公开(公告)号：WO2019125714A1

公开(公告)日：2019-06-27

申请号：PCT/US2018/062898

申请日：2018-11-28

申请人： QUALCOMM INCORPORATED

发明人： JONG, Alex Kwang Ho ,  YUN, Jay Chunsup ,  KIM, Donghyun ,  GULATI, Rahul ,  JOHNSON, Brendon Lewis ,  GRUBER, Andrew Evan

IPC分类号： G06T1/20

CPC分类号： G06F11/277 ,  G06F11/2236 ,  G06T1/20 ,  G06T7/0002 ,  G06T7/97 ,  G06T2207/30168

摘要： A graphics processing unit (GPU) of a GPU subsystem of a computing device operates in a first rendering mode to process graphics data to produce a first image. The GPU operates in a second rendering mode to process the graphics data to produce a second image. The computing device detects whether a fault has occurred in the GPU subsystem based at least in part on comparing the first image with the second image.

公开(公告)号：WO2019113017A1

公开(公告)日：2019-06-13

申请号：PCT/US2018/063778

申请日：2018-12-04

申请人： GOOGLE LLC

发明人： DODGE, Benjamin ,  REDGRAVE, Jason Rupert ,  MA, Xiaoyu

IPC分类号： G06F13/28 ,  G06T1/20 ,  G06T1/60

CPC分类号： G06F13/28 ,  G06T1/20 ,  G06T1/60

摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating, by an image sensor of a computing device, frame data comprising sub-frames of image pixel data. A first resource of the system-on-chip provides the frame data to a second resource of the system-on-chip. The frame data is provided to the second resource using a first data path included in the system-on-chip. The first resource provides a token to the second resource using a second data path included in the system-on-chip. A processor of the system-on-chip, uses the token to synchronize production of sub-frames of image pixel data provided by the first resource to the second resource and to synchronize consumption of the sub-frames of image pixel data received by the second resource from the elastic memory buffer.

公开(公告)号：WO2019061066A1

公开(公告)日：2019-04-04

申请号：PCT/CN2017/103638

申请日：2017-09-27

申请人： INTEL CORPORATION ,  YUAN, Feng ,  ZONG, Wei ,  ZHAO, Juan ,  WU, Junkai

发明人： YUAN, Feng ,  ZONG, Wei ,  ZHAO, Juan ,  WU, Junkai

IPC分类号： G06T3/00

CPC分类号： G06T1/20

摘要： An apparatus and method for efficient image optimized image stitching. For example, one embodiment of an apparatus comprises: feature search area identification circuitry/logic to narrow down a feature search area based on possible overlap between two image frames; feature detection circuitry/logic to identify a plurality of feature points in a first image frame of the two image frames; feature matching circuitry/logic to map one or more of the plurality of feature points from the first image frame to corresponding feature points in the right image frame; image frame stitching and blending circuitry/logic to stitch the first image frame and second image frame based on the mapping of the feature points between the two image frames and to blend a portion of the first image frame with a portion of the second image frame.

公开(公告)号：WO2018200079A1

公开(公告)日：2018-11-01

申请号：PCT/US2018/021388

申请日：2018-03-07

申请人： APPLE INC.

发明人： PARK, Sung Hee ,  WANG, Muge

IPC分类号： G06F17/15 ,  G06N3/063 ,  G06K9/00

CPC分类号： G06T1/20 ,  G06F17/153 ,  G06K9/00973 ,  G06K9/4642 ,  G06K9/627 ,  G06N3/0454 ,  G06N3/063 ,  G06T5/001 ,  G06T5/20

摘要： Embodiments relate to a configurable convolution engine that receives configuration information to perform convolution and other deep machine learning operations on streaming input data of various formats. The convolution engine may include two convolution circuits that each generate a stream of values by applying convolution kernels to input data. The stream of values may each define multiple channels of image data. A channel merge circuit interleaves the streams of values from the convolution circuits to generate an output stream of output values. The output stream includes the data multiple channels of each input stream arranged in an interleaved manner.

公开(公告)号：WO2018194204A1

公开(公告)日：2018-10-25

申请号：PCT/KR2017/004495

申请日：2017-04-27

申请人： 한국과학기술원

发明人： 유회준 ,  강상훈

IPC分类号： G06T17/20 ,  G06K9/00 ,  G06T1/20 ,  G06T1/60

CPC分类号： G06K9/00 ,  G06T1/20 ,  G06T1/60 ,  G06T17/20

摘要： 본 발명의 3차원 안면 정면화 시스템은, 외부로부터 입력된 2차원 안면 이미지에 대해 안면 특징 점을 추출하고, 추출된 상기 특징 점을 기반으로 3차원 정면화 연산을 통해 정면의 안면 이미지를 생성하기 위한 3차원 안면 정면화 시스템에 있어서, 상기 특징 점 추출 연산 및 상기 3차원 정면화 연산을 수행하기 위해 병렬로 배치된 복수개의 연산기들; 상기 연산기들 각각에 1 : 1로 대응하도록 직결되어 한 쌍의 조합을 이루는 복수개의 로컬 메모리들; 상기 연산기들 각각이 공통적으로 접근할 수 있는 공유 메모리; 및 상기 연산기들, 상기 로컬 메모리들 및 상기 공유 메모리를 제어하는 컨트롤러를 포함하며, 온 칩(on chip)의 집적회로 형태를 갖는 기술을 제공함에 기술적 특징이 있다.

公开(公告)号：WO2018136963A1

公开(公告)日：2018-07-26

申请号：PCT/US2018/014906

申请日：2018-01-23

申请人： KINETICA DB, INC.

发明人： VIJ, Amit ,  NEGAHBAN, Nima ,  GLASER, Eli ,  JEONG, Byungil

IPC分类号： G06F3/048

CPC分类号： G06T1/20 ,  G06F7/08 ,  G06F7/14 ,  G06F16/2246 ,  G06F16/2282 ,  G06F16/26 ,  G06T1/60 ,  G06T2210/12 ,  G06T2210/36 ,  H04L67/12

摘要： A technique for rendering database data in visualized form using a distributed computer system including a plurality of networked worker nodes each including a graphics processing unit (GPU) is disclosed. The technique includes receiving, at a head node, a user request to render data, forwarding the request to the worker nodes, processing, in parallel, by the worker nodes, chunks of respective shards of data to be rendered. The technique also includes merging, in parallel, by each of the worker nodes, initial images formed by the processing within respective shards, to form a plurality of integrated images, merging, in parallel, respective integrated images to form worker node images, and transmitting respective worker node images to the sink node. The technique also includes merging the worker node images to form a final image, converting the final image to an output image, and providing the output image to the user.

公开(公告)号：WO2018120446A1

公开(公告)日：2018-07-05

申请号：PCT/CN2017/077106

申请日：2017-03-17

申请人： 华中科技大学

发明人： 张天序 ,  李欢 ,  郑畅 ,  张培阳 ,  向叮

IPC分类号： G06T1/20

CPC分类号： G06T1/20 ,  G06T1/60 ,  H04N1/3877

摘要： 一种面向实时目标识别的异构处理机并行协调处理方法，该方法基于高效的互联结构以及高低速、多总线数据同步传输设计，对复杂算法进行分解，合理分配到相应的软硬件资源上，通过DSP作为主控器件，根据实际需求适时的调用各个异构器件，使得各个异构器件能够协调同步有序工作，解决了同构结构处理系统存在的计算复杂、耗时长、功耗大等问题。

公开(公告)号：WO2018119602A1

公开(公告)日：2018-07-05

申请号：PCT/CN2016/112185

申请日：2016-12-26

申请人： 深圳前海达闼云端智能科技有限公司

发明人： 王洛威 ,  廉士国

IPC分类号： G06F9/44

CPC分类号： G06F9/54 ,  G06T1/20

摘要： 一种渲染方法及装置，涉及图像处理技术领域，能够降低CPU负载率，提高GPU与CPU间的带宽利用率。该方法包括在用户对应的用户线程中，配置所述用户提交的渲染任务数据的渲染过程状态（101）；将至少一个在用户线程中为所述渲染任务数据配置的渲染过程状态后的缓存数据发送至渲染主线程（102）；通过所述渲染主线程将所述缓存数据发送至图形处理器GPU进行图形渲染（103）。该渲染方法及装置用于图形渲染。

公开(公告)号：WO2018097577A1

公开(公告)日：2018-05-31

申请号：PCT/KR2017/013284

申请日：2017-11-21

申请人： 경희대학교 산학협력단

发明人： 박광훈 ,  윤성재 ,  홍석종 ,  권우원

IPC分类号： G06T19/00 ,  G06T1/20 ,  G06T9/00

CPC分类号： G06T1/20 ,  G06T9/00 ,  G06T19/00

摘要： 본 개시는 복수의 퍼스펙티브(perspective) 영상을 포함하는 영상의 부/복호화 방법 및 장치에 관한 것이다. 본 개시에 따르는 부호화 방법은 하나 이상의 퍼스펙티브 영상을 선택하고, 상기 선택된 퍼스펙티브 영상에 대한 부호화를 시작하고, 상기 선택된 퍼스펙티브 영상의 부호화 진행 정도에 따라 의존성이 해결된 하나 이상의 이웃 퍼스펙티브에 대한 부호화를 시작하는 단계를 포함할 수 있다.

公开(公告)号：WO2018075181A1

公开(公告)日：2018-04-26

申请号：PCT/US2017/052192

申请日：2017-09-19

申请人： INTEL CORPORATION

发明人： CHENG, Bu Qi ,  CHEN, Wei-Yi ,  LUEH, Guei-Yuan

IPC分类号： G06F9/30 ,  G06T1/20

CPC分类号： G06F8/41 ,  G06F8/433 ,  G06F9/30145 ,  G06F9/3838 ,  G06F9/3851 ,  G06T1/20

摘要： Methods and apparatus relating to techniques for compiler-based instruction scoreboarding. In an example, an apparatus comprises logic, at least partially comprising hardware logic, to remove unnecessary dependence edges from a data dependency graph, partition the data dependency graph into a plurality of sub-graphs, determine a live range for each of the plurality of sub-graphs, and assign a scoreboard entry to each of the plurality of sub-graphs, wherein sub-graphs which have interfering live ranges are assigned different scoreboard entries. Other embodiments are also disclosed and claimed.

摘要翻译： 涉及用于基于编译器的指令记分板的技术的方法和设备。 在一个示例中，一种装置包括至少部分地包括硬件逻辑的逻辑，用于从数据依赖图中去除不必要的依赖边，将数据依赖图划分成多个子图，为多个子图中的每一个确定活动范围 并且将记分板条目分配给所述多个子图中的每一个，其中具有干扰生存区间的子图被分配不同的记分板条目。 其他实施例也被公开和要求保护。