Date: Tue, 4 Aug 2015 13:06:28 +0200 From: Agnieszka Bielec <bielecagnieszka8@...il.com> To: john-dev@...ts.openwall.com Subject: Re: PHC: Argon2 on CPU 2015-08-02 23:07 GMT+02:00 Lukas Odzioba <lukas.odzioba@...il.com>: > 2015-08-02 22:46 GMT+02:00 Agnieszka Bielec <bielecagnieszka8@...il.com>: >> even SSE4_1 but I don't know if only one instruction >> blake2b-round.h:#define LOADU(p) _mm_loadu_si128( (__m128i *)(p) ) >> can make that it's SSE4_1 version (?) > > According to Intel's Intrinsics Guide: > https://software.intel.com/sites/landingpage/IntrinsicsGuide/ > this is an intrinsics for SSE2 instruction, if this is what you are asking for. > Also I guess that we should use unaligned access only where it is necessary. however argon2 uses SSE4_1 because reaches file blake2b-load-sse-41.h but I tested the speed with removed part with SSE4 and was the same
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.