Abstract: One or more embodiments of the invention facilitate displaying application icons of a guest environment in a host environment of a mobile device, wherein the guest environment is running in a virtual machine supported by a hypervisor running within the host environment. One method comprises forwarding, by a hypervisor-aware service running in the virtual machine to the hypervisor, a list of applications installed in a guest operating system (OS) of the virtual machine. For each of the installed applications, the hypervisor provides metadata to a host OS running in the host environment, wherein the metadata comprises an application icon and an instruction to launch a proxy application installed in the host environment. Upon a launch of the proxy application when a user selects the application icon, the proxy application requests the hypervisor to communicate with the hypervisor-aware service to launch the installed application in the guest environment.

Abstract: Systems and methods relate to indexing of performance and cost of workloads in a computing environment. The computing environment may include a virtualized computing environment. According to some embodiments, a performance index relating to a plurality of workloads executing in the computing environment may be generated, where the performance index is based at least in part on performance and cost of use of one or more resources in the computing environment by the plurality of workloads. The index may be normalized. If the performance or cost of a particular workload departs from an expected performance or cost determined from the average performance and/or cost in the computing environment, resources may be reallocated to the workloads such that the performance or cost of the workload is closer to its expected performance or cost based on the performance index.

Abstract: A technique for predictive distributed resource scheduling and distributed power management includes analyzing patterns in the workload, predicting future workloads, and making recommendations for changes to the virtual computing environment. In addition, a cost-benefit analysis can be performed to determine whether the recommended change would likely result in improved performance.

Abstract: In a multiple computer environment, workloads are classified as first-class or second-class, depending on their priorities. The workloads are profiled to determine computer capabilities that they are expected to use. Based upon this information, second-class workloads are chosen for execution alongside first-class workloads in such a way that the expected capabilities used by the first-class and second-class workloads are complementary.

Abstract: Scheduling threads in a multi-threaded/multi-core processor having a given instruction window, and scheduling a predefined number N of threads among a set of M active threads in each context switch interval are provided. The actual power consumption of each running thread during a given context switch interval is determined, and a predefined priority level is associated with each thread among the active threads based on the actual power consumption determined for the threads. The power consumption expected for each active thread during the next context switch interval in the current instruction window (CIW_Power_Th) is predicted, and a set of threads to be scheduled among the active threads are selected from the priority level associated with each active thread and the power consumption predicted for each active thread in the current instruction window.

Abstract: Systems and methods are disclosed for assigning an I/O resource to a virtual PCI device. An example system includes an I/O resource table that stores a pool of one or more available I/O resources for assignment to one or more virtual PCI devices. The system also includes a hypervisor that maintains the pool of I/O resources, assigns one or more I/O resources from the pool to a virtual PCI device, and notifies a guest running on a virtual machine that the one or more I/O resources is assigned to the virtual PCI device. The hypervisor and virtual machine are executable on a host, and the virtual PCI device is exposed to the guest.

Abstract: A management device includes: a memory; and a processor coupled to the memory. The processor executes a process including: storing therein an assignment table including first assignment information indicating whether a job is assigned to the information processing devices and second assignment information indicating that a job is constantly assigned to virtual information processing devices arranged at ends of a connection relation of the information processing devices; searching regions in which idle information processing devices assigned with no job are arranged continuously, using the assignment table stored at the storing; specifying a region appropriate for assignment of a job as an assignment target among the regions searched by the searching; and assigning the job as the assignment target to the region specified by the specifying.

Abstract: Techniques for reclaiming resources from guest computing systems while those systems are waiting for responses to requests in virtualized and/or distributed computer systems are described herein. At a time after issuing a request and determining that the response will take longer than a threshold length of time, one or more computer system entities within a computer system invoke one or more computer system capabilities to at least instantiate a listener object, transfer the listener object to another system domain, suspend the guest computing system and reclaim resources from the suspended guest computing system. When the response is returned to the listener object, the guest computer system is restored and the response is forwarded to the restored guest. While the guest computing system is suspended, the reclaimed resources are made available to other computer system entities.

Abstract: Systems and methods are described for analyzing and verifying distributed applications. In one embodiment, an application program is executed as independently executable components. During execution, redundant portions of application program data are aggregated. A property of the application program is verified using the aggregated application program data to represent code execution paths.

Abstract: Method to perform an operation, the operation comprising processing a first logical partition on a shared processor for the duration of a dispatch cycle, issuing, by a hypervisor, at a predefined time prior to completion of the dispatch cycle, a lightweight hypervisor decrementer (HDEC) interrupt specifying a cache line address buffer location in a virtual processor, and responsive to the lightweight HDEC, writing, by the shared processor, a set of cache line addresses used by the first logical partition to the cache line address buffer location in the virtual processor.

Abstract: The present invention relates to an apparatus and a method for validating application deployment topology in a cloud environment. There is provided an apparatus for validating application deployment topology in a cloud environment comprising: a topology skeleton generator configured to generate, based on multiple VMs and script packages running on the VMs created by a user and required to deploy an application as well as running order of script packages and data dependency between script packages set by the user, a topology skeleton that comprises at least scripts of script packages of respective VMs and running order of the script packages; and a simulator configured to simulate a runtime environment in the cloud environment at the apparatus, thereby validating the running order and data dependency with respect to the topology skeleton, wherein the simulator is installed in the apparatus by using a simulator installation package retrieved from the cloud environment.

Abstract: Provided are methods of determining success of a software process that includes multiple process operations, ones of which use multiple programs for execution. Such methods may include receiving a request to perform the software process. The request includes a process map that defines the process operations corresponding to the software process and process operation success criteria to determine the success or failure of ones of the process operations. The process operations are scheduled to be performed serial to one another according to the process map. Data corresponding to results of ones of the process operations is collected. Results of the data are evaluated to define whether the ones of the process programs executed successfully based on the process operation success criteria to determine if the software process is a success or a failure.

Abstract: Systems and methods for virtual machine data replication with shared resources. An example method may include: identifying resources that are shared across a plurality of virtual machines, storing a copy of the resources, receiving, an indication of a portion of virtual storage of a virtual machine to be replicated, determining that the portion of virtual storage is not included in the resources, in response to the determination, updating a replicated copy of the virtual machine in view of the portion of virtual storage, the replicated copy further including the resources that are shared across a plurality of virtual machines, determining an initialization efficiency metric in relation to the replicated copy, and in response to the determination that the initialization efficiency metric exceeds an efficiency threshold, storing a copy of the virtual storage.

Abstract: A computer system for managing the execution of threads including at least one central processing unit which performs interleaved execution of a plurality of threads throughout a plurality of virtual processors from said same central processing unit, and a handler for distributing the execution of the threads throughout the virtual processors. The computer system further includes means for classifying threads to be executed according to several predetermined types, and the handler for distributing the execution of threads directs each thread to be executed to a virtual processor according to the type thereof.

Abstract: Debugging and testing are aided by removing portions of software which are not relevant to a particular scenario. Upon replay, scenario behavior occurs. A reduction tool selects a function exercised during the replay, disables it to provide a test version of the software, replays the scenario to the test version to produce a candidate behavior, and compares the candidate behavior to the scenario behavior. When the candidate behavior matches the scenario behavior the tool removes the disabled function, thereby providing a reduced version of the software which is functionally equivalent to the full version but has fewer functions to manage. The tool may also remove unexercised code. Trimming unexercised code and reducing exercised but irrelevant code may be interleaved. Caching, dynamic uniform resource locator mapping, hypertext markup language code refactoring, and/or avoidance of certain random elements may also facilitate exhibiting, testing, or debugging web applications.

Abstract: A method comprising calculating for each agent, an average quality of tasks that were completed in the past by the agent; allocating tasks to the agents, wherein said allocating comprises selecting an agent to perform a task, the selection is based on the average quality of the agent; in response to the agent completing the task, computing a reward for the agent, wherein the reward is calculated according to a total contribution of the agent to the system by completing the task; whereby biasing said allocating to prefer allocating tasks to a first agent over a second agent, if a quality of the first agent is greater than a quality of the second agent, wherein said biasing is not dependent on prior knowledge of the qualities. Optionally, the agents choose whether or not to perform a task and an agent's quality affects the contributions of the agent performing tasks.

Abstract: Methods and systems for task timeouts as a function of input data size are disclosed. A definition of a task is received. The definition of the task indicates a set of input data for the task. A timeout duration for the task is determined based on the set of input data. The timeout duration varies with one or more characteristics of the set of input data. The execution of the task is initiated. The execution of the task is stopped if the execution of the task exceeds the timeout duration.

Abstract: Various embodiments provide techniques and constructs to improve execution speed of distributed iterative computation using heterogeneous specialized resources including, for example, processors and accelerators. Iteration over an arbitrary sub-graph without loop unrolling including for algorithms with data-dependent loop termination and large iteration counts, including as a result of nested iteration, are supported in a resource-efficient manner without adding vertices to a dataflow graph to represent iteration constructs. Instead, some or all of the existing vertices within the sub-graph that is to be iterated upon based on having additional and/or modified ports and channels associated with them.

Abstract: Various embodiments of the present disclosure provide techniques and mechanisms for providing a fast multi-level scheduler, implemented using a plurality of smaller schedulers, the plurality of smaller schedulers together performing the functions of a single conventional scheduler.

Abstract: Performance measurement of hardware accelerators, where one or more computer processors are operably coupled to at least one hardware accelerator, and a computer memory is operatively coupled to the one or more computer processors, including operating by the one or more processors the accelerator at saturation, submitting data processing tasks by the processors to the accelerator at a rate that saturates the data processing resources of the accelerator, causing the accelerator to decline at least some of the submitted tasks; and while the accelerator is operating at saturation, measuring by the processors accelerator performance according to a period of time during which the accelerator accepts a plurality of submitted tasks.