Abstract: Disclosed embodiments provide a virtual topology in response to an allocation request. The virtual topology is a synchronized subgraph of the physical topology. The synchronized subgraph virtual topology mirrors the physical topology in terms of tree structure. However, merely sharing the physical topology with users/customers is not feasible, as it may reveal additional infrastructure details such as MAC addresses, IP addresses, and the like, that can compromise security and/or jeopardize multi-tenant operations. Disclosed embodiments create virtual topology structures with obfuscated node data, so that important data such as physical IP addresses and/or MAC addresses are hidden from the end-users. Thus, disclosed embodiments provide the benefits of performance enhancement that comes from sharing the topology without the downside of compromising security by revealing physical topology details.

Abstract: Approaches presented herein enable provisional scheduling of resources in a cloud computing environment. More specifically, a first group request to host an application is obtained. This first group request includes one or more virtual units, which each have one or more topological constraints. One or more resources are scheduled for each of the virtual units. This scheduling includes provisionally allocating the resources to each of the virtual units according to the topological constraints. Each resource comprises a respective weight. In response to obtaining a second group request, the resources are provisionally re-allocated to one or more virtual units of the second group request according to one or more topological constraints of the second group request and the respective weight of each of the resources. This re-allocating minimizes a summation of each respective weight of the resources. A new respective weight is then assigned to each of the resources.

Abstract: Disclosed embodiments provide a virtual topology in response to an allocation request. The virtual topology is a synchronized subgraph of the physical topology. The synchronized subgraph virtual topology mirrors the physical topology in terms of tree structure. However, merely sharing the physical topology with users/customers is not feasible, as it may reveal additional infrastructure details such as MAC addresses, IP addresses, and the like, that can compromise security and/or jeopardize multi-tenant operations. Disclosed embodiments create virtual topology structures with obfuscated node data, so that important data such as physical IP addresses and/or MAC addresses are hidden from the end-users. Thus, disclosed embodiments provide the benefits of performance enhancement that comes from sharing the topology without the downside of compromising security by revealing physical topology details.

Abstract: Systems and techniques that facilitate backend quantum runtimes are provided. In various embodiments, a system can comprise a memory that can store computer-executable components. The system can further comprise a processor that can be operably coupled to the memory and that can execute the computer-executable components stored in the memory. In various embodiments, the computer-executable components can comprise an execution orchestration engine component that can parse a computer program into classical and quantum portions and that can host the computer program by instantiating a classical computing resource.

Abstract: Embodiments relate to a system, program product, and method for supporting elastic execution of a machine learning (ML) workload using application based profiling. A joint profile comprised of both ML application execution and resource usage data is generated. One or more feature(s) and signature(s) from the joint profile are identified, and a ML execution model for ML application execution and resource usage is built. The ML execution model leverages the feature(s) and signature(s) and is applied to provide one or more directives to subsequent application execution. The application of the ML execution model supports and enables the ML execution to elastically allocate and request one or more resources from a resource management component, with the elastic allocation supporting application execution.

Abstract: Methods and systems for controlling process priority for one or more work units having one or more processes. The method includes monitoring a combination of a throughput value and a response time value for each work unit, detecting a change in load level for each work unit based on a correlation between the throughput value and the response time value to adjust a priority level associated with the work unit, and reallocating one or more resources to the work unit when the priority level exceeds a predetermined threshold value.

Abstract: Systems, computer-implemented methods, and computer program products that facilitate identifying computer software vulnerabilities, and more specifically, execute an approximate representation of software to produce a fingerprint are provided. In one example, a system is provided. The system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can include a filter component and an execution component. The filter component can filter a platform-independent intermediate representation to a filtered representation. The execution component can execute the filtered representation on a virtual machine to produce an output vector which can be used to identify computer software vulnerabilities.

Abstract: Embodiments relate to a system, program product, and method for supporting elastic execution of a machine learning (ML) workload using application based profiling. A joint profile comprised of both ML application execution and resource usage data is generated. One or more feature(s) and signature(s) from the joint profile are identified, and a ML execution model for ML application execution and resource usage is built. The ML execution model leverages the feature(s) and signature(s) and is applied to provide one or more directives to subsequent application execution. The application of the ML execution model supports and enables the ML execution to elastically allocate and request one or more resources from a resource management component, with the elastic allocation supporting application execution.

Abstract: Embodiments for data caching and data-aware placement for machine learning by a processor. Data may be cached in a distributed data store to one or more local compute nodes of cluster of nodes with the cached data. A new job may be scheduled, according to cache and data locality awareness, on the one or more local compute nodes with the cached data needed for execution.

Abstract: Systems, computer-implemented methods, and computer program products that facilitate identifying computer software vulnerabilities, and more specifically, execute an approximate representation of software to produce a fingerprint are provided. In one example, a system is provided. The system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can include a filter component and an execution component. The filter component can filter a platform-independent intermediate representation to a filtered representation. The execution component can execute the filtered representation on a virtual machine to produce an output vector which can be used to identify computer software vulnerabilities.

Abstract: A method for reducing reactivation time of services that includes examining page faults that occur during processing of a service after the service has been inactive to provide a plurality of prefetch groups, and formulating a prefetch decision tree from page fault data in the prefetch groups. Pages from an initial page table for the service following a reactivated service request are then compared with the prefetched pages in the resident memory in accordance with the prefetch decision tree. Pages in the page table that are not included in said prefetched pages are paged in. A process to provide to provide the service is executed using the page table. Executing the process substantially avoids page faults.

Abstract: A method, information processing system, and computer program product are provided for managing operating system interference on applications in a parallel processing system. A mapping of hardware multi-threading threads to at least one processing core is determined, and first and second sets of logical processors of the at least one processing core are determined. The first set includes at least one of the logical processors of the at least one processing core, and the second set includes at least one of a remainder of the logical processors of the at least one processing core. A processor schedules application tasks only on the logical processors of the first set of logical processors of the at least one processing core. Operating system interference events are scheduled only on the logical processors of the second set of logical processors of the at least one processing core.

Abstract: Embodiments for data caching and data-aware placement for machine learning by a processor. Data may be cached in a distributed data store to one or more local compute nodes of cluster of nodes with the cached data. A new job may be scheduled, according to cache and data locality awareness, on the one or more local compute nodes with the cached data needed for execution.

Abstract: Methods and systems for controlling process priority for one or more work units having one or more processes. The method includes monitoring a combination of a throughput value and a response time value for each work unit, detecting a change in load level for each work unit based on a correlation between the throughput value and the response time value to adjust a priority level associated with the work unit, and reallocating one or more resources to the work unit when the priority level exceeds a predetermined threshold value.

Abstract: A method for reducing reactivation time of services that includes examining page faults that occur during processing of a service after the service has been inactive to provide a plurality of prefetch groups, and formulating a prefetch decision tree from page fault data in the prefetch groups. Pages from an initial page table for the service following a reactivated service request are then compared with the prefetched pages in the resident memory in accordance with the prefetch decision tree. Pages in the page table that are not included in said prefetched pages are paged in. A process to provide to provide the service is executed using the page table. Executing the process substantially avoids page faults.

Abstract: A method for reducing reactivation time of services that includes examining page faults that occur during processing of a service after the service has been inactive to provide a plurality of prefetch groups, and formulating a prefetch decision tree from page fault data in the prefetch groups. Pages from an initial page table for the service following a reactivated service request are then compared with the prefetched pages in the resident memory in accordance with the prefetch decision tree. Pages in the page table that are not included in said prefetched pages are paged in. A process to provide to provide the service is executed using the page table. Executing the process substantially avoids page faults.

Abstract: Various embodiments monitor system noise in a parallel computing system. In one embodiment, at least one set of system noise data is stored in a shared buffer during a first computation interval. The set of system noise data is detected during the first computation interval and is associated with at least one parallel thread in a plurality of parallel threads. Each thread in the plurality of parallel threads is a thread of a program. The set of system noise data is filtered during a second computation interval based on at least one filtering condition creating a filtered set of system noise data. The filtered set of system noise data is then stored.

Abstract: Using a metadata of a layer, a prediction factor including a level of participation of the layer in a set of container images is computed. Each container image includes a corresponding set of layers and is usable to configure a container in a container-based virtualized data processing environment. Using a set of levels of participation corresponding to a set of layers, and using a condition in a prediction algorithm, a subset of layers that have to be pre-provisioned at a node is predicted. The subset of layers is adjusted, to form an adjusted subset of layers, by looking ahead at a container requirement of a workload that is planned for processing at a future time. The adjusted subset of layers is caused to be provisioned on the node prior to the future time.

Abstract: A data processing system includes a plurality of virtual machines each having associated memory pages; a shared memory page cache that is accessible by each of the plurality of virtual machines; and a global hash map that is accessible by each of the plurality of virtual machines. The data processing system is configured such that, for a particular memory page stored in the shared memory page cache that is associated with two or more of the plurality of virtual machines, there is a single key stored in the global hash map that identifies at least a storage location in the shared memory page cache of the particular memory page. The system can be embodied at least partially in a cloud computing system.

Abstract: Methods and systems for controlling process priority for one or more work units having one or more processes. The method includes monitoring a combination of a throughput value and a response time value for each work unit, detecting a change in load level for each work unit based on a correlation between the throughput value and the response time value to adjust a priority level associated with the work unit, and reallocating one or more resources to the work unit when the priority level exceeds a predetermined threshold value.