Virtualized SHA computational engine

A method, comprising:

• transmitting to a working memory via a plurality of switches a first input message;
• transmitting to the working memory via the plurality of switches a first portion of a second input message;
• transmitting to the working memory via the plurality of switches a second portion of the second input message independently from the first portion;
• simultaneously storing a first context corresponding to the first input message and a second context corresponding to the second input message in a context memory;
• and
• finishing calculations for generating a first output digest in a set of hardware computational elements based on the first input message and the first context after starting calculations for generating second output digest based the second input message and the second context and before finishing the calculations for generating of the second output digest in the set of hardware computation elements.

A system, comprising:

• a plurality of command queues each configured to store one or more commands;
• a job packet manager comprising a plurality of switches coupled with the plurality of command queues;
• and
• a computational engine coupled with the job packet manager, wherein the job packet manager is configured to distribute each of a first job packet and a second job packet to the computational engine, wherein the first job packet and the second job packet are associated with different commands, and wherein the computational engine comprises a set of hardware computational elements configured to finish calculations for generating a first output digest based on the first job packet and a first context after starting calculations for generating a second output digest based the second job packet and a second context and before completing the calculations for generating the second output digest.