![intel c compiler performance intel c compiler performance](http://i1.sinaimg.cn/IT/cr/2013/0903/3207548749.png)
GNU can run everywhere, but performance is around 2.5x worse on Linux for our application use case because it doesn't perform many of the optimisations that Intel does. My own tests found that PGI compiler performance was worse than Intel for C++, and that now appears to have been discontinued on Windows anyway with NVidia's new HPC compiler suite replacing it.
#INTEL C COMPILER PERFORMANCE UPGRADE#
We upgrade fairly regularly and that provides us with less work. So we can use it on Linux and Windows, and provides MPI cross platform. This is not really true IMO, but even as an aside, the Intel compiler has the enormous advantage of being available cross platform. There are other compilers with similar or better performance. We already tell people to set those environment variables in our documentation.
![intel c compiler performance intel c compiler performance](https://3.bp.blogspot.com/-zTArv1JFIQg/W_enCKdeT1I/AAAAAAAADjg/_0wYJouTCEYEOiFjrPwp3Rex_8ldedLUgCLcBGAs/s1600/dotchart.png)
We're well aware of this in my work, but the reality is that all our big corporate clients use Intel hardware. Circumstances differ, and I'm pointing out contrary experience, understanding the measurements and what determined them. It's expected to run large amounts of VASP-like code publishes usage of the current system.
#INTEL C COMPILER PERFORMANCE SERIAL#
It's not as if most codes topped out an arithmetic intensity and there was a serious problem with serial performance, even if MKL had been significantly better than the free libraries, which it wasn't.įor a recent exercise, spending rather more money on AMD CPUs for the UK Tier 1 system, look at the Archer2 reference and benchmarking for it. The large core-count AMD boxes were simply a better bet for the range of work on a university HPC system. I measured and paid attention to the MPI, which benefited everything using alltoallv. Anyhow, my all-free-software version of cp2k was faster on it than an all-Intel version on slightly faster CPUs on an otherwise equivalent cluster. If I'd had more influence on the purchase, as opposed to observing the process, we wouldn't have ended up with a pure sandybridge system, which was a mistake. I didn't see figures in what I was responding to. I don't remember, because the measurements on the £1M purchase was maybe five years ago, but they taught a useful lesson.