International Business Machines Corporation

Robert John Urquhart

Frank Eliot Levine

Jimmie Earl DeWitt, Jr

Christopher Michael Richardson

Robert Tod Dimpsey

William Preston Alexander, Iii

Robert Francis Berry

Riaz Yousuf Hussain

Enio Manuel Pineda

Chester Charles John, Jr

John Day Howard

Jesse Mannes Gordon

Scott Thomas Jones

Kean G Kuiper

William Robert Reynolds

Milena Milenkovic

Geoffrey Owen Blandy

Michael Richard Fortin

Larry K Loucks

Virgil Anthony Albaugh

Mary Susan Neff

Ronald O'Neal Edmark

Phani Achanta

Donald Lawrence Mulvey

Khoa D Nguyen

Maher Afif Saba

David A Garrison

Susan C Williams

Gary Michael Beauregard

James K Landis

Veronica A Bonebrake

Vance R Bass

Michael Terrell Vanover

Thomas W Keller, Jr

Luc Rene Smolders

Weiming Gu

Phani Gopal V Achanta

Raymond Morris Bryant

John A Voltin

Paul Jerome Kilpatrick

William Presten Alexander, Iii

Clive Richard Kates

Mamata Misra

Virgil A Albaugh

A method and apparatus for identifying a minimum call tree data structure from a plurality of call tree data structures are provided. With the apparatus and method, call tree data structures are generated for two or more executions of a build of a computer program. The apparatus and method perform a 'tree-minimization' operation in which the two or more call trees generated during runs of the computer program are walked and only those nodes that are present in each of the tree data structures are maintained in a minimized tree data structure. In addition, the minimum values for these common nodes are maintained in the minimized tree data structure. In this way, asynchronous events are removed from the minimum tree data structure and analysis may focus on those areas of the computer program that are consistent between runs of the computer program.

Removal of asynchronous events in complex application performance analysis

Hardware assist to autonomically patch code. The present invention provides hardware microcode to a new type of metadata to selectively identify instructions to be patched for specific performance optimization functions. The present invention also provides a new flag in the machine status register (MSR) to enable or disable a performance monitoring application or process to perform code-patching functions. If the code patching function is enabled, the application or process may patch code at run time by associating the metadata with the selected instructions. The metadata includes pointers pointing to the patch code block code. The program code may be patched autonomically without modifying original code.

Autonomic hardware assist for patching code

A data processing system for processing instructions is shown. Instructions are received at a processor in the data processing system. If a selected indicator is associated with the instruction, counting of each event associated with the execution of the instruction is enabled.

Counting instruction execution and data accesses

A method, apparatus, and computer instructions for qualifying events by types of interrupt when interrupt occurs in the processor of a data processing system. A programmable performance monitoring unit (PMU) is used to program hardware counters that collect events associated with a type of interrupt, including nested interrupts. The performance monitoring unit may also count events that occur while servicing interrupt requests based upon the state of interrupt processing. Events that are known to the performance monitoring unit such as instruction retired, TLB misses, may be counted at the same time using a number of performance monitoring counters in the performance monitoring unit.

Qualifying collection of performance monitoring events by types of interrupt when interrupt occurs

A method, apparatus, and computer instructions in a processor for selectively performing operations on data. An operation to be performed on data is identified to form an identified operation. A determination is made as to whether metadata identifying a state of the data is associated with the data. A determination is made as to whether the identified operation can be performed on the data based on the state of the data, in response to the metadata being associated with the data. The operation is performed on the data if the state of the data allows for the operation to be performed. The processor selectively performs the operations based on the state of the data.

Identifying access states for variables

A method, an apparatus, and a computer program product in a data processing system are presented for using hardware assistance for gathering performance information that significantly reduces the overhead in gathering such information. Performance indicators are associated with instructions or memory locations, and processing of the performance indicators enables counting of events associated with execution of those instructions or events associated with accesses to those memory locations. The performance information that has been dynamically gathered from the assisting hardware is available to the software application during runtime in order to autonomically affect the behavior of the software application, particularly to enhance its performance. For example, the counted events may be used to autonomically control an execution-path selection within the software application.

Method and system for autonomic execution path selection in an application

Illustrative embodiments cover a data processing system for processing instructions and monitoring accesses to memory location ranges. An instruction for execution is identified. A determination is made as to whether the instruction is within a contiguous range of instructions. Execution information relating to the instruction is identified if the instruction is within the contiguous range of instructions. With memory location accesses, an access to a memory location is identified. A determination of whether the memory location is within a contiguous range of memory locations is made. Access information is identified if the memory location is within the contiguous range of memory locations.

Counting instruction and memory location ranges

A method and apparatus for automatically performing regression processing on trace data are provided. With the apparatus and method, call tree data structures are generated for two or more executions of two or more builds of a computer program. The apparatus and method perform a 'tree-minimization' operation on each set of call tree data structures for each of the builds to generate minimized call tree data structures for each build of the computer program. The minimized call tree data structures are then subtracted from one another to generate a subtracted minimized call tree data structure. From this subtracted minimized call tree data structure, the portions of the computer program that are different from build to build and which appreciably and consistently affect the difference in execution of the computer program from build to build may be identified. Thus, the analyst's attention is directed to these areas of the computer program code which may be optimized in order to obtain better execution of the computer program.

Method for automatic detection of build regressions

Illustrative embodiments disclose presenting coverage data relating to data access occurring during execution of code. The coverage data containing data access indicators associated with memory locations is obtained. The data access indicators that have been set by a processor in the data processing system in response to access of the memory locations during execution of the code by the processor are identified to form set data access indicators. Each set instruction access indicator is associated with a portion of the memory locations allocated for the code. A presentation for coverage data is generated, wherein the set data access indicators are identified in the presentation.

Autonomic test case feedback using hardware assistance for data coverage

Autonomic method and apparatus for hardware assist for patching code

A method, apparatus, and computer instructions for providing hardware assistance to prefetch data during execution of code by a process or in the data processing system. In response to loading an instruction in the code into a cache, a determination is made by a processor unit as to whether a prefetch indicator is associated with the instruction. In response to the prefetch indicator being associated with the instruction, a pointer to a data structure identified by the prefetch indicator is selectively prefetched into the cache in the processor.

Method and apparatus for hardware assistance for prefetching a pointer to a data structure identified by a prefetch indicator

A method, an apparatus, and a computer program product in a data processing system are presented for using hardware assistance for gathering performance information that significantly reduces the overhead in gathering such information. Performance indicators are associated with instructions or memory locations, and processing of the performance indicators enables counting of events associated with execution of those instructions or events associated with accesses to those memory locations. The performance information that has been dynamically gathered from the assisting hardware is available to the software application during runtime in order to autonomically affect the behavior of the software application, particularly to enhance its performance. For example, the counted events may be used to autonomically collecting statistical information about the ability of a software application to successfully acquire a semaphore.

Method and system for autonomic monitoring of semaphore operations in an application

A method, apparatus, and computer instructions for determining computer flows autonomically using hardware assisted thread stack and cataloged symbolic data. When a new thread is spawned during execution of a computer program, new thread work area is allocated by the operating system in memory for storage of call stack information for the new thread. Hardware registers are set with values corresponding to the new thread work area. Upon context switch, values of the registers are saved in a context save area for future restoration. When call stack data is post-processed, the operating system or a device driver copies call stack data from the thread work areas to a consolidated buffer and each thread is mapped to a process. Symbolic data may be obtained based on the process identifier and address of the method/routine that was called/returned in the thread. Corresponding program flow is determined using retrieved symbolic data and call stack data.

Method and apparatus for determining computer program flows autonomically using hardware assisted thread stack tracking and cataloged symbolic data

A method, apparatus, and computer instructions in a data processing system for monitoring the execution of instructions and accesses to memory locations. If an instruction is associated with a indicator, a counter associated with the instruction is incremented in response to detecting execution of the instruction. The indicator may be associated with a memory location with a counter associated with the memory location being incremented in response to an access of the memory location.

Method and apparatus for counting execution of specific instructions and accesses to specific data locations

Growing community of inventors

Austin, TX, United States of America

Robert John Urquhart