Re: [Mono-list] numerical performance comparison [C++ vs JVM vs Mono]

2010-10-04 Thread Rodrigo Kumpera
Hi Jonathan, Mono 64bits uses the x87 square root instruction which is far from optimal since it requires 2 stores and 1 load. Zoltan, is it possible to switch to SQRTSD? And, yes, mono does have some issues with register allocation. It's something that will be worked on in the mid term thou.

Re: [Mono-list] numerical performance comparison [C++ vs JVM vs Mono]

2010-10-04 Thread ted leslie
i did the exact same thing, and dumped the assembly generated by c and c# on nbody, in addition to the sqrt issue, which i believe is pre and post a SSEn, where mono isn't as uptodate on full use of SSEn , the other issue was, mono did a few sets of unnecessary register transfer, as compared to

[Mono-list] numerical performance comparison [C++ vs JVM vs Mono]

2010-10-04 Thread Jonathan Shore
Hi, I am looking forward to moving all of my code from Java / C++ to F# / C# in the very near future. I took the nbody code from the language shootout and ran with 500 million iterations (much more than used in the shootout to provide a fair comparison) on ubuntu server on a core i7 920 box.