Abstract: Systems and methods are provided for optimizing data storage and improving the speed of data retrieval in a data store, such as a storage server connected to a large network through the use of bucketing techniques to create efficient data structures for storing received key-value datasets at one or more storage servers. Fast key-value read requests and key-value retrievals may be accomplished through the use of multiphase lookup operations on the one or more storage servers. The system is optimized for best performance of retrieval through the separation of the write and read mechanisms. Systems and methods provided herein control the level of wastefulness on the back end of a system and reduce read operation inefficiencies on the front end of a system.

Abstract: The disclosed distributed task coordination ensures task execution while minimizing both the risk of duplicate execution and resources consumed for coordination. Execution is guaranteed, while only best efforts are used to avoid duplication. Example solutions include requesting, by a node, a first lease from a first set of nodes; based at least on obtaining at least one first lease, requesting, by the node, a second lease from a second set of nodes; based at least on the node obtaining at least one second lease, determining a majority holder of second leases; and based at least on obtaining the majority of second leases, executing, by the node, a task associated with the at least one second lease. In some examples, the nodes comprise online processing units (NPUs). In some examples, if a first node begins executing the task and fails, another node automatically takes over to ensure completion.

Abstract: The disclosed distributed task coordination ensures task execution while minimizing both the risk of duplicate execution and resources consumed for coordination. Execution is guaranteed, while only best efforts are used to avoid duplication. Example solutions include requesting, by a node, a first lease from a first set of nodes; based at least on obtaining at least one first lease, requesting, by the node, a second lease from a second set of nodes; based at least on the node obtaining at least one second lease, determining a majority holder of second leases; and based at least on obtaining the majority of second leases, executing, by the node, a task associated with the at least one second lease. In some examples, the nodes comprise online processing units (NPUs). In some examples, if a first node begins executing the task and fails, another node automatically takes over to ensure completion.

Abstract: The disclosed distributed task coordination ensures task execution while minimizing both the risk of duplicate execution and resources consumed for coordination. Execution is guaranteed, while only best efforts are used to avoid duplication. Example solutions include requesting, by a node, a first lease from a first set of nodes; based at least on obtaining at least one first lease, requesting, by the node, a second lease from a second set of nodes; based at least on the node obtaining at least one second lease, determining a majority holder of second leases; and based at least on obtaining the majority of second leases, executing, by the node, a task associated with the at least one second lease. In some examples, the nodes comprise online processing units (NPUs). In some examples, if a first node begins executing the task and fails, another node automatically takes over to ensure completion.

Abstract: The disclosed distributed task coordination ensures task execution while minimizing both the risk of duplicate execution and resources consumed for coordination. Execution is guaranteed, while only best efforts are used to avoid duplication. Example solutions include requesting, by a node, a first lease from a first set of nodes; based at least on obtaining at least one first lease, requesting, by the node, a second lease from a second set of nodes; based at least on the node obtaining at least one second lease, determining a majority holder of second leases; and based at least on obtaining the majority of second leases, executing, by the node, a task associated with the at least one second lease. In some examples, the nodes comprise online processing units (NPUs). In some examples, if a first node begins executing the task and fails, another node automatically takes over to ensure completion.

Abstract: The disclosed distributed task coordination ensures task execution while minimizing both the risk of duplicate execution and resources consumed for coordination. Execution is guaranteed, while only best efforts are used to avoid duplication. Example solutions include requesting, by a node, a first lease from a first set of nodes; based at least on obtaining at least one first lease, requesting, by the node, a second lease from a second set of nodes; based at least on the node obtaining at least one second lease, determining a majority holder of second leases; and based at least on obtaining the majority of second leases, executing, by the node, a task associated with the at least one second lease. In some examples, the nodes comprise online processing units (NPUs). In some examples, if a first node begins executing the task and fails, another node automatically takes over to ensure completion.

Abstract: Systems and methods are provided for optimizing data storage and improving the speed of data retrieval in a data store, such as a storage server connected to a large network through the use of bucketing techniques to create efficient data structures for storing received key-value datasets at one or more storage servers. Fast key-value read requests and key-value retrievals may be accomplished through the use of multiphase lookup operations on the one or more storage servers. The system is optimized for best performance of retrieval through the separation of the write and read mechanisms. Systems and methods provided herein control the level of wastefulness on the back end of a system and reduce read operation inefficiencies on the front end of a system.

Abstract: A recommendation system is implemented using modified matrix factorization on top of a content-based matrix to provide both user-to-item and item-to-item content-based recommendations while exposing the full depth of transitive relationships among recommendations. Content information such as features and characteristics may be represented in a usage matrix in which features are treated as users would be in traditional matrix factorization. Matrix factorization is applied to the “features-as-users” matrix to build a content-based model in which features and items are embedded in a low dimension latent space. User history is employed for system training by locating user vectors within the latent space. Recommendations that are near to the vector can be provided to the users along with explanations (e.g., a recommendation is given because of an item's proximity to a particular feature).