Graphic processor based accelerator system and method

A method of performing a sequence of computations on a computer system comprising a central processing unit (CPU), a main memory operably coupled to the central processing unit via a bus, an accelerator operably coupled to the CPU and the main memory via the bus, the accelerator comprising a graphics processing unit (GPU) and an accelerator memory, the method comprising:

• (A) performing, by the GPU, the sequence of computations on a first portion of the input data so as to generate a first portion of the output data, intermediate computations in the sequence of computations yielding intermediate results;
• (B) in parallel with performing the sequence of computations by the GPU in (A), transferring a second portion of the input data from the main memory to the accelerator via the bus;
• and
• (C) in parallel with performing the sequence of computations by the GPU in (A), transferring a second portion of the output data from the accelerator memory to the main memory via the bus.

A method of executing computations representing an artificial neural network on a computer system comprising at least one central processing unit (CPU), a processing unit, a first memory partition, and a second memory partition, the method comprising:

• executing, by the at least one CPU, a user interaction stream, the user interaction stream controlling transfer of inputs to the artificial neural network to the first memory partition and the second memory partition;
• executing, by the processing unit, a computational stream, the computational stream controlling data exchange between the user interaction stream and the computational stream during execution of the computations representing the artificial neural network;
• shifting control of a data exchange between the user interaction stream and the computational stream to the computational stream in response to starting execution of the computations representing the artificial neural network;
• shifting control of the data exchange between the user interaction stream and the computational stream to the user interaction stream in response to completion or interruption of the computations representing the artificial neural network;
• queueing a user command received by the user interaction stream during execution of the computations representing the artificial neural network;
• and
• executing the user command during execution of the computations representing the artificial neural network at times determined by the computational stream.

A system for executing computations representing an artificial neural network, the system comprising:

• a camera to acquire input data for the artificial neural network;
• a first memory partition;
• a second memory partition;
• at least one central processing unit (CPU), operably coupled to the camera, the first memory partition, and the second memory partition, to execute a user interaction stream, the user interaction stream controlling transfer of the input data acquired by the camera to the first memory partition and the second memory partition during execution of the computations representing the artificial neural network;
• a processing unit, operably coupled to the first memory partition, the second memory partition, and the at least one CPU, to execute a computational stream, the computational stream controlling transfer of the input data from the first memory partition and the second memory partition during execution of the computations representing the artificial neural network, the execution of the computations representing the artificial neural network occurring while the camera is acquiring the input data;
• and
• a controller, operably coupled to the at least one CPU and the processing unit, to queue user interactions received by the user interaction stream during the execution of the computations representing the artificial neural network for performance at times selected to avoid data corruption.