Sorry for taking long to reply - I am rather off the grid now, so
feel free to fix prefix scans without my involvement.
Dnia 2011-02-21, pon o godzinie 19:15 -0500, Andreas Kloeckner pisze:
- can you please resend this as an attachment? It's hard to fish out of
the text of an email.
- please avoid using floating point functions (log, ceil, floor) in
integer contexts. PyCUDA comes with a bitlog2 function that does what
you need, I think.
Once I get the file posted on the PyCUDA branch, I'll write a more
complete review. I agree with your assessment of inclusive vs exclusive
scan. I'd say go ahead and kill the inclusive version.
Tomasz, what's your take here?
I have included both inclusive and exclusive scans to have two
different, independent implementations.
I agree that inclusive version is rather naive version - but I think
that having two different implementation where one can be used
to test other can have some advantages. At the same time for now
code is rather complicated, so I am not sure if there is more
advantages or disadvantages. Feel free to change this code.
Tomasz Rybak <bogomips(a)post.pl> GPG/PGP key ID: 2AD5 9860
Fingerprint A481 824E 7DD3 9C0E C40A 488E C654 FB33 2AD5 9860