International Business Machines Corporation

Globalfoundries Inc.

Norman Bobroff

Peter Hans Westerink

Arun Kwangil Iyengar

Liana Liyow Fong

Andrzej P Kochut

Seetharami R Seelam

Yanbin Liu

Michael H Dawson

Kirk Alan Beaty

Alan Edward Rosenbluth

Martin J Hirzel

Rodney A Kendall

Todd W Mummert

Fabio Benedetti

Gautam Kar

Alan Braz

Peter Hans Westernick

Michael Hilton Dawson

Gunjan Khanna

Techniques facilitating guiding machine learning models and related components are provided. In one example, a computer-implemented method comprises identifying, by a device operatively coupled to a processor, a set of models, wherein the set of models includes respective model components; determining, by the device, one or more model relations among the respective model components, wherein the one or more model relations respectively comprise a vector of component relations between respective pairwise ones of the model components; and suggesting, by the device, a subset of the set of models based on a mapping of the component relations.

Guiding machine learning models and related components

A method, information processing system, and computer readable storage medium, periodically monitor, with a processing system, information related to an application's memory usage including a maximum heap memory size and a garbage collection activity level. Based on determining that the garbage collection activity level is below a first threshold, releasing memory from the application by reducing the maximum heap memory size.

Computer memory usage by releasing unused heap space

A method, information processing system, and computer readable storage medium, periodically monitor, with a processing system, information related to an application's memory usage including a maximum heap memory size, an in use heap memory size, and a garbage collection activity level. Based on determining that the garbage collection activity level is below a first threshold, estimating an amount of memory that can be released from the application by reducing the maximum heap memory size. Based on determining that the estimated amount of memory that can be released from the application is above a second threshold, attempting to release memory from the application.

Memory use for garbage collected computer environments

A method, information processing system, and computer readable storage medium, vary a maximum heap memory size for one application of a plurality of applications based on monitoring garbage collection activity levels for the plurality of applications, each application including a heap memory, and unused memory in the heap memory being reclaimed by a garbage collector.

Optimizing memory usage across multiple applications based on garbage collection activity

A method and structure for dynamic memory re-allocation for an application runtime environment (ARE) includes receiving, through an interface of an application runtime environment (ARE), a first set of internal operational metrics of the ARE executing at a current setting S1 on a processor of a computer. A first performance P1 of the ARE is determined at the current setting S1 using the received first set of internal operation metrics. The current setting S1 of the ARE is varied to a new setting S2. A second set of internal operational metrics of the ARE executing at the new setting S2 is received through the interface of the ARE. A second performance P2 of the ARE is determined at the new setting S2, using the received second set of internal operation metrics. A memory allocation for the ARE is re-allocated, based on the determined performances P1 and P2.

Active control of memory for java virtual machines and other application runtime environments

Optimizing memory usage across multiple applications in the presence of garbage collection

Optimizing memory usage across multiple garbage collected computer environments

An apparatus includes at least one processor executing a method for managing memory among a plurality of concurrently-running virtual machines, and a non-transitory memory device that stores a set of computer readable instructions for implementing and executing said memory management method. A memory optimization mechanism can reduce a memory usage of a virtual machine at a cost of increasing a central processing unit (CPU) usage. Information on a memory usage and a CPU usage of each virtual machine is periodically collected. When a first virtual machine exhibits high memory use, at least one second virtual machine with an extra CPU capacity is identified. A memory optimization mechanism is applied to the second virtual machine to reduce memory used by the second virtual machine, thereby providing a portion of freed memory that is then allocated to the first virtual machine.

System and method for improving memory usage in virtual machines at a cost of increasing CPU usage

A method for allocating memory among a plurality of computing systems includes assigning a free memory threshold to each computing system, dynamically varying at least one free memory threshold for at least one computing system based on a past memory usage of the at least one computing system, periodically monitoring each computing system for memory usage and in response to the monitoring determining that an amount of free memory for the computer system is below the free memory threshold for the computing system, allocating memory from the free memory pool to the computing system.

Dynamically optimizing memory allocation across virtual machines

A method and structure for dynamic memory re-allocation for an application runtime environment (ARE) includes receiving, through an interface of an application runtime environment (ARE), a first set of internal operational metrics of the ARE executing at a current setting Son a processor of a computer. A first performance Pof the ARE is determined at the current setting Susing the received first set of internal operation metrics. The current setting Sof the ARE is varied to a new setting S. A second set of internal operational metrics of the ARE executing at the new setting Sis received through the interface of the ARE. A second performance Pof the ARE is determined at the new setting S, using the received second set of internal operation metrics. A memory allocation for the ARE is re-allocated, based on the determined performances Pand P

A method (and system) for managing memory among virtual machines in a system having a plurality of virtual machines, includes providing at least one memory optimization mechanism which can reduce memory usage of a virtual machine at a cost of increasing CPU usage. Information on memory usage and CPU usage of each virtual machine is periodically collected. In response to detecting that a first virtual machine exhibits a high level of memory use, at least one second virtual machine with extra CPU capacity is identified. The at least one memory optimization mechanism is applied to the at least one second virtual machine, to reduce memory used by the at least one second virtual machine, thereby providing a portion of freed memory. The portion of freed memory is then allocated to the first virtual machine.

System and method improving memory usage in virtual machines by releasing additional memory at the cost of increased CPU overhead

System and method for improving memory usage in virtual machines

Methods and apparatus are provided for evaluating potential resource capacity in a system where there is elasticity and competition between a plurality of containers. A dynamic potential capacity is determined for at least one container in a plurality of containers competing for a total capacity of a larger container. A current utilization by each of the plurality of competing containers is obtained, and an equilibrium capacity is determined for each of the competing containers. The equilibrium capacity indicates a capacity that the corresponding container is entitled to. The dynamic potential capacity is determined based on the total capacity, a comparison of one or more of the current utilizations to one or more of the corresponding equilibrium capacities and a relative resource weight of each of the plurality of competing containers. The dynamic potential capacity is optionally recalculated when the set of plurality of containers is changed or after the assignment of each work element.

Methods and apparatus for resource capacity evaluation in a system of virtual containers

A method, processing system, and computer readable storage medium, reduce heap memory used by an application, where unused memory in the heap memory is reclaimed by a garbage collector. A processor periodically monitors the application's memory usage including maximum heap memory size, committed heap memory size, in use heap memory size, and a garbage collection activity level. The processor, based on determining that the monitored garbage collection activity level is below a threshold, releases unused heap memory from the application by reducing the maximum heap memory size.

Growing community of inventors

Katonah, NY, United States of America

Norman Bobroff