公开(公告)号：US20170024191A1

公开(公告)日：2017-01-26

申请号：US14803110

申请日：2015-07-20

Applicant: QUALCOMM INCORPORATED

Inventor： JAMES LYALL ESLIGER ,  WILSON KWAN ,  MARK BAPST

IPC: G06F9/45 ,  G06F9/44

CPC classification number: G06F8/41 ,  G06F1/324 ,  G06F1/329 ,  G06F1/3296 ,  G06F8/443 ,  G06F8/71 ,  G06F9/50 ,  G06F11/3409 ,  G06F11/3442 ,  Y02D10/22

Abstract: Various embodiments of methods and systems for proactive resource allocation and configuration are disclosed. An exemplary method first compiles and links a profile instrumented application with a compiler comprising a profile guided optimization feature that inserts calls to a profiler runtime. The profile instrumented application is executed on a target device using one or more workload datasets representative of probable workloads. During execution, based on recognition of the inserted calls, an instrumentation-based profile dataset is generated in association with each of the one or more workload datasets. Next, the profile instrumented application is recompiled and relinked based on the instrumentation-based profile datasets to create a set of profile guided optimizations to the source code, thereby resulting in an optimized application. The optimized application may be executed and monitored to generate a revised profile dataset useful for providing instructions to the target device for optimal workload allocation and resource configuration.

Abstract translation: 公开了用于主动资源分配和配置的方法和系统的各种实施例。 一种示例性方法首先将配置文件测试的应用程序与编译器进行编译并链接，该编译器包括将调用插入到轮廓仪运行时的轮廓引导优化特征。 使用一个或多个表示可能工作负载的工作负载数据集，在目标设备上执行配置文件化应用程序。 在执行期间，基于对插入的呼叫的识别，与一个或多个工作负载数据集中的每一个相关联地生成基于仪表的配置文件数据集。 接下来，基于基于仪器的配置文件数据集重新编译和重新链接配置文件的应用程序，以创建一组对源代码进行的轮廓引导优化，从而导致优化的应用程序。 可以执行和监视优化的应用程序以生成修改的简档数据集，其用于向目标设备提供用于最佳工作负载分配和资源配置的指令。

公开(公告)号：US20210012207A1

公开(公告)日：2021-01-14

申请号：US16506913

申请日：2019-07-09

Applicant: QUALCOMM Incorporated

Inventor： HEE JUN PARK ,  WILSON KWAN

IPC: G06N3/10 ,  G06N3/04 ,  G06F9/50

Abstract: Neural network workload re-allocation in a system-on-chip having multiple heterogenous processors executing one or more neural network units may be based on measurements associated with the processors' conditions and on metadata associated with the neural network units. Metadata may be contained in an input file along with neural network information. Measurements characterizing operation of the processors may be obtained and compared with one or more thresholds. A neural network unit executing on a processor may be identified as a candidate for re-allocation based on metadata associated with the neural network unit and results of the comparisons. A target processor may be identified based on the metadata and results of the comparisons, and the candidate neural network neural network unit may be re-allocated to the target processor.