You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@mkannwischer and my paper https://kannwischer.eu/papers/2022_armv8keccak.pdf investigates a myriad of different hybrid Keccak implementations. In mlkem-native, we do have scalar-v8a and scalar-v8a-v84a hybrids, but they are not as aggressively micro-optimized as the ones in the paper.
We should compare the performance of mlkem-native's current (and FV'ed) implementations to that from the paper, and decide whether there's merit in optimizing them further.
The text was updated successfully, but these errors were encountered:
@mkannwischer and my paper https://kannwischer.eu/papers/2022_armv8keccak.pdf investigates a myriad of different hybrid Keccak implementations. In mlkem-native, we do have scalar-v8a and scalar-v8a-v84a hybrids, but they are not as aggressively micro-optimized as the ones in the paper.
We should compare the performance of mlkem-native's current (and FV'ed) implementations to that from the paper, and decide whether there's merit in optimizing them further.
The text was updated successfully, but these errors were encountered: