From: Eric Botcazou <ebotca...@adacore.com> Date: Sun, 25 Sep 2011 20:44:37 +0200
>> Eric, could you give this a quick spin on Solaris? Even if you >> don't have a FMAF capable cpu available, at least make sure the >> configury assembler feature detection bits work properly. > > This seems to work just fine on Solaris. Thanks for testing. >> And any other form of feedback is appreciated as well. This patch >> works fine for me with current binutils under Linux with a Niagara-3 >> processor. > > Why fall back to -xv8plusb/-xarch=v9b for Niagara-3 if > !HAVE_AS_FMAF_HPC_VIS3? > Reading the new binutils bits, it seems that -xv8plusc/-xarch=v9c would be > the > perfect match instead. We don't use any of the 'c' features, and also with binutils if 'd' isn't available then 'c' isn't either as I added them both at the same time. So if you really want me to try to downgrade to 'c' I'll need to add a seperate configure test for the availability of that option. > +mfmaf > +Target Report Mask(FMAF) > +Use UltraSPARC Fused Multiply extensions > > Maybe "Fused Multiply-Add extensions". Why is the final 'f' for exactly? FMA stands for "Fused Multiply-Add Floating-point", there are integer versions too which I'll add support for in the future. The integer ones are referred to as "IMA". >> I've done --with-cpu=niagara3 builds plus full testsuite regression >> check on sparc-linux-gnu. I also made sure that FMAF is actually >> being used by the compiler. > > Probably worth mentioning in gcc-4.7/changes.html too. Absolutely. I'll commit this with the -mfmaf description change you suggested, if you still want me to tweak the v9d fallback, we can stitch that up later.
