Also known as: General-purpose computing on graphics processing units

GPGPU (general-purpose computing on graphics processing units) is the practice of using a GPU to run ordinary computation rather than only rendering images.¹

Overview

A GPU contains thousands of small cores built to shade pixels in parallel. When a problem can be expressed as the same operation applied to many data elements at once — the same SIMD/data-parallel pattern a vector processor exploits — those cores can be redirected at it. Early GPGPU work smuggled math through the graphics pipeline; dedicated APIs like CUDA and the cross-vendor OpenCL later exposed the hardware directly, making GPGPU mainstream for scientific computing, cryptography, and machine learning.

What it’s for

GPGPU shines on large, regular, parallel workloads and is the foundation of modern deep learning, where it long preceded purpose-built AI accelerators. It is poor at branch-heavy, sequential work, which still belongs on the CPU. In a software-defined radio context, GPGPU can accelerate wideband DSP — large FFTs, polyphase channelizers splitting one capture into many channels — but the cost of moving samples to and from the GPU only pays off when the channel count is high.

Sources

1. General-purpose computing on graphics processing units — Wikipedia, on using GPUs for non-graphics computation. ↩

See also

• Graphics processing unit (GPU)
• CUDA
• Hardware acceleration
• Vector processor
• Central processing unit (CPU)
• AI accelerator