Abstract: Systems and methods for optimizing data flow in an integrated circuit includes creating a task graph based on transforming an optimized network graph for a neural network application, wherein creating the task graph includes: enumerating a plurality of distinct tasks based on a decomposition of each of a plurality of network operations of the optimized network graph; and allocating a data buffer to each of pairs of dependent tasks of the plurality of distinct tasks based on the decomposition of each of the plurality of network operations of the optimized network graph; encoding a token-informed task scheduler based on a composition of the task graph, wherein the encoding the token-informed task scheduler includes: programming the token-informed task scheduler to cause an execution of the plurality of distinct tasks based on identifying a state of a respective data buffer between each of the pairs of dependent tasks.

Abstract: Systems and methods for optimizing data flow in an integrated circuit includes creating a task graph based on transforming an optimized network graph for a neural network application, wherein creating the task graph includes: enumerating a plurality of distinct tasks based on a decomposition of each of a plurality of network operations of the optimized network graph; and allocating a data buffer to each of pairs of dependent tasks of the plurality of distinct tasks based on the decomposition of each of the plurality of network operations of the optimized network graph; encoding a token-informed task scheduler based on a composition of the task graph, wherein the encoding the token-informed task scheduler includes: programming the token-informed task scheduler to cause an execution of the plurality of distinct tasks based on identifying a state of a respective data buffer between each of the pairs of dependent tasks.

Abstract: Systems and methods for optimizing data flow in an integrated circuit includes creating a task graph based on transforming an optimized network graph for a neural network application, wherein creating the task graph includes: enumerating a plurality of distinct tasks based on a decomposition of each of a plurality of network operations of the optimized network graph; and allocating a data buffer to each of pairs of dependent tasks of the plurality of distinct tasks based on the decomposition of each of the plurality of network operations of the optimized network graph; encoding a token-informed task scheduler based on a composition of the task graph, wherein the encoding the token-informed task scheduler includes: programming the token-informed task scheduler to cause an execution of the plurality of distinct tasks based on identifying a state of a respective data buffer between each of the pairs of dependent tasks.

Abstract: Systems and methods for optimizing data flow in an integrated circuit includes creating a task graph based on transforming an optimized network graph for a neural network application, wherein creating the task graph includes: enumerating a plurality of distinct tasks based on a decomposition of each of a plurality of network operations of the optimized network graph; and allocating a data buffer to each of pairs of dependent tasks of the plurality of distinct tasks based on the decomposition of each of the plurality of network operations of the optimized network graph; encoding a token-informed task scheduler based on a composition of the task graph, wherein the encoding the token-informed task scheduler includes: programming the token-informed task scheduler to cause an execution of the plurality of distinct tasks based on identifying a state of a respective data buffer between each of the pairs of dependent tasks.

Abstract: A read request for a data object is received from a first processing thread. Responsive to the read request, it is determined whether a cached version of the data object is available from a global cache. If the cached version of the data object is not available from the global cache, a result is immediately returned to the first processing thread to indicate that the data object is not available from the global cache. The first processing thread is freed from waiting for the data object to become available from the global cache. A cache refresh message is enqueued, for the data object, in a message queue to cause a second different processing thread to subsequently dequeue the cache refresh message for the data object and build the data object in the global cache using underlying data persisted in and retrieved from a primary data source among the one or more primary data sources.

Abstract: Systems and methods of providing extended presence information for multi-user devices are described. Communication devices used in conference rooms represent a different nature than single user devices such as a personal computer. Conference rooms also have attributes that may be added to existing presence information and provide an enhanced experience for scheduling and dissemination of conference room capabilities. Information such as actual people in attendance may be added to the presence information maintained by a presence server to provide an overall enhancement to the meeting room whether it is physically a single conference room or a multitude of endpoints remotely connected to a conference.

Abstract: Systems and methods of providing extended presence information for multi-user devices are described. Communication devices used in conference rooms represent a different nature than single user devices such as a personal computer. Conference rooms also have attributes that may be added to existing presence information and provide an enhanced experience for scheduling and dissemination of conference room capabilities. Information such as actual people in attendance may be added to the presence information maintained by a presence server to provide an overall enhancement to the meeting room whether it is physically a single conference room or a multitude of endpoints remotely connected to a conference.

Abstract: Systems and methods of providing extended presence information for multi-user devices are described. Communication devices used in conference rooms represent a different nature than single user devices such as a personal computer. Conference rooms also have attributes that may be added to existing presence information and provide an enhanced experience for scheduling and dissemination of conference room capabilities. Information such as actual people in attendance may be added to the presence information maintained by a presence server to provide an overall enhancement to the meeting room whether it is physically a single conference room or a multitude of endpoints remotely connected to a conference.

Abstract: Systems and methods of providing extended presence information for multi-user devices are described. Communication devices used in conference rooms represent a different nature than single user devices such as a personal computer. Conference rooms also have attributes that may be added to existing presence information and provide an enhanced experience for scheduling and dissemination of conference room capabilities. Information such as actual people in attendance may be added to the presence information maintained by a presence server to provide an overall enhancement to the meeting room whether it is physically a single conference room or a multitude of endpoints remotely connected to a conference.