head	1.1;
branch	1.1.1;
access;
symbols
	netbsd-9-5-RELEASE:1.1.1.3
	netbsd-11-0-RELEASE:1.1.1.4
	netbsd-11-0-RC7:1.1.1.4
	netbsd-11-0-RC6:1.1.1.4
	netbsd-11-0-RC5:1.1.1.4
	netbsd-11-0-RC4:1.1.1.4
	netbsd-11-0-RC3:1.1.1.4
	netbsd-11-0-RC2:1.1.1.4
	netbsd-11-0-RC1:1.1.1.4
	perseant-exfatfs-base-20250801:1.1.1.4
	netbsd-11:1.1.1.4.0.10
	netbsd-11-base:1.1.1.4
	netbsd-10-1-RELEASE:1.1.1.4
	perseant-exfatfs-base-20240630:1.1.1.4
	perseant-exfatfs:1.1.1.4.0.8
	perseant-exfatfs-base:1.1.1.4
	netbsd-8-3-RELEASE:1.1.1.2
	netbsd-9-4-RELEASE:1.1.1.3
	netbsd-10-0-RELEASE:1.1.1.4
	netbsd-10-0-RC6:1.1.1.4
	netbsd-10-0-RC5:1.1.1.4
	netbsd-10-0-RC4:1.1.1.4
	netbsd-10-0-RC3:1.1.1.4
	netbsd-10-0-RC2:1.1.1.4
	netbsd-10-0-RC1:1.1.1.4
	netbsd-10:1.1.1.4.0.6
	netbsd-10-base:1.1.1.4
	netbsd-9-3-RELEASE:1.1.1.3
	gmp-6-2-1:1.1.1.4
	cjep_sun2x-base1:1.1.1.4
	cjep_sun2x:1.1.1.4.0.4
	cjep_sun2x-base:1.1.1.4
	cjep_staticlib_x-base1:1.1.1.4
	netbsd-9-2-RELEASE:1.1.1.3
	cjep_staticlib_x:1.1.1.4.0.2
	cjep_staticlib_x-base:1.1.1.4
	netbsd-9-1-RELEASE:1.1.1.3
	gmp-6-2-0:1.1.1.4
	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	2011.06.20.05.54.39;	author mrg;	state Exp;
branches
	1.1.1.1;
next	;

1.1.1.1
date	2011.06.20.05.54.39;	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	2017.08.22.09.40.49;	author mrg;	state Exp;
branches;
next	1.1.1.4;
commitid	W5kmAIk8hwVpSb4A;

1.1.1.4
date	2020.09.27.00.27.05;	author mrg;	state Exp;
branches;
next	;
commitid	BWuUFuEU17KgrCpC;

1.1.1.1.2.1
date	2014.05.22.14.09.06;	author yamt;	state Exp;
branches;
next	;
commitid	nx2BSsHy0NPeAxBx;

1.1.1.1.8.1
date	2014.08.19.23.59.55;	author tls;	state Exp;
branches;
next	;
commitid	jTnpym9Qu0o4R1Nx;


desc
@@


1.1
log
@Initial revision
@
text
@dnl  AMD64 mpn_bdiv_q_1, mpn_pi1_bdiv_q_1 -- schoolbook Hensel division by
dnl  1-limb divisor, returning quotient only.

dnl  Copyright 2001, 2002, 2004, 2005, 2006, 2009 Free Software Foundation,
dnl  Inc.

dnl  This file is part of the GNU MP Library.

dnl  The GNU MP Library is free software; you can redistribute it and/or modify
dnl  it under the terms of the GNU Lesser General Public License as published
dnl  by the Free Software Foundation; either version 3 of the License, or (at
dnl  your option) any later version.

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

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	     cycles/limb
C K8,K9:	10
C K10:		10
C P4:		33
C P6 core2:	13.25
C P6 corei7:	14
C P6 atom:	42


C INPUT PARAMETERS
C rp		rdi
C up		rsi
C n		rdx
C d		rcx
C di		r8	just mpn_pi1_bdiv_q_1
C shift		r9	just mpn_pi1_bdiv_q_1


ASM_START()
	TEXT
	ALIGN(16)
PROLOGUE(mpn_bdiv_q_1)
	push	%rbx

	mov	%rcx, %rax
	xor	R32(%rcx), R32(%rcx)	C shift count
	mov	%rdx, %r10

	bt	$0, R32(%rax)
	jnc	L(evn)			C skip bsfq unless divisor is even

L(odd):	mov	%rax, %rbx
	shr	R32(%rax)
	and	$127, R32(%rax)		C d/2, 7 bits

ifdef(`PIC',`
	mov	binvert_limb_table@@GOTPCREL(%rip), %rdx
',`
	movabs	$binvert_limb_table, %rdx
')

	movzbl	(%rdx,%rax), R32(%rax)	C inv 8 bits

	mov	%rbx, %r11		C d without twos

	lea	(%rax,%rax), R32(%rdx)	C 2*inv
	imul	R32(%rax), R32(%rax)	C inv*inv
	imul	R32(%rbx), R32(%rax)	C inv*inv*d
	sub	R32(%rax), R32(%rdx)	C inv = 2*inv - inv*inv*d, 16 bits

	lea	(%rdx,%rdx), R32(%rax)	C 2*inv
	imul	R32(%rdx), R32(%rdx)	C inv*inv
	imul	R32(%rbx), R32(%rdx)	C inv*inv*d
	sub	R32(%rdx), R32(%rax)	C inv = 2*inv - inv*inv*d, 32 bits

	lea	(%rax,%rax), %r8	C 2*inv
	imul	%rax, %rax		C inv*inv
	imul	%rbx, %rax		C inv*inv*d
	sub	%rax, %r8		C inv = 2*inv - inv*inv*d, 64 bits

	jmp	L(com)

L(evn):	bsf	%rax, %rcx
	shr	R8(%rcx), %rax
	jmp	L(odd)
EPILOGUE()

PROLOGUE(mpn_pi1_bdiv_q_1)
	push	%rbx

	mov	%rcx, %r11		C d
	mov	%rdx, %r10		C n
	mov	%r9, %rcx		C shift
L(com):
	mov	(%rsi), %rax		C up[0]

	dec	%r10
	jz	L(one)

	mov	8(%rsi), %rdx		C up[1]
	lea	(%rsi,%r10,8), %rsi	C up end
	lea	(%rdi,%r10,8), %rdi	C rp end
	neg	%r10			C -n

	shrd	R8(%rcx), %rdx, %rax

	xor	R32(%rbx), R32(%rbx)
	jmp	L(ent)

	ALIGN(8)
L(top):
	C rax	q
	C rbx	carry bit, 0 or 1
	C rcx	shift
	C rdx
	C rsi	up end
	C rdi	rp end
	C r10	counter, limbs, negative

	mul	%r11			C carry limb in rdx
	mov	(%rsi,%r10,8), %rax
	mov	8(%rsi,%r10,8), %r9
	shrd	R8(%rcx), %r9, %rax
	nop
	sub	%rbx, %rax		C apply carry bit
	setc	R8(%rbx)
	sub	%rdx, %rax		C apply carry limb
	adc	$0, %rbx
L(ent):	imul	%r8, %rax
	mov	%rax, (%rdi,%r10,8)
	inc	%r10
	jnz	L(top)

	mul	%r11			C carry limb in rdx
	mov	(%rsi), %rax		C up high limb
	shr	R8(%rcx), %rax
	sub	%rbx, %rax		C apply carry bit
	sub	%rdx, %rax		C apply carry limb
	imul	%r8, %rax
	mov	%rax, (%rdi)
	pop	%rbx
	ret

L(one):	shr	R8(%rcx), %rax
	imul	%r8, %rax
	mov	%rax, (%rdi)
	pop	%rbx
	ret
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
@d4 2
a5 2
dnl  Copyright 2001, 2002, 2004, 2005, 2006, 2009, 2011, 2012 Free Software
dnl  Foundation, Inc.
d14 1
a14 1
dnl  The GNU MP Library is distributed in the hope that it will be useful, but
d26 6
a31 7
C AMD K8,K9	10
C AMD K10	10
C Intel P4	33
C Intel core2	13.25
C Intel corei	14
C Intel atom	42
C VIA nano	 ?
d35 6
a40 6
define(`rp',		`%rdi')
define(`up',		`%rsi')
define(`n',		`%rdx')
define(`d',		`%rcx')
define(`di',		`%r8')		C	just mpn_pi1_bdiv_q_1
define(`ncnt',		`%r9')		C	just mpn_pi1_bdiv_q_1
a41 2
ABI_SUPPORT(DOS64)
ABI_SUPPORT(STD64)
a46 1
	FUNC_ENTRY(4)
d50 1
a50 1
	xor	R32(%rcx), R32(%rcx)	C ncnt count
d60 5
a64 1
	LEA(	binvert_limb_table, %rdx)
a92 3
	FUNC_ENTRY(4)
IFDOS(`	mov	56(%rsp), %r8	')
IFDOS(`	mov	64(%rsp), %r9	')
d97 3
a99 3
	mov	%r9, %rcx		C ncnt

L(com):	mov	(up), %rax		C up[0]
d104 3
a106 3
	mov	8(up), %rdx		C up[1]
	lea	(up,%r10,8), up		C up end
	lea	(rp,%r10,8), rp		C rp end
d118 1
a118 1
	C rcx	ncnt
d120 2
d125 2
a126 2
	mov	(up,%r10,8), %rax
	mov	8(up,%r10,8), %r9
d134 1
a134 1
	mov	%rax, (rp,%r10,8)
d139 1
a139 1
	mov	(up), %rax		C up high limb
d144 1
a144 1
	mov	%rax, (rp)
a145 1
	FUNC_EXIT()
d150 1
a150 1
	mov	%rax, (rp)
a151 1
	FUNC_EXIT()
@


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
@d4 2
a5 2
dnl  Copyright 2001, 2002, 2004, 2005, 2006, 2009, 2011, 2012 Free Software
dnl  Foundation, Inc.
d14 1
a14 1
dnl  The GNU MP Library is distributed in the hope that it will be useful, but
d26 6
a31 7
C AMD K8,K9	10
C AMD K10	10
C Intel P4	33
C Intel core2	13.25
C Intel corei	14
C Intel atom	42
C VIA nano	 ?
d35 6
a40 6
define(`rp',		`%rdi')
define(`up',		`%rsi')
define(`n',		`%rdx')
define(`d',		`%rcx')
define(`di',		`%r8')		C	just mpn_pi1_bdiv_q_1
define(`ncnt',		`%r9')		C	just mpn_pi1_bdiv_q_1
a41 2
ABI_SUPPORT(DOS64)
ABI_SUPPORT(STD64)
a46 1
	FUNC_ENTRY(4)
d50 1
a50 1
	xor	R32(%rcx), R32(%rcx)	C ncnt count
d60 5
a64 1
	LEA(	binvert_limb_table, %rdx)
a92 3
	FUNC_ENTRY(4)
IFDOS(`	mov	56(%rsp), %r8	')
IFDOS(`	mov	64(%rsp), %r9	')
d97 3
a99 3
	mov	%r9, %rcx		C ncnt

L(com):	mov	(up), %rax		C up[0]
d104 3
a106 3
	mov	8(up), %rdx		C up[1]
	lea	(up,%r10,8), up		C up end
	lea	(rp,%r10,8), rp		C rp end
d118 1
a118 1
	C rcx	ncnt
d120 2
d125 2
a126 2
	mov	(up,%r10,8), %rax
	mov	8(up,%r10,8), %r9
d134 1
a134 1
	mov	%rax, (rp,%r10,8)
d139 1
a139 1
	mov	(up), %rax		C up high limb
d144 1
a144 1
	mov	%rax, (rp)
a145 1
	FUNC_EXIT()
d150 1
a150 1
	mov	%rax, (rp)
a151 1
	FUNC_EXIT()
@


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
@d4 2
a5 2
dnl  Copyright 2001, 2002, 2004, 2005, 2006, 2009, 2011, 2012 Free Software
dnl  Foundation, Inc.
d14 1
a14 1
dnl  The GNU MP Library is distributed in the hope that it will be useful, but
d26 6
a31 7
C AMD K8,K9	10
C AMD K10	10
C Intel P4	33
C Intel core2	13.25
C Intel corei	14
C Intel atom	42
C VIA nano	 ?
d35 6
a40 6
define(`rp',		`%rdi')
define(`up',		`%rsi')
define(`n',		`%rdx')
define(`d',		`%rcx')
define(`di',		`%r8')		C	just mpn_pi1_bdiv_q_1
define(`ncnt',		`%r9')		C	just mpn_pi1_bdiv_q_1
a41 2
ABI_SUPPORT(DOS64)
ABI_SUPPORT(STD64)
a46 1
	FUNC_ENTRY(4)
d50 1
a50 1
	xor	R32(%rcx), R32(%rcx)	C ncnt count
d60 5
a64 1
	LEA(	binvert_limb_table, %rdx)
a92 3
	FUNC_ENTRY(4)
IFDOS(`	mov	56(%rsp), %r8	')
IFDOS(`	mov	64(%rsp), %r9	')
d97 3
a99 3
	mov	%r9, %rcx		C ncnt

L(com):	mov	(up), %rax		C up[0]
d104 3
a106 3
	mov	8(up), %rdx		C up[1]
	lea	(up,%r10,8), up		C up end
	lea	(rp,%r10,8), rp		C rp end
d118 1
a118 1
	C rcx	ncnt
d120 2
d125 2
a126 2
	mov	(up,%r10,8), %rax
	mov	8(up,%r10,8), %r9
d134 1
a134 1
	mov	%rax, (rp,%r10,8)
d139 1
a139 1
	mov	(up), %rax		C up high limb
d144 1
a144 1
	mov	%rax, (rp)
a145 1
	FUNC_EXIT()
d150 1
a150 1
	mov	%rax, (rp)
a151 1
	FUNC_EXIT()
@


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
@d4 1
a4 1
dnl  Copyright 2001, 2002, 2004-2006, 2009, 2011, 2012 Free Software
d8 1
a8 1
dnl
d10 4
a13 14
dnl  it under the terms of either:
dnl
dnl    * the GNU Lesser General Public License as published by the Free
dnl      Software Foundation; either version 3 of the License, or (at your
dnl      option) any later version.
dnl
dnl  or
dnl
dnl    * the GNU General Public License as published by the Free Software
dnl      Foundation; either version 2 of the License, or (at your option) any
dnl      later version.
dnl
dnl  or both in parallel, as here.
dnl
d16 5
a20 6
dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
dnl  for more details.
dnl
dnl  You should have received copies of the GNU General Public License and the
dnl  GNU Lesser General Public License along with the GNU MP Library.  If not,
dnl  see https://www.gnu.org/licenses/.
@


1.1.1.4
log
@initial import of GMP 6.2.0.  changes include:

- Bug fixes to gmp_snprintf, conversion to double, mpz_powm,
  and mpf_set_str.
- New functions for factorial, primorial, fibonacci, mpz_2fac_ui,
  and mpz_mfac_uiui.
- MIPS r6 cores are now supported.
- Various speeds ups.
@
text
@d1 2
a2 1
dnl  AMD64 mpn_bdiv_q_1, mpn_pi1_bdiv_q_1 -- Hensel division by 1-limb divisor.
d4 2
a5 2
dnl  Copyright 2001, 2002, 2004-2006, 2010-2012, 2017 Free Software Foundation,
dnl  Inc.
d35 10
a44 21
C	    cycles/limb    cycles/limb
C	       norm	       unorm
C AMD K8,K9	11		11
C AMD K10	11		11
C AMD bull	13.5		14
C AMD pile	14		15
C AMD steam
C AMD excavator
C AMD bobcat	14		14
C AMD jaguar	14.5		15
C Intel P4	33		33
C Intel core2	13.5		13.25
C Intel NHM	14		14
C Intel SBR	8		8.25
C Intel IBR	7.75		7.85
C Intel HWL	8		8
C Intel BWL	8		8
C Intel SKL	8		8
C Intel atom	34		36
C Intel SLM	13.7		13.5
C VIA nano	19.25		19.25	needs re-measuring
d69 1
a69 1
	jnc	L(evn)			C skip bsf unless divisor is even
d96 1
a96 1
	jmp	L(pi1)
d113 1
a113 1
L(pi1):	mov	(up), %rax		C up[0]
d118 2
a119 1
	lea	8(up,%r10,8), up	C up end
d123 2
a124 2
	test	R32(%rcx), R32(%rcx)
	jnz	L(unorm)		C branch if count != 0
d126 1
a126 1
	jmp	L(nent)
d129 12
a140 2
L(ntop):mul	%r11			C carry limb in rdx	0 10
	mov	-8(up,%r10,8), %rax	C
d142 7
a148 7
	setc	R8(%rbx)		C
	sub	%rdx, %rax		C apply carry limb	5
	adc	$0, R32(%rbx)		C			6
L(nent):imul	%r8, %rax		C			6
	mov	%rax, (rp,%r10,8)	C
	inc	%r10			C
	jnz	L(ntop)
d150 3
a152 19
	mov	-8(up), %r9		C up high limb
	jmp	L(com)

L(unorm):
	mov	(up,%r10,8), %r9	C up[1]
	shr	R8(%rcx), %rax		C
	neg	R32(%rcx)
	shl	R8(%rcx), %r9		C
	neg	R32(%rcx)
	or	%r9, %rax
	xor	R32(%rbx), R32(%rbx)
	jmp	L(uent)

	ALIGN(8)
L(utop):mul	%r11			C carry limb in rdx	0 10
	mov	(up,%r10,8), %rax	C
	shl	R8(%rcx), %rax		C
	neg	R32(%rcx)
	or	%r9, %rax
d154 3
a156 16
	setc	R8(%rbx)		C
	sub	%rdx, %rax		C apply carry limb	5
	adc	$0, R32(%rbx)		C			6
L(uent):imul	%r8, %rax		C			6
	mov	(up,%r10,8), %r9	C
	shr	R8(%rcx), %r9		C
	neg	R32(%rcx)
	mov	%rax, (rp,%r10,8)	C
	inc	%r10			C
	jnz	L(utop)

L(com):	mul	%r11			C carry limb in rdx
	sub	%rbx, %r9		C apply carry bit
	sub	%rdx, %r9		C apply carry limb
	imul	%r8, %r9
	mov	%r9, (rp)
@