Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

High-throughput modular inversion calculation method and system in parallel environment

A high-throughput, computing method technology, applied in the field of information security, can solve problems such as unsatisfactory throughput, and achieve the effect of avoiding computing overhead, reducing thread warp differentiation, and high throughput

Active Publication Date: 2021-05-14
XIDIAN UNIV
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0014]Aiming at the problems existing in the prior art, the present invention provides a high-throughput modular inverse calculation method and system in a parallel environment, aiming to solve the existing There is a problem of unsatisfactory throughput when the algorithm is applied in a parallel environment

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • High-throughput modular inversion calculation method and system in parallel environment
  • High-throughput modular inversion calculation method and system in parallel environment
  • High-throughput modular inversion calculation method and system in parallel environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] Aiming at the purpose of improving the throughput of modular inverse computing on a parallel computing platform, the present invention proposes a parallelized and improved high-throughput modular inverse computing method based on simultaneous modular inverse algorithms. The specific process is as follows:

[0066] S1: In the data division stage, select appropriate parameters according to the scale of the input data and the computing power of the parallel computing platform. This parameter indicates the number of data contained in each group after grouping. According to this parameter, the data is grouped and numbered, and then the original input is established. One-to-one mapping relationship between data and grouped data.

[0067] S2: In the parallel inversion stage, open multiple threads on the parallel computing device to receive the input corresponding to multiple sets of data, and run the simultaneous modular inversion algorithm in parallel among the threads. The s...

Embodiment 2

[0070] Such as Figure 4 As shown, the high-throughput modular inverse calculation method under the parallel environment of the present invention accepts a 1 , a 2 ,...,a 2048 A total of 2048 inverse values ​​and modulus p, output A total of 2048 modular inverse values, a i , and p are both 256-bit large integers, including three stages:

[0071] (1) In the data division stage, the parameter k=32 is selected according to the number 2048 of the inverse values ​​to be calculated and the computing power of the parallel computing platform, and the inverse values ​​to be calculated are divided into numbering i=1, 2, ..., 64, 64 in total A set of data, wherein each set of data includes a total of 32 inverse values ​​to be calculated with numbers j=1, 2, ..., 32. After completing the division, establish a 1 , a 2 ,...,a 2048 The 2048 input values ​​and the divided data a i,j (i=1,2,...,64, j=1,2,...,32) mapping relationship:

[0072] (2) In the parallel inversion stage...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention belongs to the technical field of information security, and discloses a high-throughput modular inversion calculation method and system in a parallel environment. M to-be-inversed values (a1, a2, ..., am) and a modulus p are received, m modular inversion values are output, wherein the processes comprise three stages: a data division stage, a parallel inversion stage and a data group integration stage. The high-throughput modular inversion computing system in the parallel environment comprises a data division module based on parallel platform computing resources, a parallel inversion module based on a simultaneous modular inversion algorithm, a data set integration module based on a mapping relation and a performance analysis module based on a historical operation result. According to the method, the characteristic that modular inverse operation is converted into modular multiplication operation through the simultaneous modular inverse algorithm is utilized, so that the high-concurrency modular inverse time thread beam differentiation phenomenon is relieved, and the parallel simultaneous modular inverse algorithm is designed for solving the problem that the serial simultaneous modular inverse algorithm cannot give full play to all performance of a parallel platform. Therefore, the modular inverse operation throughput in the parallel environment is greatly improved.

Description

technical field [0001] The invention belongs to the technical field of information security, and in particular relates to a high-throughput modular inverse calculation method and system in a parallel environment. Background technique [0002] At present, with the development of e-commerce, e-commerce platforms need to perform more and more large-scale digital signature calculations every second to ensure the security of transactions. As a general-purpose high-performance parallel computing platform, GPU (Graphics Processing Unit) is very suitable for accelerated computing of such high-concurrency business. However, in a parallel environment with weak branch prediction capabilities such as the GPU, the modular inversion algorithm, which requires a large number of branch judgments, is a major bottleneck in improving the total throughput of digital signature algorithms. [0003] At present, the commonly used modular inverse calculation methods are based on the extended Euclide...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F7/72G06F21/64
CPCG06F7/721G06F21/64Y02D10/00
Inventor 朱辉黄煜坤李晖刘兴东李临风
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products