On Tue, Dec 04, 2018 at 18:34:18 +0000, Alex Bennée wrote: > > Emilio G. Cota <c...@braap.org> writes: (snip) > > Note that the IBM and ARM machines benefit from having > > HARDFLOAT_2F{32,64}_USE_FP set to 0. Otherwise their performance > > can suffer significantly: > > Is this just the latency of pushing the number into a SIMD register and > checking the flags compared to a bitmask check?
That's the case in the generated x86 assembly, so I presume the same it's happening in the other ISAs (I didn't check the assembly there). (snip) > > Hmm the diff is confusing but the changes look fine in the final code: > > Reviewed-by: Alex Bennée <alex.ben...@linaro.org> Thanks! E.