head	1.1;
branch	1.1.1;
access;
symbols
	netbsd-11-0-RC5:1.1.1.2
	netbsd-11-0-RC4:1.1.1.2
	netbsd-11-0-RC3:1.1.1.2
	netbsd-11-0-RC2:1.1.1.2
	netbsd-11-0-RC1:1.1.1.2
	perseant-exfatfs-base-20250801:1.1.1.2
	netbsd-11:1.1.1.2.0.18
	netbsd-11-base:1.1.1.2
	netbsd-10-1-RELEASE:1.1.1.2
	perseant-exfatfs-base-20240630:1.1.1.2
	perseant-exfatfs:1.1.1.2.0.16
	perseant-exfatfs-base:1.1.1.2
	netbsd-8-3-RELEASE:1.1.1.1
	netbsd-9-4-RELEASE:1.1.1.2
	netbsd-10-0-RELEASE:1.1.1.2
	netbsd-10-0-RC6:1.1.1.2
	netbsd-10-0-RC5:1.1.1.2
	netbsd-10-0-RC4:1.1.1.2
	netbsd-10-0-RC3:1.1.1.2
	netbsd-10-0-RC2:1.1.1.2
	netbsd-10-0-RC1:1.1.1.2
	netbsd-10:1.1.1.2.0.14
	netbsd-10-base:1.1.1.2
	netbsd-9-3-RELEASE:1.1.1.2
	gmp-6-2-1:1.1.1.2
	cjep_sun2x-base1:1.1.1.2
	cjep_sun2x:1.1.1.2.0.12
	cjep_sun2x-base:1.1.1.2
	cjep_staticlib_x-base1:1.1.1.2
	netbsd-9-2-RELEASE:1.1.1.2
	cjep_staticlib_x:1.1.1.2.0.10
	cjep_staticlib_x-base:1.1.1.2
	netbsd-9-1-RELEASE:1.1.1.2
	gmp-6-2-0:1.1.1.2
	phil-wifi-20200421:1.1.1.2
	phil-wifi-20200411:1.1.1.2
	is-mlppp:1.1.1.2.0.8
	is-mlppp-base:1.1.1.2
	phil-wifi-20200406:1.1.1.2
	netbsd-8-2-RELEASE:1.1.1.1
	netbsd-9-0-RELEASE:1.1.1.2
	netbsd-9-0-RC2:1.1.1.2
	netbsd-9-0-RC1:1.1.1.2
	phil-wifi-20191119:1.1.1.2
	netbsd-9:1.1.1.2.0.6
	netbsd-9-base:1.1.1.2
	phil-wifi-20190609:1.1.1.2
	netbsd-8-1-RELEASE:1.1.1.1
	netbsd-8-1-RC1:1.1.1.1
	pgoyette-compat-merge-20190127:1.1.1.2
	pgoyette-compat-20190127:1.1.1.2
	pgoyette-compat-20190118:1.1.1.2
	pgoyette-compat-1226:1.1.1.2
	pgoyette-compat-1126:1.1.1.2
	pgoyette-compat-1020:1.1.1.2
	pgoyette-compat-0930:1.1.1.2
	pgoyette-compat-0906:1.1.1.2
	netbsd-7-2-RELEASE:1.1.1.1
	pgoyette-compat-0728:1.1.1.2
	netbsd-8-0-RELEASE:1.1.1.1
	phil-wifi:1.1.1.2.0.4
	phil-wifi-base:1.1.1.2
	pgoyette-compat-0625:1.1.1.2
	netbsd-8-0-RC2:1.1.1.1
	pgoyette-compat-0521:1.1.1.2
	pgoyette-compat-0502:1.1.1.2
	pgoyette-compat-0422:1.1.1.2
	netbsd-8-0-RC1:1.1.1.1
	pgoyette-compat-0415:1.1.1.2
	pgoyette-compat-0407:1.1.1.2
	pgoyette-compat-0330:1.1.1.2
	pgoyette-compat-0322:1.1.1.2
	pgoyette-compat-0315:1.1.1.2
	netbsd-7-1-2-RELEASE:1.1.1.1
	pgoyette-compat:1.1.1.2.0.2
	pgoyette-compat-base:1.1.1.2
	netbsd-7-1-1-RELEASE:1.1.1.1
	matt-nb8-mediatek:1.1.1.1.0.38
	matt-nb8-mediatek-base:1.1.1.1
	gmp-6-1-2:1.1.1.2
	perseant-stdc-iso10646:1.1.1.1.0.36
	perseant-stdc-iso10646-base:1.1.1.1
	netbsd-8:1.1.1.1.0.34
	netbsd-8-base:1.1.1.1
	prg-localcount2-base3:1.1.1.1
	prg-localcount2-base2:1.1.1.1
	prg-localcount2-base1:1.1.1.1
	prg-localcount2:1.1.1.1.0.32
	prg-localcount2-base:1.1.1.1
	pgoyette-localcount-20170426:1.1.1.1
	bouyer-socketcan-base1:1.1.1.1
	pgoyette-localcount-20170320:1.1.1.1
	netbsd-7-1:1.1.1.1.0.30
	netbsd-7-1-RELEASE:1.1.1.1
	netbsd-7-1-RC2:1.1.1.1
	netbsd-7-nhusb-base-20170116:1.1.1.1
	bouyer-socketcan:1.1.1.1.0.28
	bouyer-socketcan-base:1.1.1.1
	pgoyette-localcount-20170107:1.1.1.1
	netbsd-7-1-RC1:1.1.1.1
	pgoyette-localcount-20161104:1.1.1.1
	netbsd-7-0-2-RELEASE:1.1.1.1
	localcount-20160914:1.1.1.1
	netbsd-7-nhusb:1.1.1.1.0.26
	netbsd-7-nhusb-base:1.1.1.1
	pgoyette-localcount-20160806:1.1.1.1
	pgoyette-localcount-20160726:1.1.1.1
	pgoyette-localcount:1.1.1.1.0.24
	pgoyette-localcount-base:1.1.1.1
	netbsd-7-0-1-RELEASE:1.1.1.1
	netbsd-7-0:1.1.1.1.0.22
	netbsd-7-0-RELEASE:1.1.1.1
	netbsd-7-0-RC3:1.1.1.1
	netbsd-7-0-RC2:1.1.1.1
	netbsd-7-0-RC1:1.1.1.1
	netbsd-6-0-6-RELEASE:1.1.1.1
	netbsd-6-1-5-RELEASE:1.1.1.1
	netbsd-7:1.1.1.1.0.20
	netbsd-7-base:1.1.1.1
	yamt-pagecache-base9:1.1.1.1
	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:1.1.1.1.0.18
	tls-earlyentropy-base:1.1.1.1
	riastradh-xf86-video-intel-2-7-1-pre-2-21-15:1.1.1.1
	riastradh-drm2-base3:1.1.1.1
	netbsd-6-1-3-RELEASE:1.1.1.1
	netbsd-6-0-4-RELEASE:1.1.1.1
	gmp-5-1-3:1.1.1.1
	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:1.1.1.1
	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	2011.06.20.05.54.43;	author mrg;	state Exp;
branches
	1.1.1.1;
next	;

1.1.1.1
date	2011.06.20.05.54.43;	author mrg;	state Exp;
branches;
next	1.1.1.2;

1.1.1.2
date	2017.08.22.09.40.49;	author mrg;	state Exp;
branches;
next	;
commitid	W5kmAIk8hwVpSb4A;


desc
@@


1.1
log
@Initial revision
@
text
@dnl  mpn_sqr_basecase for Pentium 4 and P6 models with SSE2 (i.e., 9,D,E,F).

dnl  Copyright 2001, 2002, 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 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
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
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 TODO:
C  * Improve ad-hoc outer loop code and register handling.  Some feed-in
C    scheduling could improve things by several cycles per outer iteration.
C  * In Lam3...Lam1 code for, keep accumulation operands in registers, without
C    storing intermediates to rp.
C  * We might want to keep 32 in a free mm register, since the register form is
C    3 bytes and the immediate form is 4 bytes.  About 80 bytes to save.
C  * Look into different loop alignment, we now expand the code about 50 bytes
C    with possibly needless alignment.
C  * Use OSP, should solve feed-in latency problems.
C  * Address relative slowness for un<=3 for Pentium M.  The old code is there
C    considerably faster.  (1:20/14, 2:34:32, 3:66/57)

C INPUT PARAMETERS
C rp		sp + 4
C up		sp + 8
C un		sp + 12

	TEXT
	ALIGN(16)
PROLOGUE(mpn_sqr_basecase)
	mov	4(%esp), %edx		C rp
	mov	8(%esp), %eax		C up
	mov	12(%esp), %ecx		C un

	cmp	$2, %ecx
	jc	L(un1)
	jz	L(un2)
	cmp	$4, %ecx
	jc	L(un3)
	jz	L(un4)
	jmp	L(big)

L(un1):	mov	(%eax), %eax
	mov	%edx, %ecx
	mul	%eax
	mov	%eax, (%ecx)
	mov	%edx, 4(%ecx)
	ret
L(un2):	movd	(%eax), %mm0		C				un=2
	movd	(%eax), %mm2		C				un=2
	movd	4(%eax), %mm1		C				un=2
	pmuludq	%mm0, %mm0		C 64b weight 0			un=2
	pmuludq	%mm1, %mm2		C 64b weight 32			un=2
	pmuludq	%mm1, %mm1		C 64b weight 64			un=2
	movd	%mm0, (%edx)		C				un=2
	psrlq	$32, %mm0		C 32b weight 32			un=2
	pcmpeqd	%mm7, %mm7		C				un=2
	psrlq	$33, %mm7		C 0x000000007FFFFFFF		un=2
	pand	%mm2, %mm7		C 31b weight 32			un=2
	psrlq	$31, %mm2		C 33b weight 65			un=2
	psllq	$1, %mm7		C 31b weight 33			un=2
	paddq	%mm7, %mm0		C				un=2
	movd	%mm0, 4(%edx)		C				un=2
	psrlq	$32, %mm0		C				un=2
	paddq	%mm2, %mm1		C				un=2
	paddq	%mm0, %mm1		C				un=2
	movd	%mm1, 8(%edx)		C				un=2
	psrlq	$32, %mm1		C				un=2
	movd	%mm1, 12(%edx)		C				un=2
	emms
	ret
L(un3):	movd	(%eax), %mm7		C				un=3
	movd	4(%eax), %mm6		C				un=3
	pmuludq	%mm7, %mm6		C				un=3
	movd	8(%eax), %mm2		C				un=3
	pmuludq	%mm7, %mm2		C				un=3
	movd	%mm6, 4(%edx)		C				un=3
	psrlq	$32, %mm6		C				un=3
	paddq	%mm2, %mm6		C				un=3
	movd	%mm6, 8(%edx)		C				un=3
	psrlq	$32, %mm6		C				un=3
	movd	%mm6, 12(%edx)		C				un=3
	lea	4(%edx), %edx		C				un=3
	lea	4(%eax), %eax		C				un=3
	jmp	L(am1)
L(un4):	movd	(%eax), %mm7		C				un=4
	movd	4(%eax), %mm6		C				un=4
	pmuludq	%mm7, %mm6		C				un=4
	movd	8(%eax), %mm0		C				un=4
	pmuludq	%mm7, %mm0		C				un=4
	movd	12(%eax), %mm1		C				un=4
	pmuludq	%mm7, %mm1		C				un=4
	movd	%mm6, 4(%edx)		C				un=4
	psrlq	$32, %mm6		C				un=4
	paddq	%mm0, %mm6		C				un=4
	movd	%mm6, 8(%edx)		C				un=4
	psrlq	$32, %mm6		C				un=4
	paddq	%mm1, %mm6		C				un=4
	movd	%mm6, 12(%edx)		C				un=4
	psrlq	$32, %mm6		C				un=4
	movd	%mm6, 16(%edx)		C				un=4
	lea	4(%edx), %edx		C				un=4
	lea	4(%eax), %eax		C				un=4
	jmp	L(am2)

L(big):	push	%esi
	push	%ebx
	push	%edi
	pxor	%mm6, %mm6
	movd	(%eax), %mm7		C
	lea	4(%eax), %esi		C init up, up++
	lea	4(%eax), %eax		C up2++  FIXME: should fix offsets
	lea	4(%edx), %edi		C init rp, rp++
	lea	4(%edx), %edx		C rp2++
	lea	-4(%ecx), %ebx		C loop count
	and	$3, %ecx
	jz	L(3m)
	cmp	$2, %ecx
	ja	L(2m)
	jb	L(0m)

L(1m):
	movd	(%eax), %mm4		C				m 1
	lea	(%ebx), %ecx		C inner loop count		m 1
	pmuludq	%mm7, %mm4		C				m 1
	movd	4(%eax), %mm3		C				m 1
	pmuludq	%mm7, %mm3		C				m 1
	movd	8(%eax), %mm0		C				m 1
	jmp	L(m01)			C				m 1
	ALIGN(16)			C				m 1
L(lpm1):
	pmuludq	%mm7, %mm4		C				m 1
	paddq	%mm0, %mm6		C				m 1
	movd	4(%eax), %mm3		C				m 1
	movd	%mm6, -8(%edx)		C				m 1
	psrlq	$32, %mm6		C				m 1
	pmuludq	%mm7, %mm3		C				m 1
	paddq	%mm1, %mm6		C				m 1
	movd	8(%eax), %mm0		C				m 1
	movd	%mm6, -4(%edx)		C				m 1
	psrlq	$32, %mm6		C				m 1
L(m01):	pmuludq	%mm7, %mm0		C				m 1
	paddq	%mm4, %mm6		C				m 1
	movd	12(%eax), %mm1		C				m 1
	movd	%mm6, (%edx)		C				m 1
	psrlq	$32, %mm6		C				m 1
	pmuludq	%mm7, %mm1		C				m 1
	paddq	%mm3, %mm6		C				m 1
	movd	16(%eax), %mm4		C				m 1
	movd	%mm6, 4(%edx)		C				m 1
	psrlq	$32, %mm6		C				m 1
	lea	16(%eax), %eax		C				m 1
	lea	16(%edx), %edx		C				m 1
	sub	$4, %ecx		C				m 1
	ja	L(lpm1)			C				m 1
	pmuludq	%mm7, %mm4		C				m 1
	paddq	%mm0, %mm6		C				m 1
	movd	%mm6, -8(%edx)		C				m 1
	psrlq	$32, %mm6		C				m 1
	paddq	%mm1, %mm6		C				m 1
	jmp	L(0)

L(2m):
	movd	(%eax), %mm1		C				m 2
	lea	(%ebx), %ecx		C inner loop count		m 2
	pmuludq	%mm7, %mm1		C				m 2
	movd	4(%eax), %mm4		C				m 2
	pmuludq	%mm7, %mm4		C				m 2
	movd	8(%eax), %mm3		C				m 2
	jmp	L(m10)			C				m 2
	ALIGN(16)			C				m 2
L(lpm2):
	pmuludq	%mm7, %mm4		C				m 2
	paddq	%mm0, %mm6		C				m 2
	movd	8(%eax), %mm3		C				m 2
	movd	%mm6, -4(%edx)		C				m 2
	psrlq	$32, %mm6		C				m 2
L(m10):	pmuludq	%mm7, %mm3		C				m 2
	paddq	%mm1, %mm6		C				m 2
	movd	12(%eax), %mm0		C				m 2
	movd	%mm6, (%edx)		C				m 2
	psrlq	$32, %mm6		C				m 2
	pmuludq	%mm7, %mm0		C				m 2
	paddq	%mm4, %mm6		C				m 2
	movd	16(%eax), %mm1		C				m 2
	movd	%mm6, 4(%edx)		C				m 2
	psrlq	$32, %mm6		C				m 2
	pmuludq	%mm7, %mm1		C				m 2
	paddq	%mm3, %mm6		C				m 2
	movd	20(%eax), %mm4		C				m 2
	movd	%mm6, 8(%edx)		C				m 2
	psrlq	$32, %mm6		C				m 2
	lea	16(%eax), %eax		C				m 2
	lea	16(%edx), %edx		C				m 2
	sub	$4, %ecx		C				m 2
	ja	L(lpm2)			C				m 2
	pmuludq	%mm7, %mm4		C				m 2
	paddq	%mm0, %mm6		C				m 2
	movd	%mm6, -4(%edx)		C				m 2
	psrlq	$32, %mm6		C				m 2
	paddq	%mm1, %mm6		C				m 2
	jmp	L(1)

L(3m):
	movd	(%eax), %mm0		C				m 3
	lea	(%ebx), %ecx		C inner loop count		m 3
	pmuludq	%mm7, %mm0		C				m 3
	movd	4(%eax), %mm1		C				m 3
	pmuludq	%mm7, %mm1		C				m 3
	movd	8(%eax), %mm4		C				m 3
	jmp	L(lpm3)			C				m 3
	ALIGN(16)			C				m 3
L(lpm3):
	pmuludq	%mm7, %mm4		C				m 3
	paddq	%mm0, %mm6		C				m 3
	movd	12(%eax), %mm3		C				m 3
	movd	%mm6, (%edx)		C				m 3
	psrlq	$32, %mm6		C				m 3
	pmuludq	%mm7, %mm3		C				m 3
	paddq	%mm1, %mm6		C				m 3
	movd	16(%eax), %mm0		C				m 3
	movd	%mm6, 4(%edx)		C				m 3
	psrlq	$32, %mm6		C				m 3
	pmuludq	%mm7, %mm0		C				m 3
	paddq	%mm4, %mm6		C				m 3
	movd	20(%eax), %mm1		C				m 3
	movd	%mm6, 8(%edx)		C				m 3
	psrlq	$32, %mm6		C				m 3
	pmuludq	%mm7, %mm1		C				m 3
	paddq	%mm3, %mm6		C				m 3
	movd	24(%eax), %mm4		C				m 3
	movd	%mm6, 12(%edx)		C				m 3
	psrlq	$32, %mm6		C				m 3
	lea	16(%eax), %eax		C				m 3
	lea	16(%edx), %edx		C				m 3
	sub	$4, %ecx		C				m 3
	ja	L(lpm3)			C				m 3
	pmuludq	%mm7, %mm4		C				m 3
	paddq	%mm0, %mm6		C				m 3
	movd	%mm6, (%edx)		C				m 3
	psrlq	$32, %mm6		C				m 3
	paddq	%mm1, %mm6		C				m 3
	jmp	L(2)

L(0m):
	movd	(%eax), %mm3		C				m 0
	lea	(%ebx), %ecx		C inner loop count		m 0
	pmuludq	%mm7, %mm3		C				m 0
	movd	4(%eax), %mm0		C				m 0
	pmuludq	%mm7, %mm0		C				m 0
	movd	8(%eax), %mm1		C				m 0
	jmp	L(m00)			C				m 0
	ALIGN(16)			C				m 0
L(lpm0):
	pmuludq	%mm7, %mm4		C				m 0
	paddq	%mm0, %mm6		C				m 0
	movd	(%eax), %mm3		C				m 0
	movd	%mm6, -12(%edx)		C				m 0
	psrlq	$32, %mm6		C				m 0
	pmuludq	%mm7, %mm3		C				m 0
	paddq	%mm1, %mm6		C				m 0
	movd	4(%eax), %mm0		C				m 0
	movd	%mm6, -8(%edx)		C				m 0
	psrlq	$32, %mm6		C				m 0
	pmuludq	%mm7, %mm0		C				m 0
	paddq	%mm4, %mm6		C				m 0
	movd	8(%eax), %mm1		C				m 0
	movd	%mm6, -4(%edx)		C				m 0
	psrlq	$32, %mm6		C				m 0
L(m00):	pmuludq	%mm7, %mm1		C				m 0
	paddq	%mm3, %mm6		C				m 0
	movd	12(%eax), %mm4		C				m 0
	movd	%mm6, (%edx)		C				m 0
	psrlq	$32, %mm6		C				m 0
	lea	16(%eax), %eax		C				m 0
	lea	16(%edx), %edx		C				m 0
	sub	$4, %ecx		C				m 0
	ja	L(lpm0)			C				m 0
	pmuludq	%mm7, %mm4		C				m 0
	paddq	%mm0, %mm6		C				m 0
	movd	%mm6, -12(%edx)		C				m 0
	psrlq	$32, %mm6		C				m 0
	paddq	%mm1, %mm6		C				m 0
	jmp	L(3)

L(outer):
	lea	8(%edi), %edi		C rp += 2
	movd	(%esi), %mm7		C				am 3
	mov	%edi, %edx		C rp2 = rp			am 3
	lea	4(%esi), %esi		C up++				am 3
	lea	(%esi), %eax		C up2 = up			am 3
	movd	(%eax), %mm0		C				am 3
	lea	(%ebx), %ecx		C inner loop count		am 3
	pxor	%mm6, %mm6		C				am 3
	pmuludq	%mm7, %mm0		C				am 3
	movd	4(%eax), %mm1		C				am 3
	movd	(%edx), %mm4		C				am 3
	pmuludq	%mm7, %mm1		C				am 3
	movd	8(%eax), %mm2		C				am 3
	paddq	%mm0, %mm4		C				am 3
	movd	4(%edx), %mm5		C				am 3
	jmp	L(lam3)			C				am 3
	ALIGN(16)			C				am 3
L(lam3):
	pmuludq	%mm7, %mm2		C				am 3
	paddq	%mm4, %mm6		C				am 3
	movd	12(%eax), %mm3		C				am 3
	paddq	%mm1, %mm5		C				am 3
	movd	8(%edx), %mm4		C				am 3
	movd	%mm6, (%edx)		C				am 3
	psrlq	$32, %mm6		C				am 3
	pmuludq	%mm7, %mm3		C				am 3
	paddq	%mm5, %mm6		C				am 3
	movd	16(%eax), %mm0		C				am 3
	paddq	%mm2, %mm4		C				am 3
	movd	12(%edx), %mm5		C				am 3
	movd	%mm6, 4(%edx)		C				am 3
	psrlq	$32, %mm6		C				am 3
	pmuludq	%mm7, %mm0		C				am 3
	paddq	%mm4, %mm6		C				am 3
	movd	20(%eax), %mm1		C				am 3
	paddq	%mm3, %mm5		C				am 3
	movd	16(%edx), %mm4		C				am 3
	movd	%mm6, 8(%edx)		C				am 3
	psrlq	$32, %mm6		C				am 3
	pmuludq	%mm7, %mm1		C				am 3
	paddq	%mm5, %mm6		C				am 3
	movd	24(%eax), %mm2		C				am 3
	paddq	%mm0, %mm4		C				am 3
	movd	20(%edx), %mm5		C				am 3
	movd	%mm6, 12(%edx)		C				am 3
	psrlq	$32, %mm6		C				am 3
	lea	16(%eax), %eax		C				am 3
	lea	16(%edx), %edx		C				am 3
	sub	$4, %ecx		C				am 3
	ja	L(lam3)			C				am 3
	pmuludq	%mm7, %mm2		C				am 3
	paddq	%mm4, %mm6		C				am 3
	paddq	%mm1, %mm5		C				am 3
	movd	8(%edx), %mm4		C				am 3
	movd	%mm6, (%edx)		C				am 3
	psrlq	$32, %mm6		C				am 3
	paddq	%mm5, %mm6		C				am 3
	paddq	%mm2, %mm4		C				am 3
L(2):	movd	%mm6, 4(%edx)		C				am 3
	psrlq	$32, %mm6		C				am 3
	paddq	%mm4, %mm6		C				am 3
	movd	%mm6, 8(%edx)		C				am 3
	psrlq	$32, %mm6		C				am 3
	movd	%mm6, 12(%edx)		C				am 3

	lea	8(%edi), %edi		C rp += 2
	movd	(%esi), %mm7		C				am 2
	mov	%edi, %edx		C rp2 = rp			am 2
	lea	4(%esi), %esi		C up++				am 2
	lea	(%esi), %eax		C up2 = up			am 2
	movd	(%eax), %mm1		C				am 2
	lea	(%ebx), %ecx		C inner loop count		am 2
	pxor	%mm6, %mm6		C				am 2
	pmuludq	%mm7, %mm1		C				am 2
	movd	4(%eax), %mm2		C				am 2
	movd	(%edx), %mm5		C				am 2
	pmuludq	%mm7, %mm2		C				am 2
	movd	8(%eax), %mm3		C				am 2
	paddq	%mm1, %mm5		C				am 2
	movd	4(%edx), %mm4		C				am 2
	jmp	L(am10)			C				am 2
	ALIGN(16)			C				am 2
L(lam2):
	pmuludq	%mm7, %mm2		C				am 2
	paddq	%mm4, %mm6		C				am 2
	movd	8(%eax), %mm3		C				am 2
	paddq	%mm1, %mm5		C				am 2
	movd	4(%edx), %mm4		C				am 2
	movd	%mm6, -4(%edx)		C				am 2
	psrlq	$32, %mm6		C				am 2
L(am10):
	pmuludq	%mm7, %mm3		C				am 2
	paddq	%mm5, %mm6		C				am 2
	movd	12(%eax), %mm0		C				am 2
	paddq	%mm2, %mm4		C				am 2
	movd	8(%edx), %mm5		C				am 2
	movd	%mm6, (%edx)		C				am 2
	psrlq	$32, %mm6		C				am 2
	pmuludq	%mm7, %mm0		C				am 2
	paddq	%mm4, %mm6		C				am 2
	movd	16(%eax), %mm1		C				am 2
	paddq	%mm3, %mm5		C				am 2
	movd	12(%edx), %mm4		C				am 2
	movd	%mm6, 4(%edx)		C				am 2
	psrlq	$32, %mm6		C				am 2
	pmuludq	%mm7, %mm1		C				am 2
	paddq	%mm5, %mm6		C				am 2
	movd	20(%eax), %mm2		C				am 2
	paddq	%mm0, %mm4		C				am 2
	movd	16(%edx), %mm5		C				am 2
	movd	%mm6, 8(%edx)		C				am 2
	psrlq	$32, %mm6		C				am 2
	lea	16(%eax), %eax		C				am 2
	lea	16(%edx), %edx		C				am 2
	sub	$4, %ecx		C				am 2
	ja	L(lam2)			C				am 2
	pmuludq	%mm7, %mm2		C				am 2
	paddq	%mm4, %mm6		C				am 2
	paddq	%mm1, %mm5		C				am 2
	movd	4(%edx), %mm4		C				am 2
	movd	%mm6, -4(%edx)		C				am 2
	psrlq	$32, %mm6		C				am 2
	paddq	%mm5, %mm6		C				am 2
	paddq	%mm2, %mm4		C				am 2
L(1):	movd	%mm6, (%edx)		C				am 2
	psrlq	$32, %mm6		C				am 2
	paddq	%mm4, %mm6		C				am 2
	movd	%mm6, 4(%edx)		C				am 2
	psrlq	$32, %mm6		C				am 2
	movd	%mm6, 8(%edx)		C				am 2

	lea	8(%edi), %edi		C rp += 2
	movd	(%esi), %mm7		C				am 1
	mov	%edi, %edx		C rp2 = rp			am 1
	lea	4(%esi), %esi		C up++				am 1
	lea	(%esi), %eax		C up2 = up			am 1
	movd	(%eax), %mm2		C				am 1
	lea	(%ebx), %ecx		C inner loop count		am 1
	pxor	%mm6, %mm6		C				am 1
	pmuludq	%mm7, %mm2		C				am 1
	movd	4(%eax), %mm3		C				am 1
	movd	(%edx), %mm4		C				am 1
	pmuludq	%mm7, %mm3		C				am 1
	movd	8(%eax), %mm0		C				am 1
	paddq	%mm2, %mm4		C				am 1
	movd	4(%edx), %mm5		C				am 1
	jmp	L(am01)			C				am 1
	ALIGN(16)			C				am 1
L(lam1):
	pmuludq	%mm7, %mm2		C				am 1
	paddq	%mm4, %mm6		C				am 1
	movd	4(%eax), %mm3		C				am 1
	paddq	%mm1, %mm5		C				am 1
	movd	(%edx), %mm4		C				am 1
	movd	%mm6, -8(%edx)		C				am 1
	psrlq	$32, %mm6		C				am 1
	pmuludq	%mm7, %mm3		C				am 1
	paddq	%mm5, %mm6		C				am 1
	movd	8(%eax), %mm0		C				am 1
	paddq	%mm2, %mm4		C				am 1
	movd	4(%edx), %mm5		C				am 1
	movd	%mm6, -4(%edx)		C				am 1
	psrlq	$32, %mm6		C				am 1
L(am01):
	pmuludq	%mm7, %mm0		C				am 1
	paddq	%mm4, %mm6		C				am 1
	movd	12(%eax), %mm1		C				am 1
	paddq	%mm3, %mm5		C				am 1
	movd	8(%edx), %mm4		C				am 1
	movd	%mm6, (%edx)		C				am 1
	psrlq	$32, %mm6		C				am 1
	pmuludq	%mm7, %mm1		C				am 1
	paddq	%mm5, %mm6		C				am 1
	movd	16(%eax), %mm2		C				am 1
	paddq	%mm0, %mm4		C				am 1
	movd	12(%edx), %mm5		C				am 1
	movd	%mm6, 4(%edx)		C				am 1
	psrlq	$32, %mm6		C				am 1
	lea	16(%eax), %eax		C				am 1
	lea	16(%edx), %edx		C				am 1
	sub	$4, %ecx		C				am 1
	ja	L(lam1)			C				am 1
	pmuludq	%mm7, %mm2		C				am 1
	paddq	%mm4, %mm6		C				am 1
	paddq	%mm1, %mm5		C				am 1
	movd	(%edx), %mm4		C				am 1
	movd	%mm6, -8(%edx)		C				am 1
	psrlq	$32, %mm6		C				am 1
	paddq	%mm5, %mm6		C				am 1
	paddq	%mm2, %mm4		C				am 1
L(0):	movd	%mm6, -4(%edx)		C				am 1
	psrlq	$32, %mm6		C				am 1
	paddq	%mm4, %mm6		C				am 1
	movd	%mm6, (%edx)		C				am 1
	psrlq	$32, %mm6		C				am 1
	movd	%mm6, 4(%edx)		C				am 1

	lea	8(%edi), %edi		C rp += 2
	movd	(%esi), %mm7		C				am 0
	mov	%edi, %edx		C rp2 = rp			am 0
	lea	4(%esi), %esi		C up++				am 0
	lea	(%esi), %eax		C up2 = up			am 0
	movd	(%eax), %mm3		C				am 0
	lea	(%ebx), %ecx		C inner loop count		am 0
	pxor	%mm6, %mm6		C				am 0
	pmuludq	%mm7, %mm3		C				am 0
	movd	4(%eax), %mm0		C				am 0
	movd	(%edx), %mm5		C				am 0
	pmuludq	%mm7, %mm0		C				am 0
	movd	8(%eax), %mm1		C				am 0
	paddq	%mm3, %mm5		C				am 0
	movd	4(%edx), %mm4		C				am 0
	jmp	L(am00)			C				am 0
	ALIGN(16)			C				am 0
L(lam0):
	pmuludq	%mm7, %mm2		C				am 0
	paddq	%mm4, %mm6		C				am 0
	movd	(%eax), %mm3		C				am 0
	paddq	%mm1, %mm5		C				am 0
	movd	-4(%edx), %mm4		C				am 0
	movd	%mm6, -12(%edx)		C				am 0
	psrlq	$32, %mm6		C				am 0
	pmuludq	%mm7, %mm3		C				am 0
	paddq	%mm5, %mm6		C				am 0
	movd	4(%eax), %mm0		C				am 0
	paddq	%mm2, %mm4		C				am 0
	movd	(%edx), %mm5		C				am 0
	movd	%mm6, -8(%edx)		C				am 0
	psrlq	$32, %mm6		C				am 0
	pmuludq	%mm7, %mm0		C				am 0
	paddq	%mm4, %mm6		C				am 0
	movd	8(%eax), %mm1		C				am 0
	paddq	%mm3, %mm5		C				am 0
	movd	4(%edx), %mm4		C				am 0
	movd	%mm6, -4(%edx)		C				am 0
	psrlq	$32, %mm6		C				am 0
L(am00):
	pmuludq	%mm7, %mm1		C				am 0
	paddq	%mm5, %mm6		C				am 0
	movd	12(%eax), %mm2		C				am 0
	paddq	%mm0, %mm4		C				am 0
	movd	8(%edx), %mm5		C				am 0
	movd	%mm6, (%edx)		C				am 0
	psrlq	$32, %mm6		C				am 0
	lea	16(%eax), %eax		C				am 0
	lea	16(%edx), %edx		C				am 0
	sub	$4, %ecx		C				am 0
	ja	L(lam0)			C				am 0
	pmuludq	%mm7, %mm2		C				am 0
	paddq	%mm4, %mm6		C				am 0
	paddq	%mm1, %mm5		C				am 0
	movd	-4(%edx), %mm4		C				am 0
	movd	%mm6, -12(%edx)		C				am 0
	psrlq	$32, %mm6		C				am 0
	paddq	%mm5, %mm6		C				am 0
	paddq	%mm2, %mm4		C				am 0
L(3):	movd	%mm6, -8(%edx)		C				am 0
	psrlq	$32, %mm6		C				am 0
	paddq	%mm4, %mm6		C				am 0
	movd	%mm6, -4(%edx)		C				am 0
	psrlq	$32, %mm6		C				am 0
	movd	%mm6, (%edx)		C				am 0
	sub	$4, %ebx		C				am 0
	ja	L(outer)			C				am 0

	mov	%edi, %edx
	mov	%esi, %eax
	pop	%edi
	pop	%ebx
	pop	%esi

L(am3):	C up[un-1..un-3] x up[un-4]
	lea	8(%edx), %edx		C rp2 += 2
	movd	(%eax), %mm7
	movd	4(%eax), %mm1
	movd	8(%eax), %mm2
	movd	12(%eax), %mm3
	movd	(%edx), %mm4
	pmuludq	%mm7, %mm1
	movd	4(%edx), %mm5
	pmuludq	%mm7, %mm2
	movd	8(%edx), %mm6
	pmuludq	%mm7, %mm3
	paddq	%mm1, %mm4
	paddq	%mm2, %mm5
	paddq	%mm3, %mm6
	movd	%mm4, (%edx)
	psrlq	$32, %mm4
	paddq	%mm5, %mm4
	movd	%mm4, 4(%edx)
	psrlq	$32, %mm4
	paddq	%mm6, %mm4
	movd	%mm4, 8(%edx)
	psrlq	$32, %mm4
	movd	%mm4, 12(%edx)		C FIXME feed through!
	lea	4(%eax), %eax

L(am2):	C up[un-1..un-2] x up[un-3]
	lea	8(%edx), %edx		C rp2 += 2
	movd	(%eax), %mm7
	movd	4(%eax), %mm1
	movd	8(%eax), %mm2
	movd	(%edx), %mm4
	movd	4(%edx), %mm5
	pmuludq	%mm7, %mm1
	pmuludq	%mm7, %mm2
	paddq	%mm1, %mm4
	paddq	%mm2, %mm5
	movd	%mm4, (%edx)
	psrlq	$32, %mm4
	paddq	%mm5, %mm4
	movd	%mm4, 4(%edx)
	psrlq	$32, %mm4
	movd	%mm4, 8(%edx)		C FIXME feed through!
	lea	4(%eax), %eax

L(am1):	C up[un-1] x up[un-2]
	lea	8(%edx), %edx		C rp2 += 2
	movd	(%eax), %mm7
	movd	4(%eax), %mm2
	movd	(%edx), %mm4
	pmuludq	%mm7, %mm2
	paddq	%mm2, %mm4
	movd	%mm4, (%edx)
	psrlq	$32, %mm4
	movd	%mm4, 4(%edx)

C *** diag stuff, use elementary code for now

	mov	4(%esp), %edx		C rp
	mov	8(%esp), %eax		C up
	mov	12(%esp), %ecx		C un

	movd	(%eax), %mm2
	pmuludq	%mm2, %mm2		C src[0]^2

	pcmpeqd	%mm7, %mm7
	psrlq	$32, %mm7

	movd	4(%edx), %mm3		C dst[1]

	movd	%mm2, (%edx)
	psrlq	$32, %mm2

	psllq	$1, %mm3		C 2*dst[1]
	paddq	%mm3, %mm2
	movd	%mm2, 4(%edx)
	psrlq	$32, %mm2

	sub	$2, %ecx

L(diag):
	movd	4(%eax), %mm0		C src limb
	add	$4, %eax
	pmuludq	%mm0, %mm0
	movq	%mm7, %mm1
	pand	%mm0, %mm1		C diagonal low
	psrlq	$32, %mm0		C diagonal high

	movd	8(%edx), %mm3
	psllq	$1, %mm3		C 2*dst[i]
	paddq	%mm3, %mm1
	paddq	%mm1, %mm2
	movd	%mm2, 8(%edx)
	psrlq	$32, %mm2

	movd	12(%edx), %mm3
	psllq	$1, %mm3		C 2*dst[i+1]
	paddq	%mm3, %mm0
	paddq	%mm0, %mm2
	movd	%mm2, 12(%edx)
	add	$8, %edx
	psrlq	$32, %mm2

	sub	$1, %ecx
	jnz	L(diag)

	movd	4(%eax), %mm0		C src[size-1]
	pmuludq	%mm0, %mm0
	pand	%mm0, %mm7		C diagonal low
	psrlq	$32, %mm0		C diagonal high

	movd	8(%edx), %mm3		C dst[2*size-2]
	psllq	$1, %mm3
	paddq	%mm3, %mm7
	paddq	%mm7, %mm2
	movd	%mm2, 8(%edx)
	psrlq	$32, %mm2

	paddq	%mm0, %mm2
	movd	%mm2, 12(%edx)		C dst[2*size-1]

	emms
	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
@@


1.1.1.2
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

d8 3
a10 13
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.
d14 2
a15 2
dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
dnl  for more details.
d17 2
a18 3
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/.
@