Abstract: A method of configuring a System-on-Chip (SoC) to execute a Convolutional Neural Network (CNN) by (i) receiving scheduling schemes each specifying a sequence of operations executable by Processing Units (PUs) of the SoC; (ii) selecting, a scheduling scheme for a current layer of the CNN; (iii) determining a current state of memory for a storage location in the SoC allocated for storing feature map data from the CNN; (iv) selecting, from the plurality of scheduling schemes and dependent upon the scheduling scheme for the current layer of the CNN, a set of candidate scheduling schemes for a next layer of the CNN; and (v) selecting, from the set of candidate scheduling schemes dependent upon the determined current state of memory, a scheduling scheme for the next layer of the CNN.

Abstract: A method of configuring a System on Chip to execute a CNN process comprising CNN layers, the method comprising, for each schedule: determining memory access amount information describing how many memory accesses are required; expressing the memory access amount information as relationships describing reusability of data; combining the relationships with a cost of writing and reading from external memory, to form memory access information; determining a memory allocation for on-chip memory of the SoC for the input FMs and the output FMs; and determining, dependent upon the memory access information and the memory allocation for each schedule; a schedule which minimises the memory access information of external memory access for the CNN layer of the CNN process; and a memory allocation associated with the determined schedule.

Abstract: A method of configuring a System on Chip to execute a CNN process comprising CNN layers, the method comprising, for each schedule: determining memory access amount information describing how many memory accesses are required; expressing the memory access amount information as relationships describing reusability of data; combining the relationships with a cost of writing and reading from external memory, to form memory access information; determining a memory allocation for on-chip memory of the SoC for the input FMs and the output FMs; and determining, dependent upon the memory access information and the memory allocation for each schedule; a schedule which minimises the memory access information of external memory access for the CNN layer of the CNN process; and a memory allocation associated with the determined schedule.

Abstract: A method of configuring a System-on-Chip (SoC) to execute a Convolutional Neural Network (CNN) by (i) receiving scheduling schemes each specifying a sequence of operations executable by Processing Units (PUs) of the SoC; (ii) selecting, a scheduling scheme for a current layer of the CNN; (iii) determining a current state of memory for a storage location in the SoC allocated for storing feature map data from the CNN; (iv) selecting, from the plurality of scheduling schemes and dependent upon the scheduling scheme for the current layer of the CNN, a set of candidate scheduling schemes for a next layer of the CNN; and (v) selecting, from the set of candidate scheduling schemes dependent upon the determined current state of memory, a scheduling scheme for the next layer of the CNN.

Abstract: A method for processing a packet comprising an ordered sequence of packet parts is disclosed. The method uses a set of hardware processing modules, and the method comprises the steps of broadcasting, in a step the next header field of a received packet part to the set of processing modules, and processing, in a step the received packet part by a sub-set of the modules dependent upon the broadcast next header field.

Abstract: An architecture for selectively powering a receive module (108) is disclosed. The architecture comprises the receive module (108) which is functionally adapted, while power is applied to the receive module (108) by a power module (601), and after a power-up time interval has elapsed, to process a traffic packet. The architecture further comprises the power module (601) that is adapted to apply power to the receive module 108 dependent upon arrival of a wake-up packet.

Abstract: A method for processing a packet comprising an ordered sequence of packet parts is disclosed. The method uses a set of hardware processing modules, and the method comprises the steps of broadcasting, in a step the next header field of a received packet part to the set of processing modules, and processing, in a step the received packet part by a sub-set of the modules dependent upon the broadcast next header field.

Abstract: An architecture for selectively powering a receive module (108) is disclosed. The architecture comprises the receive module (108) which is functionally adapted, while power is applied to the receive module (108) by a power module (601), and after a power-up time interval has elapsed, to process a traffic packet. The architecture further comprises the power module (601) that is adapted to apply power to the receive module 108 dependent upon arrival of a wake-up packet.