/*-
 * ====================================================
 * Copyright (C) 1993 by Sun Microsystems, Inc. All rights reserved.
 * Copyright (c) 2008 Steven G. Kargl, David Schultz, Bruce D. Evans.
 *
 * Developed at SunSoft, a Sun Microsystems, Inc. business.
 * Permission to use, copy, modify, and distribute this
 * software is freely granted, provided that this notice 
 * is preserved.
 * ====================================================
 *
 * k_sinl.c and k_cosl.c merged by Steven G. Kargl
 */

static const long double
C1 =  0.04166666666666666666666666666666658424671L,
C2 = -0.001388888888888888888888888888863490893732L,
C3 =  0.00002480158730158730158730158600795304914210L,
C4 = -0.2755731922398589065255474947078934284324e-6L,
C5 =  0.2087675698786809897659225313136400793948e-8L,
C6 = -0.1147074559772972315817149986812031204775e-10L,
C7 =  0.4779477332386808976875457937252120293400e-13L,
S1 = -0.16666666666666666666666666666666666606732416116558L,
S2 =  0.0083333333333333333333333333333331135404851288270047L,
S3 = -0.00019841269841269841269841269839935785325638310428717L,
S4 =  0.27557319223985890652557316053039946268333231205686e-5L,
S5 = -0.25052108385441718775048214826384312253862930064745e-7L,
S6 =  0.16059043836821614596571832194524392581082444805729e-9L,
S7 = -0.76471637318198151807063387954939213287488216303768e-12L,
S8 =  0.28114572543451292625024967174638477283187397621303e-14L;

static const double
C8  = -0.1561920696721507929516718307820958119868e-15,
C9  =  0.4110317413744594971475941557607804508039e-18,
C10 = -0.8896592467191938803288521958313920156409e-21,
C11 =  0.1601061435794535138244346256065192782581e-23,
S9  = -0.82206352458348947812512122163446202498005154296863e-17,
S10 =  0.19572940011906109418080609928334380560135358385256e-19,
S11 = -0.38680813379701966970673724299207480965452616911420e-22,
S12 =  0.64038150078671872796678569586315881020659912139412e-25;

static inline void
__kernel_sincosl(long double x, long double y, int iy, long double *sn, 
    long double *cs)
{
	long double hz, r, v, w, z;

	z = x * x;
	v = z * x;
	/*
	 * XXX Replace Horner scheme with an algorithm suitable for CPUs
	 * with more complex pipelines.
	 */
	r = S2 + z * (S3 + z * (S4 + z * (S5 + z * (S6 + z * (S7 + z * (S8 +
	    z * (S9 + z * (S10 + z * (S11 + z * S12)))))))));

	if (iy == 0)
		*sn = x + v * (S1 + z * r);
	else
		*cs = x - ((z * (y / 2 - v * r) - y) - v * S1);

	hz = z / 2;
	w = 1 - hz;
	r = z * (C1 + z * (C2 + z * (C3 + z * (C4 + z * (C5 + z * (C6 + 
	    z * (C7 + z * (C8 + z * (C9 + z * (C10 + z * C11))))))))));

	*cs =  w + (((1 - w) - hz) + (z * r - x * y));
}