head	1.1;
branch	1.1.1;
access;
symbols
	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_popcount, mpn_hamdist -- population count and hamming distance.

dnl  Copyright 2004, 2005, 2007 Free Software Foundation, 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		     popcount	      hamdist
C		    cycles/limb	    cycles/limb
C K8,K9:		 6		 7
C K10:			 6		 7
C P4:			12		14.3
C P6-15:		 7		 8

C TODO
C  * Tune.  It should be possible to reach 5 c/l for popcount and 6 c/l for
C    hamdist for K8/K9.


ifdef(`OPERATION_popcount',`
  define(`func',`mpn_popcount')
  define(`up',		`%rdi')
  define(`n',		`%rsi')
  define(`h55555555',	`%r10')
  define(`h33333333',	`%r11')
  define(`h0f0f0f0f',	`%rcx')
  define(`h01010101',	`%rdx')
  define(`HAM',		`dnl')
')
ifdef(`OPERATION_hamdist',`
  define(`func',`mpn_hamdist')
  define(`up',		`%rdi')
  define(`vp',		`%rsi')
  define(`n',		`%rdx')
  define(`h55555555',	`%r10')
  define(`h33333333',	`%r11')
  define(`h0f0f0f0f',	`%rcx')
  define(`h01010101',	`%r14')
  define(`HAM',		`$1')
')


MULFUNC_PROLOGUE(mpn_popcount mpn_hamdist)

ASM_START()
	TEXT
	ALIGN(32)
PROLOGUE(func)

	pushq	%r12
	pushq	%r13
 HAM(`	pushq	%r14		')

	movq	$0x5555555555555555, h55555555
	movq	$0x3333333333333333, h33333333
	movq	$0x0f0f0f0f0f0f0f0f, h0f0f0f0f
	movq	$0x0101010101010101, h01010101

	leaq	(up,n,8), up
 HAM(`	leaq	(vp,n,8), vp	')
	negq	n

	xorl	%eax, %eax

	btq	$0, n
	jnc	L(oop)

	movq	(up,n,8), %r8
 HAM(`	xorq	(vp,n,8), %r8	')

	movq	%r8, %r9
	shrq	%r8
	andq	h55555555, %r8
	subq	%r8, %r9

	movq	%r9, %r8
	shrq	$2, %r9
	andq	h33333333, %r8
	andq	h33333333, %r9
	addq	%r8, %r9		C 16 4-bit fields (0..4)

	movq	%r9, %r8
	shrq	$4, %r9
	andq	h0f0f0f0f, %r8
	andq	h0f0f0f0f, %r9
	addq	%r8, %r9		C 8 8-bit fields (0..16)

	imulq	h01010101, %r9		C sum the 8 fields in high 8 bits
	shrq	$56, %r9

	addq	%r9, %rax		C add to total
	addq	$1, n
	jz	L(done)

	ALIGN(16)
L(oop):	movq	(up,n,8), %r8
	movq	8(up,n,8), %r12
 HAM(`	xorq	(vp,n,8), %r8	')
 HAM(`	xorq	8(vp,n,8), %r12	')

	movq	%r8, %r9
	movq	%r12, %r13
	shrq	%r8
	shrq	%r12
	andq	h55555555, %r8
	andq	h55555555, %r12
	subq	%r8, %r9
	subq	%r12, %r13

	movq	%r9, %r8
	movq	%r13, %r12
	shrq	$2, %r9
	shrq	$2, %r13
	andq	h33333333, %r8
	andq	h33333333, %r9
	andq	h33333333, %r12
	andq	h33333333, %r13
	addq	%r8, %r9		C 16 4-bit fields (0..4)
	addq	%r12, %r13		C 16 4-bit fields (0..4)

	addq	%r13, %r9		C 16 4-bit fields (0..8)
	movq	%r9, %r8
	shrq	$4, %r9
	andq	h0f0f0f0f, %r8
	andq	h0f0f0f0f, %r9
	addq	%r8, %r9		C 8 8-bit fields (0..16)

	imulq	h01010101, %r9		C sum the 8 fields in high 8 bits
	shrq	$56, %r9

	addq	%r9, %rax		C add to total
	addq	$2, n
	jnc	L(oop)

L(done):
 HAM(`	popq	%r14		')
	popq	%r13
	popq	%r12
	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
@d3 1
a3 1
dnl  Copyright 2004, 2005, 2007, 2010, 2011, 2012 Free Software Foundation, Inc.
d26 4
a29 7
C AMD K8,K9		 6		 7
C AMD K10		 6		 7
C Intel P4		12		14.3
C Intel core2		 7		 8
C Intel corei		 ?		 7.3
C Intel atom		16.5		17.5
C VIA nano		 8.75		10.4
a43 1
  define(`POP',		`$1')
a54 1
  define(`POP',		`dnl')
a60 3
ABI_SUPPORT(DOS64)
ABI_SUPPORT(STD64)

d65 45
a109 46
 POP(`	FUNC_ENTRY(2)		')
 HAM(`	FUNC_ENTRY(3)		')
	push	%r12
	push	%r13
 HAM(`	push	%r14		')

	mov	$0x5555555555555555, h55555555
	mov	$0x3333333333333333, h33333333
	mov	$0x0f0f0f0f0f0f0f0f, h0f0f0f0f
	mov	$0x0101010101010101, h01010101

	lea	(up,n,8), up
 HAM(`	lea	(vp,n,8), vp	')
	neg	n

	xor	R32(%rax), R32(%rax)

	bt	$0, R32(n)
	jnc	L(top)

	mov	(up,n,8), %r8
 HAM(`	xor	(vp,n,8), %r8	')

	mov	%r8, %r9
	shr	%r8
	and	h55555555, %r8
	sub	%r8, %r9

	mov	%r9, %r8
	shr	$2, %r9
	and	h33333333, %r8
	and	h33333333, %r9
	add	%r8, %r9		C 16 4-bit fields (0..4)

	mov	%r9, %r8
	shr	$4, %r9
	and	h0f0f0f0f, %r8
	and	h0f0f0f0f, %r9
	add	%r8, %r9		C 8 8-bit fields (0..16)

	imul	h01010101, %r9		C sum the 8 fields in high 8 bits
	shr	$56, %r9

	mov	%r9, %rax		C add to total
	add	$1, n
	jz	L(end)
d112 43
a154 44
L(top):	mov	(up,n,8), %r8
	mov	8(up,n,8), %r12
 HAM(`	xor	(vp,n,8), %r8	')
 HAM(`	xor	8(vp,n,8), %r12	')

	mov	%r8, %r9
	mov	%r12, %r13
	shr	%r8
	shr	%r12
	and	h55555555, %r8
	and	h55555555, %r12
	sub	%r8, %r9
	sub	%r12, %r13

	mov	%r9, %r8
	mov	%r13, %r12
	shr	$2, %r9
	shr	$2, %r13
	and	h33333333, %r8
	and	h33333333, %r9
	and	h33333333, %r12
	and	h33333333, %r13
	add	%r8, %r9		C 16 4-bit fields (0..4)
	add	%r12, %r13		C 16 4-bit fields (0..4)

	add	%r13, %r9		C 16 4-bit fields (0..8)
	mov	%r9, %r8
	shr	$4, %r9
	and	h0f0f0f0f, %r8
	and	h0f0f0f0f, %r9
	add	%r8, %r9		C 8 8-bit fields (0..16)

	imul	h01010101, %r9		C sum the 8 fields in high 8 bits
	shr	$56, %r9

	add	%r9, %rax		C add to total
	add	$2, n
	jnc	L(top)

L(end):
 HAM(`	pop	%r14		')
	pop	%r13
	pop	%r12
	FUNC_EXIT()
d156 1
@


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 1
a3 1
dnl  Copyright 2004, 2005, 2007, 2010, 2011, 2012 Free Software Foundation, Inc.
d26 4
a29 7
C AMD K8,K9		 6		 7
C AMD K10		 6		 7
C Intel P4		12		14.3
C Intel core2		 7		 8
C Intel corei		 ?		 7.3
C Intel atom		16.5		17.5
C VIA nano		 8.75		10.4
a43 1
  define(`POP',		`$1')
a54 1
  define(`POP',		`dnl')
a60 3
ABI_SUPPORT(DOS64)
ABI_SUPPORT(STD64)

d65 45
a109 46
 POP(`	FUNC_ENTRY(2)		')
 HAM(`	FUNC_ENTRY(3)		')
	push	%r12
	push	%r13
 HAM(`	push	%r14		')

	mov	$0x5555555555555555, h55555555
	mov	$0x3333333333333333, h33333333
	mov	$0x0f0f0f0f0f0f0f0f, h0f0f0f0f
	mov	$0x0101010101010101, h01010101

	lea	(up,n,8), up
 HAM(`	lea	(vp,n,8), vp	')
	neg	n

	xor	R32(%rax), R32(%rax)

	bt	$0, R32(n)
	jnc	L(top)

	mov	(up,n,8), %r8
 HAM(`	xor	(vp,n,8), %r8	')

	mov	%r8, %r9
	shr	%r8
	and	h55555555, %r8
	sub	%r8, %r9

	mov	%r9, %r8
	shr	$2, %r9
	and	h33333333, %r8
	and	h33333333, %r9
	add	%r8, %r9		C 16 4-bit fields (0..4)

	mov	%r9, %r8
	shr	$4, %r9
	and	h0f0f0f0f, %r8
	and	h0f0f0f0f, %r9
	add	%r8, %r9		C 8 8-bit fields (0..16)

	imul	h01010101, %r9		C sum the 8 fields in high 8 bits
	shr	$56, %r9

	mov	%r9, %rax		C add to total
	add	$1, n
	jz	L(end)
d112 43
a154 44
L(top):	mov	(up,n,8), %r8
	mov	8(up,n,8), %r12
 HAM(`	xor	(vp,n,8), %r8	')
 HAM(`	xor	8(vp,n,8), %r12	')

	mov	%r8, %r9
	mov	%r12, %r13
	shr	%r8
	shr	%r12
	and	h55555555, %r8
	and	h55555555, %r12
	sub	%r8, %r9
	sub	%r12, %r13

	mov	%r9, %r8
	mov	%r13, %r12
	shr	$2, %r9
	shr	$2, %r13
	and	h33333333, %r8
	and	h33333333, %r9
	and	h33333333, %r12
	and	h33333333, %r13
	add	%r8, %r9		C 16 4-bit fields (0..4)
	add	%r12, %r13		C 16 4-bit fields (0..4)

	add	%r13, %r9		C 16 4-bit fields (0..8)
	mov	%r9, %r8
	shr	$4, %r9
	and	h0f0f0f0f, %r8
	and	h0f0f0f0f, %r9
	add	%r8, %r9		C 8 8-bit fields (0..16)

	imul	h01010101, %r9		C sum the 8 fields in high 8 bits
	shr	$56, %r9

	add	%r9, %rax		C add to total
	add	$2, n
	jnc	L(top)

L(end):
 HAM(`	pop	%r14		')
	pop	%r13
	pop	%r12
	FUNC_EXIT()
d156 1
@


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 1
a3 1
dnl  Copyright 2004, 2005, 2007, 2010, 2011, 2012 Free Software Foundation, Inc.
d26 4
a29 7
C AMD K8,K9		 6		 7
C AMD K10		 6		 7
C Intel P4		12		14.3
C Intel core2		 7		 8
C Intel corei		 ?		 7.3
C Intel atom		16.5		17.5
C VIA nano		 8.75		10.4
a43 1
  define(`POP',		`$1')
a54 1
  define(`POP',		`dnl')
a60 3
ABI_SUPPORT(DOS64)
ABI_SUPPORT(STD64)

d65 45
a109 46
 POP(`	FUNC_ENTRY(2)		')
 HAM(`	FUNC_ENTRY(3)		')
	push	%r12
	push	%r13
 HAM(`	push	%r14		')

	mov	$0x5555555555555555, h55555555
	mov	$0x3333333333333333, h33333333
	mov	$0x0f0f0f0f0f0f0f0f, h0f0f0f0f
	mov	$0x0101010101010101, h01010101

	lea	(up,n,8), up
 HAM(`	lea	(vp,n,8), vp	')
	neg	n

	xor	R32(%rax), R32(%rax)

	bt	$0, R32(n)
	jnc	L(top)

	mov	(up,n,8), %r8
 HAM(`	xor	(vp,n,8), %r8	')

	mov	%r8, %r9
	shr	%r8
	and	h55555555, %r8
	sub	%r8, %r9

	mov	%r9, %r8
	shr	$2, %r9
	and	h33333333, %r8
	and	h33333333, %r9
	add	%r8, %r9		C 16 4-bit fields (0..4)

	mov	%r9, %r8
	shr	$4, %r9
	and	h0f0f0f0f, %r8
	and	h0f0f0f0f, %r9
	add	%r8, %r9		C 8 8-bit fields (0..16)

	imul	h01010101, %r9		C sum the 8 fields in high 8 bits
	shr	$56, %r9

	mov	%r9, %rax		C add to total
	add	$1, n
	jz	L(end)
d112 43
a154 44
L(top):	mov	(up,n,8), %r8
	mov	8(up,n,8), %r12
 HAM(`	xor	(vp,n,8), %r8	')
 HAM(`	xor	8(vp,n,8), %r12	')

	mov	%r8, %r9
	mov	%r12, %r13
	shr	%r8
	shr	%r12
	and	h55555555, %r8
	and	h55555555, %r12
	sub	%r8, %r9
	sub	%r12, %r13

	mov	%r9, %r8
	mov	%r13, %r12
	shr	$2, %r9
	shr	$2, %r13
	and	h33333333, %r8
	and	h33333333, %r9
	and	h33333333, %r12
	and	h33333333, %r13
	add	%r8, %r9		C 16 4-bit fields (0..4)
	add	%r12, %r13		C 16 4-bit fields (0..4)

	add	%r13, %r9		C 16 4-bit fields (0..8)
	mov	%r9, %r8
	shr	$4, %r9
	and	h0f0f0f0f, %r8
	and	h0f0f0f0f, %r9
	add	%r8, %r9		C 8 8-bit fields (0..16)

	imul	h01010101, %r9		C sum the 8 fields in high 8 bits
	shr	$56, %r9

	add	%r9, %rax		C add to total
	add	$2, n
	jnc	L(top)

L(end):
 HAM(`	pop	%r14		')
	pop	%r13
	pop	%r12
	FUNC_EXIT()
d156 1
@


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
@d3 1
a3 1
dnl  Copyright 2004, 2005, 2007, 2010-2012 Free Software Foundation, Inc.
d6 1
a6 1
dnl
d8 4
a11 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
d14 5
a18 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
@d3 1
a3 1
dnl  Copyright 2004, 2005, 2007, 2010-2012, 2017 Free Software Foundation, Inc.
d69 1
a69 1
  define(`h01010101',	`%r12')
d86 4
a89 1
	push	%rbx
a90 1
	push	%rbp
d92 3
a94 1
 HAM(`	push	%r12		')
a95 1
	mov	$0x0f0f0f0f0f0f0f0f, h0f0f0f0f
d98 1
a98 1
	mov	$0x0101010101010101, h01010101
d100 3
a102 2
	test	$1, R8(n)
	jz	L(top)
d118 12
a129 2
	dec	n
	jmp	L(mid)
d133 1
a133 1
	mov	8(up,n,8), %rbx
d135 1
a135 1
 HAM(`	xor	8(vp,n,8), %rbx	')
d138 1
a138 1
	mov	%rbx, %rbp
d140 1
a140 1
	shr	%rbx
d142 1
a142 1
	and	h55555555, %rbx
d144 1
a144 1
	sub	%rbx, %rbp
d147 1
a147 1
	mov	%rbp, %rbx
d149 1
a149 1
	shr	$2, %rbp
d152 2
a153 2
	and	h33333333, %rbx
	and	h33333333, %rbp
d155 1
a155 1
	add	%rbx, %rbp		C 16 4-bit fields (0..4)
d157 2
a158 2
	add	%rbp, %r9		C 16 4-bit fields (0..8)
L(mid):	mov	%r9, %r8
d172 3
a174 3
 HAM(`	pop	%r12		')
	pop	%rbp
	pop	%rbx
@