US 11,914,447 B1
Approximate computation in digital systems using bit partitioning
Farnood Merrikh Bayat, Goleta, CA (US)
Assigned to MENTIUM TECHNOLOGIES INC., Santa Barbara, CA (US)
Filed by MENTIUM TECHNOLOGIES INC., Santa Barbara, CA (US)
Filed on Nov. 20, 2020, as Appl. No. 17/100,684.
Claims priority of provisional application 62/938,207, filed on Nov. 20, 2019.
Claims priority of provisional application 62/938,217, filed on Nov. 20, 2019.
Claims priority of provisional application 62/938,214, filed on Nov. 20, 2019.
Claims priority of provisional application 62/938,211, filed on Nov. 20, 2019.
Int. Cl. G06F 1/32 (2019.01); G06F 1/3234 (2019.01); G06F 9/50 (2006.01); G06F 5/01 (2006.01); G06F 7/523 (2006.01); G06F 7/50 (2006.01); G06F 7/544 (2006.01)
CPC G06F 1/3243 (2013.01) [G06F 5/01 (2013.01); G06F 7/50 (2013.01); G06F 7/523 (2013.01); G06F 7/5443 (2013.01); G06F 9/5027 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method for reducing power consumed in processing units used to calculate computationally expensive operations, the method comprising:
receiving a dot-product computation to be calculated at a specified number of bits;
breaking down the dot-product computation into a plurality of intermediate operations having 1-bit or 2-bit element input vectors;
assigning a gain value to each intermediate operation in the plurality of intermediate operations, wherein the gain value assigned to each intermediate operation is based on an analysis of the 1-bit or 2-bit element input vectors;
determining a threshold gain value; and
reducing the calculation precision for the intermediate operations that do not meet or exceed the threshold gain value.