US 12,333,270 B2
Calculating a floating-point function using multiple lookup tables
Mingran Wang, San Jose, CA (US); Xiaoyan Li, San Jose, CA (US); and Yongning Sheng, San Jose, CA (US)
Assigned to SambaNova Systems, Inc., Palo Alto, CA (US)
Filed by SambaNova Systems, Inc., Palo Alto, CA (US)
Filed on May 5, 2022, as Appl. No. 17/737,925.
Application 17/737,925 is a continuation of application No. 16/590,058, filed on Oct. 1, 2019, granted, now 11,327,713.
Prior Publication US 2022/0261220 A1, Aug. 18, 2022
Int. Cl. G06F 7/483 (2006.01); G06F 16/901 (2019.01); G06F 17/17 (2006.01)
CPC G06F 7/483 (2013.01) [G06F 16/9017 (2019.01); G06F 17/17 (2013.01)] 27 Claims
OG exemplary drawing
 
1. A computation unit, comprising:
input lines to provide a floating-point value, the input lines including exponent lines and mantissa lines;
a first lookup table having a first address input coupled to a first subset of the input lines and providing a first output, the first subset of the input lines including a most significant bit of the exponent lines;
a second lookup table having a second address input coupled to a second subset of the input lines and providing a second output, the second subset of the input lines excluding the most significant bit of the exponent lines;
a range detector, coupled to at least some of the input lines, to indicate, on a range output, whether the floating-point value provided on the input lines is within a specified range; and
an output stage, operatively coupled to the first output, the second output and the range output, to generate a function output based on the first output, the second output, and the range output.