[Arm-netbook] RedSleeve - New ARM Linux Distro

[Gordan Bobic]

Vladimir Pantelic wrote:
> Gordan Bobic wrote:
> 
>> It is also not even clear that 12.04 is hard-float - both list kernels
>> as armv7l, rather than armv7hl. The test where I'd have expected to see
>> no difference (gzip compression isn't exactly very FP heavy) has one of
>> the biggest differences. So I'm not convinced how relevant the results
>> are to a relative performance assessment of SF vs. HF - at a glance it
>> seems more plausible the differences come from optimizations in the
>> packages themselves and possibly a better compiler toolchain.
> 
> most of the soft float vs hard float comparisons "out there" are flawed
> because they at the same time compare (ancient) armv5 code with floating
> point *emulation* with armv7 code using the VFP and hardfp calling
> convention.

It's nowhere nearly as clear cut in the case of emulation (soft) vs 
soft-float (VFP with old ABI), as I've explained here:
http://www.raspberrypi.org/forum/distributions/redsleeve-linux-on-raspberry-pi/#p62612

In a lot of cases soft-float is actually slower than emulation.

Hard-float should be faster in all cases, but it'll only make a 
difference if the code uses a lot of FP.

> comparing *only* soft vs hard calling convention yields much more
> reasonable results:
> 
> http://markmail.org/message/to7jc6dx2h7tt7ak

Indeed, on something very FP heavy that doesn't context switch between 
functions much like povray, soft-float is only 5-10% slower than 
hard-float. I would expect soft (fully emulated) to be much slower in 
this case.

But all this will still make no difference in applications that don't 
use FP operations - I wouldn't expect to see any meaningful difference 
between soft, soft-float and hard-float on those.

Gordan