Abstract: A method and system for scheduling threads on simultaneous multithreaded processors are disclosed. Hardware and operating system communicate with one another providing information relating to thread attributes for threads executing on processing elements. The operating system determines thread scheduling based on the information.

Abstract: A computer-implemented method for filtering input/output communications of guest operating systems may include: 1) identifying a guest operating system running in a virtual machine, 2) creating an input/output filtering layer that resides outside the guest operating system, 3) intercepting, at the input/output filtering layer, an input/output communication involving the guest operating system, and then 4) performing a filtering operation on the input/output communication. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A technique for processing instructions in an electronic system is provided. In one embodiment, a processor of the electronic system may submit a unit of work to a queue accessible by a coprocessor, such as a graphics processing unit. The coprocessor may process work from the queue, and write a completion record into a memory accessible by the processor. The electronic system may be configured to switch between a polling mode and an interrupt mode based on progress made by the coprocessor in processing the work. In one embodiment, the processor may switch from an interrupt mode to a polling mode upon completion of a threshold amount of work by the coprocessor. Various additional methods, systems, and computer program products are also provided.

Abstract: Systems, methods and apparatus are provided through which in some embodiments healthcare imaging processing applications are allocated to computing resources in reference to criteria.

Abstract: A method that optimizes system performance using performance monitors is presented. The method gathers thread performance data using performance monitors for threads running on either a first ISA processor or a second ISA processor. Multiple first processors and multiple second processors may be included in a single computer system. The first processors and second processors can each access data stored in a common shared memory. The gathered thread performance data is analyzed to determine whether the corresponding thread needs additional CPU time in order to optimize system performance. If additional CPU time is needed, the amount of CPU time that the thread receives is altered (increased) so that the thread receives the additional time when it is scheduled by the scheduler. In one embodiment, the increased CPU time is accomplished by altering a priority value that corresponds to the thread.

Abstract: A method of managing resources in a virtual environment based on identifiers is disclosed. The method includes detecting an instantiation of a virtual machine and determining a delay value based on a unique identifier. The method also includes delaying an initiation of at least one support process for the virtual machine by the delay value.

Abstract: A method, information processing system, and computer readable medium for managing virtual machine imaging. The method includes receiving a request for an imaging operation associated with at least one virtual machine. A notification is sent to at least one operating system associated with the at least one virtual machine of the request for the imaging operation. The operating system is determined to be in a state for the virtual machine to be imaged. The request for the imaging operation is granting in response to determining.

Abstract: Embodiments of the invention provide systems and methods for managing an enabler and dependencies of the enabler. According to one embodiment, a method of managing an enabler can comprise requesting a management function via a management interface of the enabler. The management interface can provide an abstraction of one or more management functions for managing the enabler and/or dependencies of the enabler. In some cases, prior to requesting the management function metadata associated with the management interface can be read and a determination can be made as to whether the management function is available or unavailable. Requesting the management function via the management interface of the enabler can be performed in response to determining the management function is available. In response to determining the management function is unavailable, one or more alternative functions can be identified based on the metadata and the one or more alternative functions can be requested.

Abstract: Illustrative embodiments provide a computer implemented method, a data processing system and a computer program product for scalable scheduling of tasks in heterogeneous systems is provided. According to one embodiment, the computer implemented method comprises fetching a set of tasks to form a received input, estimating run times of tasks, calculating average estimated completion times of tasks, producing a set of ordered tasks from the received input to form a task list, identifying a machine to be assigned, and assigning an identified task from the task list to an identified machine.

Abstract: Systems and methods storing data for multi-threaded processing permit multiple execution threads to store data in a single first-in first-out (FIFO) memory. Threads are assigned to classes, with each class including one or more threads. Each class may be allocated dedicated entries in the FIFO memory. A class may also be allocated shared entries in the FIFO memory. The shared entries may be used by any thread. Data for a first thread may be stored in the FIFO memory while data for a second thread is read from the FIFO memory, even when the first thread and the second thread are not in the same class. The FIFO memory is shared between the threads to conserve die area, however each thread may be executed independently, as if each thread has a dedicated FIFO memory.

Abstract: Methods and systems are provided for unified job processing of interdependent heterogeneous tasks within a domain containing a plurality of nodes. Jobs containing components to be processed in the domain are submitted and are identified by type. A job control flow associated with the job type is identified and used to process the components of the job on various nodes within the domain. Multiple job control flows are handled simultaneously, and provisions are made for sharing common job components among jobs. The job control flow utilizes a finite state machine where a given instance of the finite state machine applies to a specific job type. The finite state machine can be expressed using extensible mark-up language schema.

Abstract: Methods and apparatus of locating an unauthorized virtual machine are disclosed. A virtual machine is registered with a management system. When the virtual machine is requested to start, the system determines whether the virtual machine is in an authorized environment. In an authorized environment, the virtual machine is enabled to operate normally. In an unauthorized environment, the virtual machine is disabled. The disabled virtual machine gathers information about the unauthorized environment and transmits the information to the virtual machine owner.

Abstract: One embodiment of the present invention sets forth a technique for selectively spawning threads within a multiprocessing system. A computation work distributor (CWD), within the system, is responsible for performing the detailed work needed to spawn a thread grid. A request to the CWD to spawn a thread grid includes a predicate table, which includes an array of flags used to indicate which thread indices should have an associated thread block spawned and which should not. Greater efficiency is achieved by only spawning thread blocks that should perform useful computation.

Abstract: Hypervisors are a new technology in the industry that enable multiple Operating Systems to co-exist on a single client. The use of a hypervisor provides a novel approach to determining the operability of an Operating System. Each Operating System is a virtualized Operating System, with its own IP address. According to a preferred embodiment, the capability Operating System has an application that is a monitor program that runs and provides information that is sent to the maintenance Operating System. The monitor program sends a status packet at regular intervals, which contains system power state and is a confirmation that the system is not hung. If the maintenance Operating System does not receive a packet at a regular interval, or in response to a query, then the maintenance Operating System will be aware that the capability Operating System is hung and will take appropriate measures.

Abstract: A technique to process interrupts on a virtualized platform. A plurality of virtual machines (VMs) runs on the virtualized platform having at least a processor. The VMs include a power VM. A VM scheduler schedules the VMs for execution on the virtualized platform according a scheduling policy. A virtualized interrupt mask controller controls masking an interrupt from an interrupting source according to the scheduling policy. An interrupt is masked from an interrupting source according to the scheduling policy for at least one of the VMs; and the at least one of the VMs is caused to get the interrupt when the at least one of the VMs is enabled according to the scheduling policy.

Abstract: A method, apparatus, and program product to allocate processor resources to a plurality of logical partitions in a computing device including a plurality of processors, each processor having at least one general purpose processing element and a plurality of synergistic processing elements. General purpose processing element resources and synergistic processing element resources are separately allocated to each logical partition. The synergistic processing element resources to each logical partition are allocated such that each synergistic processing element is assigned to a logical partition exclusively. At least one virtual processor is allocated for each logical partition. The at least one virtual processor may be allocated virtual general purpose processing element resources and virtual synergistic processing element resources that correspond to the general purpose processing element resources and synergistic processing element resources allocated to the logical partition.

Abstract: Multiple domains are created for processes of a storage server. The processes are capable of execution on a plurality of processors in the storage server. The domains include a first domain, which includes multiple threads that can execute processes in the first domain in parallel, to service data access requests. A data set managed by the storage server is logically divided into multiple subsets, and each of the subsets is assigned to exactly one of the threads in the first domain, for processing of data access requests directed to the data set.

Abstract: A system, method, program product and service for managing bidding in a resource management framework. A buyer's agent is provided to manage the bidding process for resources for a client. The buyer's agent includes the ability to submit a bid to a resource broker to acquire a set of resources for the client based on service level requirements of the client. Once the set of resources is obtained, they are monitored to ensure the required service level of the client is being met. If the service level requirements are not met, the buyer's agent automatically resubmits a bid to the resource broker. Finally, collaboration among a plurality of buyer's agents may be utilized to avoid bidding wars and the like.

Abstract: A virtual machine (VM) application may run a guest operating system (OS) and allow the guest OS to connect to USB devices connected to a computer. The VM application may filter the functions associated with the USB device so that only some of the functions of the USB device are exposed to the guest OS.

Abstract: A method and computer program product for detecting an attempt to engage a synchronization object. A tracking list for a line of code that attempted to engage the synchronization object is updated.