International Business Machines Corporation

Thomas W Aarts

Michael C Hollinger

Jason Szecheong Ma

Gundam Raghuswamyreddy

Jose Luis Ortiz

Ched D Hays

Stephan Otis Broyles

Thomas Hung Tran

William G Hoffa

According to one aspect of the present disclosure, a method and technique for a hybrid platform-dependent simulation interface is disclosed. The method includes: encoding an application with a library having a platform-independent application programming interface (API) for interacting with a simulation engine, the simulation engine providing a simulated environment for hosting the application; and encoding the library with a platform-dependent API providing an interface to the simulation engine using a platform-dependent hardware element, the platform-dependent hardware element unaffecting a non-simulation environment when the application is running in the non-simulation environment.

Hybrid platform-dependent simulation interface

Mechanisms are provided for controlling a fidelity of a simulation of a computer system. A model of the system is received that has a plurality of components. A representation of the plurality of individual components of the system is generated. A component is assigned to be a fidelity center having a highest possible associated fidelity value. Fidelity values are assigned to each other component in the plurality of individual components based on an affinity of the other component to the fidelity center. The system is simulated based on assigned fidelity values to the components in the plurality of individual components.

Determining simulation fidelity in a self-optimized simulation of a complex system

Mechanisms are provided for controlling a fidelity of a simulation of a system. A model of the system is received, the model of the system having a plurality of individual components of the system. Fidelity values are assigned to models of the individual components of the system. A simulation of the system is executed using the model of the system and the models of the individual components of the system. For each component in the plurality of individual components of the system, an activity level of the component during execution of the simulation is determined. The fidelity values of one or more of the models of the individual components of the system are dynamically adjusted during the execution of the simulation based on changes in individual activity levels of the individual components.

Dynamically adjusting simulation fidelity based on changes in activity levels of components

Mechanisms are provided for controlling a fidelity of a simulation of a system. A model of the system is received, the model of the system having a plurality of individual components of the system. Fidelity values are assigned to models of the individual components of the system. A simulation of the system is executed using the model of the system and the models of the individual components of the system. The fidelity values of one or more of the models of the individual components of the system are dynamically adjusted during the execution of the simulation by creating a checkpoint of a state of the simulation and modifying one or more fidelity values of one or more of the models of the individual components after generating the checkpoint, thereby generating a modified fidelity value state.

Dynamically adjusting simulation fidelity based on checkpointed fidelity state

Mechanisms are provided for controlling a fidelity of a simulation of a system. A model of the system is received, the model of the system having a plurality of individual components of the system. Fidelity values are assigned to models of the individual components of the system. A required fidelity value is assigned to transactions between components in the plurality of individual components of the system. A simulation of the system is executed using the model of the system and the models of the individual components of the system. The fidelity values of one or more of the models of the individual components of the system are dynamically adjusted during the execution of the simulation based on the required fidelity values assigned to the transactions.

Dynamically adjusting simulation fidelity in a self-optimized simulation of a complex system

Mechanisms are provided for controlling a fidelity of a simulation of a system. A model of the system is received, where the model has a plurality of individual components of the system. Fidelity values are assigned to models of the individual components of the system and a simulation of the system is executed using the model of the system and the models of the individual components of the system. The simulation comprises a plurality of transactions targeting a receiver component. A history of mismatches between a fidelity value associated with the receiver component and required fidelity values of the plurality of transactions targeting the receiver component is maintained. A prediction of a fidelity value to be assigned to the receiver component based on the history of mismatches is performed. A fidelity value of the receiver component is adjusted based on results of predicting the fidelity value to be assigned to the receiver component.

Dynamically predicting simulation fidelity in a self-optimized simulation of a complex system

Methods, systems and articles of manufacture for software implemented timers configured to account for purposeful or desired program stoppage. Such program stoppage is a common occurrence in debugging environments. Because such program stoppage is not indicative of an error condition, it is undesirable to include the stoppage time with the elapsed timer value. Accordingly, a process counter is implemented which is incremented only while a process of the application being debugged is executing.

Growing community of inventors

Mantorville, MN, United States of America

Thomas W Aarts