Andy Polyakov wrote:
Now I agree ;) 1.8 version is "best-balanced" for all architectures.
I'm not sure I agree: I've grabbed the 1.8 version and rebuilt openssl
1.0.1c and tested it on an i5
i5 says exactly nothing, please don't use it. Say Nehalem, Sandy Bridge,
whatever, but not i5!
and a Core 2 Duo; performance is better
than the non-patched version but it is WORSE compared to the original
version of the sha256-586.pl script that was posted here before on May
11th.
version 11/05/2015:
sha256 39017.64k 87648.54k 150106.58k 183705.94k
197330.99k
version 1.8:
sha256 33560.42k 73153.83k 121472.43k 167948.67k
180955.23k
It sounds like we're talking about Nehalem, as it's very close to
difference reported by Pavel:
i5 Lynnfield 1250 / 1426 / 1271 / 1121 / 1033
more results:
i5-560M (Arrandale):
no patch 34040.33k 74466.07k 124345.23k 152376.03k 162949.09k
patch 11/05 38922.49k 88027.86k 151124.68k 184797.07k 197566.93k
patch-1.8 33525.23k 73799.17k 122710.39k 169429.19k 182747.58k
Core2 E6550 (Conroe):
no patch 23735.61k 54419.78k 93057.45k 115254.61k 123923.11k
patch 11/05 27216.54k 63764.33k 112310.44k 138860.54k 148624.73k
patch-1.8 24118.46k 55799.57k 96415.49k 137738.58k 149411.16k
Xeon X5660 (Westmere-EP):
no patch 30288.81k 69069.08k 117933.40k 145430.53k 155427.55k
patch 11/05 34431.21k 80946.11k 142910.72k 176818.18k 189199.82k
patch-1.8 29587.88k 67710.55k 116092.16k 161652.39k 173996.99k
Xeon E5440 (Harpertown):
no patch 29626.31k 67556.19k 115481.26k 142789.83k 153533.32k
patch 11/05 33937.95k 78971.79k 138890.72k 172167.74k 184211.14k
patch-1.8 29645.14k 68659.05k 119742.60k 169329.66k 183457.25k
For all 4 platforms the 11/5/2012 patch was the fastest.
I don't have an Atom based box to test it on.
share and enjoy,
JJK / Jan Just Keijser
