Microsoft Technology Licensing, LLC

Andrew Raffman

Alessandro Forin

Tristan Anthony Brown

Jason Stewart Wohlgemuth

Youssef M Barakat

Minsang Kim

Omid Fatemieh

Gilad Odinak

Scott Randall Shell

Johannes Helander

Jesse Sage Schreiner

An operating system includes an interrupt router that dynamically steers each interrupt to one or more processors within set of processors based on overall load information from the set of processors. An interrupt source is assigned to a processor based on the load imposed by the interrupt source and the target overall load for the processor. For example, each processor can maintain information about each interrupt it processes over time. The operating system receives this historical load information to determine an expected load for interrupts of a given type from a given device, an overall load on the system, and a target load for each processor. Given a set of interrupt sources, their expected loads, and target load for each processor, each interrupt source can be assigned dynamically to a processor during runtime of the system. These assignments can be changed given current operating conditions of the system.

Operating system-managed interrupt steering in multiprocessor systems

An operating system is provided in which an interrupt router dynamically steers each interrupt to one or more processors within set of processors based on overall load information from the set of processors. An interrupt source is assigned to a processor based on the load imposed by the interrupt source and the target overall load for the processor. For example, each processor can maintain information about each interrupt it processes over time. The operating system receives this historical load information to determine an expected load for interrupts of a given type from a given device, an overall load on the system, and a target load for each processor. Given a set of interrupt sources, their expected loads, and target load for each processor, each interrupt source can be assigned dynamically to a processor during runtime of the system. On a regular basis, these assignments can be changed given current operating conditions of the system.

Various embodiments enable visual elements or objects, such as two-dimensional raster images, to be packed into a bounding region, such as a rectangular bounding region, in a manner that reduces wasted space. In at least some embodiments, a two-dimensional object packing component attempts to fit individual objects into the bounding region. The two-dimensional object packing component utilizes a span list to keep track of available space by tracking spans within the bounding region. Spans can occur laterally-adjacent placed objects and/or adjacent a placed object's bottom edge. In one or more embodiments, the span list is sorted left-to-right, top-to-bottom.

Two-dimensional object packing

Multiple non-blocking FIFO queues are concurrently maintained using atomic compare-and-swap (CAS) operations. In accordance with the invention, each queue provides direct access to the nodes stored therein to an application or thread, so that each thread may enqueue and dequeue nodes that it may choose. The prior art merely provided access to the values stored in the node. In order to avoid anomalies, the queue is never allowed to become empty by requiring the presence of at least a dummy node in the queue. The ABA problem is solved by requiring that the next pointer of the tail node in each queue point to a 'magic number' unique to the particular queue, such as the pointer to the queue head or the address of the queue head, for example. This obviates any need to maintain a separate count for each node.

Non-blocking concurrent queues with direct node access by threads

The invention is embodied in software executable on a computer having a working memory with demand-loadable components initially stored outside of the working memory, each component having an entry point including a constructor for an object. Preferably, the demand-loadable components are initially provided in a memory within the computer or a location external of the computer. A Namespace in the working memory provides access in the working memory to the components as they become needed by applications running in the computer. The Namespace provides the access by managing demand-loading and unloading of the components in the working memory.

Highly componentized system architecture with a demand-loading namespace and programming model

Increasing the level of automation when establishing and managing network connections. A connection manager operates between system level APIs and application programs, providing a level of abstraction. When a user wishes to access a remote resource included in destination network, the user simply identifies the remote resource and the connection manager performs the underlying operations. The connection manager relieves users from having to know detailed information about the remote resource and the destination network. When the connection manager receives a request to access a remote resource, connection manager may utilize extensible decision logic to identify a most appropriate connection method for connecting to a destination network. Such decision logic may include comparing prioritized connection requests to local resources available in a local computing device, as well as, comparing connection parameters associated with connection methods. The connection manager may utilize connection service provider modules to establish identified connection methods.

Increasing the level of automation when establishing and managing network connections

Multiple non-blocking FIFO queues are concurrently maintained using atomic compare-and-swap (CAS) operations. In accordance with the invention, each queue provides direct access to the nodes stored therein to an application or thread, so that each thread may enqueue and dequeue nodes that it may choose. The prior art merely provided access to the values stored in the node. In order to avoid anomalies, the queue is never allowed to become empty by requiring the presence of at least a dummy node in the queue. The ABA problem is solved by requiring that the next pointer of the tail node in each queue point to a &ldquo;magic number&rdquo; unique to the particular queue, such as the pointer to the queue head or the address of the queue head, for example. This obviates any need to maintain a separate count for each node.

Growing community of inventors

Redmond, WA, United States of America

Andrew Raffman