|
Message-ID: <1348913732.2541655.1681200997376@mail.yahoo.com> Date: Tue, 11 Apr 2023 08:16:37 +0000 (UTC) From: Chris Harrison <p0mmy_1@...oo.co.uk> To: john-users@...ts.openwall.com Subject: Re: John the Ripper efficiency Hi guys, My dissertation used JTR to compare the CPU hashing performance of 1-8 raspberry pi's using an MPICH cluster, against a selection of laptops and PC's I had around the house. This was done simply with the benchmarking facility, no passwords were cracked.Would this be of use to anybody? I did not use the whole library of hashes but did choose a good selection of them, and even with this limited selection there is a large amount of data to parse. Chris On Tue, 11 Apr 2023 at 8:45, magnum<magnumripper@...hmail.com> wrote: On 2023-04-07 17:29, Claudio André wrote: > Will run 2 OpenMP threads > Benchmarking: sha512crypt, crypt(3) $6$ (rounds=5000) [SHA512 128/128 SSE2 > 2x]... (2xOMP) DONE > Speed for cost 1 (iteration count) of 5000 > Raw: 1203 c/s real, 602 c/s virtual > > Benchmarking: sha512crypt, crypt(3) $6$ (rounds=5000) [SHA512 128/128 AVX > 2x]... (2xOMP) DONE > Speed for cost 1 (iteration count) of 5000 > Raw: 1657 c/s real, 829 c/s virtual > > Benchmarking: sha512crypt, crypt(3) $6$ (rounds=5000) [SHA512 256/256 AVX2 > 4x]... (2xOMP) DONE > Speed for cost 1 (iteration count) of 5000 > Raw: 3068 c/s real, 1541 c/s virtual > > Benchmarking: sha512crypt, crypt(3) $6$ (rounds=5000) [SHA512 512/512 > AVX512F 8x]... (2xOMP) DONE > Speed for cost 1 (iteration count) of 5000 > Raw: 8092 c/s real, 4056 c/s virtual I didn't look into this for a while. Ideally AVX2 should be 2x the speed of AVX. AVX512F includes the neat instruction vternarylogic() which is the same as nvidia's LOP3.LUT - it speeds up SHA-2 (and others) considerably and that's why it's more than double the speed of AVX2. magnum
Powered by blists - more mailing lists
Confused about mailing lists and their use? Read about mailing lists on Wikipedia and check out these guidelines on proper formatting of your messages.