Update.

2001-03-11  Ulrich Drepper  <drepper@redhat.com>

	Last-bit accurate math library implementation by IBM Haifa.
	Contributed by Abraham Ziv <ziv@il.ibm.com>, Moshe Olshansky
	<olshansk@il.ibm.com>, Ealan Henis <ealan@il.ibm.com>, and
	Anna Reitman <reitman@il.ibm.com>.
	* math/Makefile (dbl-only-routines): New variable.
	(libm-routines): Add $(dbl-only-routines).
	* sysdeps/ieee754/dbl-64/e_acos.c: Empty, definition is in e_asin.c.
	* sysdeps/ieee754/dbl-64/e_asin.c: Replaced with accurate asin
	implementation.
	* sysdeps/ieee754/dbl-64/e_atan2.c: Replaced with accurate atan2
	implementation.
	* sysdeps/ieee754/dbl-64/e_exp.c: Replaced with accurate exp
	implementation.
	* sysdeps/ieee754/dbl-64/e_lgamma_r.c: Don't use __kernel_sin and
	__kernel_cos.
	* sysdeps/ieee754/dbl-64/e_log.c: Replaced with accurate log
	implementation.
	* sysdeps/ieee754/dbl-64/e_remainder.c: Replaced with accurate
	remainder implementation.
	* sysdeps/ieee754/dbl-64/e_pow.c: Replaced with accurate pow
	implementation.
	* sysdeps/ieee754/dbl-64/e_sqrt.c: Replaced with accurate sqrt
	implementation.
	* sysdeps/ieee754/dbl-64/k_cos.c: Empty, definition is in s_sin.c.
	* sysdeps/ieee754/dbl-64/k_sin.c: Empty, definition is in s_sin.c.
	* sysdeps/ieee754/dbl-64/s_atan.c: Replaced with accurate atan
	implementation.
	* sysdeps/ieee754/dbl-64/s_cos.c: Empty, definition is in s_sin.c.
	* sysdeps/ieee754/dbl-64/s_sin.c: Replaced with accurate sin/cos
	implementation.
	* sysdeps/ieee754/dbl-64/s_sincos.c: Rewritten to not use __kernel_sin
	and __kernel_cos.
	* sysdeps/ieee754/dbl-64/s_tan.c: Replaced with accurate tan
	implementation.
	* sysdeps/ieee754/dbl-64/Dist: Add new non-code files.
	* sysdeps/ieee754/dbl-64/MathLib.h: New file.
	* sysdeps/ieee754/dbl-64/asincos.tbl: New file.
	* sysdeps/ieee754/dbl-64/atnat.h: New file.
	* sysdeps/ieee754/dbl-64/atnat2.h: New file.
	* sysdeps/ieee754/dbl-64/branred.c: New file.
	* sysdeps/ieee754/dbl-64/branred.h: New file.
	* sysdeps/ieee754/dbl-64/dla.h: New file.
	* sysdeps/ieee754/dbl-64/doasin.c: New file.
	* sysdeps/ieee754/dbl-64/doasin.h: New file.
	* sysdeps/ieee754/dbl-64/dosincos.c: New file.
	* sysdeps/ieee754/dbl-64/dosincos.h: New file.
	* sysdeps/ieee754/dbl-64/endian.h: New file.
	* sysdeps/ieee754/dbl-64/halfulp.c: New file.
	* sysdeps/ieee754/dbl-64/mpa.c: New file.
	* sysdeps/ieee754/dbl-64/mpa.h: New file.
	* sysdeps/ieee754/dbl-64/mpa2.h: New file.
	* sysdeps/ieee754/dbl-64/mpatan.c: New file.
	* sysdeps/ieee754/dbl-64/mpatan.h: New file.
	* sysdeps/ieee754/dbl-64/mpatan2.c: New file.
	* sysdeps/ieee754/dbl-64/mpexp.c: New file.
	* sysdeps/ieee754/dbl-64/mpexp.h: New file.
	* sysdeps/ieee754/dbl-64/mplog.c: New file.
	* sysdeps/ieee754/dbl-64/mplog.h: New file.
	* sysdeps/ieee754/dbl-64/mpsqrt.c: New file.
	* sysdeps/ieee754/dbl-64/mpsqrt.h: New file.
	* sysdeps/ieee754/dbl-64/mptan.c: New file.
	* sysdeps/ieee754/dbl-64/mydefs.h: New file.
	* sysdeps/ieee754/dbl-64/powtwo.tbl: New file.
	* sysdeps/ieee754/dbl-64/root.tbl: New file.
	* sysdeps/ieee754/dbl-64/sincos.tbl: New file.
	* sysdeps/ieee754/dbl-64/sincos32.c: New file.
	* sysdeps/ieee754/dbl-64/sincos32.h: New file.
	* sysdeps/ieee754/dbl-64/slowexp.c: New file.
	* sysdeps/ieee754/dbl-64/slowpow.c: New file.
	* sysdeps/ieee754/dbl-64/uasncs.h: New file.
	* sysdeps/ieee754/dbl-64/uatan.tbl: New file.
	* sysdeps/ieee754/dbl-64/uexp.h: New file.
	* sysdeps/ieee754/dbl-64/uexp.tbl: New file.
	* sysdeps/ieee754/dbl-64/ulog.h: New file.
	* sysdeps/ieee754/dbl-64/ulog.tbl: New file.
	* sysdeps/ieee754/dbl-64/upow.h: New file.
	* sysdeps/ieee754/dbl-64/upow.tbl: New file.
	* sysdeps/ieee754/dbl-64/urem.h: New file.
	* sysdeps/ieee754/dbl-64/uroot.h: New file.
	* sysdeps/ieee754/dbl-64/usncs.h: New file.
	* sysdeps/ieee754/dbl-64/utan.h: New file.
	* sysdeps/ieee754/dbl-64/utan.tbl: New file.
	* sysdeps/i386/fpu/branred.c: New file.
	* sysdeps/i386/fpu/doasin.c: New file.
	* sysdeps/i386/fpu/dosincos.c: New file.
	* sysdeps/i386/fpu/halfulp.c: New file.
	* sysdeps/i386/fpu/mpa.c: New file.
	* sysdeps/i386/fpu/mpatan.c: New file.
	* sysdeps/i386/fpu/mpatan2.c: New file.
	* sysdeps/i386/fpu/mpexp.c: New file.
	* sysdeps/i386/fpu/mplog.c: New file.
	* sysdeps/i386/fpu/mpsqrt.c: New file.
	* sysdeps/i386/fpu/mptan.c: New file.
	* sysdeps/i386/fpu/sincos32.c: New file.
	* sysdeps/i386/fpu/slowexp.c: New file.
	* sysdeps/i386/fpu/slowpow.c: New file.
	* sysdeps/ia64/fpu/branred.c: New file.
	* sysdeps/ia64/fpu/doasin.c: New file.
	* sysdeps/ia64/fpu/dosincos.c: New file.
	* sysdeps/ia64/fpu/halfulp.c: New file.
	* sysdeps/ia64/fpu/mpa.c: New file.
	* sysdeps/ia64/fpu/mpatan.c: New file.
	* sysdeps/ia64/fpu/mpatan2.c: New file.
	* sysdeps/ia64/fpu/mpexp.c: New file.
	* sysdeps/ia64/fpu/mplog.c: New file.
	* sysdeps/ia64/fpu/mpsqrt.c: New file.
	* sysdeps/ia64/fpu/mptan.c: New file.
	* sysdeps/ia64/fpu/sincos32.c: New file.
	* sysdeps/ia64/fpu/slowexp.c: New file.
	* sysdeps/ia64/fpu/slowpow.c: New file.
	* sysdeps/m68k/fpu/branred.c: New file.
	* sysdeps/m68k/fpu/doasin.c: New file.
	* sysdeps/m68k/fpu/dosincos.c: New file.
	* sysdeps/m68k/fpu/halfulp.c: New file.
	* sysdeps/m68k/fpu/mpa.c: New file.
	* sysdeps/m68k/fpu/mpatan.c: New file.
	* sysdeps/m68k/fpu/mpatan2.c: New file.
	* sysdeps/m68k/fpu/mpexp.c: New file.
	* sysdeps/m68k/fpu/mplog.c: New file.
	* sysdeps/m68k/fpu/mpsqrt.c: New file.
	* sysdeps/m68k/fpu/mptan.c: New file.
	* sysdeps/m68k/fpu/sincos32.c: New file.
	* sysdeps/m68k/fpu/slowexp.c: New file.
	* sysdeps/m68k/fpu/slowpow.c: New file.

	* iconvdata/gconv-modules: Add a number of alias, mostly for IBM
	codepages.

1 files changed, 102 insertions, 0 deletions

diff --git a/sysdeps/ieee754/dbl-64/mpsqrt.c b/sysdeps/ieee754/dbl-64/mpsqrt.c
new file mode 100644
index 0000000000..6f73fae137
--- /dev/null
+++ b/sysdeps/ieee754/dbl-64/mpsqrt.c
@@ -0,0 +1,102 @@
+
+/*
+ * IBM Accurate Mathematical Library
+ * Copyright (c) International Business Machines Corp., 2001
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or 
+ * (at your option) any later version.
+ * 
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.  
+ */
+/****************************************************************************/
+/*  MODULE_NAME:mpsqrt.c                                                    */
+/*                                                                          */
+/*  FUNCTION:mpsqrt                                                         */
+/*           fastiroot                                                      */
+/*                                                                          */
+/* FILES NEEDED:endian.h mpa.h mpsqrt.h                                     */
+/*              mpa.c                                                       */
+/* Multi-Precision square root function subroutine for precision p >= 4.    */
+/* The relative error is bounded by 3.501*r**(1-p), where r=2**24.          */
+/*                                                                          */
+/****************************************************************************/
+#include "endian.h"
+#include "mpa.h"
+
+/****************************************************************************/
+/* Multi-Precision square root function subroutine for precision p >= 4.    */
+/* The relative error is bounded by 3.501*r**(1-p), where r=2**24.          */
+/* Routine receives two pointers to  Multi Precision numbers:               */
+/* x (left argument) and y (next argument). Routine also receives precision */
+/* p as integer. Routine computes sqrt(*x) and stores result in *y          */
+/****************************************************************************/
+
+double fastiroot(double);
+
+void mpsqrt(mp_no *x, mp_no *y, int p) {
+#include "mpsqrt.h"
+
+  int i,m,ex,ey;
+  double dx,dy;
+  mp_no
+    mphalf   = {0, 0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,
+                   0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,
+                   0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,},
+    mp3halfs = {0, 0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,
+                   0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,
+                   0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,};
+  mp_no mpxn,mpz,mpu,mpt1,mpt2;
+
+  /* Prepare multi-precision 1/2 and 3/2 */
+  mphalf.e  =0;  mphalf.d[0]  =ONE;  mphalf.d[1]  =HALFRAD;
+  mp3halfs.e=1;  mp3halfs.d[0]=ONE;  mp3halfs.d[1]=ONE;  mp3halfs.d[2]=HALFRAD;
+
+  ex=EX;      ey=EX/2;     cpy(x,&mpxn,p);    mpxn.e -= (ey+ey);
+  mp_dbl(&mpxn,&dx,p);   dy=fastiroot(dx);    dbl_mp(dy,&mpu,p);
+  mul(&mpxn,&mphalf,&mpz,p);
+
+  m=mp[p];
+  for (i=0; i<m; i++) {
+    mul(&mpu,&mpu,&mpt1,p);
+    mul(&mpt1,&mpz,&mpt2,p);
+    sub(&mp3halfs,&mpt2,&mpt1,p);
+    mul(&mpu,&mpt1,&mpt2,p);
+    cpy(&mpt2,&mpu,p);
+  }
+  mul(&mpxn,&mpu,y,p);  EY += ey;
+
+  return;
+}
+
+/***********************************************************/
+/* Compute a double precision approximation for 1/sqrt(x)  */
+/* with the relative error bounded by 2**-51.              */
+/***********************************************************/
+double fastiroot(double x) {
+  union {long i[2]; double d;} p,q;
+  double y,z, t;
+  long n;
+  static const double c0 = 0.99674, c1 = -0.53380, c2 = 0.45472, c3 = -0.21553;
+  
+  p.d = x;
+  p.i[HIGH_HALF] = (p.i[HIGH_HALF] & 0x3FFFFFFF ) | 0x3FE00000 ;
+  q.d = x;
+  y = p.d;
+  z = y -1.0;
+  n = (q.i[HIGH_HALF] - p.i[HIGH_HALF])>>1;
+  z = ((c3*z + c2)*z + c1)*z + c0;            /* 2**-7         */
+  z = z*(1.5 - 0.5*y*z*z);                    /* 2**-14        */
+  p.d = z*(1.5 - 0.5*y*z*z);                  /* 2**-28        */
+  p.i[HIGH_HALF] -= n;
+  t = x*p.d;
+  return p.d*(1.5 - 0.5*p.d*t);
+}