On 06/24/2014 10:36 AM, Ramana Radhakrishnan wrote: > > > On 24/06/14 15:11, Vladimir Makarov wrote: >> A few people asked me about new performance comparison of latest GCC >> and LLVM. So I've finished it and put it on my site >> >> http://vmakarov.fedorapeople.org/spec/ >> >> The comparison is achievable from 2014 link and links under it in >> the left frame. >> >> These pages are also achievable as >> >> http://vmakarov.fedorapeople.org/spec/2014/2014.html -- what I >> compare, my motivation, major results, and my conclusions. >> >> http://vmakarov.fedorapeople.org/spec/2014/llvmgcc64.html -- The >> results of comparison on x86-64 SPECInt2000 >> >> http://vmakarov.fedorapeople.org/spec/2014/arm.html -- The >> results of comparison on ARM SPECInt2000 > > Interesting ... > > On ARM, I note that by default you are generating code for > fpu=vfpv3-d16 and armv7-a. Of interest is the fact that you aren't > using the Neon unit at all if you configure the compiler with > --with-fpu=vfpv3-d16 > Unfortunately, that is the configuration I can use on my system because of lack of libraries for other configurations.
I don't think Neon can improve score for SPECInt2000 significantly but may be I am wrong. > Did you add any other architecture specific options to your SPEC2k runs ? > > No. The only options I used are -Ofast. Could you recommend me what best options you think I should use for this processor. As I wrote, I am more interesting in aarch64 which can be used in a server (as you know RedHat works on a server market) but unfortunately I have no such machine for SPEC benchmarking.
