Re: Using the GNU GMP Library for Bignums in Emacs

[Paul Eggert <eggert@cs.ucla.edu>]

[-- Attachment #1: Type: text/plain, Size: 582 bytes --]

Eli Zaretskii wrote:
> isn't there a way to test whether a platform supports IEEE
> FP representation except by looking for ieee754.h?  AFAICS, that
> header just defines a few data structures that any IEEE-compliant
> platform should be able to work with.

We can try using ieee754.h on non-GNU platforms and see what happens. In theory, 
there could be weird platforms where it doesn't work (as no standard specifies 
IEEE 754 layout); in practice, we'll probably be OK. So I created a Gnulib 
module for ieee754.h, merged it in, and installed the attached into master.

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #2: 0001-Substitute-a-ieee754.h-on-hosts-lacking-it.patch --]
[-- Type: text/x-patch; name="0001-Substitute-a-ieee754.h-on-hosts-lacking-it.patch", Size: 16730 bytes --]

From d216d7d248199aa6c99cd642116717c5b301ae6d Mon Sep 17 00:00:00 2001
From: Paul Eggert <eggert@cs.ucla.edu>
Date: Wed, 1 Aug 2018 18:53:31 -0700
Subject: [PATCH] Substitute a <ieee754.h> on hosts lacking it

* .gitignore: Add lib/ieee754.h.
* admin/merge-gnulib (GNULIB_MODULES): Add ieee754-h.
* configure.ac: Remove ieee754.h check, as Gnulib now does that.
* etc/NEWS: Mention this.
* lib/gnulib.mk.in, m4/gnulib-comp.m4: Regenerate.
* lib/ieee754.in.h, m4/ieee754-h.m4: New files, from Gnulib.
* src/lisp.h (IEEE_FLOATING_POINT): Now a macro so that it
can be used in #if.
* src/lread.c, src/print.c: Include <ieee754.h> if
IEEE_FLOATING_POINT, not if HAVE_IEEE754_H.
* src/lread.c (string_to_number):
* src/print.c (float_to_string):
Process NaNs only on IEEE hosts, and assume <ieee754.h>
in that case.
---
 .gitignore         |   1 +
 admin/merge-gnulib |   2 +-
 configure.ac       |   1 -
 etc/NEWS           |   6 +-
 lib/gnulib.mk.in   |  29 +++++++
 lib/ieee754.in.h   | 222 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 m4/gnulib-comp.m4  |   4 +
 m4/ieee754-h.m4    |  21 +++++
 src/lisp.h         |  11 +--
 src/lread.c        |   9 +--
 src/print.c        |  25 +-----
 11 files changed, 291 insertions(+), 40 deletions(-)
 create mode 100644 lib/ieee754.in.h
 create mode 100644 m4/ieee754-h.m4

diff --git a/.gitignore b/.gitignore
index d3712b0..26fe4bb 100644
--- a/.gitignore
+++ b/.gitignore
@@ -57,6 +57,7 @@ lib/execinfo.h
 lib/fcntl.h
 lib/getopt.h
 lib/getopt-cdefs.h
+lib/ieee754.h
 lib/inttypes.h
 lib/libgnu.a
 lib/limits.h
diff --git a/admin/merge-gnulib b/admin/merge-gnulib
index 39dfaee..1397ecf 100755
--- a/admin/merge-gnulib
+++ b/admin/merge-gnulib
@@ -35,7 +35,7 @@ GNULIB_MODULES=
   fcntl fcntl-h fdatasync fdopendir
   filemode filevercmp flexmember fpieee fstatat fsusage fsync
   getloadavg getopt-gnu gettime gettimeofday gitlog-to-changelog
-  ignore-value intprops largefile lstat
+  ieee754-h ignore-value intprops largefile lstat
   manywarnings memrchr minmax mkostemp mktime nstrftime
   pipe2 pselect pthread_sigmask putenv qcopy-acl readlink readlinkat
   sig2str socklen stat-time std-gnu11 stdalign stddef stdio
diff --git a/configure.ac b/configure.ac
index dbdcce7..b691867 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1668,7 +1668,6 @@ AC_DEFUN
 
 dnl checks for header files
 AC_CHECK_HEADERS_ONCE(
-  ieee754.h
   linux/fs.h
   malloc.h
   sys/systeminfo.h
diff --git a/etc/NEWS b/etc/NEWS
index 9e7a765..6c79a46 100644
--- a/etc/NEWS
+++ b/etc/NEWS
@@ -880,9 +880,9 @@ Formerly, some of these functions ignored signs and significands of
 NaNs.  Now, all these functions treat NaN signs and significands as
 significant.  For example, (eql 0.0e+NaN -0.0e+NaN) now returns nil
 because the two NaNs have different signs; formerly it returned t.
-Also, on platforms that have <ieee754.h> Emacs now reads and prints
-NaN significands; e.g., if X is a NaN, (format "%s" X) now returns
-"0.0e+NaN", "1.0e+NaN", etc., depending on X's significand.
+Also, Emacs now reads and prints NaN significands; e.g., if X is a
+NaN, (format "%s" X) now returns "0.0e+NaN", "1.0e+NaN", etc.,
+depending on X's significand.
 
 +++
 ** The function 'make-string' accepts an additional optional argument.
diff --git a/lib/gnulib.mk.in b/lib/gnulib.mk.in
index e623921..7d28dcc 100644
--- a/lib/gnulib.mk.in
+++ b/lib/gnulib.mk.in
@@ -95,6 +95,7 @@
 #  gettime \
 #  gettimeofday \
 #  gitlog-to-changelog \
+#  ieee754-h \
 #  ignore-value \
 #  intprops \
 #  largefile \
@@ -220,6 +221,7 @@ GL_GENERATE_ALLOCA_H = @GL_GENERATE_ALLOCA_H@
 GL_GENERATE_BYTESWAP_H = @GL_GENERATE_BYTESWAP_H@
 GL_GENERATE_ERRNO_H = @GL_GENERATE_ERRNO_H@
 GL_GENERATE_EXECINFO_H = @GL_GENERATE_EXECINFO_H@
+GL_GENERATE_IEEE754_H = @GL_GENERATE_IEEE754_H@
 GL_GENERATE_LIMITS_H = @GL_GENERATE_LIMITS_H@
 GL_GENERATE_STDALIGN_H = @GL_GENERATE_STDALIGN_H@
 GL_GENERATE_STDDEF_H = @GL_GENERATE_STDDEF_H@
@@ -646,6 +648,7 @@ HAVE_WINSOCK2_H = @HAVE_WINSOCK2_H@
 HAVE_XSERVER = @HAVE_XSERVER@
 HAVE__EXIT = @HAVE__EXIT@
 HYBRID_MALLOC = @HYBRID_MALLOC@
+IEEE754_H = @IEEE754_H@
 IMAGEMAGICK_CFLAGS = @IMAGEMAGICK_CFLAGS@
 IMAGEMAGICK_LIBS = @IMAGEMAGICK_LIBS@
 INCLUDE_NEXT = @INCLUDE_NEXT@
@@ -1787,6 +1790,32 @@ EXTRA_libgnu_a_SOURCES += group-member.c
 endif
 ## end   gnulib module group-member
 
+## begin gnulib module ieee754-h
+ifeq (,$(OMIT_GNULIB_MODULE_ieee754-h))
+
+BUILT_SOURCES += $(IEEE754_H)
+
+# We need the following in order to create <ieee754.h> when the system
+# doesn't have one that works with the given compiler.
+ifneq (,$(GL_GENERATE_IEEE754_H))
+ieee754.h: ieee754.in.h $(top_builddir)/config.status
+	$(AM_V_GEN)rm -f $@-t && \
+	{ echo '/* DO NOT EDIT! GENERATED AUTOMATICALLY! */'; \
+	  sed -e 's/ifndef _GL_GNULIB_HEADER/if 0/g' \
+	    $(srcdir)/ieee754.in.h; \
+	} > $@-t && \
+	mv -f $@-t $@
+else
+ieee754.h: $(top_builddir)/config.status
+	rm -f $@
+endif
+MOSTLYCLEANFILES += ieee754.h ieee754.h-t
+
+EXTRA_DIST += ieee754.in.h
+
+endif
+## end   gnulib module ieee754-h
+
 ## begin gnulib module ignore-value
 ifeq (,$(OMIT_GNULIB_MODULE_ignore-value))
 
diff --git a/lib/ieee754.in.h b/lib/ieee754.in.h
new file mode 100644
index 0000000..316ac03
--- /dev/null
+++ b/lib/ieee754.in.h
@@ -0,0 +1,222 @@
+/* Copyright (C) 1992-2018 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
+   modify it under the terms of the GNU General Public
+   License as published by the Free Software Foundation; either
+   version 3 of the License, or (at your option) any later version.
+
+   The GNU C Library 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 General Public
+   License along with the GNU C Library; if not, see
+   <http://www.gnu.org/licenses/>.  */
+
+#ifndef _IEEE754_H
+
+#define _IEEE754_H 1
+
+#ifndef _GL_GNULIB_HEADER
+/* Ordinary glibc usage.  */
+# include <features.h>
+# include <endian.h>
+#else
+/* Gnulib usage.  */
+# ifndef __BEGIN_DECLS
+#  ifdef __cplusplus
+#   define __BEGIN_DECLS	extern "C" {
+#   define __END_DECLS		}
+#  else
+#   define __BEGIN_DECLS
+#   define __END_DECLS
+#  endif
+# endif
+# ifndef __FLOAT_WORD_ORDER
+#  define __LITTLE_ENDIAN	1234
+#  define __BIG_ENDIAN		4321
+#  ifdef WORDS_BIGENDIAN
+#   define __BYTE_ORDER __BIG_ENDIAN
+#  else
+#   define __BYTE_ORDER __LITTLE_ENDIAN
+#  endif
+#  define __FLOAT_WORD_ORDER __BYTE_ORDER
+# endif
+#endif
+
+__BEGIN_DECLS
+
+union ieee754_float
+  {
+    float f;
+
+    /* This is the IEEE 754 single-precision format.  */
+    struct
+      {
+#if	__BYTE_ORDER == __BIG_ENDIAN
+	unsigned int negative:1;
+	unsigned int exponent:8;
+	unsigned int mantissa:23;
+#endif				/* Big endian.  */
+#if	__BYTE_ORDER == __LITTLE_ENDIAN
+	unsigned int mantissa:23;
+	unsigned int exponent:8;
+	unsigned int negative:1;
+#endif				/* Little endian.  */
+      } ieee;
+
+    /* This format makes it easier to see if a NaN is a signalling NaN.  */
+    struct
+      {
+#if	__BYTE_ORDER == __BIG_ENDIAN
+	unsigned int negative:1;
+	unsigned int exponent:8;
+	unsigned int quiet_nan:1;
+	unsigned int mantissa:22;
+#endif				/* Big endian.  */
+#if	__BYTE_ORDER == __LITTLE_ENDIAN
+	unsigned int mantissa:22;
+	unsigned int quiet_nan:1;
+	unsigned int exponent:8;
+	unsigned int negative:1;
+#endif				/* Little endian.  */
+      } ieee_nan;
+  };
+
+#define IEEE754_FLOAT_BIAS	0x7f /* Added to exponent.  */
+
+
+union ieee754_double
+  {
+    double d;
+
+    /* This is the IEEE 754 double-precision format.  */
+    struct
+      {
+#if	__BYTE_ORDER == __BIG_ENDIAN
+	unsigned int negative:1;
+	unsigned int exponent:11;
+	/* Together these comprise the mantissa.  */
+	unsigned int mantissa0:20;
+	unsigned int mantissa1:32;
+#endif				/* Big endian.  */
+#if	__BYTE_ORDER == __LITTLE_ENDIAN
+# if	__FLOAT_WORD_ORDER == __BIG_ENDIAN
+	unsigned int mantissa0:20;
+	unsigned int exponent:11;
+	unsigned int negative:1;
+	unsigned int mantissa1:32;
+# else
+	/* Together these comprise the mantissa.  */
+	unsigned int mantissa1:32;
+	unsigned int mantissa0:20;
+	unsigned int exponent:11;
+	unsigned int negative:1;
+# endif
+#endif				/* Little endian.  */
+      } ieee;
+
+    /* This format makes it easier to see if a NaN is a signalling NaN.  */
+    struct
+      {
+#if	__BYTE_ORDER == __BIG_ENDIAN
+	unsigned int negative:1;
+	unsigned int exponent:11;
+	unsigned int quiet_nan:1;
+	/* Together these comprise the mantissa.  */
+	unsigned int mantissa0:19;
+	unsigned int mantissa1:32;
+#else
+# if	__FLOAT_WORD_ORDER == __BIG_ENDIAN
+	unsigned int mantissa0:19;
+	unsigned int quiet_nan:1;
+	unsigned int exponent:11;
+	unsigned int negative:1;
+	unsigned int mantissa1:32;
+# else
+	/* Together these comprise the mantissa.  */
+	unsigned int mantissa1:32;
+	unsigned int mantissa0:19;
+	unsigned int quiet_nan:1;
+	unsigned int exponent:11;
+	unsigned int negative:1;
+# endif
+#endif
+      } ieee_nan;
+  };
+
+#define IEEE754_DOUBLE_BIAS	0x3ff /* Added to exponent.  */
+
+
+union ieee854_long_double
+  {
+    long double d;
+
+    /* This is the IEEE 854 double-extended-precision format.  */
+    struct
+      {
+#if	__BYTE_ORDER == __BIG_ENDIAN
+	unsigned int negative:1;
+	unsigned int exponent:15;
+	unsigned int empty:16;
+	unsigned int mantissa0:32;
+	unsigned int mantissa1:32;
+#endif
+#if	__BYTE_ORDER == __LITTLE_ENDIAN
+# if	__FLOAT_WORD_ORDER == __BIG_ENDIAN
+	unsigned int exponent:15;
+	unsigned int negative:1;
+	unsigned int empty:16;
+	unsigned int mantissa0:32;
+	unsigned int mantissa1:32;
+# else
+	unsigned int mantissa1:32;
+	unsigned int mantissa0:32;
+	unsigned int exponent:15;
+	unsigned int negative:1;
+	unsigned int empty:16;
+# endif
+#endif
+      } ieee;
+
+    /* This is for NaNs in the IEEE 854 double-extended-precision format.  */
+    struct
+      {
+#if	__BYTE_ORDER == __BIG_ENDIAN
+	unsigned int negative:1;
+	unsigned int exponent:15;
+	unsigned int empty:16;
+	unsigned int one:1;
+	unsigned int quiet_nan:1;
+	unsigned int mantissa0:30;
+	unsigned int mantissa1:32;
+#endif
+#if	__BYTE_ORDER == __LITTLE_ENDIAN
+# if	__FLOAT_WORD_ORDER == __BIG_ENDIAN
+	unsigned int exponent:15;
+	unsigned int negative:1;
+	unsigned int empty:16;
+	unsigned int mantissa0:30;
+	unsigned int quiet_nan:1;
+	unsigned int one:1;
+	unsigned int mantissa1:32;
+# else
+	unsigned int mantissa1:32;
+	unsigned int mantissa0:30;
+	unsigned int quiet_nan:1;
+	unsigned int one:1;
+	unsigned int exponent:15;
+	unsigned int negative:1;
+	unsigned int empty:16;
+# endif
+#endif
+      } ieee_nan;
+  };
+
+#define IEEE854_LONG_DOUBLE_BIAS 0x3fff
+
+__END_DECLS
+
+#endif /* ieee754.h */
diff --git a/m4/gnulib-comp.m4 b/m4/gnulib-comp.m4
index a6e3be3..494c77c 100644
--- a/m4/gnulib-comp.m4
+++ b/m4/gnulib-comp.m4
@@ -101,6 +101,7 @@ AC_DEFUN
   # Code from module gettimeofday:
   # Code from module gitlog-to-changelog:
   # Code from module group-member:
+  # Code from module ieee754-h:
   # Code from module ignore-value:
   # Code from module include_next:
   # Code from module intprops:
@@ -295,6 +296,7 @@ AC_DEFUN
     gl_PREREQ_GETTIMEOFDAY
   fi
   gl_SYS_TIME_MODULE_INDICATOR([gettimeofday])
+  gl_IEEE754_H
   gl_INTTYPES_INCOMPLETE
   AC_REQUIRE([gl_LARGEFILE])
   gl_LIMITS_H
@@ -895,6 +897,7 @@ AC_DEFUN
   lib/gettimeofday.c
   lib/gl_openssl.h
   lib/group-member.c
+  lib/ieee754.in.h
   lib/ignore-value.h
   lib/intprops.h
   lib/inttypes.in.h
@@ -1017,6 +1020,7 @@ AC_DEFUN
   m4/gl-openssl.m4
   m4/gnulib-common.m4
   m4/group-member.m4
+  m4/ieee754-h.m4
   m4/include_next.m4
   m4/inttypes.m4
   m4/largefile.m4
diff --git a/m4/ieee754-h.m4 b/m4/ieee754-h.m4
new file mode 100644
index 0000000..bf7c332
--- /dev/null
+++ b/m4/ieee754-h.m4
@@ -0,0 +1,21 @@
+# Configure ieee754-h module
+
+dnl Copyright 2018 Free Software Foundation, Inc.
+dnl This file is free software; the Free Software Foundation
+dnl gives unlimited permission to copy and/or distribute it,
+dnl with or without modifications, as long as this notice is preserved.
+
+AC_DEFUN([gl_IEEE754_H],
+[
+  AC_REQUIRE([AC_C_BIGENDIAN])
+  AC_CHECK_HEADERS_ONCE([ieee754.h])
+  if test $ac_cv_header_ieee754_h = yes; then
+    IEEE754_H=
+  else
+    IEEE754_H=ieee754.h
+    AC_DEFINE([_GL_REPLACE_IEEE754_H], 1,
+              [Define to 1 if <ieee754.h> is missing.])
+  fi
+  AC_SUBST([IEEE754_H])
+  AM_CONDITIONAL([GL_GENERATE_IEEE754_H], [test -n "$IEEE754_H"])
+])
diff --git a/src/lisp.h b/src/lisp.h
index 96de60e..bdece81 100644
--- a/src/lisp.h
+++ b/src/lisp.h
@@ -2670,17 +2670,14 @@ XFLOAT_DATA (Lisp_Object f)
 
 /* Most hosts nowadays use IEEE floating point, so they use IEC 60559
    representations, have infinities and NaNs, and do not trap on
-   exceptions.  Define IEEE_FLOATING_POINT if this host is one of the
+   exceptions.  Define IEEE_FLOATING_POINT to 1 if this host is one of the
    typical ones.  The C11 macro __STDC_IEC_559__ is close to what is
    wanted here, but is not quite right because Emacs does not require
    all the features of C11 Annex F (and does not require C11 at all,
    for that matter).  */
-enum
-  {
-    IEEE_FLOATING_POINT
-      = (FLT_RADIX == 2 && FLT_MANT_DIG == 24
-	 && FLT_MIN_EXP == -125 && FLT_MAX_EXP == 128)
-  };
+
+#define IEEE_FLOATING_POINT (FLT_RADIX == 2 && FLT_MANT_DIG == 24 \
+			     && FLT_MIN_EXP == -125 && FLT_MAX_EXP == 128)
 
 /* A character, declared with the following typedef, is a member
    of some character set associated with the current buffer.  */
diff --git a/src/lread.c b/src/lread.c
index 290b0f6..9a025d8 100644
--- a/src/lread.c
+++ b/src/lread.c
@@ -72,7 +72,7 @@ along with GNU Emacs.  If not, see <https://www.gnu.org/licenses/>.  */
 #define file_tell ftell
 #endif
 
-#if HAVE_IEEE754_H
+#if IEEE_FLOATING_POINT
 # include <ieee754.h>
 #endif
 
@@ -3756,21 +3756,18 @@ string_to_number (char const *string, int base, int flags)
 	      cp += 3;
 	      value = INFINITY;
 	    }
+#if IEEE_FLOATING_POINT
 	  else if (cp[-1] == '+'
 		   && cp[0] == 'N' && cp[1] == 'a' && cp[2] == 'N')
 	    {
 	      state |= E_EXP;
 	      cp += 3;
-#if HAVE_IEEE754_H
 	      union ieee754_double u
 		= { .ieee_nan = { .exponent = -1, .quiet_nan = 1,
 				  .mantissa0 = n >> 31 >> 1, .mantissa1 = n }};
 	      value = u.d;
-#else
-	      /* NAN is a "positive" NaN on all known Emacs hosts.  */
-	      value = NAN;
-#endif
 	    }
+#endif
 	  else
 	    cp = ecp;
 	}
diff --git a/src/print.c b/src/print.c
index add2160..34c7fa1 100644
--- a/src/print.c
+++ b/src/print.c
@@ -40,7 +40,7 @@ along with GNU Emacs.  If not, see <https://www.gnu.org/licenses/>.  */
 #include <ftoastr.h>
 #include <math.h>
 
-#if HAVE_IEEE754_H
+#if IEEE_FLOATING_POINT
 # include <ieee754.h>
 #endif
 
@@ -1013,34 +1013,15 @@ float_to_string (char *buf, double data)
       strcpy (buf, minus_infinity_string + positive);
       return sizeof minus_infinity_string - 1 - positive;
     }
+#if IEEE_FLOATING_POINT
   if (isnan (data))
     {
-#if HAVE_IEEE754_H
       union ieee754_double u = { .d = data };
       uprintmax_t hi = u.ieee_nan.mantissa0;
       return sprintf (buf, &"-%"pMu".0e+NaN"[!u.ieee_nan.negative],
 		      (hi << 31 << 1) + u.ieee_nan.mantissa1);
-#else
-      /* Prepend "-" if the NaN's sign bit is negative.
-	 The sign bit of a double is the bit that is 1 in -0.0.  */
-      static char const NaN_string[] = "0.0e+NaN";
-      int i;
-      union { double d; char c[sizeof (double)]; } u_data, u_minus_zero;
-      bool negative = 0;
-      u_data.d = data;
-      u_minus_zero.d = - 0.0;
-      for (i = 0; i < sizeof (double); i++)
-	if (u_data.c[i] & u_minus_zero.c[i])
-	  {
-	    *buf = '-';
-	    negative = 1;
-	    break;
-	  }
-
-      strcpy (buf + negative, NaN_string);
-      return negative + sizeof NaN_string - 1;
-#endif
     }
+#endif
 
   if (NILP (Vfloat_output_format)
       || !STRINGP (Vfloat_output_format))
-- 
2.7.4