Skip to content

R
riscv-gcc-1
Commit 2d295af5 by Zack Weinberg
Options

aclocal.m4 (gcc_AC_EXAMINE_OBJECT, [...]): Delete. 

	* aclocal.m4 (gcc_AC_EXAMINE_OBJECT, gcc_AC_C_FLOAT_FORMAT): Delete.
	* configure.in: Don't call gcc_AC_C_FLOAT_FORMAT.
	* defaults.h: Remove reference to HOST_FLOAT_WORDS_BIG_ENDIAN
	in comment.

From-SVN: r64672
parent 649eaf9b
Showing with 17 additions and 162 deletions
gcc/ChangeLog
2003-03-21 Zack Weinberg <zack@codesourcery.com>
* aclocal.m4 (gcc_AC_EXAMINE_OBJECT, gcc_AC_C_FLOAT_FORMAT): Delete.
* configure.in: Don't call gcc_AC_C_FLOAT_FORMAT.
* defaults.h: Remove reference to HOST_FLOAT_WORDS_BIG_ENDIAN
in comment.
2003-03-21 DJ Delorie <dj@redhat.com>
* optabs.c (init_integral_libfuncs): Make sure we init at least up
......@@ -16,7 +23,7 @@
variables in macros.
2003-03-21 Eric Botcazou <ebotcazou@libertysurf.fr>
Richard Henderson <rth@redhat.com>
Richard Henderson <rth@redhat.com>
PR optimization/8366
* config/sparc/sparc.h: (SYMBOLIC_CONST): New macro.
......@@ -45,7 +52,7 @@
mingw. Simplify special spec logic. Define "wrappers" around
certain include path defines to accommodate -mno-cygwin.
Remove some #if 0'ed code.
(STANDARD_INCLUDE_DIR) Always define when not cross-compiling.
(STANDARD_INCLUDE_DIR) Always define when not cross-compiling.
(LINK_SPEC): Don't use cyg search prefix when -mno-cygwin.
(GCC_DRIVER_HOST_INITIALIZATION): Define as call to mingw_scan.
* config/i386/mingw32.h: Remove definitions common to cygwin and
......@@ -67,14 +74,14 @@
operands in case MULT_EXPR of 2003-02-16 patch.
2003-03-20 Daniel Berlin <dberlin@dberlin.org>
Merge changes from new-regalloc-branch
Merge changes from new-regalloc-branch
From Michael Matz <matz@suse.de>
* df.c (df_ref_record_1): Move init of loc to safe point.
Only recurse on interesting things in parallels.
Handle CLASS_CANNOT_CHANGE_MODE smarter.
(df_uses_record): Ditto.
* df.h (DF_REF_MEM_OK): New enum member, used to mark ref's which
it's already okay to use memory operands in (IE doesn't require
adding another insn or anything).
......@@ -134,9 +141,9 @@
* cpplib.h: Update declaration to match.
* c-opts.c (push_command_line_line, finish_options): Change
cpp_rename_file calls to cpp_change_file.
* line-map.c (add_line_map): Allow leaving the outermost file.
Allowing entering an outermost-file after the initial time.
Allowing entering an outermost-file after the initial time.
* toplev.c (pop_srcloc): Allow popping from initial file.
......@@ -190,7 +197,7 @@
not index register.
* config/s390/s390.md ("*tsthiCCT_only"): Remove '?' from
Q alternative.
("*movdi_64", "*movsi", "movhi", "movqi_64", "movqi",
("*movdi_64", "*movsi", "movhi", "movqi_64", "movqi",
"*movdf_64", "*movsf"): Add '?' to Q->Q alternatives.
("*extractqi", "*extracthi", "*zero_extendhisi2_31",
"*zero_extendqisi2_31", "*zero_extendqihi2_31",
......
gcc/aclocal.m4
......@@ -885,145 +885,6 @@ elif test $ac_cv_c_charset = EBCDIC; then
[Define if the host execution character set is EBCDIC.])
fi])
dnl Utility macro used by next two tests.
dnl AC_EXAMINE_OBJECT(C source code,
dnl commands examining object file,
dnl [commands to run if compile failed]):
dnl
dnl Compile the source code to an object file; then convert it into a
dnl printable representation. All unprintable characters and
dnl asterisks (*) are replaced by dots (.). All white space is
dnl deleted. Newlines (ASCII 0x10) in the input are preserved in the
dnl output, but runs of newlines are compressed to a single newline.
dnl Finally, line breaks are forcibly inserted so that no line is
dnl longer than 80 columns and the file ends with a newline. The
dnl result of all this processing is in the file conftest.dmp, which
dnl may be examined by the commands in the second argument.
dnl
AC_DEFUN([gcc_AC_EXAMINE_OBJECT],
[AC_LANG_SAVE
AC_LANG_C
dnl Next bit cribbed from AC_TRY_COMPILE.
cat > conftest.$ac_ext <<EOF
[#line __oline__ "configure"
#include "confdefs.h"
$1
]EOF
if AC_TRY_EVAL(ac_compile); then
od -c conftest.o |
sed ['s/^[0-7]*[ ]*/ /
s/\*/./g
s/ \\n/*/g
s/ [0-9][0-9][0-9]/./g
s/ \\[^ ]/./g'] |
tr -d '
' | tr -s '*' '
' | fold | sed '$a\
' > conftest.dmp
$2
ifelse($3, , , else
$3
)dnl
fi
rm -rf conftest*
AC_LANG_RESTORE])
dnl Floating point format probe.
dnl The basic concept is the same as the above: grep the object
dnl file for an interesting string. We have to watch out for
dnl rounding changing the values in the object, however; this is
dnl handled by ignoring the least significant byte of the float.
dnl
dnl Does not know about VAX G-float or C4x idiosyncratic format.
dnl It does know about PDP-10 idiosyncratic format, but this is
dnl not presently supported by GCC. S/390 "binary floating point"
dnl is in fact IEEE (but maybe we should have that in EBCDIC as well
dnl as ASCII?)
dnl
AC_DEFUN([gcc_AC_C_FLOAT_FORMAT],
[AC_CACHE_CHECK(floating point format, ac_cv_c_float_format,
[gcc_AC_EXAMINE_OBJECT(
[/* This will not work unless sizeof(double) == 8. */
extern char sizeof_double_must_be_8 [sizeof(double) == 8 ? 1 : -1];
/* This structure must have no internal padding. */
struct possibility {
char prefix[8];
double candidate;
char postfix[8];
};
#define C(cand) { "\nformat:", cand, ":tamrof\n" }
struct possibility table [] =
{
C( 3.25724264705901305206e+01), /* @@IEEEFP - IEEE 754 */
C( 3.53802595280598432000e+18), /* D__float - VAX */
C( 5.32201830133125317057e-19), /* D.PDP-10 - PDP-10 - the dot is 0x13a */
C( 1.77977764695171661377e+10), /* IBMHEXFP - s/390 format, ascii */
C(-5.22995989424860458374e+10) /* IBMHEXFP - s/390 format, EBCDIC */
};],
[if grep 'format:.@IEEEF.:tamrof' conftest.dmp >/dev/null 2>&1; then
ac_cv_c_float_format='IEEE (big-endian)'
elif grep 'format:.I@@PFE.:tamrof' conftest.dmp >/dev/null 2>&1; then
ac_cv_c_float_format='IEEE (big-endian)'
elif grep 'format:.FEEEI@.:tamrof' conftest.dmp >/dev/null 2>&1; then
ac_cv_c_float_format='IEEE (little-endian)'
elif grep 'format:.EFP@@I.:tamrof' conftest.dmp >/dev/null 2>&1; then
ac_cv_c_float_format='IEEE (little-endian)'
elif grep 'format:.__floa.:tamrof' conftest.dmp >/dev/null 2>&1; then
ac_cv_c_float_format='VAX D-float'
elif grep 'format:..PDP-1.:tamrof' conftest.dmp >/dev/null 2>&1; then
ac_cv_c_float_format='PDP-10'
elif grep 'format:.BMHEXF.:tamrof' conftest.dmp >/dev/null 2>&1; then
ac_cv_c_float_format='IBM 370 hex'
else
AC_MSG_ERROR(Unknown floating point format)
fi],
[AC_MSG_ERROR(compile failed)])
])
# IEEE is the default format. If the float endianness isn't the same
# as the integer endianness, we have to set FLOAT_WORDS_BIG_ENDIAN
# (which is a tristate: yes, no, default). This is only an issue with
# IEEE; the other formats are only supported by a few machines each,
# all with the same endianness.
format=
fbigend=
case $ac_cv_c_float_format in
'IEEE (big-endian)' )
if test $ac_cv_c_bigendian = no; then
fbigend=1
fi
;;
'IEEE (little-endian)' )
if test $ac_cv_c_bigendian = yes; then
fbigend=0
fi
;;
'VAX D-float' )
format=VAX_FLOAT_FORMAT
;;
'PDP-10' )
format=PDP10_FLOAT_FORMAT
;;
'IBM 370 hex' )
format=IBM_FLOAT_FORMAT
;;
esac
if test -n "$format"; then
AC_DEFINE_UNQUOTED(HOST_FLOAT_FORMAT, $format,
[Define to the floating point format of the host machine, if not IEEE.])
fi
if test -n "$fbigend"; then
AC_DEFINE_UNQUOTED(HOST_FLOAT_WORDS_BIG_ENDIAN, $fbigend,
[Define to 1 if the host machine stores floating point numbers in
memory with the word containing the sign bit at the lowest address,
or to 0 if it does it the other way around.
This macro should not be defined if the ordering is the same as for
multi-word integers.])
fi
])
#serial AM2
dnl From Bruno Haible.
......
gcc/config.in
/* config.in. Generated automatically from configure.in by autoheader. */
/* config.in. Generated automatically from configure.in by autoheader 2.13. */
/* Define if using alloca.c. */
#undef C_ALLOCA
......@@ -382,17 +382,6 @@
/* 1234 = LIL_ENDIAN, 4321 = BIGENDIAN */
#undef BYTEORDER
/* Define to the floating point format of the host machine, if not IEEE. */
#undef HOST_FLOAT_FORMAT
/* Define to 1 if the host machine stores floating point numbers in
memory with the word containing the sign bit at the lowest address,
or to 0 if it does it the other way around.
This macro should not be defined if the ordering is the same as for
multi-word integers. */
#undef HOST_FLOAT_WORDS_BIG_ENDIAN
/* Define if you have a working <inttypes.h> header file. */
#undef HAVE_INTTYPES_H
......
gcc/configure.in
......@@ -697,7 +697,6 @@ AC_CHECK_HEADER(pthread.h, [have_pthread_h=yes], [have_pthread_h=])
# These tests can't be done till we know if we have limits.h.
gcc_AC_C_CHAR_BIT
AC_C_BIGENDIAN_CROSS
gcc_AC_C_FLOAT_FORMAT
# --------
# UNSORTED
......
gcc/defaults.h
......@@ -572,9 +572,8 @@ You Lose! You must define PREFERRED_DEBUGGING_TYPE!
&& !ROUND_TOWARDS_ZERO)
#endif
/* If FLOAT_WORDS_BIG_ENDIAN and HOST_FLOAT_WORDS_BIG_ENDIAN are not defined
in the header files, then this implies the word-endianness is the same as
for integers. */
/* If FLOAT_WORDS_BIG_ENDIAN is not defined in the header files,
then the word-endianness is the same as for integers. */
#ifndef FLOAT_WORDS_BIG_ENDIAN
#define FLOAT_WORDS_BIG_ENDIAN WORDS_BIG_ENDIAN
#endif
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment