Message132732
Taking a look at the patch, I see you're using the single -> half conversion routine from NumPy. This has the double rounding problem when converting double -> float -> half, so it would be better to use the double -> half routine. I implemented it with 64-bit unsigned ints, so if there are platforms not supporting 64-bit ints, something else such as using the 32-bit routine will have to be done there. |
|
Date |
User |
Action |
Args |
2011-04-01 07:58:09 | mark.wiebe | set | recipients:
+ mark.wiebe, mark.dickinson, Eli.Stevens |
2011-04-01 07:58:09 | mark.wiebe | set | messageid: <1301644689.23.0.537464553473.issue11734@psf.upfronthosting.co.za> |
2011-04-01 07:58:08 | mark.wiebe | link | issue11734 messages |
2011-04-01 07:58:08 | mark.wiebe | create | |
|