Does anyone understand why such minor upgrades resulted in a major version bump? Is this some sort of stability check point? Or some other versioning convention?
It supports a whole new architecture (Ampere) and all the good stuff that comes with it: Multi-Instance GPU partitioning, new number formats (Tfloat32, sparse INT8), 3rd gen of Tensor Cores, and asynchronous copy/asynchronous barriers. These are huge features.
Well, I think a new microarchitecture means a major bump. So between that and version bumps to to actual major software features, you get to 11 within 13 years or so.
Also, GCC 9.x compatibility may seem minor to some, but is significant for others. I also think there's some C++17 support in kernels - that's something too.
Ooh, I missed those. Support for C++17 is pretty major. Thanks. Perhaps my memory is fuzzy, I just remember the CUDA 9->10 switch having some significant (but not major) performance and feature changes.
p1esk|5 years ago
einpoklum|5 years ago
Also, GCC 9.x compatibility may seem minor to some, but is significant for others. I also think there's some C++17 support in kernels - that's something too.
cjhanks|5 years ago
ibn-python|5 years ago
gowld|5 years ago
bigdict|5 years ago