This is the mail archive of the libc-alpha@sourceware.org mailing list for the glibc project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: [QUERY] How many platforms are using the soft-float ieee128 math


On 17-10-2013 16:46, Steven Munroe wrote:
> As we consider evolving the emerging powerpc64le platform, it seems like
> an opportunity to make ABI changes/improvements at this early stage.
> Changes we would not consider for the existing BE PowerPC ecosystem.
>
> For example moving long double from IBM double-double to standard
> ieee128. With newer generation hardware providing VMX/VSX with stronger
> logical and integer arithmetic capabilities, emulating ieee128 is more
> viable now then in the past.
>
> But. we would like to understand the viability of the current soft-float
> ieee128 and libm functions. How many platforms are using it now and what
> is their experience.
>
> When I look at x86_64 we see long double is still generating x87 80-bit
> float. I was disappointed to learn that -m128bit-long-double only
> effects data alignment.
>
>From a simple search:

$ grep -w ldbl-128 `find . -iname Implies`
./ports/sysdeps/mips/mips64/n64/Implies:ieee754/ldbl-128
./ports/sysdeps/mips/mips64/n32/Implies:ieee754/ldbl-128
./ports/sysdeps/alpha/Implies:ieee754/ldbl-128
./ports/sysdeps/aarch64/Implies:ieee754/ldbl-128
./sysdeps/s390/Implies:ieee754/ldbl-128
./sysdeps/sparc/sparc64/Implies:ieee754/ldbl-128
./sysdeps/sparc/sparc32/Implies:ieee754/ldbl-128

And I believe it will be interesting to align with other architectures.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]