Skip to content

Make sure to not count the blas kernel init time in the speed tests. #182

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

Closed
abergeron wants to merge 1 commit into from
Closed

Make sure to not count the blas kernel init time in the speed tests. #182

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions code/test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -193,6 +193,14 @@ def do_tests():
import theano.gpuarray
if do_gpu:
theano.gpuarray.use('cuda')
# Make sure to initialize the blas kernel here to not count
# this time in the runs below.
import pygpu
a = pygpu.empty((2, 2), dtype='float32',
context=theano.gpuarray.type.get_context(None))
Copy link
Copy Markdown
Member

@nouiz nouiz Jan 17, 2017

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why not do this in theano/gpuarray/init.py use() function?

Copy link
Copy Markdown
Contributor Author

@abergeron abergeron Jan 20, 2017

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I guess we could do it, yes.

pygpu.blas.gemm(0, a, a, 0, a, overwrite_c=True)
del a

gpu_times = do_tests()
times_dic['gpu'] = gpu_times
test_total += numpy.size(gpu_times)
Expand Down