speedup in mpfr_fma and mpfr_fms

new functions mpfr_fmma and mpfr_fmms
modified mbench/fma to compute b*c+c instead of b*b+c (b*c+d would be better)


git-svn-id: svn://scm.gforge.inria.fr/svn/mpfr/trunk@9788 280ebfd0-de03-0410-8827-d642c229c3f4

1 files changed, 3 insertions, 1 deletions

diff --git a/NEWS b/NEWS
index f006866d1..68435d76d 100644
--- a/NEWS
+++ b/NEWS
@@ -40,6 +40,7 @@ Changes from versions 3.1.* to version 3.2.0:
   rounding to nearest-away (as defined in IEEE 754-2008).
 - New functions mpfr_nrandom and mpfr_erandom to generate random numbers
   following normal and exponential distributions respectively.
+- New functions mpfr_fmma and mpfr_fmms to compute a*b+c*d and a*b-c*d.
 - The behavior of the mpfr_set_exp function changed, as it could easily
   yield undefined behavior in some cases (this modifies both the API and
   the ABI).
@@ -62,7 +63,8 @@ Changes from versions 3.1.* to version 3.2.0:
 - New MPFRbench program (see the tools/bench directory).
 - Speedup in the mpfr_const_euler function (contributed by Fredrik Johansson),
   in the computation of Bernoulli numbers (used in mpfr_gamma, mpfr_li2,
-  mpfr_digamma, mpfr_lngamma and mpfr_lgamma), and in mpfr_div.
+  mpfr_digamma, mpfr_lngamma and mpfr_lgamma), in mpfr_div, in mpfr_fma
+  and mpfr_fms.
 - Bug fixes. In particular: a speed improvement when the --enable-assert
   or --enable-assert=full configure option is used with GCC; mpfr_get_str
   now sets the NaN flag on NaN input.