Add narrowing square root functions

This patch adds the narrowing square root functions from TS 18661-1 /
TS 18661-3 / C2X to glibc's libm: fsqrt, fsqrtl, dsqrtl, f32sqrtf64,
f32sqrtf32x, f32xsqrtf64 for all configurations; f32sqrtf64x,
f32sqrtf128, f64sqrtf64x, f64sqrtf128, f32xsqrtf64x, f32xsqrtf128,
f64xsqrtf128 for configurations with _Float64x and _Float128;
__f32sqrtieee128 and __f64sqrtieee128 aliases in the powerpc64le case
(for calls to fsqrtl and dsqrtl 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, so the description of those generally
applies to this patch as well.  However, the not-actually-narrowing
cases (where the two types involved in the function have the same
floating-point format) are aliased to sqrt, sqrtl or sqrtf128 rather
than needing a separately built not-actually-narrowing function such
as was needed for add / sub / mul / div.  Thus, there is no
__nldbl_dsqrtl name for ldbl-opt because no such name was needed
(whereas the other functions needed such a name since the only other
name for that entry point was e.g. f32xaddf64, not reserved by TS
18661-1); the headers are made to arrange for sqrt to be called in
that case instead.

The DIAG_* calls in sysdeps/ieee754/soft-fp/s_dsqrtl.c are because
they were observed to be needed in GCC 7 testing of
riscv32-linux-gnu-rv32imac-ilp32.  The other sysdeps/ieee754/soft-fp/
files added didn't need such DIAG_* in any configuration I tested with
build-many-glibcs.py, but if they do turn out to be needed in more
files with some other configuration / GCC version, they can always be
added there.

I reused the same test inputs in auto-libm-test-in as for
non-narrowing sqrt rather than adding extra or separate inputs for
narrowing sqrt.  The tests in libm-test-narrow-sqrt.inc also follow
those for non-narrowing sqrt.

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, 11 insertions, 0 deletions

diff --git a/sysdeps/powerpc/fpu/libm-test-ulps b/sysdeps/powerpc/fpu/libm-test-ulps
index 513c434..a605aeb 100644
--- a/sysdeps/powerpc/fpu/libm-test-ulps
+++ b/sysdeps/powerpc/fpu/libm-test-ulps
@@ -1623,6 +1623,9 @@ ldouble: 1
 Function: "sqrt_downward":
 ldouble: 1
 
+Function: "sqrt_ldouble":
+double: 1
+
 Function: "sqrt_towardzero":
 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 b038700..abab686 100644
--- a/sysdeps/powerpc/powerpc64/le/fpu/multiarch/float128-ifunc-macros.h
+++ b/sysdeps/powerpc/powerpc64/le/fpu/multiarch/float128-ifunc-macros.h
@@ -32,6 +32,7 @@
 #undef declare_mgen_finite_alias
 #undef declare_mgen_alias
 #undef declare_mgen_alias_r
+#undef declare_mgen_alias_narrow
 
 #define libm_alias_finite(from, to)
 #define libm_alias_float128_r(from, to, r)
@@ -40,6 +41,7 @@
 #define declare_mgen_finite_alias(from, to)
 #define declare_mgen_alias(from, to)
 #define declare_mgen_alias_r(from, to)
+#define declare_mgen_alias_narrow(from, to)
 
 /*  Likewise, disable hidden symbol support.  This is not needed
     for the implementation objects as the redirects already give
diff --git a/sysdeps/powerpc/powerpc64/le/fpu/multiarch/float128-ifunc.h b/sysdeps/powerpc/powerpc64/le/fpu/multiarch/float128-ifunc.h
index 001cbf7..392c66b 100644
--- a/sysdeps/powerpc/powerpc64/le/fpu/multiarch/float128-ifunc.h
+++ b/sysdeps/powerpc/powerpc64/le/fpu/multiarch/float128-ifunc.h
@@ -27,7 +27,9 @@
 
 /* Include the real math.h to avoid optimizations caused by include/math.h
    (e.x fabsf128 prototype is masked by an inline definition).*/
+#define f64xsqrtf128 __hide_f64xsqrtf128
 #include <math/math.h>
+#undef f64xsqrtf128
 #include <math_private.h>
 #include <complex.h>
 #include <first-versions.h>
@@ -36,6 +38,7 @@
 
 #include <libm-alias-float128.h>
 #include <libm-alias-finite.h>
+#include <math-narrow-alias.h>
 
 /* _F128_IFUNC2(func, from, r)
       Generate an ifunc symbol func ## r from the symbols
@@ -149,6 +152,9 @@
 /* scalbnf128 is an alias of ldexpf128.  */
 #define DECL_ALIAS_s_ldexp(f) MAKE_IFUNCP_R (f,) MAKE_IFUNCP_WRAP_R (wrap_, scalbn,)
 
+/* f64xsqrtf128 is an alias of sqrtf128.  */
+#define DECL_ALIAS_w_sqrt(f) MAKE_IFUNCP_R (f,) libm_alias_float128_narrow (__sqrt, sqrt)
+
 /* Declare an IFUNC for a symbol which only exists
    to provide long double == ieee128 ABI.  */
 #define DECL_LDOUBLE_ALIAS(func, RTYPE, ARGS) \