Abstract: Embodiments relate to compiling neural network operations into tasks that may be performed in a streaming manner by a neural processor. In a streaming operation, a tensor is spatially partitioned, and tasks associated two or more layers of the neural network are performed simultaneously in an overlapping manner. To enable efficient memory usage during streaming operation, a subset of the tasks having completion times close in time are assigned to a same portion of memory in the neural processor during a compilation process. After the tasks assigned to the same portion of the memory is finished, the portion of the memory may be flushed to make space for subsequent tasks. Multiple tasks may also be coalesced into a single task to reduce the number of tasks and more efficiently perform the operations at the neural processor.

Abstract: Embodiments relate to streaming operations in a neural processor circuit that includes a neural engine circuit and a data processor circuit. The neural engine circuit performs first operations on a first input tensor of a first layer to generate a first output tensor, and second operations on a second input tensor of a second layer at a higher hierarchy than the first layer, the second input tensor corresponding to the first output tensor. The data processor circuit stores a portion of the first input tensor for access by the neural engine circuit to perform a subset of the first operations and generate a portion of the first output tensor. The data processor circuit stores the portion of the first output tensor for access by the neural engine circuit as a portion of the second input tensor to perform a subset of the second operations.

Abstract: RFID tag ICs in a population can adjust the impedance values used to backscatter-modulate reply signals to increase the distribution or spread of backscattered signal parameters, thereby facilitating the recovery of collided tag replies. An RFID tag IC may adjust its impedance value(s) based on a reader command or independently.

Abstract: Techniques are provided to estimate the location of an RFID tag using tag read information, such as a tag read count or a tag read rate, and an opportunity metric, such as an inventory cycle duration, inventory cycle rate, or inventory cycle count. A tag tracking system determines read information for a tag in a zone and an opportunity metric associated with the tag and the zone. The tag tracking system then computes a success rate based on the tag read information and opportunity metric, and uses the success rate to estimate the location of the tag.

Abstract: Techniques are provided to estimate the location of an RFID tag using tag read information, such as a tag read count or a tag read rate, and an opportunity metric, such as an inventory cycle duration, inventory cycle rate, or inventory cycle count. A tag tracking system determines read information for a tag in a zone and an opportunity metric associated with the tag and the zone. The tag tracking system then computes a success rate based on the tag read information and opportunity metric, and uses the success rate to estimate the location of the tag.

Abstract: Techniques are provided to estimate the location of an RFID tag using tag read information, such as a tag read count or a tag read rate, and an opportunity metric, such as an inventory cycle duration, inventory cycle rate, or inventory cycle count. A tag tracking system determines read information for a tag in a zone and an opportunity metric associated with the tag and the zone. The tag tracking system then computes a success rate based on the tag read information and opportunity metric, and uses the success rate to estimate the location of the tag.

Abstract: Techniques are provided to estimate the location of an RFID tag using tag read information, such as a tag read count or a tag read rate, and an opportunity metric, such as an inventory cycle duration, inventory cycle rate, or inventory cycle count. A tag tracking system determines read information for a tag in a zone and an opportunity metric associated with the tag and the zone. The tag tracking system then computes a success rate based on the tag read information and opportunity metric, and uses the success rate to estimate the location of the tag.

Abstract: Techniques are provided to estimate the location of an RFID tag using tag read information, such as a tag read count or a tag read rate, and an opportunity metric, such as an inventory cycle duration, inventory cycle rate, or inventory cycle count. A tag tracking system determines read information for a tag in a zone and an opportunity metric associated with the tag and the zone. The tag tracking system then computes a success rate based on the tag read information and opportunity metric, and uses the success rate to estimate the location of the tag.

Abstract: RFID readers, systems, and methods are provided for overcoming the effects of RF interference. While a system is communicating in a channel, RF interference is monitored. If it is low, then hopping to another channel is performed according to an ordinary decision. But if interference is high, then hopping out to another channel can be earlier than would be dictated by the ordinary decision under the same circumstances. The earlier hopping out can result in diminishing communication in channels with a lot of RF interference.

Abstract: RFID readers, systems, and methods are provided for overcoming the effects of RF interference. While a system is communicating in a channel, RF interference is monitored. If it is low, then the next channel to be hopped onto is chosen in an unbiased manner. But if interference is high, then the next channel to be hopped onto is chosen in a biased manner that disfavors at least one channel over another, in view of the detected interference. The choice of the next channel can thus result in diminishing communication in channels with a lot of RF interference.