[libre-riscv-dev] [Bug 97] FP16 mul bug

bugzilla-daemon at libre-riscv.org bugzilla-daemon at libre-riscv.org
Tue Jul 16 10:49:14 BST 2019


Luke Kenneth Casson Leighton <lkcl at lkcl.net> changed:

           What    |Removed                     |Added
         Resolution|---                         |FIXED
             Status|CONFIRMED                   |RESOLVED

--- Comment #2 from Luke Kenneth Casson Leighton <lkcl at lkcl.net> ---
fixed: was related to the normalisation phases being entirely missing.
tiny numbers just above zero were entering the MUL phase with the
mantissa not being '1' in the MSB.  consequently the product was
nowhere near accurate.

fixed by shifting both A and B up so that the mantissa always has "1"
in the MSB.

You are receiving this mail because:
You are on the CC list for the bug.

More information about the libre-riscv-dev mailing list