S. NORDQUIST ,  Poornachandra RAO

IPC: G06T1/60 ,  G06T1/20

CPC classification number: G06T1/60 ,  G06F2212/302 ,  G06T1/20 ,  G06T15/04 ,  G09G5/363

Abstract: Approaches are disclosed for performing memory access operations in a texture processing pipeline having a first portion configured to process texture memory access operations and a second portion configured to process non-texture memory access operations. A texture unit receives a memory access request. The texture unit determines whether the memory access request includes a texture memory access operation. If the memory access request includes a texture memory access operation, then the texture unit processes the memory access request via at least the first portion of the texture processing pipeline, otherwise, the texture unit processes the memory access request via at least the second portion of the texture processing pipeline. One advantage of the disclosed approach is that the same processing and cache memory may be used for both texture operations and load/store operations to various other address spaces, leading to reduced surface area and power consumption.

Abstract translation: 公开了用于在具有被配置为处理纹理存储器访问操作的第一部分的纹理处理流水线中执行存储器访问操作的方法和被配置为处理非纹理存储器访问操作的第二部分。 纹理单元接收存储器访问请求。 纹理单元确定存储器访问请求是否包括纹理存储器访问操作。 如果存储器访问请求包括纹理存储器访问操作，则纹理单元至少通过纹理处理流水线的第一部分来处理存储器访问请求，否则，纹理单元至少经由第二部分处理存储器访问请求 纹理处理流水线。 所公开方法的一个优点是可以将相同的处理和高速缓冲存储器用于纹理操作和对各种其他地址空间的加载/存储操作，导致减小的表面积和功率消耗。