|
Message-ID: <a9fc0f4290baaa9ff4382c1423dadcc6@smtp.hushmail.com> Date: Sun, 24 May 2015 02:03:42 +0200 From: magnum <john.magnum@...hmail.com> To: john-dev@...ts.openwall.com Subject: Re: interleaving in SHA256 & SHA512 On 2015-05-23 04:55, Lei Zhang wrote: > SIMD_PARA_SHA512 = > [1] > Benchmarking: saph, SAP CODVN H (PWDSALTEDHASH) (SHA1x1024) [SHA-1/SHA-2 256/256 AVX2 8x2]... (8xOMP) DONE > Speed for cost 1 (hash type [1:sha1 2:SHA256 3:SHA384 4:SHA512]) of 1, cost 2 (iteration count) of 1024 > Many salts: 159176 c/s real, 20045 c/s virtual > Only one salt: 159744 c/s real, 19943 c/s virtual You need to re-run all those SAP H benchmark in order to actually use SHA512 at all. Your posted ones list speed for SHA1 only (it says "Speed for cost 1 of 1" which means SHA-1 according to the "1:sha1". This is SHA512 speed (on my laptop with para 1): $ ../run/john -test -form:saph -cost=4:4 Will run 8 OpenMP threads Benchmarking: saph, SAP CODVN H (PWDSALTEDHASH) (SHA1x1024) [SHA-1/SHA-2 128/128 AVX 4x2]... (8xOMP) DONE Speed for cost 1 (hash type [1:sha1 2:SHA256 3:SHA384 4:SHA512]) of 4, cost 2 (iteration count) of 7500 Many salts: 1950 c/s real, 253 c/s virtual Only one salt: 1861 c/s real, 250 c/s virtual 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.