>From b9853935d1bb1d0518705c320cb3c47ddc9642ca Mon Sep 17 00:00:00 2001 From: Szabolcs Nagy Date: Tue, 16 Oct 2018 22:20:39 +0000 Subject: [PATCH 01/18] 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. --- include/math.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/include/math.h b/include/math.h index fea34686..14f28ec8 100644 --- 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); -- 2.19.1