Abstract: Instruction generation for a data processing array and microcontroller includes generating a tensor-level intermediate representation from a machine learning model using kernel expressions. Statements of the tensor-level intermediate representation are partitioned into a first set of statements and a second set of statements. From the first set of statements, kernel instructions are generated based on a reconfigurable neural engine model. The kernel instructions are executable by a compute tile of a data processing array to implement compute functions of the machine learning model. From the set of second statements, microcontroller instructions are generated based on a super-graph model. The microcontroller instructions are executable by a microcontroller of the data processing array to move data into and out from the data processing array.

Abstract: In a wireless communications system, a base station transmits power control signals (e.g., the power control bits of a power control sub-channel) to a mobile using a forward-link channel that is decoupled from all other signals transmitted from that base station to that mobile. For example, the decoupled forward-link channel may be a common power control channel. The mobile then uses the power control signals received in the decoupled forward-link channel to control its power level for transmitting one or more reverse-link channels to the base station. The ability of base stations to use decoupled forward-link channels in order to transmit their power control signals to a mobile enables a mobile to operate with different active sets for the forward and reverse links. This enables forward-link data traffic to be implemented using a simplex mode, even when the mobile is operating in soft handoff in the reverse link.