Re: [PATCH 00/12] crypto: sha256 - Use partial block API
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: 2025-05-01 05:19:16
Also in:
linux-arch, linux-arm-kernel, linux-crypto, linux-mips, linux-riscv, linux-s390, lkml, sparclinux
On Wed, Apr 30, 2025 at 07:26:17PM -0700, Eric Biggers wrote:
Interesting approach -- pushing out misguided optimizations without data, then demanding data for them to be reverted. It's obviously worse for len % 64 < 56 for the reason I gave, so this is a waste of time IMO. But since you're insisting on data anyway, here are some quick benchmarks on AMD Zen 5 (not going to bother formatting into a table): Before your finup "optimization":
Thanks, I'll revert to the single-block version. -- Email: Herbert Xu [off-list ref] Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt