Reduced sized encoding of packet length field

Abstract

Implementations of the present disclosure are directed to systems and methods for reducing the size of packet headers without reducing the range of packet lengths supported. A packet header includes a fixed-width length field. Using a linear encoding, the maximum packet size is a linear function of the fixed-width length field. Thus, to expand the range of sizes available, either the granularity of the field must be decreased (e.g., by changing the measure of the field from flits to double-flits) or the size of the field must be increased (e.g., by changing the size of the field from 4 bits to 5 bits). However, by using a non-linear encoding, the difference between the minimum and maximum size can be increased without decreasing the granularity within a first range of field values and without increasing the size of the length field.

Dependencies are inferred from the claim text.