In message <[EMAIL PROTECTED]> on Tue, 09 Dec 2003 14:28:23 +0100, Andy Polyakov <[EMAIL PROTECTED]> said:
appro> This is a poll for votes. appro> appro> It was noted that [at least] Intel IA-32 compiler, linux-ia32-icc appro> target, generates *noticeably*, 30% to be specific, faster code for SHA1 appro> than hand-coded assembler implementation on at least P4 platform. I have appro> re-tuned SHA1 assembler implementation which now performs as following: appro> appro> compared with current compared with icc appro> assembler impl. generated code appro> Pentium -25% +37% appro> PIII/AMD +8% +16% appro> P4 +85%(!) +45% appro> appro> Options for integrating re-tuned code are: appro> appro> 1. replace crypto/sha/asm/sha1-586.pl and let couple of Pentium users appro> suffer 25% performance loss; appro> 2. add crypto/sha/asm/sha1-686.pl, make it default, so that couple of appro> Pentium users *can* pull old code if they need 25% back; appro> 3. add crypto/sha/asm/sha1-686.pl and have ./config choose between two appro> versions, depending on which computer ./config is executed; #1: +1 ----- Please consider sponsoring my work on free software. See http://www.free.lp.se/sponsoring.html for details. You don't have to be rich, a $10 donation is appreciated! -- Richard Levitte \ Tunnlandsv�gen 3 \ [EMAIL PROTECTED] [EMAIL PROTECTED] \ S-168 36 BROMMA \ T: +46-8-26 52 47 \ SWEDEN \ or +46-708-26 53 44 Procurator Odiosus Ex Infernis -- [EMAIL PROTECTED] Member of the OpenSSL development team: http://www.openssl.org/ Unsolicited commercial email is subject to an archival fee of $400. See <http://www.stacken.kth.se/~levitte/mail/> for more info. ______________________________________________________________________ OpenSSL Project http://www.openssl.org Development Mailing List [EMAIL PROTECTED] Automated List Manager [EMAIL PROTECTED]
