International Business Machines Corporation

Joran S C Siu

Michael K Gschwind

Christian Jacobi

Chung-Lung K Shum

Marcel Mitran

Aleksandar Micic

Irwin D'Souza

Filip Jeremic

Anthony Saporito

Giles R Frazier

Jose Nelson Amaral

Li Ding

Carolina Simoes Gomes

Evgenia Badiyanova

Timothy John Slegel

Dan F Greiner

Jonathan D Bradbury

William J Rooney

K Paul Muller

Vijay Sundaresan

Michael H Dawson

David S Wolpert

Mark Graham Stoodley

Timothy J Siegel

Younes Manton

Charles Robert Gracie

Zhong Liang Wang

Kenneth Blair Kent

Alexander A Vasilevskiy

Kishor V Patil

Panos Patros

Dmitri Pivkine

Sujit Bhandari

Maria Patrou

A value profiling method, system and computer program product that leverages a guarded storage facility. During code execution, a first instruction is loaded. The first instruction has a first value designating a first region of memory and the first instruction is related to a first section of the code. A determination is made as to whether a guarded mode is enabled at the first region. Responsive to an enabled guarded mode at the first region, a secondary operation is triggered. The secondary operation is in addition to a primary operation of the first instruction. The primary operation is relative to the first region of the memory. The secondary operation causes a profiling of the first section of the code.

Software-directed value profiling with hardware-based guarded storage facility

A method manages a cluster. A computer system determines a measurement of a process variable for the cluster, wherein the process variable indicates a quality of service for the cluster. The computer system determines a comparison between the measurement of the process variable and a desired value for the process variable. The computer system determines an adjustment to a setpoint for a runtime metric in the cluster based on the comparison, wherein the runtime metric is a control variable for the cluster. The computer system updates the setpoint for the runtime metric in a controller for the cluster using the adjustment, wherein the runtime metric is used by the controller as the control variable to scale a set of resources in the cluster to cause a value of the runtime metric to move towards the setpoint.

Automatic cluster scaling based on varying workloads

Systems and methods for object load introspection using guarded storage are disclosed. In embodiments, a computer-implemented method includes: determining objects of interest designated by a user; splitting a first subset of a predetermined memory heap into guarded regions based on a number of objects of interest; allocating each of the objects of interest to a respective one of the guarded regions and remaining objects to a second subset of the predetermined memory heap; executing a program; detecting one of the objects of interest is loaded from one of the guarded regions; generating a trap that transfers control of the executing the program to a signal handler, wherein the signal handler is designated to perform a user-defined task associated with the one of the objects of interest; and executing, by the signal handler of the computing device, the user-defined task.

Object load introspection using guarded storage

An approach for optimizing a copying of a data object in a concurrent copying garbage collection operation is provided. In an embodiment, a source copy of the data object to be copied as part of the garbage collection operation is identified. A copying of the source copy to a target location is initiated by a primary accessing thread. This initiating of the copying includes the creation of a temporary target object header for the target object in the target location that contains an indicator set to indicate that the copying is ongoing. As the copying is occurring, the execution of any other accessing threads that are attempting to use the data object are held for as long as the indicator indicates that the copying is ongoing. Once the copying has completed, the target object header is replaced with a copy of the source object header, resetting the indicator.

Copying and forwarding for concurrent copying garbage collection

Embodiments relate to lightweight interrupts for condition checking. An aspect includes determining, by a condition checker in a computer system, that a condition occurs for an application executing on the computer system. Another aspect includes, based on determining that the condition occurs for the application, determining whether lightweight interrupts are enabled. Yet another aspect includes based on determining that lightweight interrupts are enabled, issuing a lightweight interrupt to the application and handling the instruction by the application.

Lightweight interrupts for condition checking

A multiple processor core computer system interface assigns instructions to partially functional processor cores based on processing resources available in each partially functional core. Each processor core is labeled as fully functional, partially functional, or non-functional, and an indicator is provided for each partially functional processor core that shows what processing resources are available for a respective core. The indicators can be stored in memory after final test. The interface can monitor cores for changes in available resources and update respective indicators, such as by superseding an existing indicator with or creating a new indicator in read-write memory.

Computer system using partially functional processor core

Techniques relate to automated compiler operation verification. In response to performing an optimization to a compiler configured to execute on a processor of a computer system, a determination is made of whether a fingerprint is present in software that is currently executing on the processor of the computer system. The software is compiled by the compiler, and the fingerprint comprises a representation of a sequence of behavior that occurs on the processor while the software is executing. The fingerprint is configured to correspond to the optimization of the compiler. In response to determining that the fingerprint is not present in the software currently executing on the processor, a determination is made that optimization to the compiler has not occurred. In response to determining that the fingerprint is present in the software executing on the processor, a verification is made that the optimization of the compiler has occurred.

Automated compiler operation verification

According to some embodiments, a method for controlling a processor state with transient cache memory is described. The method may include identifying, via a processor, a memory section having a memory address, retrieving, via the processor, memory control information, and controlling the processor state by allowing a memory access to the transient cache memory based on the memory control information.

Dynamic management of a processor state with transient cache memory

Embodiments are directed to identifying, by an apparatus comprising a processing device, a pattern in a graph that has a support value greater than a threshold, wherein: the graph comprises a plurality of weighted nodes coupled to one another by one or more weighted edges, and each of the plurality of nodes is associated with at least one weighted attribute.

Identification of performance bottlenecks

One embodiment of a method for eliminating redundant operations establishing common properties includes identifying a first virtual register storing a first value having a common property. The method may assign the first virtual register to use a real register. The method may further identify a second virtual register storing a second value also having the common property. The method may assign the second virtual register to use the same real register after the first value is no longer live. As a result of assigning the second virtual register to the first real register, the method may eliminate an operation configured to establish the common property for the second virtual register since this operation is redundant and is no longer needed.

Eliminating redundant operations for common properties using shared real registers

Systems, methods, and computer products for evaluating robustness of a list scheduling framework. Exemplary embodiments include a method for evaluating the robustness of a list scheduling framework, the method including identifying a set of compiler benchmarks known to be sensitive to an instruction scheduler, running the set of benchmarks against a heuristic under test, H and collect an execution time Exec(H[G]), where G is a directed a-cyclical graph, running the set of benchmarks against a plurality of random heuristics H[G], and collect a plurality of respective execution times Exec(H[G]), computing a robustness of the list scheduling framework, and checking robustness check it against a pre-determined threshold.

Methods, systems, and computer products for evaluating robustness of a list scheduling framework

Growing community of inventors

Thornhill, Canada

Joran S C Siu