grawk Posted March 5, 2009 Report Share Posted March 5, 2009 I'm actually sort of surprised by this grawk. Is the model really that data intensive that disk access is a problem or do the researchers do something stupid like write every time step? I mean if you're writing to disk you're screwed as far at simulation throughput. One of the models is IO bound, and one is cpu bound. And all the post processing is IO bound. Quote Link to comment Share on other sites More sharing options...
Dreadhead Posted March 5, 2009 Report Share Posted March 5, 2009 One of the models is IO bound, and one is cpu bound. And all the post processing is IO bound. Oh ok. I wonder what's in the model to make it IO bound. Sounds like lots of look-up tables or something. I wasn't thinking about post processing , that's almost always io bound as you say. Quote Link to comment Share on other sites More sharing options...
grawk Posted March 5, 2009 Report Share Posted March 5, 2009 lots of weather modelling is based on lookup tables. The fudge factor for the "uh, this is what we think it will do" Quote Link to comment Share on other sites More sharing options...
Dreadhead Posted March 5, 2009 Report Share Posted March 5, 2009 lots of weather modelling is based on lookup tables. The fudge factor for the "uh, this is what we think it will do" Yup that's part of what makes me worry Quote Link to comment Share on other sites More sharing options...
grawk Posted March 5, 2009 Report Share Posted March 5, 2009 Why worry, they're accurate out to 4 hrs. Climate research is all a sham for funding anyway. Quote Link to comment Share on other sites More sharing options...
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.