公开(公告)号：US09741089B2

公开(公告)日：2017-08-22

申请号：US14267969

申请日：2014-05-02

Applicant: ARM Limited

Inventor： Anders Lassen ,  Jorn Nystad ,  Alexis Mather ,  Sean Tristram Ellis

IPC: G09G5/39 ,  G06T15/00 ,  G06T11/00 ,  G06T1/60 ,  G06T1/20 ,  G06T11/40

CPC classification number: G06T1/60 ,  G06T1/20 ,  G06T11/001 ,  G06T11/40 ,  G06T15/005 ,  G09G5/39 ,  G09G2360/122

Abstract: A tile-based graphics processing pipeline comprising a rasteriser 3, a renderer 6, a tile buffer 10 configured to store rendered fragment data locally to the graphics processing pipeline prior to that data being written out to an external memory, a write out stage 13 configured to write data stored in the tile buffer to an external memory, and a programmable processing stage 14. The programmable processing stage 14 is operable under the control of graphics program instructions to read fragment data stored in the tile buffer 10 on a random access basis, perform a processing operation using the read fragment data, and write the result of the processing operation into the tile buffer 10 or to an external memory.

公开(公告)号：US09558585B2

公开(公告)日：2017-01-31

申请号：US13907550

申请日：2013-05-31

Applicant: ARM Limited

Inventor： Jorn Nystad ,  Frode Heggelund

IPC: G06T15/40

CPC classification number: G06T15/40

Abstract: A graphics processing pipeline 1 includes a rasteriser 3 that tests patches representing respective different regions of a render output against the edges of primitives 2 to determine if the primitive at least partially covers the patch and an early depth test stage 4 that performs early depth tests for primitives in respect of patches of the render output that the primitive has been found by the rasteriser at least partially to cover, by using depth test information 5 associated with a patch indicating the number and distribution of different depth value regions associated with the patch to determine the depth value region or regions associated with the patch that the primitive should be depth tested against, and then performing a depth test or tests for the primitive in respect of the respective determined depth value region or regions associated with the patch.

Abstract translation: 图形处理管线1包括光栅化器3，光栅化器3针对图元2的边缘测试表示渲染输出的相应不同区域的片段，以确定原始图案是否至少部分地覆盖贴片以及早期深度测试阶段4，其进行早期深度测试 通过使用与指示与补丁相关联的不同深度值区域的数量和分布的补丁相关联的深度测试信息5来至少部分地覆盖由光栅化器发现的原始图案的渲染输出的补码的原语，以确定 与补片相关联的深度值区域或区域，该基元应该相对于相应的确定的深度值区域或与该补片相关联的区域进行深度测试，然后对基元进行深度测试或测试。

公开(公告)号：US09535700B2

公开(公告)日：2017-01-03

申请号：US13918664

申请日：2013-06-14

Applicant: ARM Limited

Inventor： Jorn Nystad ,  Andreas Engh-Halstvedt

IPC: G06F15/04 ,  G06F9/38

CPC classification number: G06F9/3802 ,  G06F9/3851

Abstract: A data processing system includes an execution pipeline that includes one or more programmable execution stages which execute execution threads to execute instructions to perform data processing operations. Instructions to be executed by a group of execution threads are first fetched into an instruction cache and then read from the instruction cache for execution by the thread group. When an instruction to be executed by a thread group is present in a cache line in the instruction cache, or is to be fetched into an allocated cache line in the instruction cache, a pointer to the location of the instruction in the instruction cache is stored for the thread group. This stored pointer is then used to retrieve the instruction for execution by the thread group from the instruction cache.

Abstract translation: 数据处理系统包括执行流水线，该执行流水线包括执行执行线程以执行指令以执行数据处理操作的一个或多个可编程执行阶段。 由一组执行线程执行的指令首先被提取到指令高速缓存中，然后从指令高速缓存读取以供线程组执行。 当指令高速缓存中的高速缓存线中存在要由线程组执行的指令，或者将其提取到指令高速缓存中的分配的高速缓存行时，存储指向高速缓存中指令位置的指针 为线程组。 然后，该存储的指针用于从指令高速缓存中检索线程组执行的指令。

公开(公告)号：US09519982B2

公开(公告)日：2016-12-13

申请号：US13907559

申请日：2013-05-31

Applicant: ARM Limited

Inventor： Frode Heggelund ,  Jorn Nystad

IPC: G06T11/40

CPC classification number: G06T11/40

Abstract: A rasterizer and a method of performing rasterization in a graphics processing pipeline are disclosed. A rasterizer of a graphics processing pipeline tests larger patches of a render output to be generated against a primitive to be rasterized, to determine if the primitive covers (at least in part) any smaller patches of the render output that the larger patch encompasses. The larger patch is then sub-divided into any covered smaller patches, and the process repeated. The rasterizer also identifies when a given smaller patch of the render output is found to entirely pass the edge test for an edge of the primitive in question when the larger patch encompassing that smaller patch is tested, notes that event in state information associated with the primitive edge in question, and then uses that state information to skip the testing of the edge in question against the smaller patch of the render output.

Abstract translation: 公开了一种在图形处理流水线中执行光栅化的光栅化器和方法。 图形处理流水线的光栅化器测试要针对待光栅化的原语产生的渲染输出的较大补丁，以确定原始是否覆盖（至少部分地）较大补丁包含的任何较小补丁的渲染输出。 然后将较大的补丁细分为任何覆盖的较小补丁，并重复该过程。 当测试包含该较小补丁的较大修补程序时，光栅化器还识别当给定的较小补丁的渲染输出被发现完全通过所讨论的原语的边缘的边缘测试时，注意到与原始数据相关联的状态信息中的事件 边缘，然后使用该状态信息跳过相关边缘的测试对较小的渲染输出的补丁。

公开(公告)号：US09514563B2

公开(公告)日：2016-12-06

申请号：US14015897

申请日：2013-08-30

Applicant: ARM Limited

Inventor： Sean Tristram Ellis ,  Jorn Nystad ,  Andreas Engh-Halstvedt

IPC: G06T15/00

CPC classification number: G06T15/005 ,  G06T11/40

Abstract: When processing a set of tiles to generate an output in a tile based graphics processing pipeline, the pipeline, for one or more tiles of the set of tiles, renders one or more render targets containing data to be used in a processing operation (602), and stores the render targets in the tile buffer (604). It also stores some but not all of the sampling position values for a render target or targets for use when processing an adjacent tile of the set of tiles (606). It then performs a processing operation for the tile using the stored render target or targets (608) and one or more stored sampling position values from another, adjacent tile of the set of tiles (610), to generate an output for the tile (612).

Abstract translation: 当处理一组瓦片以在基于瓦片的图形处理流水线中生成输出时，对于该瓦片组的一个或多个瓦片，流水线呈现包含要在处理操作（602）中使用的数据的一个或多个渲染目标， 并将渲染目标存储在瓦片缓冲器（604）中。 当处理一组瓦片（606）的相邻瓦片时，它还存储一些而不是所有的渲染目标的采样位置值或用于使用的目标。 然后，它使用存储的渲染目标或目标（608）和来自瓦片组（610）的另一个相邻瓦片的一个或多个存储的采样位置值来执行瓦片的处理操作，以生成瓦片（612）的输出 ）。

公开(公告)号：US09122646B2

公开(公告)日：2015-09-01

申请号：US13623744

申请日：2012-09-20

Applicant: ARM Limited

Inventor： Sean Ellis ,  Andreas Engh-halstvedt ,  Jorn Nystad

IPC: G06T1/20 ,  G06T11/40 ,  G06F15/16 ,  G06F9/50

CPC classification number: G06F15/16 ,  G06F9/5083 ,  G06T1/20 ,  G06T11/40

Abstract: In a tile-based graphics processing system having plural rendering processors, the set of tiles 31 to be processed to generate an output frame 30 for display is partitioned among the different rendering processors by defining respective tile traversal paths 32, 33, 34, 35 for each rendering processor that start at a tile initially allocated to the processor and that, at least for the initial tiles along the path, traverse to spatially adjacent tiles in the output, and that will traverse every tile to be rendered if followed to their end. The next tile for a given rendering processor to process is then selected as being the next tile along its defined path, unless the next tile in the path has already been processed (or is already being processed) by another rendering processor, in which case the next tile to be allocated to the rendering processor is selected to be a free tile further on in the tile traversal path for that processor.

Abstract translation: 在具有多个渲染处理器的基于瓦片的图形处理系统中，要处理以生成用于显示的输出帧30的瓦片组31在不同的渲染处理器之间通过定义相应的瓦片穿越路径32,33,34,35进行划分，用于 每个渲染处理器从最初分配给处理器的瓦片开始，并且至少对于沿着路径的初始瓦片，遍历输出中的空间相邻的瓦片，并且如果跟随到它们的结尾，则遍历要渲染的每个瓦片。 然后，将待处理的给定渲染处理器的下一个图块选择为沿其定义的路径的下一个图块，除非路径中的下一个图块已经被另一个渲染处理器处理（或已被处理），在这种情况下 将要分配给渲染处理器的下一个瓦片选择为该处理器的瓦片穿越路径中的另外的空闲瓦片。

公开(公告)号：US20150109313A1

公开(公告)日：2015-04-23

申请号：US14056727

申请日：2013-10-17

Applicant: ARM LIMITED

Inventor： Frode Heggelund ,  Andreas Engh-Halstvedt ,  Jorn Nystad ,  Henrik Ohlsson

IPC: G06T1/20

CPC classification number: G06T11/40 ,  G06T15/005 ,  G06T15/40

Abstract: Operating a graphics processing pipeline that includes processing stages including a rasteriser that rasterises input primitives to generate graphics fragments to be processed, each graphics fragment having one or more sampling points associated with it, and a renderer that processes fragments generated by the rasteriser to generate output fragment data for output to a render output, comprising the following steps: (i) determining first information to test whether at least a part of a primitive should be processed further; (ii) using at least some of the first information to decide whether to process at least a part of the primitive further; and if it is decided that at least a part of the primitive is to be processed further: (iii) determining further information to be used in further processing of the primitive; and (iv) further processing at least a part of the primitive using the determined further information.

Abstract translation: 操作图形处理流水线，其中包括处理阶段，包括栅格化输入基元以生成要处理的图形片段的光栅化器，每个图形片段具有与之相关联的一个或多个采样点;以及渲染器，其处理由光栅器产生的片段以产生输出 用于输出到渲染输出的片段数据，包括以下步骤：（i）确定第一信息以测试是否应进一步处理图元的至少一部分; （ii）使用所述第一信息中的至少一些来决定是否进一步处理所述原语的至少一部分; 并且如果确定要进一步处理所述原语的至少一部分：（iii）确定将用于进一步处理所述原语的另外的信息; 以及（iv）使用所确定的进一步的信息进一步处理所述原语的至少一部分。

公开(公告)号：US20140354670A1

公开(公告)日：2014-12-04

申请号：US13907559

申请日：2013-05-31

Applicant: ARM Limited

Inventor： Frode Heggelund ,  Jorn Nystad

IPC: G06T11/00

CPC classification number: G06T11/40

Abstract: A rasteriser 10 of a graphics processing pipeline 1 tests larger patches of a render output to be generated against a primitive to be rasterised, to determine if the primitive covers (at least in part) any smaller patches of the render output that the larger patch encompasses. The larger patch is then sub-divided into any covered smaller patches, and the process repeated.The rasteriser 10 also identifies when a given smaller patch of the render output is found to entirely pass the edge test for an edge of the primitive in question when the larger patch encompassing that smaller patch is tested, notes that event in state information associated with the primitive edge in question, and then uses that state information to skip the testing of the edge in question against the smaller patch of the render output.

Abstract translation: 图形处理流水线1的光栅化器10测试要针对待光栅化的原语生成的渲染输出的较大补丁，以确定该原图是否覆盖（至少部分地）较大补丁包含的渲染输出的任何较小补丁 。 然后将较大的补丁细分为任何覆盖的较小补丁，并重复该过程。 当测试包含该较小补丁的较大修补程序时，光栅器10还识别何时发现给定的较小补丁的渲染输出完全通过所讨论的原语的边缘的边缘测试，注意到与状态信息相关联的事件 原始边缘，然后使用该状态信息跳过相关边缘的测试与较小的补丁输出。

公开(公告)号：US20140267283A1

公开(公告)日：2014-09-18

申请号：US13836887

申请日：2013-03-15

Applicant: ARM Limited

Inventor： Jorn Nystad ,  Anders Lassen

IPC: G06T9/00

CPC classification number: G06T9/00

Abstract: To encode a texture to be used in a graphics processing system, the texture is first downscaled to generate a lower resolution representation of the texture 41. An upscaled version 42 of the lower resolution version of the texture is then compared to the original texture to determine a set of difference values indicating for each texel the difference between the value of the texel in the upscaled version of the texture and in the original texture 43. An encoded texture data block is then generated for each 8×8 block of texels in the original texture 44. Each encoded texture data block contains a base colour value taken from the lower resolution representation of the texture and a set of index values indicating the difference data from the determined set of difference data to be used when decoding the block of texture data to generate the data values to be used for the texture data elements that the block of texture data represents.

Abstract translation: 为了对要在图形处理系统中使用的纹理进行编码，纹理首先被缩小以产生纹理41的较低分辨率表示。然后将纹理的较低分辨率版本的升序版本42与原始纹理进行比较以确定 指示每个纹理的一组差值，即纹理的放大版本和原始纹理43中的纹素的值之间的差异。然后，针对原始纹​​理中的每个8×8块纹素生成编码纹理数据块 每个编码的纹理数据块包含从纹理的较低分辨率表示取得的基色值，以及一组索引值，指示当将纹理数据块解码时所使用的所确定的差分数据集合的差分数据 生成要用于纹理数据块表示的纹理数据元素的数据值。

公开(公告)号：US20140152684A1

公开(公告)日：2014-06-05

申请号：US13690159

申请日：2012-11-30

Applicant: ARM LIMITED

Inventor： Jorn Nystad ,  Andreas Engh-Halstvedt ,  Edvard Sorgard ,  Thomas Jeremy Olson ,  Marius Bjorge

IPC: G06T11/00

CPC classification number: G06T15/04 ,  G06T11/40

Abstract: A graphics virtual texturing system in which textures stored in a storage medium of a host system are divided into respective pages that are then loaded into a local memory of a graphics processing system for use. Each page of a graphics texture has an associated fade factor value that can be set by an application that is to use the texture to control the contribution that the page will be used to make to any texturing result that is generated using the texture page in question. The graphics processing system then controls the contribution of texture data from a texture page to texturing result data to be generated in accordance with the fade factor value associated with the texture page in question. This allows texture paging to be done in a more visually pleasing manner than just a binary “page-is-here”/“page-is-not-here” switch.

Abstract translation: 图形虚拟纹理系统，其中存储在主机系统的存储介质中的纹理被划分为相应的页面，然后将其加载到图形处理系统的本地存储器中以供使用。 图形纹理的每个页面都具有相关联的渐变因子值，该值可由应用程序设置，该应用程序将使用纹理来控制页面将用于使用所讨论的纹理页面生成的任何纹理结果的贡献 。 图形处理系统然后根据与所讨论的纹理页面相关联的渐变因子值来控制纹理数据从纹理页面到纹理结果数据的贡献。 这允许纹理分页以更加视觉上令人愉快的方式来完成，而不仅仅是二进制“page-is-here”/“page-is-not-here”开关。