From e216951f509b71da193da2fc63e25b998740d58b Mon Sep 17 00:00:00 2001 From: Szabolcs Nagy Date: Wed, 15 May 2013 23:08:52 +0000 Subject: math: use double_t for temporaries to avoid stores on i386 When FLT_EVAL_METHOD!=0 (only i386 with x87 fp) the excess precision of an expression must be removed in an assignment. (gcc needs -fexcess-precision=standard or -std=c99 for this) This is done by extra load/store instructions which adds code bloat when lot of temporaries are used and it makes the result less precise in many cases. Using double_t and float_t avoids these issues on i386 and it makes no difference on other archs. For now only a few functions are modified where the excess precision is clearly beneficial (mostly polynomial evaluations with temporaries). object size differences on i386, gcc-4.8: old new __cosdf.o 123 95 __cos.o 199 169 __sindf.o 131 95 __sin.o 225 203 __tandf.o 207 151 __tan.o 605 499 erff.o 1470 1416 erf.o 1703 1649 j0f.o 1779 1745 j0.o 2308 2274 j1f.o 1602 1568 j1.o 2286 2252 tgamma.o 1431 1424 math/*.o 64164 63635 --- src/math/__log1pf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/math/__log1pf.h') diff --git a/src/math/__log1pf.h b/src/math/__log1pf.h index 99492c5a..f2fbef29 100644 --- a/src/math/__log1pf.h +++ b/src/math/__log1pf.h @@ -22,7 +22,7 @@ Lg4 = 0xf89e26.0p-26; /* 0.24279078841 */ static inline float __log1pf(float f) { - float hfsq,s,z,R,w,t1,t2; + float_t hfsq,s,z,R,w,t1,t2; s = f/(2.0f + f); z = s*s; -- cgit 1.4.1