[llvm-commits] LLVM patch to support ARM fused multiply add/subtract instructions

[Anton Korobeynikov]

Hal,

> Just to be clear, are you advocating associating this with UnsafeFPMath
> or with !NoExcessFPPrecision? I think that it should be the latter, as
> that is what the PPC backend does (and that seems to match the intent of
> the TargetOptions API authors), but unlike -ffast-math
> (-enable-unsafe-fp-math), this will cause the patterns to be enabled by
> default.
In the patch Ana posted FMA patterns were associated with ~NoExcessFPPrecision.
This is pretty much fine. But the "usual" VMLA patterns should not be
"downgraded" to
LessPreciseFPMAD, because it's not true.
-- 
With best regards, Anton Korobeynikov
Faculty of Mathematics and Mechanics, Saint Petersburg State University