Version 2.2 of the optimized implementations is now available.

Compared to the previous version, this package provides some new implementations, all written by Ronny Van Keer, STMicroelectronics, namely:

• An assembly implementation for ARM processors, optimized for Cortex-M3 specifically—although at this point it is written in the syntax of RVCT's armcc/armasm, not yet in a syntax understood by GCC.
• A simple yet optimized implementation in C covering from Keccak-f[200] to Keccak-f[1600].
• An implementation in C meant to be reasonably compact in terms of both code size and memory usage. (E.g., we provide an API for giving partial input chunks, where these partial input chunks are XORed directly into the state of Keccak to remove the need of a separate message queue.)

The new package also contains various improvements here and there, including a wider range of supported variants. A subset of these new variants and implementations has been submitted to eBASH.