US 11,755,431 B2
Identification of optimal bit apportionments for digital functions subject to soft errors
Steven J. Manson, Tucson, AZ (US)
Assigned to Rattheon Company, Waltham, MA (US)
Filed by Raytheon Company, Waltham, MA (US)
Filed on Sep. 2, 2021, as Appl. No. 17/464,938.
Prior Publication US 2023/0205651 A1, Jun. 29, 2023
Int. Cl. G06F 11/18 (2006.01); G06F 11/16 (2006.01); G06F 11/14 (2006.01)
CPC G06F 11/167 (2013.01) [G06F 11/1471 (2013.01); G06F 11/187 (2013.01); G06F 2201/82 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
identifying multiple apportionments, each apportionment identifying numbers of bit copies to be stored in at least one memory for at least some bits of a data value;
for each of the apportionments, estimating a numerical error associated with use of the apportionment with a specified function, the numerical error estimated by creating errors in bit copies of multiple data values processed using the specified function;
combining portions of different ones of the apportionments having lower estimated numerical errors to create multiple derived apportionments;
for each of the derived apportionments, estimating a numerical error associated with use of the derived apportionment with the specified function; and
selecting a final apportionment for use with the specified function, the final apportionment comprising or based on at least one of the derived apportionments.