> When you think about machine learning, especially deep neural nets, it turns out GPUs are much better at performance and scale for those algorithms
Perhaps we should stop calling them GPUs. Now seems a good time for it.
Perhaps we should stop calling them GPUs. Now seems a good time for it.
Standard Hyperparallel Integrated Technology?
I do so love fun with acronyms...
AIPUs
It does a good job of communicating their main functionality.