(NB am using "asm goto" feature in the above code, it interacts poorly with optimization sometimes because gcc does not know it depends on the flags status) Jeroen van Bemmel, 13 years ago Comment on the SSE4.2 strlen() implementation: it actually performs much worse than the following SSE2...
Note that they are using SSE instead of AVX, so the issue doesn't seem to be inside the implementation of strlen but rather what is passed to strlen. Edit: Running with lldb gives even more information and it seems to be related to a panic which couldn't be handled: (lldb) r Process...