Mastering Cryptography Speed: Boost Performance with SSE, AVX, NEON & More 🔐

Most computer architectures, for example, x86, AMD64 and ARMv7 support efficient operations on vectors of data. The computational power of these instructions are most easily exploited if the same long streams of computations are carried out on independent sets of data. This is, for example, the case in many cryptanalytic computations. However, also single cryptographic computations can benefit from the computational power of vector instructions. In my talk I will consider various examples of such cryptographic computations and describe what implementation techniques are required to make best use of the vector instruction sets of various computer architectures.