define FP_FAST_FMA* when fma* can be inlined

FP_FAST_FMA can be defined if "the fma function generally executes about
as fast as, or faster than, a multiply and an add of double operands",
which can only be true if the fma call is inlined as an instruction.

gcc sets __FP_FAST_FMA if __builtin_fma is inlined as an instruction,
but that does not mean an fma call will be inlined (e.g. it is defined
with -fno-builtin-fma), other compilers (clang) don't even have such
macro, but this is the closest we can get.

(even if the libc fma implementation is a single instruction, the extern
call overhead is already too big when the macro is used to decide between
x*y+z and fma(x,y,z) so it cannot be based on libc only, defining the
macro unconditionally on targets which have fma in the base isa is also
incorrect: the compiler might not inline fma anyway.)

this solution works with gcc unless fma inlining is explicitly turned off.

diff --git a/include/math.h b/include/math.h
index fea34686001b3df8835e6067efd0de886e184d7f..14f28ec8c646596aee2d78c662a65584def559a1 100644 (file)
--- a/include/math.h
+++ b/include/math.h
@@ -36,6 +36,18 @@ extern "C" {
 #define FP_SUBNORMAL 3
 #define FP_NORMAL    4
 
+#ifdef __FP_FAST_FMA
+#define FP_FAST_FMA 1
+#endif
+
+#ifdef __FP_FAST_FMAF
+#define FP_FAST_FMAF 1
+#endif
+
+#ifdef __FP_FAST_FMAL
+#define FP_FAST_FMAL 1
+#endif
+
 int __fpclassify(double);
 int __fpclassifyf(float);
 int __fpclassifyl(long double);