| 摘要 |
A computing device, which may be implemented as an integrated circuit, is constructed of a microprocessor (30) and one or more neural network co-processors (32). The microprocessor (30) normally executes programs which transfer data to the neural network coprocessors (32), which are used to compute complicated mathematical functions. Direct Memory Access (DMA) is also used to transfer data. Each neural network co-processor (32) interfaces to the microprocessor in a manner substantially similar to that of a conventional memory device. The co-processor (32) does not require any instructions and is configured to execute mathematical operations simply by being pre-loaded with gating functions and weight values. In addition, the co-processor (32) executes a plurality of arithmetic operations in parallel, and the results of such operations are simply read from the co-processor.
|
