Skip to content

More comprehensive benchmark #25

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.

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

Closed
aminya opened this issue Nov 27, 2019 · 6 comments · Fixed by #30
Closed

More comprehensive benchmark #25

aminya opened this issue Nov 27, 2019 · 6 comments · Fixed by #30
Assignees
Milestone

Comments

@aminya
Copy link
Member

aminya commented Nov 27, 2019

Work is in progress in https://github.com/aminya/AcuteBenchmark.jl

@aminya aminya self-assigned this Nov 27, 2019
@aminya aminya added this to the V 1.0 milestone Nov 27, 2019
@Crown421
Copy link
Collaborator

This might be relevant here:
https://discourse.julialang.org/t/repeated-benchmark-causes-ram-creep/31533/5

@aminya
Copy link
Member Author

aminya commented Nov 28, 2019

That is strange, I didn't have any issues. I have 8GB of RAM on Windows 10.

@Crown421
Copy link
Collaborator

How many have you been running in a given session?

@aminya
Copy link
Member Author

aminya commented Nov 29, 2019

In https://github.com/juliamatlab/Julia-Matlab-Benchmark I used 17 functions * 23 sizes * running each 4 times!

@aminya
Copy link
Member Author

aminya commented Dec 21, 2019

AcuteBenchmark is almost ready.
https://github.com/aminya/AcuteBenchmark.jl

I will change to that for VML.jl some time this week

This was referenced Dec 31, 2019
@Crown421
Copy link
Collaborator

What we should also do is test this against Yeppp and AppleAccelerate. From my personal experience VML is superior to both, but it would be nice to quantify that.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants