From 9755bc4686d8cd6a0e9539040b903e9e9291c319 Mon Sep 17 00:00:00 2001 From: Joseph Myers Date: Thu, 27 Sep 2018 12:35:23 +0000 Subject: Use round functions not __round functions in glibc libm. Continuing the move to use, within libm, public names for libm functions that can be inlined as built-in functions on many architectures, this patch moves calls to __round functions to call the corresponding round names instead, with asm redirection to __round when the calls are not inlined. An additional complication arises in sysdeps/ieee754/ldbl-128ibm/e_expl.c, where a call to roundl, with the result converted to int, gets converted by the compiler to call lroundl in the case of 32-bit long, so resulting in localplt test failures. It's logically correct to let the compiler make such an optimization; an appropriate asm redirection of lroundl to __lroundl is thus added to that file (it's not needed anywhere else). Tested for x86_64, and with build-many-glibcs.py. * include/math.h [!_ISOMAC && !(__FINITE_MATH_ONLY__ && __FINITE_MATH_ONLY__ > 0) && !NO_MATH_REDIRECT] (round): Redirect using MATH_REDIRECT. * sysdeps/aarch64/fpu/s_round.c: Define NO_MATH_REDIRECT before header inclusion. * sysdeps/aarch64/fpu/s_roundf.c: Likewise. * sysdeps/ieee754/dbl-64/s_round.c: Likewise. * sysdeps/ieee754/dbl-64/wordsize-64/s_round.c: Likewise. * sysdeps/ieee754/float128/s_roundf128.c: Likewise. * sysdeps/ieee754/flt-32/s_roundf.c: Likewise. * sysdeps/ieee754/ldbl-128/s_roundl.c: Likewise. * sysdeps/ieee754/ldbl-96/s_roundl.c: Likewise. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_round.c: Likewise. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_roundf.c: Likewise. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_round.c: Likewise. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_roundf.c: Likewise. * sysdeps/riscv/rv64/rvd/s_round.c: Likewise. * sysdeps/riscv/rvf/s_roundf.c: Likewise. * sysdeps/ieee754/ldbl-128ibm/s_roundl.c: Likewise. (round): Redirect to __round. (__roundl): Call round instead of __round. * sysdeps/powerpc/fpu/math_private.h [_ARCH_PWR5X] (__round): Remove macro. [_ARCH_PWR5X] (__roundf): Likewise. * sysdeps/ieee754/dbl-64/e_gamma_r.c (gamma_positive): Use round functions instead of __round variants. * sysdeps/ieee754/flt-32/e_gammaf_r.c (gammaf_positive): Likewise. * sysdeps/ieee754/ldbl-128/e_gammal_r.c (gammal_positive): Likewise. * sysdeps/ieee754/ldbl-128ibm/e_gammal_r.c (gammal_positive): Likewise. * sysdeps/ieee754/ldbl-96/e_gammal_r.c (gammal_positive): Likewise. * sysdeps/x86/fpu/powl_helper.c (__powl_helper): Likewise. * sysdeps/ieee754/ldbl-128ibm/e_expl.c (lroundl): Redirect to __lroundl. (__ieee754_expl): Call roundl instead of __roundl. --- sysdeps/aarch64/fpu/s_round.c | 1 + sysdeps/aarch64/fpu/s_roundf.c | 1 + sysdeps/ieee754/dbl-64/e_gamma_r.c | 2 +- sysdeps/ieee754/dbl-64/s_round.c | 1 + sysdeps/ieee754/dbl-64/wordsize-64/s_round.c | 1 + sysdeps/ieee754/float128/s_roundf128.c | 1 + sysdeps/ieee754/flt-32/e_gammaf_r.c | 2 +- sysdeps/ieee754/flt-32/s_roundf.c | 1 + sysdeps/ieee754/ldbl-128/e_gammal_r.c | 2 +- sysdeps/ieee754/ldbl-128/s_roundl.c | 1 + sysdeps/ieee754/ldbl-128ibm/e_expl.c | 11 +++++++--- sysdeps/ieee754/ldbl-128ibm/e_gammal_r.c | 2 +- sysdeps/ieee754/ldbl-128ibm/s_roundl.c | 7 +++++-- sysdeps/ieee754/ldbl-96/e_gammal_r.c | 2 +- sysdeps/ieee754/ldbl-96/s_roundl.c | 1 + sysdeps/powerpc/fpu/math_private.h | 24 ---------------------- .../powerpc32/power4/fpu/multiarch/s_round.c | 1 + .../powerpc32/power4/fpu/multiarch/s_roundf.c | 1 + sysdeps/powerpc/powerpc64/fpu/multiarch/s_round.c | 1 + sysdeps/powerpc/powerpc64/fpu/multiarch/s_roundf.c | 1 + sysdeps/riscv/rv64/rvd/s_round.c | 1 + sysdeps/riscv/rvf/s_roundf.c | 1 + sysdeps/x86/fpu/powl_helper.c | 2 +- 23 files changed, 33 insertions(+), 35 deletions(-) (limited to 'sysdeps') diff --git a/sysdeps/aarch64/fpu/s_round.c b/sysdeps/aarch64/fpu/s_round.c index 275b00f..ae020d3 100644 --- a/sysdeps/aarch64/fpu/s_round.c +++ b/sysdeps/aarch64/fpu/s_round.c @@ -16,6 +16,7 @@ License along with the GNU C Library; if not, see . */ +#define NO_MATH_REDIRECT #include #include diff --git a/sysdeps/aarch64/fpu/s_roundf.c b/sysdeps/aarch64/fpu/s_roundf.c index 201ffc5..f87609b 100644 --- a/sysdeps/aarch64/fpu/s_roundf.c +++ b/sysdeps/aarch64/fpu/s_roundf.c @@ -16,6 +16,7 @@ License along with the GNU C Library; if not, see . */ +#define NO_MATH_REDIRECT #include #include diff --git a/sysdeps/ieee754/dbl-64/e_gamma_r.c b/sysdeps/ieee754/dbl-64/e_gamma_r.c index 2cfe6d6..7707c06 100644 --- a/sysdeps/ieee754/dbl-64/e_gamma_r.c +++ b/sysdeps/ieee754/dbl-64/e_gamma_r.c @@ -88,7 +88,7 @@ gamma_positive (double x, int *exp2_adj) starting by computing pow (X_ADJ, X_ADJ) with a power of 2 factored out. */ double exp_adj = -eps; - double x_adj_int = __round (x_adj); + double x_adj_int = round (x_adj); double x_adj_frac = x_adj - x_adj_int; int x_adj_log2; double x_adj_mant = __frexp (x_adj, &x_adj_log2); diff --git a/sysdeps/ieee754/dbl-64/s_round.c b/sysdeps/ieee754/dbl-64/s_round.c index fa9e831..012b6dc 100644 --- a/sysdeps/ieee754/dbl-64/s_round.c +++ b/sysdeps/ieee754/dbl-64/s_round.c @@ -17,6 +17,7 @@ License along with the GNU C Library; if not, see . */ +#define NO_MATH_REDIRECT #include #include diff --git a/sysdeps/ieee754/dbl-64/wordsize-64/s_round.c b/sysdeps/ieee754/dbl-64/wordsize-64/s_round.c index 3323621..2dfd1ed 100644 --- a/sysdeps/ieee754/dbl-64/wordsize-64/s_round.c +++ b/sysdeps/ieee754/dbl-64/wordsize-64/s_round.c @@ -17,6 +17,7 @@ License along with the GNU C Library; if not, see . */ +#define NO_MATH_REDIRECT #include #include diff --git a/sysdeps/ieee754/float128/s_roundf128.c b/sysdeps/ieee754/float128/s_roundf128.c index 1eb36f2..d9f6fa4 100644 --- a/sysdeps/ieee754/float128/s_roundf128.c +++ b/sysdeps/ieee754/float128/s_roundf128.c @@ -1,2 +1,3 @@ +#define NO_MATH_REDIRECT #include #include "../ldbl-128/s_roundl.c" diff --git a/sysdeps/ieee754/flt-32/e_gammaf_r.c b/sysdeps/ieee754/flt-32/e_gammaf_r.c index 7d9a6cb..6a9e28a 100644 --- a/sysdeps/ieee754/flt-32/e_gammaf_r.c +++ b/sysdeps/ieee754/flt-32/e_gammaf_r.c @@ -81,7 +81,7 @@ gammaf_positive (float x, int *exp2_adj) starting by computing pow (X_ADJ, X_ADJ) with a power of 2 factored out. */ float exp_adj = -eps; - float x_adj_int = __roundf (x_adj); + float x_adj_int = roundf (x_adj); float x_adj_frac = x_adj - x_adj_int; int x_adj_log2; float x_adj_mant = __frexpf (x_adj, &x_adj_log2); diff --git a/sysdeps/ieee754/flt-32/s_roundf.c b/sysdeps/ieee754/flt-32/s_roundf.c index 7c95125..a411de6 100644 --- a/sysdeps/ieee754/flt-32/s_roundf.c +++ b/sysdeps/ieee754/flt-32/s_roundf.c @@ -17,6 +17,7 @@ License along with the GNU C Library; if not, see . */ +#define NO_MATH_REDIRECT #include #include diff --git a/sysdeps/ieee754/ldbl-128/e_gammal_r.c b/sysdeps/ieee754/ldbl-128/e_gammal_r.c index 184798f..837395e 100644 --- a/sysdeps/ieee754/ldbl-128/e_gammal_r.c +++ b/sysdeps/ieee754/ldbl-128/e_gammal_r.c @@ -96,7 +96,7 @@ gammal_positive (_Float128 x, int *exp2_adj) starting by computing pow (X_ADJ, X_ADJ) with a power of 2 factored out. */ _Float128 exp_adj = -eps; - _Float128 x_adj_int = __roundl (x_adj); + _Float128 x_adj_int = roundl (x_adj); _Float128 x_adj_frac = x_adj - x_adj_int; int x_adj_log2; _Float128 x_adj_mant = __frexpl (x_adj, &x_adj_log2); diff --git a/sysdeps/ieee754/ldbl-128/s_roundl.c b/sysdeps/ieee754/ldbl-128/s_roundl.c index 22789ce..4f0184f 100644 --- a/sysdeps/ieee754/ldbl-128/s_roundl.c +++ b/sysdeps/ieee754/ldbl-128/s_roundl.c @@ -18,6 +18,7 @@ License along with the GNU C Library; if not, see . */ +#define NO_MATH_REDIRECT #include #include diff --git a/sysdeps/ieee754/ldbl-128ibm/e_expl.c b/sysdeps/ieee754/ldbl-128ibm/e_expl.c index a502455..0c33d88 100644 --- a/sysdeps/ieee754/ldbl-128ibm/e_expl.c +++ b/sysdeps/ieee754/ldbl-128ibm/e_expl.c @@ -134,6 +134,11 @@ static const long double C[] = { 1.98412698413981650382436541785404286E-04L, }; +/* Avoid local PLT entry use from (int) roundl (...) being converted + to a call to lroundl in the case of 32-bit long and roundl not + inlined. */ +long int lroundl (long double) asm ("__lroundl"); + long double __ieee754_expl (long double x) { @@ -149,15 +154,15 @@ __ieee754_expl (long double x) SET_RESTORE_ROUND (FE_TONEAREST); - n = __roundl (x*M_1_LN2); + n = roundl (x*M_1_LN2); x = x-n*M_LN2_0; xl = n*M_LN2_1; - tval1 = __roundl (x*TWO8); + tval1 = roundl (x*TWO8); x -= __expl_table[T_EXPL_ARG1+2*tval1]; xl -= __expl_table[T_EXPL_ARG1+2*tval1+1]; - tval2 = __roundl (x*TWO15); + tval2 = roundl (x*TWO15); x -= __expl_table[T_EXPL_ARG2+2*tval2]; xl -= __expl_table[T_EXPL_ARG2+2*tval2+1]; diff --git a/sysdeps/ieee754/ldbl-128ibm/e_gammal_r.c b/sysdeps/ieee754/ldbl-128ibm/e_gammal_r.c index 3680121..6361d35 100644 --- a/sysdeps/ieee754/ldbl-128ibm/e_gammal_r.c +++ b/sysdeps/ieee754/ldbl-128ibm/e_gammal_r.c @@ -95,7 +95,7 @@ gammal_positive (long double x, int *exp2_adj) starting by computing pow (X_ADJ, X_ADJ) with a power of 2 factored out. */ long double exp_adj = -eps; - long double x_adj_int = __roundl (x_adj); + long double x_adj_int = roundl (x_adj); long double x_adj_frac = x_adj - x_adj_int; int x_adj_log2; long double x_adj_mant = __frexpl (x_adj, &x_adj_log2); diff --git a/sysdeps/ieee754/ldbl-128ibm/s_roundl.c b/sysdeps/ieee754/ldbl-128ibm/s_roundl.c index 94a62dc..156be26 100644 --- a/sysdeps/ieee754/ldbl-128ibm/s_roundl.c +++ b/sysdeps/ieee754/ldbl-128ibm/s_roundl.c @@ -20,12 +20,15 @@ /* This has been coded in assembler because GCC makes such a mess of it when it's coded in C. */ +#define NO_MATH_REDIRECT #include #include #include #include #include +double round (double) asm ("__round"); + long double __roundl (long double x) @@ -39,7 +42,7 @@ __roundl (long double x) && __builtin_isless (__builtin_fabs (xh), __builtin_inf ()), 1)) { - hi = __round (xh); + hi = round (xh); if (hi != xh) { /* The high part is not an integer; the low part only @@ -62,7 +65,7 @@ __roundl (long double x) else { /* The high part is a nonzero integer. */ - lo = __round (xl); + lo = round (xl); if (fabs (lo - xl) == 0.5) { if (xh > 0 && xl < 0) diff --git a/sysdeps/ieee754/ldbl-96/e_gammal_r.c b/sysdeps/ieee754/ldbl-96/e_gammal_r.c index b097033..49428eb 100644 --- a/sysdeps/ieee754/ldbl-96/e_gammal_r.c +++ b/sysdeps/ieee754/ldbl-96/e_gammal_r.c @@ -89,7 +89,7 @@ gammal_positive (long double x, int *exp2_adj) starting by computing pow (X_ADJ, X_ADJ) with a power of 2 factored out. */ long double exp_adj = -eps; - long double x_adj_int = __roundl (x_adj); + long double x_adj_int = roundl (x_adj); long double x_adj_frac = x_adj - x_adj_int; int x_adj_log2; long double x_adj_mant = __frexpl (x_adj, &x_adj_log2); diff --git a/sysdeps/ieee754/ldbl-96/s_roundl.c b/sysdeps/ieee754/ldbl-96/s_roundl.c index c5c304c..1eeed01 100644 --- a/sysdeps/ieee754/ldbl-96/s_roundl.c +++ b/sysdeps/ieee754/ldbl-96/s_roundl.c @@ -17,6 +17,7 @@ License along with the GNU C Library; if not, see . */ +#define NO_MATH_REDIRECT #include #include diff --git a/sysdeps/powerpc/fpu/math_private.h b/sysdeps/powerpc/fpu/math_private.h index 7f2acbb..2ed56fa 100644 --- a/sysdeps/powerpc/fpu/math_private.h +++ b/sysdeps/powerpc/fpu/math_private.h @@ -35,28 +35,4 @@ __ieee754_sqrtf128 (_Float128 __x) } #endif -#if defined _ARCH_PWR5X - -# ifndef __round -# define __round(x) \ - ({ double __z; \ - __asm __volatile ( \ - " frin %0,%1\n" \ - : "=f" (__z) \ - : "f" (x)); \ - __z; }) -# endif -# ifndef __roundf -# define __roundf(x) \ - ({ float __z; \ - __asm __volatile ( \ - " frin %0,%1\n" \ - " frsp %0,%0\n" \ - : "=f" (__z) \ - : "f" (x)); \ - __z; }) -# endif - -#endif /* defined _ARCH_PWR5X */ - #endif /* _PPC_MATH_PRIVATE_H_ */ diff --git a/sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_round.c b/sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_round.c index 65e7801..e5b27da 100644 --- a/sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_round.c +++ b/sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_round.c @@ -16,6 +16,7 @@ License along with the GNU C Library; if not, see . */ +#define NO_MATH_REDIRECT #include #include #include diff --git a/sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_roundf.c b/sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_roundf.c index 0d923a2..659a989 100644 --- a/sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_roundf.c +++ b/sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_roundf.c @@ -16,6 +16,7 @@ License along with the GNU C Library; if not, see . */ +#define NO_MATH_REDIRECT #include #include #include diff --git a/sysdeps/powerpc/powerpc64/fpu/multiarch/s_round.c b/sysdeps/powerpc/powerpc64/fpu/multiarch/s_round.c index bfa4d81..cd9291b 100644 --- a/sysdeps/powerpc/powerpc64/fpu/multiarch/s_round.c +++ b/sysdeps/powerpc/powerpc64/fpu/multiarch/s_round.c @@ -16,6 +16,7 @@ License along with the GNU C Library; if not, see . */ +#define NO_MATH_REDIRECT #include #include #include diff --git a/sysdeps/powerpc/powerpc64/fpu/multiarch/s_roundf.c b/sysdeps/powerpc/powerpc64/fpu/multiarch/s_roundf.c index 3d77156..bd8b4a4 100644 --- a/sysdeps/powerpc/powerpc64/fpu/multiarch/s_roundf.c +++ b/sysdeps/powerpc/powerpc64/fpu/multiarch/s_roundf.c @@ -16,6 +16,7 @@ License along with the GNU C Library; if not, see . */ +#define NO_MATH_REDIRECT #include #include #include diff --git a/sysdeps/riscv/rv64/rvd/s_round.c b/sysdeps/riscv/rv64/rvd/s_round.c index b3e5bc4..e375d4d 100644 --- a/sysdeps/riscv/rv64/rvd/s_round.c +++ b/sysdeps/riscv/rv64/rvd/s_round.c @@ -16,6 +16,7 @@ License along with the GNU C Library. If not, see . */ +#define NO_MATH_REDIRECT #include #include #include diff --git a/sysdeps/riscv/rvf/s_roundf.c b/sysdeps/riscv/rvf/s_roundf.c index 87839de..685a8e3 100644 --- a/sysdeps/riscv/rvf/s_roundf.c +++ b/sysdeps/riscv/rvf/s_roundf.c @@ -16,6 +16,7 @@ License along with the GNU C Library. If not, see . */ +#define NO_MATH_REDIRECT #include #include #include diff --git a/sysdeps/x86/fpu/powl_helper.c b/sysdeps/x86/fpu/powl_helper.c index 651eedd..469fd0f 100644 --- a/sysdeps/x86/fpu/powl_helper.c +++ b/sysdeps/x86/fpu/powl_helper.c @@ -216,7 +216,7 @@ __powl_helper (long double x, long double y) /* Split the base-2 logarithm of the result into integer and fractional parts. */ - long double log2_res_int = __roundl (log2_res_hi); + long double log2_res_int = roundl (log2_res_hi); long double log2_res_frac = log2_res_hi - log2_res_int + log2_res_lo; /* If the integer part is very large, the computed fractional part may be outside the valid range for f2xm1. */ -- cgit v1.1