facebook-pixel

Chien-Ping Lu

About Me

Chien-Ping Lu, PhD, is an expert and leader in GPU and AI Hardware. Also known as CP, he is a GPU veteran having worked on Nvidia’s nForce chipsets with integrated GPU and on MediaTek’s team. He has several patents, which relate to GPUs and machine learning.  He helped co-found HSA (Heterogeneous System Architecture) Foundation to push Heterogeneous Computing in 2012, and also served as the chair of the Programmer's Reference Spec working group.
 

All Tensors Secretly Wish to be Themselves

Welcome to the world of tensors in AI. It is now time to get used to the curse of dimensionality. It is also an industry standard practice to flatten tensors all the way to matrices to leverage the highly optimized libraries for matrix multiplication (MM) or MM accelerators (MMAs), even though tensors are considered to be the most fundamental data type in all major AI frameworks. Matrices are generally considered to be special cases of tensors by the AI community.

The Harvard Innovation Lab

Made in Boston @

The Harvard Innovation Lab

350

Matching Providers

Matching providers 2
comments powered by Disqus.