Data processing method and processing core

Abstract

The embodiment of the invention provides a data processing method and a processing core. The method comprises the steps of receiving a calculation instruction, wherein the calculation instruction carries input data and a calculation type, and the calculation type comprises a modular multiplication type or a modular exponentiation type; according to the calculation type, determining a state sequence of a state machine, each state in the state sequence corresponding to a preset operation step; switching the state of the state machine according to the state sequence, outputting a first control signal to a corresponding multiplexer in each state of the state machine so as to control calculation data input into a Montgomery calculation unit through the multiplexer in each state, and executing operation steps corresponding to all the states based on the calculation data by the Montgomery calculation unit, wherein the calculation data comprises input data and / or an intermediate result obtained in a previous state; and after the operation step corresponding to the last state of the state sequence is executed, obtaining a calculation result of the calculation instruction. According to the embodiment of the invention, on the basis of reducing the circuit area overhead, the speed and concurrency of modular operation can be improved.

Description

technical field [0001] The invention relates to the technical field of computers, in particular to a data processing method and a processing core. Background technique [0002] Security and privacy computing uses cryptographic protocols based on semi-homomorphic or homomorphic encryption protocols for ciphertext calculation and transmission of big data. The modular multiplication operation and modular exponentiation operation of large integers are the basic operation units for realizing semi-homomorphic and homomorphic encryption algorithms. In addition, in a typical semi-homomorphic and homomorphic algorithm, there are usually both modular multiplication and modular exponentiation. Therefore, the underlying implementation of the algorithm needs to support both the modular multiplication of large integers and the modular exponentiation of large integers. [0003] Modular multiplication and modular exponentiation of large integers require multiple iterative operations, and t...

AI Technical Summary

Problems solved by technology

[0003] The modular multiplication operation and modular exponentiation operation of large integers require multiple iterative operations, and the calculation cost is high. If the calculation is performed directly through software, the calculation efficiency is difficult to meet the needs of massive data calculation scenarios.

If the calculation is performed by hardware circuits, since the modular multiplication operation and the modular exponentiation operation are separate modules, the overall circuit area will be the sum of the circuit area of ​​each operation unit, resulting in a large overhead of circuit resources, which not only consumes a lot of hardware costs, but also Computational performance affecting privacy computing systems

Images