Closed Cuda-Chen closed 1 year ago
I would say "No" at first glance. At present, the SSE intrinsics coverage reaches 99%, and I am moving forward the extended AVX2NEON, which would reuse the infrastructure of SSE2NEON. The SHA1 series depend on wider memory access, and I would stick to AVX translation first.
Got it. Then I will close this issue for not confusing users.
Though
_mm_sha1
intrinsics do not belong to SSE, I consider I would like to implement as SHA-1 is a widely used has function.