md5($salt.$pass) vs md5($pass.$salt) speeds

[spin711]

Hi everyone,
I'm playing with a list of MD5 hashes that have password length of 11 (lowered alpha-numeric) and salt length of 14. I have to attack with md5($salt.$pass)


Because the keyspace is too large 36^11, speed is critical and I noticed in the benchmark result that md5($pass.$salt) has almost the same speed with raw MD5 (-m 0), which nearly double as compare to md5($salt.$pass).

Can someone explain why they are both "half MD5" but so different in speed? Prepend is costly than append?
Is there any other ways to improve this attack?

Thank you!

[atom]

There's multiple reasons. The way how hashcat exploits some weakness in MD5 to get additional acceleration requires it to change only the first 4 bytes of the input data. Since this part is fixed (because of the salt) it cannot use the acceleration.

For half MD5 it's completely different and therefore a bit confusing how you go from md5(p.s) to half-md5. For half MD5 the hash is not known in full, therefore we can not reverse the internal hash state up to a certain point to do the early reject.

[spin711]

Thanks Atom for correcting me.
Guess I have to wait