Messages in this thread | | | Subject | Re: x86 memcpy performance | From | Valdis.Kletnieks@vt ... | Date | Mon, 15 Aug 2011 22:34:35 -0400 |
| |
On Sun, 14 Aug 2011 11:59:10 +0200, Borislav Petkov said:
> Benchmarking with 10000 iterations, average results: > size XM MM speedup > 119 540.58 449.491 0.8314969419
> 12273 2307.86 4042.88 1.751787902 > 13924 2431.8 4224.48 1.737184756 > 14335 2469.4 4218.82 1.708440514 > 15018 2675.67 1904.07 0.711622886 > 16374 2989.75 5296.26 1.771470902 > 24564 4262.15 7696.86 1.805863077 > 27852 4362.53 3347.72 0.7673805572 > 28672 5122.8 7113.14 1.388524413 > 30033 4874.62 8740.04 1.792967931
The numbers for 15018 and 27852 are *way* odd for the MM case. I don't feel really good about this till we understand what happened for those two cases.
Also, anytime I see "10000 iterations", I ask myself if the benchmark rigging took proper note of hot/cold cache issues. That *may* explain the two oddball results we see above - but not knowing more about how it was benched, it's hard to say.
[unhandled content-type:application/pgp-signature] | |