Methods, systems, apparatus, and program products that can generate scaled-down load test models for testing real-world loads are disclosed herein. One method includes providing a test environment of a system including multiple nodes. The test environment includes virtual nodes corresponding to the system nodes and each virtual node functions under a virtual load similar to each corresponding node functioning under a real-world load. The method further includes utilizing a machine learning algorithm to repeatedly apply at least one virtual load to the virtual node(s) in the test environment until a scaled-down load test model mimicking the system under a pre-defined real-world load is generated. Here, the virtual load(s) applied to the virtual node(s) is/are comparatively smaller relative to each of corresponding real-world loads for the node(s) defining the pre-defined real-world load. Systems, apparatus, and program products that include and/or perform the methods are also disclosed herein.

Systems and methods for simulating cyber-physical systems are disclosed. A plurality of geographic simulation layers representing respective infrastructure sectors of a real-world environment may be generated, and the layers may be linked together with one another to create a multi-layer simulation. The associations between the layers of the simulation may be adjusted, and characteristics of the simulation layers themselves may be adjusted, to ensure that the simulation conforms to characteristics of the real-world environment being simulated. In some embodiments, a multi-user simulation system allows users at separate terminals to execute attack inputs and defense inputs against the simulation to try to destabilize and stabilize the simulation, respectively. Results of the attack inputs and defense inputs may be simultaneously displayed on a plurality of terminals.

A model-based approach to determining an optimal configuration for a data center may use an environmental chamber to characterize the performance of various data center configurations at different combinations of temperature and altitude. Telemetry data may be recorded from different configurations as they execute a stress workload at each temperature/altitude combination, and the telemetry data may be used to train a corresponding library of models. When a new data center is being configured, the temperature/altitude of the new data center may be used to select a pre-trained model from a similar temperature/altitude. Performance of the current configuration can be compared to the performance of the model, and if the model performs better, a new configuration based on the model may be used as an optimal configuration for the data center.

Disclosed are various embodiments of real-time simulation of the performance of a compute accelerator workload associated with a remotely accessed working set. The compute accelerator workload is cloned and executed on candidate hosts to select a destination host. Efficiency metrics for respective hosts are based on an execution velocity counter, a non-local page reference velocity counter, and a non-local page dirty velocity counter. A destination host is selected from the candidate hosts based on the efficiency metrics, and the compute accelerator is executed on the destination host.

Techniques for predicting anomalies in forecasted time-series data are disclosed. A system. A system predicts whether a monitored computing system will experience anomalies by comparing forecasted values associated with components in the monitored computing system to threshold values. The system utilizes time-series machine learning models to forecast workloads of computing resources in the monitored computing system. The system trains and tests multiple different versions of a time-series model and selects the most accurate version to generate forecasts for a particular workload in the computing system. The system compares the forecasts to threshold values to predict anomalies. Based on detecting anomalies, the system generates recommendations for remediating predicted anomalies.

Methods and systems are disclosed for emulating, in a platform, the performance of a target platform. Techniques disclosed include receiving, by the platform, values of system features, associated with a target performance of the target platform; and setting, by the platform, one or more configuration knobs, based on the received values of system features, to match a performance of the platform to the target performance of the target platform.

Automatic definition of windows for trace analysis. For each process step, the trace data are aligned to both the start of the process step and the end of the process step, and statistics including rate of change are calculated from both the start of the process step and the end of the process step. Windows are generated based on analysis of the calculated statistics.

A system includes a host data processing system and a target platform coupled to the host data processing system. The target platform includes an emulation system. The emulation system includes a processor system, an emulation circuit coupled to the processor system through an integrated circuit (IC) interconnect, and a performance monitor coupled to the IC interconnect. The emulation system receives, from the host data processing system, a software emulation model and a data traffic pattern. The emulation system emulates a system architecture by executing the software emulation model within the processor system and implementing the data traffic pattern over the IC interconnect using the emulation circuit. The emulation system provides, to the host data processing system, measurement data collected by the performance monitor during the emulation.

A method includes identifying, by a computing device, activities of a machine using a digital twin of a machine; running, by the computing device, simulations of the activities on the digital twin; determining, by the computing device, a performance issue in the machine using the simulations; and deploying, by the computing device, a capability to address the performance issue.

Disclosed are hardware and techniques for testing computer processes in a network system by simulating computer process faults and identifying risk associated with correcting the simulated fault and identifying computer processes that may depend on the corrected computer process. The interdependent computer processes in a network may be determined by evaluating a risk matrix having a risk score and non-functional requirement score. An analysis of the risk score and non-functional requirement score accounts for interdependencies between computer processes and identified corrective actions that may be used to determine an optimal network environment. The optimal network environment may be updated dynamically based on changing computer process interdependencies and the determined risk and robustness scores.