Vitalik: I hope more researchers working on ZK and FHE can use overhead ratio to express performance instead of operations per second.
Vitalik posted on the X platform, "I hope more people who do ZK (zero-knowledge proof) and FHE (fully homomorphic encryption) can express performance using cost ratio, rather than just saying 'we can do N calculations per second'. This way is less dependent on hardware and can provide a very useful metric: how much efficiency am I sacrificing when I change the application from 'trust-based' to 'cryptography-based'? It is also more suitable for performance estimation, because as a developer, I already know how much time the original calculation takes, so I can estimate the performance by simply multiplying the cost ratio. (Yes, I know this is not easy, because the types of operations between execution and proof are different, especially in SIMD/parallelization and memory access methods, so even the cost ratio still partially depends on hardware. However, I still believe that the 'cost ratio' is a very valuable metric, although it is not perfect.)"
