Fujitsu Corporation

Jim Enright

Nicholas Wilson

Michael Li

A system for executing simulation jobs including: a job scheduler receiving a job request from a system user, the request specifying a simulation job and user-defined resource settings for the job; computing hardware resources executing simulation jobs designated by the scheduler which instructs the resources to execute the job with the settings; a performance monitor generates performance statistics; a statistics memory stores a characterization, the settings, and performance statistics for the job; an alert generator determines jobs similar to the specified job, to identify a first job having the same characterization as a second job, and for which the settings differ between the jobs, determining an improved performance statistic in one of the first and second jobs relative to the other, to generate an alert to the user indicating the resource settings of the job identified as having improved performance statistics.

System, controller, method, and program for executing simulation jobs

A method of producing a benchmark application for testing input/output&#x2014;I/O&#x2014;settings of a computer application, the method comprising: compiling trace data relating to operations to be executed by the computer application; grouping the trace data into one or more phases, based on different stages in the execution of the computer application to which the operations relate; identifying patterns in the trace data and comparing the patterns; producing simplified trace data in which trace data having similar patterns are combined; and outputting a benchmark application which includes the simplified trace data and information indicating where the trace data have been combined.

Method and apparatus for producing a benchmark application for performance testing

A method of job scheduling in a computing environment, comprising collecting historical job data related to job submissions received from a plurality of users, the historical job data comprising: resource request data indicative of resources requested by the user for executing a job, and resource usage data indicative of actual resources used to execute the job; calculating a believability score for each of the plurality of users based on a comparison between the job resource request data and the resource usage data related to job submissions received from the user, the believability score indicating a degree to which the user overestimates resources required to execute jobs; receiving a new job submission from a user, specifying a new job that is to be executed and resources requested by the user for executing the new job; and scheduling the new job for execution based on the believability score for the user.

Job scheduling based on historical job data

A method of porting source code for use in a runtime environment including a tool chain with a compiler for building the source code, in which the method comprises obtaining a source code fragment associated with a build error during the source code build in the runtime environment; creating a signature of the source code fragment; automatically comparing the signature with entries in an error database constructed from a history of previous build errors in the runtime environment and their fixes in the form of source code and/or tool chain modifications; using the comparison to find one or more similar previous build errors to the build error and thus to identify one or more of the source code and/or tool chain modifications as candidate solutions to the build error; compiling the source code with each of the candidate source code and/or tool chain modifications in turn until the source code compiles without reproducing the build error; and storing the build error in the error database and storing the modification with which the source code compiles without reproducing the build error as its fix.

Growing community of inventors

Slough, United Kingdom

Jim Enright