Systems and methods for performance benchmarking-based selection of processor for generating graphic primitives. An example method comprises: initializing, by a computer system comprising a plurality of processors of a plurality of processor types, a current value of a graphic primitive parameter; for each processor type of the plurality of processor types, computing a corresponding value of a performance metric by generating, using at least one processor of a currently selected processor type, a corresponding graphic primitive of a specified graphic primitive type, wherein the graphic primitive is characterized by the current value of the graphic primitive parameter; and estimating, based on the computed performance metric values, a threshold value of the graphic primitive parameter.

In a present invention embodiment, time series data is received including information pertaining to a corresponding attribute of monitored activity on a processing device. An upper bound of the time series data is determined based on a weighted combination of a prior upper bound and a current value derived from the time series data. Greater weight is provided to greater values in the time series data based on an exponent applied to the prior upper bound and the current value and an effect of older values in the time series data decays over time based on a smoothing factor applied to exponential values of the prior upper bound and the current value. The upper bound is applied to a profile of an entity, and abnormal activity on the processing device is detected based on a comparison of the upper bound to a corresponding bound of the profile.

Techniques for detecting a modification to a configuration of a system are disclosed. For example, a method comprises the step of collecting a first data set for a system at a first time instance, wherein the first data set comprises inventory data for a configuration of the system present at the first time instance. The method compares the first data set to a second data set, wherein the second data set comprises inventory data for a configuration of the system present at a second time instance. The method obtains a third data set based on the comparison of the first data set and the second data set, wherein the third data set comprises data indicative of any differences between the inventory data for the configuration of the system present at the first time instance and the inventory data for the configuration of the system present at the second time instance.

A method for enabling a power of a processor to exceed preset thermal design power (TDP) includes monitoring a usage of the processor; and adjusting a TDP when the usage exceeds a threshold such that an adjusted power of the processor exceeds the preset TDP.

In one or more embodiments, one or more systems, one or more methods, and/or one or more processes may measure at least one of a first height value and a first width value of a first eye diagram of a first signal; measure at least one of a second height value and a second width value of a second eye diagram of a second signal; determine at least one of a height difference value and a width difference value respectively between the at least one of the first height value and the first width value of the first eye diagram and the at least one of the second height value and the second width value of the second eye diagram; and determine that the at least one of the height difference value and the width difference value respectively meets or exceeds a height threshold value or a width threshold value.

A temperature control system, adapted to a central processing unit powered by a power supply module of an electronic device, is provided. The temperature control system includes a setting module, a first temperature detecting module, a second temperature detecting module, and a power adjusting module. The setting module is configured to set a target temperature of the CPU and a target temperature of the power supply module. The first temperature detecting module is configured to obtain a detected temperature of the CPU. The second temperature detecting module is electrically connected to the power supply module, to obtain a detected temperature of the power supply module. The power adjusting module is configured to adjust a control parameter of the CPU or the power supply module based on a first temperature difference between the target temperature of the CPU and the detected temperature of the CPU or a second temperature difference between the target temperature of the power supply module and the detected temperature of the power supply module.

Mechanisms are provided for intelligently identifying an execution environment to execute a computing job. An execution time of the computing job in each execution environment of a plurality of execution environments is predicted by applying a set of existing machine learning models matching execution context information and key parameters of the computing job and execution environment information of the execution environment. The predicted execution time of the machine learning models is aggregated. The aggregated predicted execution times of the computing job are summarized for the plurality of execution environments. Responsive to a selection of an execution environment from the plurality of execution environments based on the summary of the aggregated predicted execution times of the computing job, the computing job is executed in the selected execution environment. Related data during the execution of the computing job in the selected execution environment is collected.

The present invention provides a smart overclocking method for a computer device with a multi-core CPU and abasic input/output system (BIOS) where an overclocking database is stored therein, which comprises: booting the computer device, logging in the BIOS and performing an overclocking function; acquiring overclocking parameters from the overclocking database; conducting adjustment/settlement of the clock rate and the voltage of the multi-core CPU based on the overclocking parameters; conducting a Heavy Load Testing (HLT) on the multi-core CPU; reading out working results data of the multi-core CPU and determining whether any of them have exceeded limits. Hence, overclocking can be completed within 10 min. or less, without causing shut down of the computer device, and without causing working temperature or working voltage of multi-core CPU to be higher than 90° C. or 1500 mV during Heavy Load Testing (HLT).

A computer implemented method, performed in a data processing system comprising a performance monitoring unit. The method comprises receiving a set of computer-readable instructions to be executed by the data processing system to implement at least a portion of a neural network, wherein one or more of the instructions is labeled with one or more performance monitoring labels based upon one or more features of the neural network. The method further comprises configuring the performance monitoring unit to count one or more events occurring in one or more components of the data processing system based on the one or more performance monitoring labels.

Systems and methods herein describe accessing a data processing pipeline, causing presentation of the data processing pipeline on a graphical user interface of a computing device; receiving a selection of a first user interface element within the graphical user interface, generating a datafile representing the data processing pipeline, submitting the datafile and an application to a software framework using an application programming interface, receiving, from the application, the generated datasets, applying the data operations the data processing pipeline, collecting performance data metrics from the data processing pipeline, and dynamically updating the graphical user interface with the collected performance data metrics.