This problem is quite difficult to deal with. I thought about it on the way home, and I don't want to have config.guess return:
nocona-lahf-unknown-gnu-linux How does the 32 bit code decide if MMX is available etc? I suppose config.guess returns p4mmx. That's just nasty. Feature flags should be dealt with separately. I don't even really like passing flags to the yasm code because it means doctoring the yasm build system, which is already complicated enough. Hmm, how does it distinguish processors which support SSE in 32 bit mode? Surely it doesn't do p4mmxsse. If we could exclude all 64 bit models not having support for LAHF by having config.guess identify them as x86_64 only, i.e. not amd64, core2, nocona, etc, then they can just run with the default x86_64 code. We need to remember to make all changes in fat.c as well as config.guess. Of course this doesn't help Brian much, who probably wants the core 2 code to run on all 64 bit intel processors so that he doesn't need a separate build project for them. IIt may also slow those processors down (though who knows, really). I'm open to other suggestions, but so far nothing else looks appealing. Bill. 2009/3/14 Jason Moxham <ja...@njkfrudils.plus.com>: > > > > > Early Intel CPUs with Intel 64 lacked LAHF and SAHF instructions available in > AMD64 until introduction of Pentium 4 G1 step in December 2005. LAHF and SAHF > are load and store instructions, respectively, for certain status flags. > These instructions are used for virtualization and floating-point condition > handling. > > > I'll find out model numbers soon > > > > On Saturday 14 March 2009 17:20:25 Gonzalo Tornaria wrote: >> On Sat, Mar 14, 2009 at 1:45 PM, Jason Moxham <ja...@njkfrudils.plus.com> > wrote: >> > I pretty sure all core2 cpus have lahf,sahf , it's just some Pentium D >> > dont have it . You can test the lahf_lm feature bit in cpuid to see if >> > it's got it >> >> Tested in: >> >> My laptop: model 6 / family 15 (core 2 duo T5300). >> My desktop is family 15 / model 6 (pentium D 930). >> >> The "lahf_lm" feature is present in both according to /proc/cpuinfo. >> >> Note that the laptop is "low end" core 2 (in the sense it has no VT >> extensions). The pentium D is "high end" (in the sense it has VT >> extensions --- low end would be pentium D 8xx). Maybe that makes a >> difference? >> >> OTOH, the kvm 64 bit virtual cpu (kvm 72) doesn't seem to know about >> the "lahf_lm" (meaning, it won't report it in cpuid, even if the host >> processor has it. I assume the instructions would work anyway.) >> >> Gonzalo >> >> > > > > > --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
