This is the mail archive of the
mailing list for the glibc project.
[QUERY] How many platforms are using the soft-float ieee128 math
- From: Steven Munroe <munroesj at linux dot vnet dot ibm dot com>
- To: "GNU C. Library" <libc-alpha at sourceware dot org>
- Cc: wschmidt at us dot ibm dot com, azanella at us dot ibm dot com, Ulrich Weigand <Ulrich dot Weigand at de dot ibm dot com>
- Date: Thu, 17 Oct 2013 14:46:24 -0500
- Subject: [QUERY] How many platforms are using the soft-float ieee128 math
- Authentication-results: sourceware.org; auth=none
- Reply-to: munroesj at us dot ibm dot com
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.