Andrew Kerr

Andrew is a Senior GPU Compute Architect at NVIDIA. He joined NVIDIA's Compute Architecture group in 2012 after finishing his Ph.D. at Georgia Institute of Technology. Lately, Andrew's technical focus has been to design and implement abstractions for linear algebra on GPUs to facilitate programmability as performance continues to scale.

Posts by Andrew Kerr

Artificial Intelligence

CUTLASS: Fast Linear Algebra in CUDA C++

Update May 21, 2018: CUTLASS 1.0 is now available as Open Source software at the CUTLASS repository. CUTLASS 1.0 has changed substantially from our preview… 25 MIN READ