GPGPU
General Purpose computing on Graphics Processing Units; using GPUs to run non-graphics computations.
As defined in #403: How Jensen Works
Where it comes up · 2
- #403: How Jensen Works3 claims
- #376: Jensen Huang: Founder of Nvidia2 claims
Most important claims · 5 of 5Search all claims for “GPGPU” →
- Jensen recognized that general-purpose GPU computing could expand NVIDIA's market beyond graphics, so he built CUDA, a programming model that lets scientists and engineers use GPU computing power, to generate demand by making GPUs easier to program.#376: Jensen Huang: Founder of Nvidia
- Huang saw that researchers using GPUs for non-graphical computing signaled a huge opportunity, so he hired the researcher who coined GPGPU and pushed CUDA to make GPUs easy to program, expanding the market beyond graphics.#403: How Jensen Works
- The first use of NVIDIA GPUs for non-graphics work came in a 2002 research paper on simulating cloud movement, where researchers hacked GPUs to reframe computations as graphics functions and reported large speedups over CPUs.#376: Jensen Huang: Founder of Nvidia
- Huang recognized the AI trend early, invested heavily over two decades, including when others advised against it, and concentrated resources on his greatest opportunity until Nvidia was positioned to capture it.#403: How Jensen Works
- Repeated wonky machine learning developments in top five emails led Huang to decide Nvidia needed to invest more in tools for accelerating workloads on GPUs, which became central to the AI boom.#403: How Jensen Works