Abstract: Systems, apparatuses and methods may provide for technology that identifies an embedding table associated with a neural network. The neural network is associated with a plurality of compute nodes. The technology further identifies a number of entries of the embedding table, and determines whether to process gradients associated with the embedding table as dense gradients or sparse gradients based on the number of entries.

Abstract: Systems, apparatuses and methods may provide technology for optimizing an inference neural network model that performs asymmetric quantization by generating a quantized neural network, wherein model weights of the neural network are quantized as signed integer values, and wherein an input layer of the neural network is configured to quantize input values as unsigned integer values, generating a weights accumulation table based on the quantized model weights and a kernel size for the neural network, and generating an output restoration function for an output layer of the neural network based on the weights accumulation table and the kernel size. The technology may also perform per-input channel quantization. The technology may also perform mixed-precision auto-tuning.

Abstract: A method and apparatus for keeping statistical inference accuracy with 8-bit winograd convolution. A calibration dataset and a pretrained CNN comprising 32-bit floating point weight values may be sampled to generate an input activation tensor and a weight tensor. A transformed input activation tensor may be generated by multiplying the input activation tensor and an input matrix to generate a transformed input activation tensor. A transformed weight tensor may be generated by multiplying the weight tensor and a weight matrix. A scale factor may be computed for each transformed tensor. An 8-bit CNN model including the scale factors may be generated.

Abstract: Technologies for device-independent application testing include a host computing device and one or more test computing devices. The host computer device records user interface events generated by an application of the test computing device and video data indicative of the display interface of the application. The host computing device detects user interface objects in the video data that correspond to user interface events using a computer vision algorithm, which may include image feature detection or optical character recognition. The host computing device generates an object-based test script that identifies the user interface object and a user interaction. The host computing device may identify the user interface object in the display interface of an application executed by a different test computing device using the computer vision algorithm. The host computing device performs the specified user interaction on the detected user interface object. Other embodiments are described and claimed.

Abstract: In a system that is capable of operating in a broadcast mode and a switched mode, it is advantageous to be able to shift program delivery between the two modes. Thus when one video program is being delivered to at least a first customer in a first mode, this program may be delivered to at least a second customer in a second mode that is different from the first mode. In this manner, the video program that is being delivered to first customer will be maintained in the original mode while new requests for this program will be served in a different mode until the delivery of the program to the first customer has been completed. In other words, legacy program delivery is maintained until the program delivery has been completed or otherwise terminated, while delivery of the program in response to new requests for the same program will be delivered in a different mode instead.

Abstract: A method and system of providing switched broadcasting of content to a number of consumers. The content may be transmitted in pieces over broadcast and switched transmission tiers. The broadcast tier being characterized by the continuous transmission of content and the switched tier being characterized by on demand or request based transmission of content.

Abstract: Methods and systems to display platform graphics during initialization of an computer system, including to interrupt initialization of an operating system and to update a video frame buffer with platform graphics data when the initialization of the operating system is interrupted, and to merge platform graphics data with graphics generated by operating system initialization logic. The methods and systems include virtualization methods and systems and system management mode methods and systems.

Abstract: In a system that is capable of operating in a broadcast mode and a switched mode, it is advantageous to be able to shift program delivery between the two modes. Thus when one video program is being delivered to at least a first customer in a first mode, this program may be delivered to at least a second customer in a second mode that is different from the first mode. In this manner, the video program that is being delivered to first customer will be maintained in the original mode while new requests for this program will be served in a different mode until the delivery of the program to the first customer has been completed. In other words, legacy program delivery is maintained until the program delivery has been completed or otherwise terminated, while delivery of the program in response to new requests for the same program will be delivered in a different mode instead.

Abstract: A method and system of providing switched broadcasting of content to a number of consumers. The content may be transmitted in pieces over broadcast and switched transmission tiers. The broadcast tier being characterized by the continuous transmission of content and the switched tier being characterized by on demand or request based transmission of content.

Abstract: The invention specifies a method of allocating resources efficiently for network capacity management of voice traffic in a packet based broadband network. The method includes the specifications of the logical network architecture, its components, the information model associated with the components, and the computation algorithms for network capacity management. The invention is independent of the transport network technologies.