Abstract: Systems, methods, and computer-executable instructions for determining a computation schedule for a recurrent neural network (RNN). A matrix multiplication (MM) directed-acyclic graph (DAG) is received for the RNN. Valid phased computation schedules for the RNN are generated. Each of the valid phase computation schedule includes an ordering of MM operations. For each of the plurality of valid phased computation schedules, each of the MM operations is partitioned to processor cores based on L3 cache to L2 cache data movement. The RNN is executed based on the valid phased computation schedules. A final computation schedule is stored. The final computation schedule is used for future executions of the RNN.

Abstract: A method for semantic search includes receiving a query vector including a semantic feature value for each of a plurality of semantic feature dimensions. A cluster is selected from a plurality of different candidate clusters held in a relatively fast memory, each candidate cluster including a plurality of compressed answer vectors. A subset of the plurality of compressed answer vectors are promoted as candidate answers. For each of the candidate answers, a corresponding uncompressed answer vector is retrieved from a relatively slower memory. A selected answer is promoted from among the candidate answers.

Abstract: A method for semantic search includes receiving a query vector including a semantic feature value for each of a plurality of semantic feature dimensions. A cluster is selected from a plurality of different candidate clusters held in a relatively fast memory, each candidate cluster including a plurality of compressed answer vectors. A subset of the plurality of compressed answer vectors are promoted as candidate answers. For each of the candidate answers, a corresponding uncompressed answer vector is retrieved from a relatively slower memory. A selected answer is promoted from among the candidate answers.

Abstract: Systems, methods, and computer-executable instructions for approximating a softmax layer are disclosed. A small world graph that includes a plurality of nodes is constructed for a vocabulary of a natural language model. A context vector is transformed. The small world graph is searched using the transformed context vector to identify a top-K hypothesis. A distance from the context vector for each of the top-K hypothesis is determined. The distance is transformed to an original inner product space. A softmax distribution is computed for the softmax layer over the inner product space of the top-K hypothesis. The softmax layer is useful for determining a next word in a speech recognition or machine translation.

Abstract: Systems, methods, and computer-executable instructions for approximating a softmax layer are disclosed. A small world graph that includes a plurality of nodes is constructed for a vocabulary of a natural language model. A context vector is transformed. The small world graph is searched using the transformed context vector to identify a top-K hypothesis. A distance from the context vector for each of the top-K hypothesis is determined. The distance is transformed to an original inner product space. A softmax distribution is computed for the softmax layer over the inner product space of the top-K hypothesis. The softmax layer is useful for determining a next word in a speech recognition or machine translation.

Abstract: Systems, methods, and computer-executable instructions for determining a computation schedule for a recurrent neural network (RNN). A matrix multiplication (MM) directed-acyclic graph (DAG) is received for the RNN. Valid phased computation schedules for the RNN are generated. Each of the valid phase computation schedule includes an ordering of MM operations. For each of the plurality of valid phased computation schedules, each of the MM operations is partitioned to processor cores based on L3 cache to L2 cache data movement. The RNN is executed based on the valid phased computation schedules. A final computation schedule is stored. The final computation schedule is used for future executions of the RNN.