Steven Rieder · @rieder
217 followers · 272 posts · Server mastodon.social

I would like to make use of the in my system, but unfortunately it seems to only work with and in . If anyone has managed to do calculations (and can point me to a working example), that would be great!

#gpu #apple #silicon #metal #singleprecision #doubleprecision #Astrodon

Last updated 1 year ago

Steven Rieder · @rieder
24 followers · 37 posts · Server astrodon.social

What I found out:
- there’s a (simple) example on GitHub that I could make work. It seems to be really fast.
- not sure yet how to link with ++ but I found headers that should make this work
- metal doesn’t seem to support . Boo! , please implement this!

#Metal #nbody #c #doubleprecision #apple

Last updated 2 years ago

claude · @mathr
288 followers · 2739 posts · Server post.lurk.org

Hearsay has it that 64bit on is , but using two 32bit integers is even much (I tested with ).

#doubleprecision #floatingpoint #gpu #slow #softfloat #slower #opencl

Last updated 5 years ago