diff options
author | Ulrich Drepper <drepper@redhat.com> | 2001-03-12 00:04:52 +0000 |
---|---|---|
committer | Ulrich Drepper <drepper@redhat.com> | 2001-03-12 00:04:52 +0000 |
commit | e4d8276142b9c07b23043ef44b0fe8fa7bcc3121 (patch) | |
tree | f153a80b6ce0fdd3261ff18a16fd80bd965231c3 /sysdeps/ieee754/dbl-64/dla.h | |
parent | d3c8723f6415af59a6ec14fcb918ad0e4d1fb588 (diff) | |
download | glibc-e4d8276142b9c07b23043ef44b0fe8fa7bcc3121.tar.gz glibc-e4d8276142b9c07b23043ef44b0fe8fa7bcc3121.tar.xz glibc-e4d8276142b9c07b23043ef44b0fe8fa7bcc3121.zip |
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.
Diffstat (limited to 'sysdeps/ieee754/dbl-64/dla.h')
-rw-r--r-- | sysdeps/ieee754/dbl-64/dla.h | 173 |
1 files changed, 173 insertions, 0 deletions
diff --git a/sysdeps/ieee754/dbl-64/dla.h b/sysdeps/ieee754/dbl-64/dla.h new file mode 100644 index 0000000000..693d1a1f79 --- /dev/null +++ b/sysdeps/ieee754/dbl-64/dla.h @@ -0,0 +1,173 @@ + +/* + * 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: dla.h */ +/* */ +/* This file holds C language macros for 'Double Length Floating Point */ +/* Arithmetic'. The macros are based on the paper: */ +/* T.J.Dekker, "A floating-point Technique for extending the */ +/* Available Precision", Number. Math. 18, 224-242 (1971). */ +/* A Double-Length number is defined by a pair (r,s), of IEEE double */ +/* precision floating point numbers that satisfy, */ +/* */ +/* abs(s) <= abs(r+s)*2**(-53)/(1+2**(-53)). */ +/* */ +/* The computer arithmetic assumed is IEEE double precision in */ +/* round to nearest mode. All variables in the macros must be of type */ +/* IEEE double. */ +/***********************************************************************/ + +/* CN = 1+2**27 = '41a0000002000000' IEEE double format */ +#define CN 134217729.0 + + +/* Exact addition of two single-length floating point numbers, Dekker. */ +/* The macro produces a double-length number (z,zz) that satisfies */ +/* z+zz = x+y exactly. */ + +#define EADD(x,y,z,zz) \ + z=(x)+(y); zz=(ABS(x)>ABS(y)) ? (((x)-(z))+(y)) : (((y)-(z))+(x)); + + +/* Exact subtraction of two single-length floating point numbers, Dekker. */ +/* The macro produces a double-length number (z,zz) that satisfies */ +/* z+zz = x-y exactly. */ + +#define ESUB(x,y,z,zz) \ + z=(x)-(y); zz=(ABS(x)>ABS(y)) ? (((x)-(z))-(y)) : ((x)-((y)+(z))); + + +/* Exact multiplication of two single-length floating point numbers, */ +/* Veltkamp. The macro produces a double-length number (z,zz) that */ +/* satisfies z+zz = x*y exactly. p,hx,tx,hy,ty are temporary */ +/* storage variables of type double. */ + +#define EMULV(x,y,z,zz,p,hx,tx,hy,ty) \ + p=CN*(x); hx=((x)-p)+p; tx=(x)-hx; \ + p=CN*(y); hy=((y)-p)+p; ty=(y)-hy; \ + z=(x)*(y); zz=(((hx*hy-z)+hx*ty)+tx*hy)+tx*ty; + + +/* Exact multiplication of two single-length floating point numbers, Dekker. */ +/* The macro produces a nearly double-length number (z,zz) (see Dekker) */ +/* that satisfies z+zz = x*y exactly. p,hx,tx,hy,ty,q are temporary */ +/* storage variables of type double. */ + +#define MUL12(x,y,z,zz,p,hx,tx,hy,ty,q) \ + p=CN*(x); hx=((x)-p)+p; tx=(x)-hx; \ + p=CN*(y); hy=((y)-p)+p; ty=(y)-hy; \ + p=hx*hy; q=hx*ty+tx*hy; z=p+q; zz=((p-z)+q)+tx*ty; + + +/* Double-length addition, Dekker. The macro produces a double-length */ +/* number (z,zz) which satisfies approximately z+zz = x+xx + y+yy. */ +/* An error bound: (abs(x+xx)+abs(y+yy))*4.94e-32. (x,xx), (y,yy) */ +/* are assumed to be double-length numbers. r,s are temporary */ +/* storage variables of type double. */ + +#define ADD2(x,xx,y,yy,z,zz,r,s) \ + r=(x)+(y); s=(ABS(x)>ABS(y)) ? \ + (((((x)-r)+(y))+(yy))+(xx)) : \ + (((((y)-r)+(x))+(xx))+(yy)); \ + z=r+s; zz=(r-z)+s; + + +/* Double-length subtraction, Dekker. The macro produces a double-length */ +/* number (z,zz) which satisfies approximately z+zz = x+xx - (y+yy). */ +/* An error bound: (abs(x+xx)+abs(y+yy))*4.94e-32. (x,xx), (y,yy) */ +/* are assumed to be double-length numbers. r,s are temporary */ +/* storage variables of type double. */ + +#define SUB2(x,xx,y,yy,z,zz,r,s) \ + r=(x)-(y); s=(ABS(x)>ABS(y)) ? \ + (((((x)-r)-(y))-(yy))+(xx)) : \ + ((((x)-((y)+r))+(xx))-(yy)); \ + z=r+s; zz=(r-z)+s; + + +/* Double-length multiplication, Dekker. The macro produces a double-length */ +/* number (z,zz) which satisfies approximately z+zz = (x+xx)*(y+yy). */ +/* An error bound: abs((x+xx)*(y+yy))*1.24e-31. (x,xx), (y,yy) */ +/* are assumed to be double-length numbers. p,hx,tx,hy,ty,q,c,cc are */ +/* temporary storage variables of type double. */ + +#define MUL2(x,xx,y,yy,z,zz,p,hx,tx,hy,ty,q,c,cc) \ + MUL12(x,y,c,cc,p,hx,tx,hy,ty,q) \ + cc=((x)*(yy)+(xx)*(y))+cc; z=c+cc; zz=(c-z)+cc; + + +/* Double-length division, Dekker. The macro produces a double-length */ +/* number (z,zz) which satisfies approximately z+zz = (x+xx)/(y+yy). */ +/* An error bound: abs((x+xx)/(y+yy))*1.50e-31. (x,xx), (y,yy) */ +/* are assumed to be double-length numbers. p,hx,tx,hy,ty,q,c,cc,u,uu */ +/* are temporary storage variables of type double. */ + +#define DIV2(x,xx,y,yy,z,zz,p,hx,tx,hy,ty,q,c,cc,u,uu) \ + c=(x)/(y); MUL12(c,y,u,uu,p,hx,tx,hy,ty,q) \ + cc=(((((x)-u)-uu)+(xx))-c*(yy))/(y); z=c+cc; zz=(c-z)+cc; + + +/* Double-length addition, slower but more accurate than ADD2. */ +/* The macro produces a double-length */ +/* number (z,zz) which satisfies approximately z+zz = (x+xx)+(y+yy). */ +/* An error bound: abs(x+xx + y+yy)*1.50e-31. (x,xx), (y,yy) */ +/* are assumed to be double-length numbers. r,rr,s,ss,u,uu,w */ +/* are temporary storage variables of type double. */ + +#define ADD2A(x,xx,y,yy,z,zz,r,rr,s,ss,u,uu,w) \ + r=(x)+(y); \ + if (ABS(x)>ABS(y)) { rr=((x)-r)+(y); s=(rr+(yy))+(xx); } \ + else { rr=((y)-r)+(x); s=(rr+(xx))+(yy); } \ + if (rr!=0.0) { \ + z=r+s; zz=(r-z)+s; } \ + else { \ + ss=(ABS(xx)>ABS(yy)) ? (((xx)-s)+(yy)) : (((yy)-s)+(xx)); \ + u=r+s; \ + uu=(ABS(r)>ABS(s)) ? ((r-u)+s) : ((s-u)+r) ; \ + w=uu+ss; z=u+w; \ + zz=(ABS(u)>ABS(w)) ? ((u-z)+w) : ((w-z)+u) ; } + + +/* Double-length subtraction, slower but more accurate than SUB2. */ +/* The macro produces a double-length */ +/* number (z,zz) which satisfies approximately z+zz = (x+xx)-(y+yy). */ +/* An error bound: abs(x+xx - (y+yy))*1.50e-31. (x,xx), (y,yy) */ +/* are assumed to be double-length numbers. r,rr,s,ss,u,uu,w */ +/* are temporary storage variables of type double. */ + +#define SUB2A(x,xx,y,yy,z,zz,r,rr,s,ss,u,uu,w) \ + r=(x)-(y); \ + if (ABS(x)>ABS(y)) { rr=((x)-r)-(y); s=(rr-(yy))+(xx); } \ + else { rr=(x)-((y)+r); s=(rr+(xx))-(yy); } \ + if (rr!=0.0) { \ + z=r+s; zz=(r-z)+s; } \ + else { \ + ss=(ABS(xx)>ABS(yy)) ? (((xx)-s)-(yy)) : ((xx)-((yy)+s)); \ + u=r+s; \ + uu=(ABS(r)>ABS(s)) ? ((r-u)+s) : ((s-u)+r) ; \ + w=uu+ss; z=u+w; \ + zz=(ABS(u)>ABS(w)) ? ((u-z)+w) : ((w-z)+u) ; } + + + + + + + |