-
公开(公告)号:AU2018226440B2
公开(公告)日:2020-06-04
申请号:AU2018226440
申请日:2018-09-05
Applicant: APPLE INC
Inventor: MUNSHI AAFTAB , SANDMEL JEREMY
IPC: G06F9/50
Abstract: DATA PARALLEL COMPUTING ON MULTIPLE PROCESSORS A method and an apparatus that allocate one or more physical compute devices such as CPUs or GPUs attached to a host processing unit running an application for executing one or more threads of the application are described. The allocation may be based on data representing a processing capability requirement from the application for executing an executable in the one or more threads. A compute device identifier may be associated with the allocated physical compute devices to schedule and execute the executable in the one or more threads concurrently in one or more of the allocated physical compute devices concurrently.
-
公开(公告)号:AU2014221239B2
公开(公告)日:2016-05-19
申请号:AU2014221239
申请日:2014-09-04
Applicant: APPLE INC
Inventor: MUNSHI AAFTAB , SANDMEL JEREMY
IPC: G06F9/50
Abstract: DATA PARALLEL COMPUTING ON MULTIPLE PROCESSORS A method and an apparatus that allocate one or more physical compute devices such as CPUs or GPUs attached to a host processing unit running an application for executing one or more threads of the application are described. The allocation may be based on data representing a processing capability requirement from the application for executing an executable in the one or more threads. A compute device identifier may be associated with the allocated physical compute devices to schedule and execute the executable in the one or more threads concurrently in one or more of the allocated physical compute devices concurrently.
-
公开(公告)号:AU2013217637B2
公开(公告)日:2016-01-14
申请号:AU2013217637
申请日:2013-01-31
Applicant: APPLE INC
Inventor: SANDMEL JEREMY , SCHAFFER JOSHUA H , PATTERSON TOBY C , COFFMAN PATRICK , STAHL GEOFFREY , HARPER JOHN S
IPC: G06F3/14
Abstract: Systems, methods, and computer readable media for dynamically setting an executing application's display buffer size are described. To ameliorate display device overscan operations, the size of an executing application's display buffer may be set based on the display device's extent and a display mode. In addition, contents of the executing application's display buffer may be operated on as they are moved to a frame buffer based on the display mode. In one mode, for example, display buffer contents may be scaled before being placed into the frame buffer. In another mode, a black border may be placed around display buffer contents as it is placed into the frame buffer. In yet another mode, display buffer contents may be copied into the frame buffer without further processing.
-
公开(公告)号:AU2018226440A1
公开(公告)日:2018-09-27
申请号:AU2018226440
申请日:2018-09-05
Applicant: APPLE INC
Inventor: MUNSHI AAFTAB , SANDMEL JEREMY
IPC: G06F9/50
Abstract: DATA PARALLEL COMPUTING ON MULTIPLE PROCESSORS A method and an apparatus that allocate one or more physical compute devices such as CPUs or GPUs attached to a host processing unit running an application for executing one or more threads of the application are described. The allocation may be based on data representing a processing capability requirement from the application for executing an executable in the one or more threads. A compute device identifier may be associated with the allocated physical compute devices to schedule and execute the executable in the one or more threads concurrently in one or more of the allocated physical compute devices concurrently.
-
公开(公告)号:AU2016213890A1
公开(公告)日:2016-09-01
申请号:AU2016213890
申请日:2016-08-12
Applicant: APPLE INC
Inventor: MUNSHI AAFTAB , SANDMEL JEREMY
IPC: G06F9/50
Abstract: DATA PARALLEL COMPUTING ON MULTIPLE PROCESSORS A method and an apparatus that allocate one or more physical compute devices such as CPUs or GPUs attached to a host processing unit running an application for executing one or more threads of the application are described. The allocation may be based on data representing a processing capability requirement from the application for executing an executable in the one or more threads. A compute device identifier may be associated with the allocated physical compute devices to schedule and execute the executable in the one or more threads concurrently in one or more of the allocated physical compute devices concurrently.
-
公开(公告)号:AU2016203532A1
公开(公告)日:2016-06-16
申请号:AU2016203532
申请日:2016-05-27
Applicant: APPLE INC
Inventor: MUNSHI AAFTAB , SANDMEL JEREMY
Abstract: A method and an apparatus that schedule a plurality of executables in a schedule queue for execution in one or more physical compute devices such as CPUs or GPUs concurrently are described. One or more executables are compiled online from a source having an existing executable for a type of physical compute devices different from the one or more physical compute devices. Dependency relations among elements corresponding to scheduled executables are determined to select an executable to be executed by a plurality of threads concurrently in more than one of the physical compute devices. A thread initialized for executing an executable in a GPU of the physical compute devices are initialized for execution in another CPU of the physical compute devices if the GPU is busy with graphics processing threads. Sources and existing executables for an API function are stored in an API library to execute a plurality of executables in a plurality of physical compute devices, including the existing executables and online compiled executables from the sources.
-
公开(公告)号:AU2016213890B2
公开(公告)日:2018-06-28
申请号:AU2016213890
申请日:2016-08-12
Applicant: APPLE INC
Inventor: MUNSHI AAFTAB , SANDMEL JEREMY
IPC: G06F9/50
Abstract: DATA PARALLEL COMPUTING ON MULTIPLE PROCESSORS A method and an apparatus that allocate one or more physical compute devices such as CPUs or GPUs attached to a host processing unit running an application for executing one or more threads of the application are described. The allocation may be based on data representing a processing capability requirement from the application for executing an executable in the one or more threads. A compute device identifier may be associated with the allocated physical compute devices to schedule and execute the executable in the one or more threads concurrently in one or more of the allocated physical compute devices concurrently.
-
公开(公告)号:AU2016203532B2
公开(公告)日:2018-01-18
申请号:AU2016203532
申请日:2016-05-27
Applicant: APPLE INC
Inventor: MUNSHI AAFTAB , SANDMEL JEREMY
IPC: G06F9/50
Abstract: A method and an apparatus that schedule a plurality of executables in a schedule queue for execution in one or more physical compute devices such as CPUs or GPUs concurrently are described. One or more executables are compiled online from a source having an existing executable for a type of physical compute devices different from the one or more physical compute devices. Dependency relations among elements corresponding to scheduled executables are determined to select an executable to be executed by a plurality of threads concurrently in more than one of the physical compute devices. A thread initialized for executing an executable in a GPU of the physical compute devices are initialized for execution in another CPU of the physical compute devices if the GPU is busy with graphics processing threads. Sources and existing executables for an API function are stored in an API library to execute a plurality of executables in a plurality of physical compute devices, including the existing executables and online compiled executables from the sources.
-
公开(公告)号:AU2011253721B2
公开(公告)日:2014-06-05
申请号:AU2011253721
申请日:2011-11-28
Applicant: APPLE INC
Inventor: MUNSHI AAFTAB , SANDMEL JEREMY
IPC: G06F9/50
Abstract: A method includes loading an executable compiled from a source for a processing unit to perform a data processing task in a target processing unit, detecting a difference between the processing unit and the target processing unit and compiling, in response to the detecting the difference, the source for the target processing unit based on the difference. Other disclosed methods include methods for selecting one of the plurality of executables for execution in the plurality of processing units based on the condition. A still further method includes determining automatically a plurality of types of target data processing units to perform a data processing function and compiling and executing an executable for the determined types of target data. Another method includes compiling and storing an executable for a type of processing units from a source to perform a data processing function, to be retrieved from an API library for executing an executable in response to a request to the API library from an application running in a host processing unit separate from the one or more processing units.
-
公开(公告)号:AU2011253819B2
公开(公告)日:2014-05-22
申请号:AU2011253819
申请日:2011-12-02
Applicant: APPLE INC
Inventor: MUNSHI AAFTAB , SANDMEL JEREMY
Abstract: A method and an apparatus that schedule a plurality of executables in a schedule queue for execution in one or more physical compute devices such as CPUs or GPUs concurrently are described. One or more executables are compiled online from a source having an existing executable for a type of physical compute devices different from the one or more physical compute devices. Dependency relations among elements corresponding to scheduled executables are determined to select an executable to be executed by a plurality of threads concurrently in more than one of the physical compute devices. A thread initialized for executing an executable in a GPU of the physical compute devices are initialized for execution in another CPU of the physical compute devices if the GPU is busy with graphics processing threads. Sources and existing executables for an API function are stored in an API library to execute a plurality of executables in a plurality of physical compute devices, including the existing executables and online compiled executables from the sources.
-
-
-
-
-
-
-
-
-