Closed jedisct1 closed 9 hours ago
MACs:
aegis-128x4 mac: 71291 MiB/s
aegis-128x2 mac: 62049 MiB/s
aegis-128l mac: 31178 MiB/s
aegis-256x4 mac: 28398 MiB/s
aegis-256x2 mac: 15602 MiB/s
aegis-256 mac: 8226 MiB/s
siphash128-1-3: 7064 MiB/s
siphash128-2-4: 4277 MiB/s
hmac-sha256: 2126 MiB/s
hmac-sha512: 742 MiB/s
Modern Intel CPUs with the VAES extension can handle more than a single AES block per instruction.
So can some ARM and RISC-V CPUs. Software implementations with bitslicing can also greatly benefit from this.
Implement low-level operations on AES block vectors, and the parallel AEGIS variants on top of them.
AMD Zen4:
AES-GCM, and anything based on AES-CTR are also going to benefit from this later.