Good to hear from you!
On 11/17/22 10:36 PM, Mike McCarty wrote:
Hi Scott - Thanks for providing input! Do you have a minimal example that shows the type of calculations you would like to be faster with extended precision? Just so we are clear on the goal for this use case.
The majority of what we do is have a vector of extended precision times that we do various kinds of algebra on, using many NumPy routines and vectorized custom functions.
We don't usually have to do too many LAPACK-style heavy-duty matrix operations in extended precision.
Would you or some of your colleagues be open to helping maintain a library that adds the 80-bit extended precision dtype into NumPy? This would be a variation of Ralf's "option A."
The NumPy community has resources and assistance for onboarding new contributors, and I'm happy to provide additional assistance.
There are possibly a couple of us who might be willing to have a look at that. It is important enough for what we do that we really need a solution.