head	1.1;
branch	1.1.1;
access;
symbols
	netbsd-11-0-RC4:1.1.1.3
	netbsd-11-0-RC3:1.1.1.3
	netbsd-11-0-RC2:1.1.1.3
	netbsd-11-0-RC1:1.1.1.3
	perseant-exfatfs-base-20250801:1.1.1.3
	netbsd-11:1.1.1.3.0.18
	netbsd-11-base:1.1.1.3
	netbsd-10-1-RELEASE:1.1.1.3
	perseant-exfatfs-base-20240630:1.1.1.3
	perseant-exfatfs:1.1.1.3.0.16
	perseant-exfatfs-base:1.1.1.3
	netbsd-8-3-RELEASE:1.1.1.2
	netbsd-9-4-RELEASE:1.1.1.3
	netbsd-10-0-RELEASE:1.1.1.3
	netbsd-10-0-RC6:1.1.1.3
	netbsd-10-0-RC5:1.1.1.3
	netbsd-10-0-RC4:1.1.1.3
	netbsd-10-0-RC3:1.1.1.3
	netbsd-10-0-RC2:1.1.1.3
	netbsd-10-0-RC1:1.1.1.3
	netbsd-10:1.1.1.3.0.14
	netbsd-10-base:1.1.1.3
	netbsd-9-3-RELEASE:1.1.1.3
	gmp-6-2-1:1.1.1.3
	cjep_sun2x-base1:1.1.1.3
	cjep_sun2x:1.1.1.3.0.12
	cjep_sun2x-base:1.1.1.3
	cjep_staticlib_x-base1:1.1.1.3
	netbsd-9-2-RELEASE:1.1.1.3
	cjep_staticlib_x:1.1.1.3.0.10
	cjep_staticlib_x-base:1.1.1.3
	netbsd-9-1-RELEASE:1.1.1.3
	gmp-6-2-0:1.1.1.3
	phil-wifi-20200421:1.1.1.3
	phil-wifi-20200411:1.1.1.3
	is-mlppp:1.1.1.3.0.8
	is-mlppp-base:1.1.1.3
	phil-wifi-20200406:1.1.1.3
	netbsd-8-2-RELEASE:1.1.1.2
	netbsd-9-0-RELEASE:1.1.1.3
	netbsd-9-0-RC2:1.1.1.3
	netbsd-9-0-RC1:1.1.1.3
	phil-wifi-20191119:1.1.1.3
	netbsd-9:1.1.1.3.0.6
	netbsd-9-base:1.1.1.3
	phil-wifi-20190609:1.1.1.3
	netbsd-8-1-RELEASE:1.1.1.2
	netbsd-8-1-RC1:1.1.1.2
	pgoyette-compat-merge-20190127:1.1.1.3
	pgoyette-compat-20190127:1.1.1.3
	pgoyette-compat-20190118:1.1.1.3
	pgoyette-compat-1226:1.1.1.3
	pgoyette-compat-1126:1.1.1.3
	pgoyette-compat-1020:1.1.1.3
	pgoyette-compat-0930:1.1.1.3
	pgoyette-compat-0906:1.1.1.3
	netbsd-7-2-RELEASE:1.1.1.2
	pgoyette-compat-0728:1.1.1.3
	netbsd-8-0-RELEASE:1.1.1.2
	phil-wifi:1.1.1.3.0.4
	phil-wifi-base:1.1.1.3
	pgoyette-compat-0625:1.1.1.3
	netbsd-8-0-RC2:1.1.1.2
	pgoyette-compat-0521:1.1.1.3
	pgoyette-compat-0502:1.1.1.3
	pgoyette-compat-0422:1.1.1.3
	netbsd-8-0-RC1:1.1.1.2
	pgoyette-compat-0415:1.1.1.3
	pgoyette-compat-0407:1.1.1.3
	pgoyette-compat-0330:1.1.1.3
	pgoyette-compat-0322:1.1.1.3
	pgoyette-compat-0315:1.1.1.3
	netbsd-7-1-2-RELEASE:1.1.1.2
	pgoyette-compat:1.1.1.3.0.2
	pgoyette-compat-base:1.1.1.3
	netbsd-7-1-1-RELEASE:1.1.1.2
	matt-nb8-mediatek:1.1.1.2.0.22
	matt-nb8-mediatek-base:1.1.1.2
	gmp-6-1-2:1.1.1.3
	perseant-stdc-iso10646:1.1.1.2.0.20
	perseant-stdc-iso10646-base:1.1.1.2
	netbsd-8:1.1.1.2.0.18
	netbsd-8-base:1.1.1.2
	prg-localcount2-base3:1.1.1.2
	prg-localcount2-base2:1.1.1.2
	prg-localcount2-base1:1.1.1.2
	prg-localcount2:1.1.1.2.0.16
	prg-localcount2-base:1.1.1.2
	pgoyette-localcount-20170426:1.1.1.2
	bouyer-socketcan-base1:1.1.1.2
	pgoyette-localcount-20170320:1.1.1.2
	netbsd-7-1:1.1.1.2.0.14
	netbsd-7-1-RELEASE:1.1.1.2
	netbsd-7-1-RC2:1.1.1.2
	netbsd-7-nhusb-base-20170116:1.1.1.2
	bouyer-socketcan:1.1.1.2.0.12
	bouyer-socketcan-base:1.1.1.2
	pgoyette-localcount-20170107:1.1.1.2
	netbsd-7-1-RC1:1.1.1.2
	pgoyette-localcount-20161104:1.1.1.2
	netbsd-7-0-2-RELEASE:1.1.1.2
	localcount-20160914:1.1.1.2
	netbsd-7-nhusb:1.1.1.2.0.10
	netbsd-7-nhusb-base:1.1.1.2
	pgoyette-localcount-20160806:1.1.1.2
	pgoyette-localcount-20160726:1.1.1.2
	pgoyette-localcount:1.1.1.2.0.8
	pgoyette-localcount-base:1.1.1.2
	netbsd-7-0-1-RELEASE:1.1.1.2
	netbsd-7-0:1.1.1.2.0.6
	netbsd-7-0-RELEASE:1.1.1.2
	netbsd-7-0-RC3:1.1.1.2
	netbsd-7-0-RC2:1.1.1.2
	netbsd-7-0-RC1:1.1.1.2
	netbsd-6-0-6-RELEASE:1.1.1.1
	netbsd-6-1-5-RELEASE:1.1.1.1
	netbsd-7:1.1.1.2.0.4
	netbsd-7-base:1.1.1.2
	yamt-pagecache-base9:1.1.1.2
	yamt-pagecache-tag8:1.1.1.1
	netbsd-6-1-4-RELEASE:1.1.1.1
	netbsd-6-0-5-RELEASE:1.1.1.1
	tls-earlyentropy:1.1.1.2.0.2
	tls-earlyentropy-base:1.1.1.2
	riastradh-xf86-video-intel-2-7-1-pre-2-21-15:1.1.1.2
	riastradh-drm2-base3:1.1.1.2
	netbsd-6-1-3-RELEASE:1.1.1.1
	netbsd-6-0-4-RELEASE:1.1.1.1
	gmp-5-1-3:1.1.1.2
	netbsd-6-1-2-RELEASE:1.1.1.1
	netbsd-6-0-3-RELEASE:1.1.1.1
	netbsd-6-1-1-RELEASE:1.1.1.1
	riastradh-drm2-base2:1.1.1.1
	riastradh-drm2-base1:1.1.1.1
	riastradh-drm2:1.1.1.1.0.12
	riastradh-drm2-base:1.1.1.1
	netbsd-6-1:1.1.1.1.0.16
	netbsd-6-0-2-RELEASE:1.1.1.1
	netbsd-6-1-RELEASE:1.1.1.1
	netbsd-6-1-RC4:1.1.1.1
	netbsd-6-1-RC3:1.1.1.1
	agc-symver:1.1.1.1.0.14
	agc-symver-base:1.1.1.1
	netbsd-6-1-RC2:1.1.1.1
	netbsd-6-1-RC1:1.1.1.1
	yamt-pagecache-base8:1.1.1.1
	netbsd-6-0-1-RELEASE:1.1.1.1
	yamt-pagecache-base7:1.1.1.1
	matt-nb6-plus-nbase:1.1.1.1
	yamt-pagecache-base6:1.1.1.1
	netbsd-6-0:1.1.1.1.0.10
	netbsd-6-0-RELEASE:1.1.1.1
	netbsd-6-0-RC2:1.1.1.1
	tls-maxphys:1.1.1.1.0.8
	tls-maxphys-base:1.1.1.2
	matt-nb6-plus:1.1.1.1.0.6
	matt-nb6-plus-base:1.1.1.1
	netbsd-6-0-RC1:1.1.1.1
	yamt-pagecache-base5:1.1.1.1
	yamt-pagecache-base4:1.1.1.1
	netbsd-6:1.1.1.1.0.4
	netbsd-6-base:1.1.1.1
	yamt-pagecache-base3:1.1.1.1
	yamt-pagecache-base2:1.1.1.1
	yamt-pagecache:1.1.1.1.0.2
	yamt-pagecache-base:1.1.1.1
	gmp-5-0-2:1.1.1.1
	gmp:1.1.1;
locks; strict;
comment	@;; @;


1.1
date	2011.06.20.05.54.45;	author mrg;	state Exp;
branches
	1.1.1.1;
next	;

1.1.1.1
date	2011.06.20.05.54.45;	author mrg;	state Exp;
branches
	1.1.1.1.2.1
	1.1.1.1.8.1;
next	1.1.1.2;

1.1.1.2
date	2013.11.29.07.49.48;	author mrg;	state Exp;
branches;
next	1.1.1.3;
commitid	L2Av4PuGmdoL39fx;

1.1.1.3
date	2017.08.22.09.40.48;	author mrg;	state Exp;
branches;
next	;
commitid	W5kmAIk8hwVpSb4A;

1.1.1.1.2.1
date	2014.05.22.14.09.09;	author yamt;	state Exp;
branches;
next	;
commitid	nx2BSsHy0NPeAxBx;

1.1.1.1.8.1
date	2014.08.19.23.59.57;	author tls;	state Exp;
branches;
next	;
commitid	jTnpym9Qu0o4R1Nx;


desc
@@


1.1
log
@Initial revision
@
text
@dnl  AMD64 calling conventions checking.

dnl  Copyright 2000, 2003, 2004, 2006, 2007 Free Software Foundation, Inc.
dnl
dnl  This file is part of the GNU MP Library.
dnl
dnl  The GNU MP Library is free software; you can redistribute it and/or
dnl  modify it under the terms of the GNU Lesser General Public License as
dnl  published by the Free Software Foundation; either version 3 of the
dnl  License, or (at your option) any later version.
dnl
dnl  The GNU MP Library is distributed in the hope that it will be useful,
dnl  but WITHOUT ANY WARRANTY; without even the implied warranty of
dnl  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
dnl  Lesser General Public License for more details.
dnl
dnl  You should have received a copy of the GNU Lesser General Public License
dnl  along with the GNU MP Library.  If not, see http://www.gnu.org/licenses/.


include(`../config.m4')


C void x86_fldcw (unsigned short cw);
C
C Execute an fldcw, setting the x87 control word to cw.

PROLOGUE(x86_fldcw)
	movq	%rdi, -8(%rsp)
	fldcw	-8(%rsp)
	ret
EPILOGUE()


C unsigned short x86_fstcw (void);
C
C Execute an fstcw, returning the current x87 control word.

PROLOGUE(x86_fstcw)
        movq	$0, -8(%rsp)
        fstcw	-8(%rsp)
        movq	-8(%rsp), %rax
	ret
EPILOGUE()


dnl  Instrumented profiling won't come out quite right below, since we don't
dnl  do an actual "ret".  There's only a few instructions here, so there's
dnl  no great need to get them separately accounted, just let them get
dnl  attributed to the caller.

ifelse(WANT_PROFILING,instrument,
`define(`WANT_PROFILING',no)')


C int calling_conventions (...);
C
C The global variable "calling_conventions_function" is the function to
C call, with the arguments as passed here.
C
C Perhaps the finit should be done only if the tags word isn't clear, but
C nothing uses the rounding mode or anything at the moment.

define(`WANT_RBX', eval(8*0)($1))
define(`WANT_RBP', eval(8*1)($1))
define(`WANT_R12', eval(8*2)($1))
define(`WANT_R13', eval(8*3)($1))
define(`WANT_R14', eval(8*4)($1))
define(`WANT_R15', eval(8*5)($1))

define(`JUNK_RAX', eval(8*6)($1))
define(`JUNK_R10', eval(8*7)($1))
define(`JUNK_R11', eval(8*8)($1))

define(`SAVE_RBX', eval(8*9)($1))
define(`SAVE_RBP', eval(8*10)($1))
define(`SAVE_R12', eval(8*11)($1))
define(`SAVE_R13', eval(8*12)($1))
define(`SAVE_R14', eval(8*13)($1))
define(`SAVE_R15', eval(8*14)($1))

define(`RETADDR',  eval(8*15)($1))

define(`RBX',	   eval(8*16)($1))
define(`RBP',	   eval(8*17)($1))
define(`R12',	   eval(8*18)($1))
define(`R13',	   eval(8*19)($1))
define(`R14',	   eval(8*20)($1))
define(`R15',	   eval(8*21)($1))
define(`RFLAGS',   eval(8*22)($1))


define(G,
m4_assert_numargs(1)
`GSYM_PREFIX`'$1')

	TEXT
	ALIGN(32)
PROLOGUE(calling_conventions)
	push	%rdi
	movq	G(calling_conventions_values)@@GOTPCREL(%rip), %rdi

	movq	8(%rsp), %rax
	movq	%rax, RETADDR(%rdi)

	leaq	L(return)(%rip), %rax
	movq	%rax, 8(%rsp)

	movq	%rbx, SAVE_RBX(%rdi)
	movq	%rbp, SAVE_RBP(%rdi)
	movq	%r12, SAVE_R12(%rdi)
	movq	%r13, SAVE_R13(%rdi)
	movq	%r14, SAVE_R14(%rdi)
	movq	%r15, SAVE_R15(%rdi)

	C values we expect to see unchanged, as per amd64check.c
	movq	WANT_RBX(%rdi), %rbx
	movq	WANT_RBP(%rdi), %rbp
	movq	WANT_R12(%rdi), %r12
	movq	WANT_R13(%rdi), %r13
	movq	WANT_R14(%rdi), %r14
	movq	WANT_R15(%rdi), %r15

	C Try to provoke a problem by starting with junk in the registers,
	C especially %rax which will be the return value.
	C
	C ENHANCE-ME: If we knew how many of the parameter registers were
	C actually being used we could put junk in the rest.  Maybe we could
	C get try.c to communicate this to us.
C	movq	JUNK_RAX(%rdi), %rax		C overwritten below anyway
	movq	JUNK_R10(%rdi), %r10
	movq	JUNK_R11(%rdi), %r11

	movq	G(calling_conventions_function)@@GOTPCREL(%rip), %rax
	pop	%rdi
	jmp	*(%rax)

L(return):
	movq	G(calling_conventions_values)@@GOTPCREL(%rip), %rdi

	movq	%rbx, RBX(%rdi)
	movq	%rbp, RBP(%rdi)
	movq	%r12, R12(%rdi)
	movq	%r13, R13(%rdi)
	movq	%r14, R14(%rdi)
	movq	%r15, R15(%rdi)

	pushfq
	popq	%rbx
	movq	%rbx, RFLAGS(%rdi)

	movq	G(calling_conventions_fenv)@@GOTPCREL(%rip), %rbx
	fstenv	(%rbx)
	finit

	movq	SAVE_RBX(%rdi), %rbx
	movq	SAVE_RBP(%rdi), %rbp
	movq	SAVE_R12(%rdi), %r12
	movq	SAVE_R13(%rdi), %r13
	movq	SAVE_R14(%rdi), %r14
	movq	SAVE_R15(%rdi), %r15

	jmp	*RETADDR(%rdi)

EPILOGUE()
@


1.1.1.1
log
@initial import of GMP 5.0.2.

GNU MP is a library for arbitrary precision arithmetic, operating on signed
integers, rational numbers, and floating point numbers.  It has a rich set
of functions, and the functions have a regular interface.

GMP is necessary for GCC >= 4.2.
@
text
@@


1.1.1.1.8.1
log
@Rebase to HEAD as of a few days ago.
@
text
@d3 6
a8 6
dnl  Copyright 2000, 2003, 2004, 2006, 2007, 2010 Free Software Foundation, Inc.

dnl  This file is part of the GNU MP Library test suite.

dnl  The GNU MP Library test suite is free software; you can redistribute it
dnl  and/or modify it under the terms of the GNU General Public License as
d11 8
a18 9

dnl  The GNU MP Library test suite is distributed in the hope that it will be
dnl  useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
dnl  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General
dnl  Public License for more details.

dnl  You should have received a copy of the GNU General Public License along
dnl  with the GNU MP Library test suite.  If not, see
dnl  http://www.gnu.org/licenses/.
a20 3
dnl  The current version of the code attempts to keep the call/return
dnl  prediction stack valid, but matching calls and returns.

d40 3
a42 3
	movq	$0, -8(%rsp)
	fstcw	-8(%rsp)
	movq	-8(%rsp), %rax
d47 4
a50 4
dnl  Instrumented profiling won't come out quite right below, since we don't do
dnl  an actual "ret".  There's only a few instructions here, so there's no
dnl  great need to get them separately accounted, just let them get attributed
dnl  to the caller.  FIXME this comment might no longer be true.
d100 5
a104 2
	movq	G(calling_conventions_values)@@GOTPCREL(%rip), %rax
	popq	RETADDR(%rax)
d106 27
a132 20
	movq	%rbx, SAVE_RBX(%rax)
	movq	%rbp, SAVE_RBP(%rax)
	movq	%r12, SAVE_R12(%rax)
	movq	%r13, SAVE_R13(%rax)
	movq	%r14, SAVE_R14(%rax)
	movq	%r15, SAVE_R15(%rax)

	C Values we expect to see unchanged, as per amd64check.c
	movq	WANT_RBX(%rax), %rbx
	movq	WANT_RBP(%rax), %rbp
	movq	WANT_R12(%rax), %r12
	movq	WANT_R13(%rax), %r13
	movq	WANT_R14(%rax), %r14
	movq	WANT_R15(%rax), %r15

	C Try to provoke a problem by starting with junk in the caller-saves
	C registers, especially %rax which will be the return value.
C	movq	JUNK_RAX(%rax), %rax		C overwritten below anyway
	movq	JUNK_R10(%rax), %r10
	movq	JUNK_R11(%rax), %r11
d135 2
a136 1
	call	*(%rax)
d138 2
a139 1
	movq	G(calling_conventions_values)@@GOTPCREL(%rip), %rcx
d141 6
a146 6
	movq	%rbx, RBX(%rcx)
	movq	%rbp, RBP(%rcx)
	movq	%r12, R12(%rcx)
	movq	%r13, R13(%rcx)
	movq	%r14, R14(%rcx)
	movq	%r15, R15(%rcx)
d150 1
a150 1
	movq	%rbx, RFLAGS(%rcx)
d152 3
a154 14
	movq	SAVE_RBX(%rcx), %rbx
	movq	SAVE_RBP(%rcx), %rbp
	movq	SAVE_R12(%rcx), %r12
	movq	SAVE_R13(%rcx), %r13
	movq	SAVE_R14(%rcx), %r14
	movq	SAVE_R15(%rcx), %r15

	C Overwrite parameter registers
C	mov	JUNK_R9(%rcx), %r9
C	mov	JUNK_R8(%rcx), %r8
C	mov	JUNK_RCX(%rcx), %rcx
C	mov	JUNK_RDX(%rcx), %rdx
C	mov	JUNK_RSI(%rcx), %rsi
C	mov	JUNK_RDI(%rcx), %rdi
d156 6
a161 1
	pushq	RETADDR(%rcx)
d163 1
a163 5
	movq	G(calling_conventions_fenv)@@GOTPCREL(%rip), %rcx
	fstenv	(%rcx)
	finit

	ret
@


1.1.1.1.2.1
log
@sync with head.

for a reference, the tree before this commit was tagged
as yamt-pagecache-tag8.

this commit was splitted into small chunks to avoid
a limitation of cvs.  ("Protocol error: too many arguments")
@
text
@d3 6
a8 6
dnl  Copyright 2000, 2003, 2004, 2006, 2007, 2010 Free Software Foundation, Inc.

dnl  This file is part of the GNU MP Library test suite.

dnl  The GNU MP Library test suite is free software; you can redistribute it
dnl  and/or modify it under the terms of the GNU General Public License as
d11 8
a18 9

dnl  The GNU MP Library test suite is distributed in the hope that it will be
dnl  useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
dnl  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General
dnl  Public License for more details.

dnl  You should have received a copy of the GNU General Public License along
dnl  with the GNU MP Library test suite.  If not, see
dnl  http://www.gnu.org/licenses/.
a20 3
dnl  The current version of the code attempts to keep the call/return
dnl  prediction stack valid, but matching calls and returns.

d40 3
a42 3
	movq	$0, -8(%rsp)
	fstcw	-8(%rsp)
	movq	-8(%rsp), %rax
d47 4
a50 4
dnl  Instrumented profiling won't come out quite right below, since we don't do
dnl  an actual "ret".  There's only a few instructions here, so there's no
dnl  great need to get them separately accounted, just let them get attributed
dnl  to the caller.  FIXME this comment might no longer be true.
d100 5
a104 2
	movq	G(calling_conventions_values)@@GOTPCREL(%rip), %rax
	popq	RETADDR(%rax)
d106 27
a132 20
	movq	%rbx, SAVE_RBX(%rax)
	movq	%rbp, SAVE_RBP(%rax)
	movq	%r12, SAVE_R12(%rax)
	movq	%r13, SAVE_R13(%rax)
	movq	%r14, SAVE_R14(%rax)
	movq	%r15, SAVE_R15(%rax)

	C Values we expect to see unchanged, as per amd64check.c
	movq	WANT_RBX(%rax), %rbx
	movq	WANT_RBP(%rax), %rbp
	movq	WANT_R12(%rax), %r12
	movq	WANT_R13(%rax), %r13
	movq	WANT_R14(%rax), %r14
	movq	WANT_R15(%rax), %r15

	C Try to provoke a problem by starting with junk in the caller-saves
	C registers, especially %rax which will be the return value.
C	movq	JUNK_RAX(%rax), %rax		C overwritten below anyway
	movq	JUNK_R10(%rax), %r10
	movq	JUNK_R11(%rax), %r11
d135 2
a136 1
	call	*(%rax)
d138 2
a139 1
	movq	G(calling_conventions_values)@@GOTPCREL(%rip), %rcx
d141 6
a146 6
	movq	%rbx, RBX(%rcx)
	movq	%rbp, RBP(%rcx)
	movq	%r12, R12(%rcx)
	movq	%r13, R13(%rcx)
	movq	%r14, R14(%rcx)
	movq	%r15, R15(%rcx)
d150 1
a150 1
	movq	%rbx, RFLAGS(%rcx)
d152 3
a154 14
	movq	SAVE_RBX(%rcx), %rbx
	movq	SAVE_RBP(%rcx), %rbp
	movq	SAVE_R12(%rcx), %r12
	movq	SAVE_R13(%rcx), %r13
	movq	SAVE_R14(%rcx), %r14
	movq	SAVE_R15(%rcx), %r15

	C Overwrite parameter registers
C	mov	JUNK_R9(%rcx), %r9
C	mov	JUNK_R8(%rcx), %r8
C	mov	JUNK_RCX(%rcx), %rcx
C	mov	JUNK_RDX(%rcx), %rdx
C	mov	JUNK_RSI(%rcx), %rsi
C	mov	JUNK_RDI(%rcx), %rdi
d156 6
a161 1
	pushq	RETADDR(%rcx)
d163 1
a163 5
	movq	G(calling_conventions_fenv)@@GOTPCREL(%rip), %rcx
	fstenv	(%rcx)
	finit

	ret
@


1.1.1.2
log
@initial import GMP 5.1.3 sources.  changes include:

fixes for:
- mpn_sbpi1_div_qr_sec and mpn_sbpi1_div_r_sec
- mpz_powm_ui
- AMD family 11h
- mpz_powm_sec and mpn_powm_sec
- ASSERT() fixes
- gcd, gcdext, and invert function fixes
- some PPC division operations
@
text
@d3 6
a8 6
dnl  Copyright 2000, 2003, 2004, 2006, 2007, 2010 Free Software Foundation, Inc.

dnl  This file is part of the GNU MP Library test suite.

dnl  The GNU MP Library test suite is free software; you can redistribute it
dnl  and/or modify it under the terms of the GNU General Public License as
d11 8
a18 9

dnl  The GNU MP Library test suite is distributed in the hope that it will be
dnl  useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
dnl  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General
dnl  Public License for more details.

dnl  You should have received a copy of the GNU General Public License along
dnl  with the GNU MP Library test suite.  If not, see
dnl  http://www.gnu.org/licenses/.
a20 3
dnl  The current version of the code attempts to keep the call/return
dnl  prediction stack valid, but matching calls and returns.

d40 3
a42 3
	movq	$0, -8(%rsp)
	fstcw	-8(%rsp)
	movq	-8(%rsp), %rax
d47 4
a50 4
dnl  Instrumented profiling won't come out quite right below, since we don't do
dnl  an actual "ret".  There's only a few instructions here, so there's no
dnl  great need to get them separately accounted, just let them get attributed
dnl  to the caller.  FIXME this comment might no longer be true.
d100 5
a104 2
	movq	G(calling_conventions_values)@@GOTPCREL(%rip), %rax
	popq	RETADDR(%rax)
d106 27
a132 20
	movq	%rbx, SAVE_RBX(%rax)
	movq	%rbp, SAVE_RBP(%rax)
	movq	%r12, SAVE_R12(%rax)
	movq	%r13, SAVE_R13(%rax)
	movq	%r14, SAVE_R14(%rax)
	movq	%r15, SAVE_R15(%rax)

	C Values we expect to see unchanged, as per amd64check.c
	movq	WANT_RBX(%rax), %rbx
	movq	WANT_RBP(%rax), %rbp
	movq	WANT_R12(%rax), %r12
	movq	WANT_R13(%rax), %r13
	movq	WANT_R14(%rax), %r14
	movq	WANT_R15(%rax), %r15

	C Try to provoke a problem by starting with junk in the caller-saves
	C registers, especially %rax which will be the return value.
C	movq	JUNK_RAX(%rax), %rax		C overwritten below anyway
	movq	JUNK_R10(%rax), %r10
	movq	JUNK_R11(%rax), %r11
d135 2
a136 1
	call	*(%rax)
d138 2
a139 1
	movq	G(calling_conventions_values)@@GOTPCREL(%rip), %rcx
d141 6
a146 6
	movq	%rbx, RBX(%rcx)
	movq	%rbp, RBP(%rcx)
	movq	%r12, R12(%rcx)
	movq	%r13, R13(%rcx)
	movq	%r14, R14(%rcx)
	movq	%r15, R15(%rcx)
d150 1
a150 1
	movq	%rbx, RFLAGS(%rcx)
d152 3
a154 14
	movq	SAVE_RBX(%rcx), %rbx
	movq	SAVE_RBP(%rcx), %rbp
	movq	SAVE_R12(%rcx), %r12
	movq	SAVE_R13(%rcx), %r13
	movq	SAVE_R14(%rcx), %r14
	movq	SAVE_R15(%rcx), %r15

	C Overwrite parameter registers
C	mov	JUNK_R9(%rcx), %r9
C	mov	JUNK_R8(%rcx), %r8
C	mov	JUNK_RCX(%rcx), %rcx
C	mov	JUNK_RDX(%rcx), %rdx
C	mov	JUNK_RSI(%rcx), %rsi
C	mov	JUNK_RDI(%rcx), %rdi
d156 6
a161 1
	pushq	RETADDR(%rcx)
d163 1
a163 5
	movq	G(calling_conventions_fenv)@@GOTPCREL(%rip), %rcx
	fstenv	(%rcx)
	finit

	ret
@


1.1.1.3
log
@initial import of GMP 6.1.2.  main changes from 5.1.3 below.

notes:
 - support for thumb-less ARM chips was in our port of 5.1.3, but a
   similar method has been provided upstream now
 - someone should look at the AVX failure reports, and fix them

Changes between GMP version 6.1.0 and 6.1.1

  FEATURES
  * Work around faulty cpuid on some recent Intel chips (this allows GMP to run
    on Skylake Pentiums).
  * Support thumb-less ARM chips.

Changes between GMP version 6.0.* and 6.1.0

  BUGS FIXED
  * The public function mpn_com is now correctly declared in gmp.h.
  * Healed possible failures of mpn_sec_sqr for non-cryptographic sizes for
    some obsolete CPUs.
  * Various problems related to precision for mpf have been fixed.
  * Fixed ABI incompatible stack alignment in calls from assembly code.
  * Fixed PIC bug in popcount affecting Intel processors using the 32-bit ABI.
  SPEEDUPS
  * Speedup for Intel Broadwell and Skylake through assembly code making use of
    new ADX instructions.
  * Square root is now faster when the remainder is not needed. Also the speed
    to compute the k-th root improved, for small sizes.
  FEATURES
  * New C++ functions gcd and lcm for mpz_class.
  * New public mpn functions mpn_divexact_1, mpn_zero_p, and mpn_cnd_swap.
  * New public mpq_cmp_z function, to efficiently compare rationals with
    integers.
  * Support for more 32-bit arm processors.
  * Support for AVX-less modern x86 CPUs. (Such support might be missing either
    because the CPU vendor chose to disable AVX, or because the running kernel
    lacks AVX context switch support.)
  * Support for NetBSD under Xen; we switch off AVX unconditionally under
    NetBSD since a bug in NetBSD makes AVX fail under Xen.
  MISC
  * Tuned values for FFT multiplications are provided for larger number on
    many platforms.

Changes between GMP version 5.1.* and 6.0.0
  BUGS FIXED
  * The function mpz_invert now considers any number invertible in Z/1Z.
  * The mpn multiply code now handles operands of more than 2^31 limbs
    correctly.  (Note however that the mpz code is limited to 2^32 bits on
    32-bit hosts and 2^37 bits on 64-bit hosts.)
  SPEEDUPS
  * Plain division of large operands is faster and more monotonous in operand
    size.
  * Major speedup for ARM, in particular ARM Cortex-A15, thanks to improved
    assembly.
  * Speedup for Intel Sandy Bridge, Ivy Bridge, Haswell, thanks to rewritten
    and vastly expanded assembly support.  Speedup also for the older Core 2
    and Nehalem.
  * Faster mixed arithmetic between mpq_class and double.
  FEATURES
  * Support for new Intel and AMD CPUs.
  * New public functions mpn_sec_mul and mpn_sec_sqr, implementing side-channel
    silent multiplication and squaring.
  * New public functions mpn_sec_div_qr and mpn_sec_div_r, implementing
    side-channel silent division.
  * New public functions mpn_cnd_add_n and mpn_cnd_sub_n.  Side-channel silent
    conditional addition and subtraction.
  * New public function mpn_sec_powm, implementing side-channel silent modexp.
  * New public function mpn_sec_invert, implementing side-channel silent
    modular inversion.
  * Better support for applications which use the mpz_t type, but nevertheless
    need to call some of the lower-level mpn functions.  See the documentation
    for mpz_limbs_read and related functions.
@
text
@d19 1
a19 1
dnl  https://www.gnu.org/licenses/.
d33 1
a33 1
	mov	%rdi, -8(%rsp)
d46 1
a46 1
	mov	-8(%rsp), %rax
d104 2
a105 2
	mov	G(calling_conventions_values)@@GOTPCREL(%rip), %rax
	pop	RETADDR(%rax)
d107 6
a112 6
	mov	%rbx, SAVE_RBX(%rax)
	mov	%rbp, SAVE_RBP(%rax)
	mov	%r12, SAVE_R12(%rax)
	mov	%r13, SAVE_R13(%rax)
	mov	%r14, SAVE_R14(%rax)
	mov	%r15, SAVE_R15(%rax)
d115 6
a120 6
	mov	WANT_RBX(%rax), %rbx
	mov	WANT_RBP(%rax), %rbp
	mov	WANT_R12(%rax), %r12
	mov	WANT_R13(%rax), %r13
	mov	WANT_R14(%rax), %r14
	mov	WANT_R15(%rax), %r15
d124 3
a126 3
C	mov	JUNK_RAX(%rax), %rax		C overwritten below anyway
	mov	JUNK_R10(%rax), %r10
	mov	JUNK_R11(%rax), %r11
d128 1
a128 1
	mov	G(calling_conventions_function)@@GOTPCREL(%rip), %rax
d131 1
a131 1
	mov	G(calling_conventions_values)@@GOTPCREL(%rip), %rcx
d133 17
a149 17
	mov	%rbx, RBX(%rcx)
	mov	%rbp, RBP(%rcx)
	mov	%r12, R12(%rcx)
	mov	%r13, R13(%rcx)
	mov	%r14, R14(%rcx)
	mov	%r15, R15(%rcx)

	pushf
	pop	%rbx
	mov	%rbx, RFLAGS(%rcx)

	mov	SAVE_RBX(%rcx), %rbx
	mov	SAVE_RBP(%rcx), %rbp
	mov	SAVE_R12(%rcx), %r12
	mov	SAVE_R13(%rcx), %r13
	mov	SAVE_R14(%rcx), %r14
	mov	SAVE_R15(%rcx), %r15
d159 1
a159 1
	push	RETADDR(%rcx)
d161 1
a161 1
	mov	G(calling_conventions_fenv)@@GOTPCREL(%rip), %rcx
@