New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

CUDA variant optimised beyond k-caching #104

Open

MichaelSt98 wants to merge 1 commit into develop from nams-cuda-beyond-k-caching

+3,559 −3

Contributor

MichaelSt98 commented Dec 11, 2024

Optimisation beyond k-caching:

buffering variables
pipelined global-to-shared memory copies overlapped with compute, TMA loads
- NVIDIA blog post: Controlling Data Movement to Boost Performance on the NVIDIA Ampere Architecture

likely still potential for further optimisation ...

Implemented with input from @lukasm91

k-caching vs "opt"-variant performance (compiled with nvhpc 22.11 and executed with 1 262144 128):

double-precision
- k-caching: 600 - 700 GF/s
- "opt": 700 - 850 GF/s
single-precision
- k-caching: 2300 - 3000 GF/s
- "opt": 2700 - 5000 GF/s


          CUDA variant optimised beyond k-caching, e.g., pipelined global-to-sh…

99afc47

…ared mem copies overlaped with compute

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet