https://github.com/armfazh/fld-ecc-vec

SIMD Vectorized implementation of X25519, Ed25519, X448 and Ed448
https://github.com/armfazh/fld-ecc-vec

avx2 cryptography ed25519 ed448 rfc7748 rfc8032 x25519 x448

Last synced: 14 days ago
JSON representation

SIMD Vectorized implementation of X25519, Ed25519, X448 and Ed448

• Host: GitHub
• URL: https://github.com/armfazh/fld-ecc-vec
• Owner: armfazh
• License: bsd-3-clause
• Created: 2017-10-23T21:05:15.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2024-08-09T07:37:57.000Z (3 months ago)
• Last Synced: 2024-10-25T05:09:05.537Z (21 days ago)
• Topics: avx2, cryptography, ed25519, ed448, rfc7748, rfc8032, x25519, x448
• Language: C
• Homepage: https://armfazh.github.io/publication/faz-ld-toms-2019/
• Size: 1.18 MB
• Stars: 27
• Watchers: 6
• Forks: 4
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.txt

Awesome Lists containing this project

README

        
# FLD ECC AVX2

This is a mathematical software library for computing the Edwards Digital Signature Algorithm (EdDSA) and the Diffie-Hellman functions X25519 and X448. The library is optimized with the Intel Advanced Vector eXtensions version 2 (AVX2) and is derived from a research project.

```bibtex

@article{fld_ecc_avx2,

    doi       = {10.1145/3309759},

    author    = {Armando Faz-Hern\'{a}ndez and

                 Julio L\'{o}pez and

                 Ricardo Dahab},

    title     = {High-performance Implementation of Elliptic Curve

                 Cryptography Using Vector Instructions},

    year      = {2019},

    journal   = {ACM Transactions on Mathematical Software (TOMS)},

    publisher = {ACM},

    volume    = {45},

    number    = {3},

    keywords  = {Edwards Digital Signature Algorithm, Ed25519,

                 Diffie-Hellman Protocol, AVX2 Vector Instructions,

                 Elliptic Curve Cryptography, Secure Software},

}    

```

### Compilation

To compile use:

```bash

    $ cd fld_ecc_avx2

    $ mkdir build; cd build

    $ cmake ..

    $ make all

```

### Benchmarks

For running the benchmark program use:

```bash

    $ ./bin/bench

```

The timings reported in the paper were obtained using the Clang compiler version 5.

```bash

    $ cd fld_ecc_avx2

    $ mkdir build; cd build

    $ CC=/path/to/clang cmake ..

    $ make

```

### Tests

For running the tests program use:

```bash

    $ ./bin/tests

```

### LICENSE

BSD 3-Clause [LICENSE.txt](LICENSE.txt)