On 1/16/19 2:29 AM, Thomas Huth wrote: > ... but at least it gives the same results as the DLGR instruction. The 64-bit > version gives different results - do we have a bug here?
Yes, on your inputs. udiv_qrnnd3 requires that D be "normalized", i.e. have the most siginificant bit set. (And thus N1:N0 shifted left to match, and the returned remainder shifted right to match.) r~