Thanks, it works ok now, both "core2" and "nocona". However, the benchmark seems to favor using "nocona" for a very slight margin, even if nocona will not include lahf/sahf code, but it includes core2 asm code otherwise. This must be the gcc optimization with -mtune=nocona instead of -mtune=core2.
I did 48 runs with each configuration, in an otherwise idle system. The average score was: config=nocona: avg =4654.82 (min=4619.2, max=4676.5) config=core2: avg = 4632.86 (min=4575.1, max=4652.8) unfortunately, I mistakenly deleted the log and I only kept the score for the whole benchmark, I don't have separate scores for multiply/divide, etc. Note that I had previously reported a score of 4393.2 for that same cpu. That was using gcc-4.1, and I've since upgraded to gcc 4.3.2 as included in debian/lenny (stable). Gonzalo On Sun, Mar 15, 2009 at 10:31 AM, Jason Moxham <ja...@njkfrudils.plus.com> wrote: > > Done , > remove crlf from old add/sub_n and remove yasm macros from GLOBAL_FUNC names > > > On Sunday 15 March 2009 06:05:04 Bill Hart wrote: >> Damn. It's grepping for GLOBAL_FUNC and finding yasm macros and not >> expanding them I think. Hopefully we can fix that. >> >> Bill. >> >> 2009/3/15 Gonzalo Tornaria <torna...@gmail.com>: >> > As I mentioned, in current tr...@1739, my nocona is detected as a >> > "core2" by config.guess, since it does include lahf. >> > >> > However, I tried hacking config.guess so that my cpu returns "nocona" >> > instead --- just because I wanted to benchmark it that way (and also >> > would be a test of what happens when compiling in nocona w/o lahf). >> > But now, the configure step fails. >> > >> > The variables are: >> > >> > using ABI="64" >> > CC="gcc -std=gnu99" >> > CFLAGS="-O2 -m64 -march=nocona -mtune=nocona" >> > CPPFLAGS="" >> > MPN_PATH=" x86_64/core2 x86_64 generic" >> > >> > (so, it seems to be using core2 code, after all...) >> > >> > The first errors that show up in configure output are: >> > >> > checking for struct pst_processor.psp_iticksperclktick... no >> > =yes: command not found: HAVE_NATIVE_%3 >> > =yes: command not found: HAVE_NATIVE_%2 >> > =yes: command not found: HAVE_NATIVE_%3 >> > =yes: command not found: HAVE_NATIVE_%2 >> > >> > And later: >> > >> > checking size of unsigned short... 0 >> > checking size of unsigned... 0 >> > checking size of unsigned long... 0 >> > checking size of mp_limb_t... 0 >> > configure: error: Oops, mp_limb_t doesn't seem to work >> > >> > Here it stops... >> > >> > Gonzalo >> > >> > On Sat, Mar 14, 2009 at 10:49 PM, Gonzalo Tornaria <torna...@gmail.com> > wrote: >> >> My nocona with lahf is now a "core2-unknown-linux-gnu". Thanks for >> >> upgrading it for me... I hope it still keeps my office warm in winter >> >> >> >> :-) >> >> > > > > > --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "mpir-devel" group. To post to this group, send email to mpir-devel@googlegroups.com To unsubscribe from this group, send email to mpir-devel+unsubscr...@googlegroups.com For more options, visit this group at http://groups.google.com/group/mpir-devel?hl=en -~----------~----~----~----~------~----~------~--~---
