Abstract: Embodiments include methods, apparatus, and systems for profiling metrics for computer programs. One embodiment includes a method that executes a program to obtain data for each of plural entities in the program. Equations are received for plural metrics that define events occurring in the entities. The method then displays scores for each of the entities with respect to each of the metrics in order to visually indicate which of the entities to optimize to improve performance of the program.

Abstract: In one embodiment, a computer system comprises one or more processors, and a memory module communicatively connected to the one or more processors. The memory module comprises logic instructions stored on a computer readable medium which, when executed on the one or more processors configure the one or more processors to normalize data from a first data set comprising sample based profiling data to form a first normalized data set, normalize data from a second data set comprising sample based profiling data to form a second normalized data set, combine the first normalized data set and the second normalized data set to form a merged data set, and present a portion of the merged data set on a user interface.

Abstract: In one embodiment a computer system comprises one or more processors and a memory module communicatively connected to the one or more processors. The memory module comprises logic instructions which, when executed on the one or more processors configure the one or more processors to receive an interrupt in an execution thread of a process executing at an application layer of an operating system, intercept the interrupt in a profiling collector module invoked directly from a raw machine state, execute a profiling collection process, and return control from the interrupt to the execution thread when the profiling collection process is complete.

Abstract: In one embodiment a computer system comprises one or more processors and a memory module communicatively connected to the one or more processors. The memory module comprises logic instructions which, when executed on the one or more processors configure the one or more processors to receive an interrupt in an execution thread of a process executing at an application layer of an operating system, intercept the interrupt in a profiling collector module invoked directly from a raw machine state, execute a profiling collection process, and return control from the interrupt to the execution thread when the profiling collection process is complete.

Abstract: Embodiments include methods, apparatus, and systems for profiling metrics for computer programs. One embodiment includes a method that executes a program to obtain data for each of plural entities in the program. Equations are received for plural metrics that define events occurring in the entities. The method then displays scores for each of the entities with respect to each of the metrics in order to visually indicate which of the entities to optimize to improve performance of the program.

Abstract: In one embodiment, a computer system comprises one or more processors, and a memory module communicatively connected to the one or more processors. The memory module comprises logic instructions stored on a computer readable medium which, when executed on the one or more processors configure the one or more processors to normalize data from a first data set comprising sample based profiling data to form a first normalized data set, normalize data from a second data set comprising sample based profiling data to form a second normalized data set, combine the first normalized data set and the second normalized data set to form a merged data set, and present a portion of the merged data set on a user interface.

Abstract: A method of lost-cycle measurement using a cycle counter. In some embodiments, the lost-cycle measurement method comprises: getting a current cycle counter value; finding a number of elapsed cycles between the current cycle counter value and a preceding cycle counter value; determining whether the number of elapsed cycles is indicative of lost cycles; and repeating.

Abstract: Data is received from a plurality of processes of a distributed computing arrangement. The computing arrangement contains a plurality of processing nodes. In a first processing node of the plurality of processing nodes data objects are received from a subset of the plurality of processes. A set of non-responsive processes of the plurality of processes is determined based on arrival times of the data objects relative to a current time. The data objects are aggregated into a set of data objects without waiting for data objects associated with the non-responsive processes. The set of data objects are sent to a second processing node of the plurality of processing nodes.