What is the portable 128-bit floating point type?

[Steve Kargl]

On Sat, May 25, 2019 at 03:53:57PM -0700, Steve Kargl wrote:
> On Sat, May 25, 2019 at 01:50:24PM -0700, Yuri wrote:
> > On 2019-05-25 13:04, Konstantin Belousov wrote:
> > > Neither i386 nor amd64 have hardware-supported 128 bit floating point
> > > type. long double is defined by both i386 and amd64 Unix ABI as 80 bits
> > > (10 bytes) representation as defined by IEEEE FP standard and supported
> > > by x87 FPU (not-SSE). The difference in size is due to the different
> > > natural alignment between 32 and 64 bit ISA.
> > 
> > So it looks like there is no true quad-precision float available.
> > 
> > Based on this conversation https://github.com/bluescarni/mppp/issues/186 
> > FreeBSD used to support __float128. Why was it removed?
> > 
> 
> gcc version 5 or 6 and up comes with libquadmath.  It is
> a software implementation of IEEE 128-bit floating point
> math.  You need sparc64 to have a 128-bit hardware support.
> 

BTW, using gfortran8 one finds

i386 FreeBSD
% gfortran8 -o z prec.f90 && ./z
Type         DD  BD   emin  emax
 32-bit FP:   6  24   -125   128
 64-bit FP:  15  53  -1021  1024
 80-bit FP:  15  53 -16381 16384
128-bit FP:  33 113 -16381 16384

x86_64 FreeBSD
Type         DD  BD   emin  emax
 32-bit FP:   6  24   -125   128
 64-bit FP:  15  53  -1021  1024
 80-bit FP:  18  64 -16381 16384
128-bit FP:  33 113 -16381 16384

DD = decimal digits
BD = binaray digits

All types are radix-2.

-- 
Steve