Add narrowing fma functions

This patch adds the narrowing fused multiply-add functions from TS
18661-1 / TS 18661-3 / C2X to glibc's libm: ffma, ffmal, dfmal,
f32fmaf64, f32fmaf32x, f32xfmaf64 for all configurations; f32fmaf64x,
f32fmaf128, f64fmaf64x, f64fmaf128, f32xfmaf64x, f32xfmaf128,
f64xfmaf128 for configurations with _Float64x and _Float128;
__f32fmaieee128 and __f64fmaieee128 aliases in the powerpc64le case
(for calls to ffmal and dfmal when long double is IEEE binary128).
Corresponding tgmath.h macro support is also added.

The changes are mostly similar to those for the other narrowing
functions previously added, especially that for sqrt, so the
description of those generally applies to this patch as well.  As with
sqrt, I reused the same test inputs in auto-libm-test-in as for
non-narrowing fma rather than adding extra or separate inputs for
narrowing fma.  The tests in libm-test-narrow-fma.inc also follow
those for non-narrowing fma.

The non-narrowing fma has a known bug (bug 6801) that it does not set
errno on errors (overflow, underflow, Inf * 0, Inf - Inf).  Rather
than fixing this or having narrowing fma check for errors when
non-narrowing does not (complicating the cases when narrowing fma can
otherwise be an alias for a non-narrowing function), this patch does
not attempt to check for errors from narrowing fma and set errno; the
CHECK_NARROW_FMA macro is still present, but as a placeholder that
does nothing, and this missing errno setting is considered to be
covered by the existing bug rather than needing a separate open bug.
missing-errno annotations are duly added to many of the
auto-libm-test-in test inputs for fma.

This completes adding all the new functions from TS 18661-1 to glibc,
so will be followed by corresponding stdc-predef.h changes to define
__STDC_IEC_60559_BFP__ and __STDC_IEC_60559_COMPLEX__, as the support
for TS 18661-1 will be at a similar level to that for C standard
floating-point facilities up to C11 (pragmas not implemented, but
library functions done).  (There are still further changes to be done
to implement changes to the types of fromfp functions from N2548.)

Tested as followed: natively with the full glibc testsuite for x86_64
(GCC 11, 7, 6) and x86 (GCC 11); with build-many-glibcs.py with GCC
11, 7 and 6; cross testing of math/ tests for powerpc64le, powerpc32
hard float, mips64 (all three ABIs, both hard and soft float).  The
different GCC versions are to cover the different cases in tgmath.h
and tgmath.h tests properly (GCC 6 has _Float* only as typedefs in
glibc headers, GCC 7 has proper _Float* support, GCC 8 adds
__builtin_tgmath).

3 files changed, 24 insertions, 0 deletions

diff --git a/sysdeps/powerpc/fpu/libm-test-ulps b/sysdeps/powerpc/fpu/libm-test-ulps
index fda4ca4..5f2b90b 100644
--- a/sysdeps/powerpc/fpu/libm-test-ulps
+++ b/sysdeps/powerpc/fpu/libm-test-ulps
@@ -1250,12 +1250,28 @@ ldouble: 1
 Function: "fma_downward":
 ldouble: 1
 
+Function: "fma_downward_ldouble":
+double: 1
+float: 1
+
+Function: "fma_ldouble":
+double: 1
+float: 1
+
 Function: "fma_towardzero":
 ldouble: 2
 
+Function: "fma_towardzero_ldouble":
+double: 1
+float: 1
+
 Function: "fma_upward":
 ldouble: 3
 
+Function: "fma_upward_ldouble":
+double: 1
+float: 1
+
 Function: "fmod":
 ldouble: 1
 
diff --git a/sysdeps/powerpc/powerpc64/le/fpu/multiarch/float128-ifunc-macros.h b/sysdeps/powerpc/powerpc64/le/fpu/multiarch/float128-ifunc-macros.h
index abab686..6d6f6b5 100644
--- a/sysdeps/powerpc/powerpc64/le/fpu/multiarch/float128-ifunc-macros.h
+++ b/sysdeps/powerpc/powerpc64/le/fpu/multiarch/float128-ifunc-macros.h
@@ -24,11 +24,13 @@
    from _Float128 implementation objects.  */
 #include <libm-alias-float128.h>
 #include <libm-alias-finite.h>
+#include <math-narrow-alias.h>
 
 #undef libm_alias_float128_r
 #undef libm_alias_finite
 #undef libm_alias_exclusive_ldouble
 #undef libm_alias_float128_other_r_ldbl
+#undef libm_alias_float128_narrow
 #undef declare_mgen_finite_alias
 #undef declare_mgen_alias
 #undef declare_mgen_alias_r
@@ -38,6 +40,7 @@
 #define libm_alias_float128_r(from, to, r)
 #define libm_alias_exclusive_ldouble(from, to)
 #define libm_alias_float128_other_r_ldbl(from, to, r)
+#define libm_alias_float128_narrow(from, to)
 #define declare_mgen_finite_alias(from, to)
 #define declare_mgen_alias(from, to)
 #define declare_mgen_alias_r(from, to)
diff --git a/sysdeps/powerpc/powerpc64/le/fpu/multiarch/float128-ifunc.h b/sysdeps/powerpc/powerpc64/le/fpu/multiarch/float128-ifunc.h
index 392c66b..bbe8057 100644
--- a/sysdeps/powerpc/powerpc64/le/fpu/multiarch/float128-ifunc.h
+++ b/sysdeps/powerpc/powerpc64/le/fpu/multiarch/float128-ifunc.h
@@ -27,8 +27,10 @@
 
 /* Include the real math.h to avoid optimizations caused by include/math.h
    (e.x fabsf128 prototype is masked by an inline definition).*/
+#define f64xfmaf128 __hide_f64xfmaf128
 #define f64xsqrtf128 __hide_f64xsqrtf128
 #include <math/math.h>
+#undef f64xfmaf128
 #undef f64xsqrtf128
 #include <math_private.h>
 #include <complex.h>
@@ -152,6 +154,9 @@
 /* scalbnf128 is an alias of ldexpf128.  */
 #define DECL_ALIAS_s_ldexp(f) MAKE_IFUNCP_R (f,) MAKE_IFUNCP_WRAP_R (wrap_, scalbn,)
 
+/* f64xfmaf128 is an alias of fmaf128.  */
+#define DECL_ALIAS_s_fma(f) MAKE_IFUNCP_R (f,) libm_alias_float128_narrow (__fma, fma)
+
 /* f64xsqrtf128 is an alias of sqrtf128.  */
 #define DECL_ALIAS_w_sqrt(f) MAKE_IFUNCP_R (f,) libm_alias_float128_narrow (__sqrt, sqrt)