> For all OpenSSL rc4-amd64s RC4_INT is int, not long. And for *all* > rc4-amd64 RC4_CHUNK is effectively long.
Yes, it's my fault. I also tested your new rc4-amd64.pl patch. But found performance down compared with v1.3 version both on Opteron and Nocona. Opteron 2.2G: rc4-amd64.v1.3 371MB/s rc4-amd64.new 306MB/s Nocona 3.6G: rc4-amd64.v1.3 290MB/s rc4-amd64.new 265MB/s Did you find the same phenomena? > > > > On AMD64, 'dec' is as fast as 'sub $1', but replacing 'ror' by 'shl+bswap' > > is indeed about 1% faster (thanks, I have updated rc4-amd64). Yes, I also found that. Thx, Xuekun ______________________________________________________________________ OpenSSL Project http://www.openssl.org Development Mailing List [EMAIL PROTECTED] Automated List Manager [EMAIL PROTECTED]
