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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com