You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
All the different extended floating point types like __half, bfloat, fp8, fp4, fp6, etc. are basically just a collection of N bits where M bits are dedicated to mantissa, E bits to exponent.
We can lean into this idea by creating an overarching type that is just:
floating_point<NumMantissaBits, NumExponentBits>
this would dispatch to corresponding built-in or accelerated types for the appropriate number of bits.
The content you are editing has changed. Please copy your edits and refresh the page.
All the different extended floating point types like __half, bfloat, fp8, fp4, fp6, etc. are basically just a collection of N bits where M bits are dedicated to mantissa, E bits to exponent.
We can lean into this idea by creating an overarching type that is just:
this would dispatch to corresponding built-in or accelerated types for the appropriate number of bits.
Tasks
floating_point<M, E>
limited to arithmetic operations #1666The text was updated successfully, but these errors were encountered: