公开(公告)号：US10255106B2

公开(公告)日：2019-04-09

申请号：US15007643

申请日：2016-01-27

申请人： QUALCOMM Incorporated

发明人： Navid Farazmand ,  Eduardus Antonius Metz ,  David Rigel Garcia Garcia

IPC分类号： G06F9/50 ,  G06F1/329 ,  G06F1/3234

摘要： A device for processing data includes a processing unit configured to predict an execution time of a compute kernel on a secondary processing unit and, based on the predicted execution time, make a power management decision for the secondary processing unit.

公开(公告)号：US10332230B2

公开(公告)日：2019-06-25

申请号：US14840915

申请日：2015-08-31

申请人： QUALCOMM Incorporated

发明人： Eduardus Antonius Metz ,  Song Zhao ,  Navid Farazmand ,  Qiao Shen

IPC分类号： G06T1/20 ,  G06F1/3234 ,  G06F1/20 ,  G06F1/3206 ,  G06F9/50

摘要： A method of graphics processing comprising receiving, at a graphics processing unit (GPU), a command stream, the command stream including one or more commands to be performed by the GPU and at least one command stream hint, the at least one command stream hint providing a characterization of a workload of the command stream, performing, by the GPU, a power management process based on the at least one command stream hint prior to executing the command stream, and executing, by the GPU, the command stream.

公开(公告)号：US09817431B2

公开(公告)日：2017-11-14

申请号：US15014727

申请日：2016-02-03

申请人： QUALCOMM Incorporated

发明人： Qiao Shen ,  Song Zhao ,  Navid Farazmand ,  Eduardus Antonius Metz

IPC分类号： G06F1/04 ,  G06F1/08 ,  G06F1/14 ,  G06T1/20 ,  G06F1/32

CPC分类号： G06F1/08 ,  G06F1/14 ,  G06F1/324 ,  G06F1/3265 ,  G06T1/20 ,  Y02D10/126 ,  Y02D10/153 ,  Y02D50/20

摘要： Techniques are described in which a processor determines how busy a graphics processing unit (GPU) was in rendering a current fame based on a time interval between when the GPU completed the rendering of the current frame and when the GPU completed the rendering of a previous frame that immediately precedes the current frame. The processor sets a clock rate of the GPU based on the determination of how busy the GPU was in rendering the current frame.

公开(公告)号：US20170220062A1

公开(公告)日：2017-08-03

申请号：US15014727

申请日：2016-02-03

申请人： QUALCOMM Incorporated

发明人： Qiao Shen ,  Song Zhao ,  Navid Farazmand ,  Eduardus Antonius Metz

IPC分类号： G06F1/08 ,  G06T1/20 ,  G06F1/14

CPC分类号： G06F1/08 ,  G06F1/14 ,  G06F1/324 ,  G06F1/3265 ,  G06T1/20 ,  Y02D10/126 ,  Y02D10/153 ,  Y02D50/20

摘要： Techniques are described in which a processor determines how busy a graphics processing unit (GPU) was in rendering a current fame based on a time interval between when the GPU completed the rendering of the current frame and when the GPU completed the rendering of a previous frame that immediately precedes the current frame. The processor sets a clock rate of the GPU based on the determination of how busy the GPU was in rendering the current frame.

公开(公告)号：US20170212563A1

公开(公告)日：2017-07-27

申请号：US15007643

申请日：2016-01-27

申请人： QUALCOMM Incorporated

发明人： Navid Farazmand ,  Eduardus Antonius Metz ,  David Rigel Garcia Garcia

IPC分类号： G06F1/26 ,  G06F9/50

CPC分类号： G06F9/5027 ,  G06F1/3243 ,  G06F1/329 ,  G06F9/5094 ,  Y02D10/152 ,  Y02D10/22 ,  Y02D10/24

摘要： A device for processing data includes a processing unit configured to predict an execution time of a compute kernel on a secondary processing unit and, based on the predicted execution time, make a power management decision for the secondary processing unit.

公开(公告)号：US20170199558A1

公开(公告)日：2017-07-13

申请号：US15238267

申请日：2016-08-16

申请人： QUALCOMM Incorporated

发明人： Navid Farazmand ,  Anish Muttreja ,  Eduardus Antonius Metz ,  Lucille Garwood Sylvester ,  Brian Salsbery

IPC分类号： G06F1/32

CPC分类号： G06F1/3206 ,  G06F1/324 ,  G06F1/325 ,  G06F1/3296 ,  G06F9/50 ,  G09G5/003 ,  G09G5/363 ,  G09G2330/021 ,  G09G2340/0435

摘要： At least one processor may determine, for each of a plurality of operating performance points (OPPs) that each comprise a memory frequency and a graphics processing unit (GPU) frequency, an estimated energy consumption associated with a memory and the GPU operating at the respective memory frequency and GPU frequency to process a workload based at least in part on a plurality of energy equations associated with the plurality of OPPs. The at least one processor may set the memory and the GPU to operate at the respective memory frequency and GPU frequency of one of the plurality of OPPs to process the workload based at least in part on the estimated energy consumption.

公开(公告)号：US20170061568A1

公开(公告)日：2017-03-02

申请号：US14840915

申请日：2015-08-31

申请人： QUALCOMM Incorporated

发明人： Eduardus Antonius Metz ,  Song Zhao ,  Navid Farazmand ,  Qiao Shen

IPC分类号： G06T1/20 ,  G06F1/32

CPC分类号： G06T1/20 ,  G06F1/206 ,  G06F1/3206 ,  G06F1/3243 ,  G06F9/5094 ,  Y02D10/152

摘要： A method of graphics processing comprising receiving, at a graphics processing unit (GPU), a command stream, the command stream including one or more commands to be performed by the GPU and at least one command stream hint, the at least one command stream hint providing a characterization of a workload of the command stream, performing, by the GPU, a power management process based on the at least one command stream hint prior to executing the command stream, and executing, by the GPU, the command stream.

摘要翻译： 一种图形处理方法，包括在图形处理单元（GPU）处接收命令流，所述命令流包括由GPU执行的一个或多个命令和至少一个命令流提示，所述至少一个命令流提示 提供命令流的工作负载的表征，由GPU执行基于在执行命令流之前的至少一个命令流提示以及由GPU执行命令流的功率管理进程。