Definition: GPGPU

(General Purpose computation on GPUs) Using a graphics processing unit (GPU) for general-purpose parallel processing applications rather than rendering images for the screen. To achieve quick results, applications such as sorting, matrix algebra, image processing, physical modeling and AI deep learning require the processing of many large sets of data in parallel.

GPUs are also used in desktop computers for improved voice, face and gesture recognition. Although the GPGPU acronym may not be widely used, graphics processing units (GPUs) today are doing a huge amount of non-graphics processing.

A GPU functions as a coprocessor with its own memory and executes many calculations in parallel. See AI accelerator, GPU, CUDA, OpenCL, DirectCompute, PhysX and AMD Fusion.

A Desktop GPGPU Powerhouse

This GV100 GPU from NVIDIA is a PCI Express card that performs 7.4 trillion 64-bit floating point operations per second (7.4 TFLOPS). Its Tensor performance reaches 118.5 TFLOPS (see TensorFlow). (Image courtesy of NVIDIA Corporation.)