diff options
Diffstat (limited to 'sysdeps/powerpc/fpu/e_sqrtf.c')
| -rw-r--r-- | sysdeps/powerpc/fpu/e_sqrtf.c | 43 |
1 files changed, 21 insertions, 22 deletions
diff --git a/sysdeps/powerpc/fpu/e_sqrtf.c b/sysdeps/powerpc/fpu/e_sqrtf.c index fcc74aeb19..a684cf977a 100644 --- a/sysdeps/powerpc/fpu/e_sqrtf.c +++ b/sysdeps/powerpc/fpu/e_sqrtf.c @@ -1,5 +1,5 @@ /* Single-precision floating point square root. - Copyright (C) 1997-2014 Free Software Foundation, Inc. + Copyright (C) 1997-2015 Free Software Foundation, Inc. This file is part of the GNU C Library. The GNU C Library is free software; you can redistribute it and/or @@ -24,6 +24,7 @@ #include <sysdep.h> #include <ldsodefs.h> +#ifndef _ARCH_PPCSQ static const float almost_half = 0.50000006; /* 0.5 + 2^-24 */ static const ieee_float_shape_type a_nan = {.word = 0x7fc00000 }; static const ieee_float_shape_type a_inf = {.word = 0x7f800000 }; @@ -86,26 +87,28 @@ __slow_ieee754_sqrtf (float x) /* Here we have three Newton-Raphson iterations each of a division and a square root and the remainder of the argument reduction, all interleaved. */ - sd = -(sg * sg - sx); + sd = -__builtin_fmaf (sg, sg, -sx); fsgi = (xi + 0x40000000) >> 1 & 0x7f800000; sy2 = sy + sy; - sg = sy * sd + sg; /* 16-bit approximation to sqrt(sx). */ - e = -(sy * sg - almost_half); + sg = __builtin_fmaf (sy, sd, sg); /* 16-bit approximation to + sqrt(sx). */ + e = -__builtin_fmaf (sy, sg, -almost_half); SET_FLOAT_WORD (fsg, fsgi); - sd = -(sg * sg - sx); - sy = sy + e * sy2; + sd = -__builtin_fmaf (sg, sg, -sx); + sy = __builtin_fmaf (e, sy2, sy); if ((xi & 0x7f800000) == 0) goto denorm; shx = sx * fsg; - sg = sg + sy * sd; /* 32-bit approximation to sqrt(sx), - but perhaps rounded incorrectly. */ + sg = __builtin_fmaf (sy, sd, sg); /* 32-bit approximation to + sqrt(sx), but perhaps + rounded incorrectly. */ sy2 = sy + sy; g = sg * fsg; - e = -(sy * sg - almost_half); - d = -(g * sg - shx); - sy = sy + e * sy2; + e = -__builtin_fmaf (sy, sg, -almost_half); + d = -__builtin_fmaf (g, sg, -shx); + sy = __builtin_fmaf (e, sy2, sy); fesetenv_register (fe); - return g + sy * d; + return __builtin_fmaf (sy, d, g); denorm: /* For denormalised numbers, we normalise, calculate the square root, and return an adjusted result. */ @@ -128,6 +131,7 @@ __slow_ieee754_sqrtf (float x) } return f_washf (x); } +#endif /* _ARCH_PPCSQ */ #undef __ieee754_sqrtf float @@ -135,16 +139,11 @@ __ieee754_sqrtf (float x) { double z; - /* If the CPU is 64-bit we can use the optional FP instructions. */ - if (__CPU_HAS_FSQRT) - { - /* Volatile is required to prevent the compiler from moving the - fsqrt instruction above the branch. */ - __asm __volatile (" fsqrts %0,%1\n" - :"=f" (z):"f" (x)); - } - else - z = __slow_ieee754_sqrtf (x); +#ifdef _ARCH_PPCSQ + asm ("fsqrts %0,%1\n" :"=f" (z):"f" (x)); +#else + z = __slow_ieee754_sqrtf (x); +#endif return z; } |