November 8, 2006
Jensen Huang announces CUDA
NVIDIA CEO Jensen Huang announced CUDANVIDIA's parallel computing platform — lets developers run general code on GPUs for ML and simulation. on November 8, 2006 — opening GPUs to general-purpose parallel computing.
What it was for
CUDANVIDIA's parallel computing platform — lets developers run general code on GPUs for ML and simulation. let researchers run matrix math on graphics cards — enabling the deep learningNeural networks with many layers that learn hierarchical representations from data. boom years before AlexNet. It turned NVIDIA from a gaming GPUGraphics processing unit — a chip optimized for parallel math; now used for graphics, ML, and scientific computing. vendor into an AI infrastructure company.
People
- Jensen Huang — ceo
Companies
- NVIDIA
Why it's here
CUDANVIDIA's parallel computing platform — lets developers run general code on GPUs for ML and simulation. unlocked GPUGraphics processing unit — a chip optimized for parallel math; now used for graphics, ML, and scientific computing. computing for science and machine learningSystems that learn patterns from data rather than following only explicit programmed rules..
Why it mattered
It made massively parallel hardware accessible through C extensions developers could adopt.
What it solved
GPUs were locked to graphics APIs unsuitable for numerical computing.
Media
ImageJensen HuangThe White House, Public domain, via Wikimedia Commons
Related
- Jensen Huang co-founds NVIDIAApril 5, 1993
- AlexNet wins ImageNetSeptember 2012