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	2011.06.20.05.54.39;	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	;
commitid	W5kmAIk8hwVpSb4A;

1.1.1.1.2.1
date	2014.05.22.14.09.01;	author yamt;	state Exp;
branches;
next	;
commitid	nx2BSsHy0NPeAxBx;

1.1.1.1.8.1
date	2014.08.19.23.59.50;	author tls;	state Exp;
branches;
next	;
commitid	jTnpym9Qu0o4R1Nx;


desc
@@


1.1
log
@Initial revision
@
text
@dnl  IA-64 mpn_divrem_2 -- Divide an n-limb number by a 2-limb number.

dnl  Copyright 2004, 2005 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         cycles/limb
C Itanium:    63
C Itanium 2:  46


C TODO
C  * Further optimize the loop.  We could probably do some more trickery with
C    arithmetic in the FPU, or perhaps use a non-zero addend of xma in more
C    places.
C  * Software pipeline for perhaps 5 saved cycles, around the end and start of
C    the loop.
C  * Schedule code outside of loop better.
C  * Update the comments.  They are now using the same name for the same
C    logical quantity.
C  * Handle conditional zeroing of r31 in loop more cleanly.
C  * Inline mpn_invert_limb and schedule its insns across the entire init code.
C  * Ultimately, use 2-limb, or perhaps 3-limb or 4-limb inverse.

define(`qp',`r32')
define(`qxn',`r33')
define(`np',`r34')
define(`nn',`r35')
define(`dp',`r36')

define(`fnh',`f11')
define(`fminus1',`f10')
define(`fd0',`f13')
define(`fd1',`f14')
define(`d0',`r39')
define(`d1',`r36')
define(`fnl',`f32')
define(`fdinv',`f12')

define(`R1',`r38') define(`R0',`r37')
define(`P1',`r28') define(`P0',`r27')

ASM_START()

C HP's assembler requires these declarations for importing mpn_invert_limb
	.global	mpn_invert_limb
	.type	mpn_invert_limb,@@function

PROLOGUE(mpn_divrem_2)
	.prologue
	.save ar.pfs, r42
	.save ar.lc, r44
	.save rp, r41
ifdef(`HAVE_ABI_32',
`	addp4		qp = 0, qp		C M I
	addp4		np = 0, np		C M I
	addp4		dp = 0, dp		C M I
	zxt4		nn = nn			C I
	zxt4		qxn = qxn		C I
	;;
')

	alloc		r42 = ar.pfs, 5,8,1,0	C M2
	ld8		d0 = [dp], 8		C M0M1	d0
	mov		r44 = ar.lc		C I0
	shladd		np = nn, 3, np		C M I
	;;
	ld8		d1 = [dp]		C M0M1	d1
	mov		r41 = b0		C I0
	add		r15 = -8, np		C M I
	add		np = -16, np		C M I
	mov		r40 = r0		C M I
	;;
	ld8		R1 = [r15]		C M0M1	n1
	ld8		R0 = [r34], -8		C M0M1	n0
	;;
	cmp.ltu		p6, p0 = d1, R1		C M I
	cmp.eq		p8, p0 = d1, R1		C M I
	;;
  (p8)	cmp.leu		p6, p0 = d0, R0
	cmp.ltu		p8, p9 = R0, d0
  (p6)	br.cond.dpnt	.L_high_limb_1		C FIXME: inline!
.L8:

	mov		r45 = d1
	br.call.sptk.many b0 = mpn_invert_limb	C FIXME: inline+schedule
	;;
	setf.sig	fd1 = d1		C d1
	setf.sig	fd0 = d0		C d0
	add		r14 = r33, r35		C nn + qxn
	;;
	setf.sig	fdinv = r8		C dinv
	mov		r9 = -1
	add		r35 = -3, r14
	;;
	setf.sig	fminus1 = r9
	cmp.gt		p6, p0 = r0, r35
	shladd		qp = r35, 3, qp
	mov		ar.lc = r35
	mov		r31 = 0			C n0
  (p6)	br.cond.dpnt	.Ldone
	;;
	ALIGN(16)
C *** MAIN LOOP START ***
.Loop:		C 00
	mov		r15 = R0		C nadj = n10
	cmp.le		p14, p15 = 0, R0	C check high bit of R0
	cmp.le		p8, p0 = r33, r35	C dividend limbs remaining?
	;;	C 01
	.pred.rel "mutex", p14, p15
  (p8)	ld8		r31 = [r34], -8		C n0
  (p15)	add		r15 = d1, R0		C nadj = n10 + d1
  (p15)	add		r14 = 1, R1		C nh + (nl:63)
  (p14)	mov		r14 = R1		C nh
	cmp.eq		p6, p0 = d1, R1		C nh == d1
  (p6)	br.cond.spnt	.L_R1_eq_d1
	;;	C 02
	setf.sig	f8 = r14		C n2 + (nl:63)
	setf.sig	f15 = r15		C nadj
	sub		r23 = -1, R1		C r23 = ~nh
	;;	C 03
	setf.sig	fnh = r23
	setf.sig	fnl = R0
	;;	C 08
	xma.hu		f7 = fdinv, f8, f15	C xh = HI(dinv*(nh-nmask)+nadj)
	;;	C 12
	xma.l		f7 = f7, fminus1, fnh	C nh + xh
	;;	C 16
	getf.sig	r14 = f7
	xma.hu		f9 = f7, fd1, fnl	C xh = HI(q1*d1+nl)
	xma.l		f33 = f7, fd1, fnl	C xh = LO(q1*d1+nl)
	;;	C 20
	getf.sig	r16 = f9
	sub		r24 = d1, R1
		C 21
	getf.sig	r17 = f33
	;;	C 25
	cmp.eq		p6, p7 = r16, r24
	;;	C 26
	.pred.rel "mutex", p6, p7
  (p6)	xma.l		f8 = f7, fminus1, f0	C f8 = -f7
  (p7)	xma.l		f8 = f7,fminus1,fminus1	C f8 = -f7-1
	;;	C 27
	.pred.rel "mutex", p6, p7
  (p6)	sub		r18 = 0, r14		C q = -q1
  (p7)	sub		r18 = -1, r14		C q = -q1-1
  (p6)	add		r14 = 0, r17		C n1 = xl
  (p7)	add		r14 = d1, r17		C n1 = xl + d1
	;;	C 30
	xma.hu		f9 = fd0, f8, f0	C d0*(-f7-1) = -d0*f7-d0
	xma.l		f35 = fd0, f8, f0
	;;	C 34
	getf.sig	P1 = f9		C P1
		C 35
	getf.sig	P0 = f35		C P0
	;;
.L_adj:		C 40
	cmp.ltu		p8, p0 = r31, P0	C p8 = cy from low limb
	cmp.ltu		p6, p0 = r14, P1	C p6 = prel cy from high limb
	sub		R0 = r31, P0
	sub		R1 = r14, P1
	;;	C 41
  (p8)	cmp.eq.or	p6, p0 = 0, R1		C p6 = final cy from high limb
  (p8)	add		R1 = -1, R1
	cmp.ne		p10, p0 = r0, r0	C clear p10 FIXME: use unc below!
	cmp.ne		p13, p0 = r0, r0	C clear p13 FIXME: use unc below!
	;;	C 42
  (p6)	add		R0 = R0, d0
  (p6)	add		R1 = R1, d1
  (p6)	add		r18 = -1, r18		C q--
	;;	C 43
  (p6)	cmp.ltu		p10, p0 = R0, d0
  (p6)	cmp.ltu		p0, p13 = R1, d1
	;;	C 44
  (p10)	cmp.ne.and	p0, p13 = -1, R1	C p13 = !cy
  (p10)	add		R1 = 1, R1
  (p13)	br.cond.spnt	.L_two_too_big		C jump if not cy
	;;	C 45
	st8		[qp] = r18, -8
	add		r35 = -1, r35
	mov		r31 = 0			C n0, next iteration
	br.cloop.sptk	.Loop
C *** MAIN LOOP END ***
	;;
.Ldone:
	mov		r8 = r40
	mov		b0 = r41
	add		r21 = 8, r34
	add		r22 = 16, r34
	;;
	st8		[r21] = R0
	st8		[r22] = R1
	mov		ar.pfs = r42
	mov		ar.lc = r44
	br.ret.sptk.many b0

.L_high_limb_1:
	.pred.rel "mutex", p8, p9
	sub		R0 = R0, d0
  (p8)	sub		R1 = R1, d1, 1
  (p9)	sub		R1 = R1, d1
	mov		r40 = 1
	br.sptk		.L8
	;;

.L_two_too_big:
	add		R0 = R0, d0
	add		R1 = R1, d1
	;;
	add		r18 = -1, r18		C q--
	cmp.ltu		p10, p0 = R0, d0
	;;
  (p10)	add		R1 = 1, R1
	st8		[qp] = r18, -8
	add		r35 = -1, r35
	mov		r31 = 0			C n0, next iteration
	br.cloop.sptk	.Loop
	br.sptk		.Ldone

.L_R1_eq_d1:
	add		r14 = R0, d1		C r = R0 + d1
	mov		r18 = -1		C q = -1
	;;
	cmp.leu		p6, p0 = R0, r14
 (p6)	br.cond.spnt	.L20			C jump unless cy
	;;
	sub		P1 = r14, d0
	add		R0 = r31, d0
	;;
	cmp.ltu		p8, p9 = R0, r31
	;;
	.pred.rel "mutex", p8, p9
	st8		[qp] = r18, -8
  (p8)	add		R1 = r0, P1, 1		C R1 = n1 - P1 - cy
  (p9)	add		R1 = r0, P1		C R1 = n1 - P1
	add		r35 = -1, r35
	mov		r31 = 0			C n0, next iteration
	br.cloop.sptk	.Loop
	br.sptk		.Ldone
	;;
.L20:	cmp.ne		p6, p7 = 0, d0
	;;
	.pred.rel "mutex", p6, p7
  (p6)	add		P1 = -1, d0
  (p7)	mov		P1 = d0
	sub		P0 = r0, d0
	br.sptk		.L_adj
EPILOGUE()
ASM_END()
@


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
@d1 1
a1 1
dnl  IA-64 mpn_divrem_2 -- Divide an mpn number by a normalized 2-limb number.
d3 1
a3 1
dnl  Copyright 2010, 2013 Free Software Foundation, Inc.
d9 1
a9 1
dnl  by the Free Software Foundation; either version 2.1 of the License, or (at
d18 1
a18 3
dnl  along with the GNU MP Library; see the file COPYING.LIB.  If not, write
dnl  to the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
dnl  Boston, MA 02110-1301, USA.
d22 3
a24 3
C               norm   frac
C itanium 1
C itanium 2     29     29
d28 26
a53 3
C  * Inline and interleave limb inversion code with loop setup code.
C  * We should use explicit bundling in much of the code, since it typically
C    cuts some cycles with the GNU assembler.
d55 2
a63 10
C INPUT PARAMETERS
C qp   = r32
C fn   = r33
C np   = r34
C nn   = r35
C dp   = r36

define(`f0x1', `f15')

ASM_START()
d66 3
d70 5
a74 5
`	addp4		r32 = 0, r32		C M I
	addp4		r34 = 0, r34		C M I
	addp4		r36 = 0, r36		C M I
	zxt4		r35 = r35		C I
	zxt4		r33 = r33		C I
d77 25
a101 13
	.save ar.pfs, r42
	alloc	 r42 = ar.pfs, 5, 9, 1, 0
	shladd	 r34 = r35, 3, r34
	adds	 r14 = 8, r36
	mov	 r43 = r1
	;;
	adds	 r15 = -8, r34
	ld8	 r39 = [r14]
	.save ar.lc, r45
	mov	 r45 = ar.lc
	adds	 r14 = -16, r34
	mov	 r40 = r0
	adds	 r34 = -24, r34
d103 14
a116 6
	ld8	 r38 = [r15]
	.save rp, r41
	mov	 r41 = b0
	.body
	ld8	 r36 = [r36]
	ld8	 r37 = [r14]
d118 120
a237 2
	cmp.gtu	 p6, p7 = r39, r38
  (p6)	br.cond.dptk .L8
d239 2
a240 2
	cmp.leu	 p8, p9 = r36, r37
	cmp.geu	 p6, p7 = r39, r38
d242 2
a243 7
  (p8)	cmp4.ne.and.orcm p6, p7 = 0, r0
  (p7)	br.cond.dptk .L51
.L8:
	add	 r14 = r33, r35		// un + fn
	mov	 r46 = r39		// argument to mpn_invert_limb
	;;
	adds	 r35 = -3, r14
d245 1
a245 87
	cmp.gt	 p12, p0 = r0, r35
  (p12)	br.cond.dpnt L(end)
	br.call.sptk.many b0 = mpn_invert_limb
	;;
	setf.sig f11 = r8		// di (non-final)
	setf.sig f34 = r39		// d1
	setf.sig f33 = r36		// d0
	mov	 r1 = r43
	;;
	mov	 r17 = 1
	setf.sig f9 = r38		// n2
	xma.l	 f6 = f11, f34, f0	// t0 = LO(di * d1)
	;;
	setf.sig f10 = r37		// n1
	setf.sig f15 = r17		// 1
	xma.hu	 f8 = f11, f33, f0	// s0 = HI(di * d0)
	;;
	getf.sig r17 = f6
	getf.sig r16 = f8
	mov	 ar.lc = r35
	;;
	sub	 r18 = r0, r39		// -d1
	add	 r14 = r17, r36
	;;
	setf.sig f14 = r18		// -d1
	cmp.leu	 p8, p9 = r17, r14
	add	 r16 = r14, r16
	;;
  (p9)	adds	 r19 = 0, r0
  (p8)	adds	 r19 = -1, r0
	cmp.gtu	 p6, p7 = r14, r16
	;;
  (p6)	adds	 r19 = 1, r19
	;;
ifelse(1,1,`
	cmp.gt	 p7, p6 = r0, r19
	;;
  (p6)	adds	 r8 = -1, r8		// di--
  (p6)	sub	 r14 = r16, r39		// t0 -= d1
  (p6)	cmp.ltu	 p6, p7 = r16, r39	// cy for: t0 - d1
	;;
  (p6)	cmp.gt	 p9, p8 = 1, r19
  (p7)	cmp.gt	 p9, p8 = 0, r19
  (p6)	adds	 r19 = -1, r19		// t1 -= cy
	mov	 r16 = r14
	;;
  (p8)	adds	 r8 = -1, r8		// di--
  (p8)	sub	 r14 = r16, r39		// t0 -= d1
  (p8)	cmp.ltu	 p8, p9 = r16, r39	// cy for: t0 - d1
	;;
  (p8)	cmp.gt	 p7, p6 = 1, r19
  (p9)	cmp.gt	 p7, p6 = 0, r19
  (p8)	adds	 r19 = -1, r19		// t1 -= cy
	mov	 r16 = r14
	;;
  (p6)	adds	 r8 = -1, r8		// di--
  (p6)	sub	 r14 = r16, r39		// t0 -= d1
  (p6)	cmp.ltu	 p6, p7 = r16, r39	// cy for: t0 - d1
	;;
  (p6)	cmp.gt	 p9, p8 = 1, r19
  (p7)	cmp.gt	 p9, p8 = 0, r19
  (p6)	adds	 r19 = -1, r19		// t1 -= cy
	mov	 r16 = r14
	;;
  (p8)	adds	 r8 = -1, r8		// di--
  (p8)	sub	 r14 = r16, r39		// t0 -= d1
  (p8)	cmp.ltu	 p8, p9 = r16, r39	// cy for: t0 - d1
	;;
  (p8)	adds	 r19 = -1, r19		// t1 -= cy
	mov	 r16 = r14
',`
	cmp.gt	 p8, p9 = r0, r19
  (p8)	br.cond.dpnt .L46
.L52:
	cmp.leu	 p6, p7 = r39, r16
	sub	 r14 = r16, r39
	adds	 r8 = -1, r8
	;;
  (p7)	adds	 r19 = -1, r19
	mov	 r16 = r14
	;;
  (p7)	cmp.gt	 p8, p9 = r0, r19
  (p9)	br.cond.dptk .L52
.L46:
')
	setf.sig f32 = r8		// di
	shladd	 r32 = r35, 3, r32
a246 63

	ALIGN(16)
L(top):	nop 0
	nop 0
	cmp.gt	 p8, p9 = r33, r35
	;;
 (p8)	mov	 r37 = r0
 (p9)	ld8	 r37 = [r34], -8
	xma.hu	 f8 = f9, f32, f10	//				0,29
	xma.l	 f12 = f9, f32, f10	//				0
	;;
	getf.sig r20 = f12		// q0				4
	xma.l	 f13 = f15, f8, f9	// q += n2			4
	sub	 r8 = -1, r36		// bitnot d0
	;;
	getf.sig r18 = f13		//				8
	xma.l	 f7 = f14, f13, f10	//				8
	xma.l	 f6 = f33, f13, f33	// t0 = LO(d0*q+d0)		8
	xma.hu	 f9 = f33, f13, f33	// t1 = HI(d0*q+d0)		9
	;;
	getf.sig r38 = f7		// n1				12
	getf.sig r16 = f6		//				13
	getf.sig r19 = f9		//				14
	;;
	sub	 r38 = r38, r39		// n1 -= d1			17
	;;
	cmp.ne	 p9, p0 = r0, r0	// clear p9
	cmp.leu	 p10, p11 = r16, r37	// cy for: n0 - t0		18
	;;
	sub	 r37 = r37, r16		// n0 -= t0			19
  (p11)	sub	 r38 = r38, r19, 1	// n1 -= t1 - cy		19
  (p10)	sub	 r38 = r38, r19		// n1 -= t1			19
	;;
	cmp.gtu	 p6, p7 = r20, r38	// n1 >= q0			20
	;;
  (p7)	cmp.ltu	 p9, p0 = r8, r37	//				21
  (p6)	add	 r18 = 1, r18		//
  (p7)	add	 r37 = r37, r36		//				21
  (p7)	add	 r38 = r38, r39		//				21
	;;
	setf.sig f10 = r37		// n1				22
  (p9)	add	 r38 = 1, r38		//				22
	;;
	setf.sig f9 = r38		// n2				23
	cmp.gtu	 p6, p7 = r39, r38	//				23
  (p7)	br.cond.spnt L(fix)
L(bck):	st8	 [r32] = r18, -8
	adds	 r35 = -1, r35
	br.cloop.sptk.few L(top)
	;;

L(end):	add	r14 = 8, r34
	add	r15 = 16, r34
	mov	 b0 = r41
	;;
	st8	[r14] = r37
	st8	[r15] = r38
	mov	 ar.pfs = r42
	mov	 r8 = r40
	mov	 ar.lc = r45
	br.ret.sptk.many b0
	;;
.L51:
d248 15
a262 21
	sub	 r37 = r37, r36
  (p9)	sub	 r38 = r38, r39, 1
  (p8)	sub	 r38 = r38, r39
	adds	 r40 = 1, r0
	br .L8
	;;

L(fix):	cmp.geu	 p6, p7 = r39, r38
	cmp.leu	 p8, p9 = r36, r37
	;;
  (p8)	cmp4.ne.and.orcm p6, p7 = 0, r0
  (p6)	br.cond.dptk L(bck)
	sub	 r37 = r37, r36
  (p9)	sub	 r38 = r38, r39, 1
  (p8)	sub	 r38 = r38, r39
	adds	 r18 = 1, r18
	;;
	setf.sig f9 = r38		// n2
	setf.sig f10 = r37		// n1
	br	 L(bck)

@


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
@d1 1
a1 1
dnl  IA-64 mpn_divrem_2 -- Divide an mpn number by a normalized 2-limb number.
d3 1
a3 1
dnl  Copyright 2010, 2013 Free Software Foundation, Inc.
d9 1
a9 1
dnl  by the Free Software Foundation; either version 2.1 of the License, or (at
d18 1
a18 3
dnl  along with the GNU MP Library; see the file COPYING.LIB.  If not, write
dnl  to the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
dnl  Boston, MA 02110-1301, USA.
d22 3
a24 3
C               norm   frac
C itanium 1
C itanium 2     29     29
d28 26
a53 3
C  * Inline and interleave limb inversion code with loop setup code.
C  * We should use explicit bundling in much of the code, since it typically
C    cuts some cycles with the GNU assembler.
d55 2
a63 10
C INPUT PARAMETERS
C qp   = r32
C fn   = r33
C np   = r34
C nn   = r35
C dp   = r36

define(`f0x1', `f15')

ASM_START()
d66 3
d70 5
a74 5
`	addp4		r32 = 0, r32		C M I
	addp4		r34 = 0, r34		C M I
	addp4		r36 = 0, r36		C M I
	zxt4		r35 = r35		C I
	zxt4		r33 = r33		C I
d77 25
a101 13
	.save ar.pfs, r42
	alloc	 r42 = ar.pfs, 5, 9, 1, 0
	shladd	 r34 = r35, 3, r34
	adds	 r14 = 8, r36
	mov	 r43 = r1
	;;
	adds	 r15 = -8, r34
	ld8	 r39 = [r14]
	.save ar.lc, r45
	mov	 r45 = ar.lc
	adds	 r14 = -16, r34
	mov	 r40 = r0
	adds	 r34 = -24, r34
d103 14
a116 6
	ld8	 r38 = [r15]
	.save rp, r41
	mov	 r41 = b0
	.body
	ld8	 r36 = [r36]
	ld8	 r37 = [r14]
d118 120
a237 2
	cmp.gtu	 p6, p7 = r39, r38
  (p6)	br.cond.dptk .L8
d239 2
a240 2
	cmp.leu	 p8, p9 = r36, r37
	cmp.geu	 p6, p7 = r39, r38
d242 2
a243 7
  (p8)	cmp4.ne.and.orcm p6, p7 = 0, r0
  (p7)	br.cond.dptk .L51
.L8:
	add	 r14 = r33, r35		// un + fn
	mov	 r46 = r39		// argument to mpn_invert_limb
	;;
	adds	 r35 = -3, r14
d245 1
a245 87
	cmp.gt	 p12, p0 = r0, r35
  (p12)	br.cond.dpnt L(end)
	br.call.sptk.many b0 = mpn_invert_limb
	;;
	setf.sig f11 = r8		// di (non-final)
	setf.sig f34 = r39		// d1
	setf.sig f33 = r36		// d0
	mov	 r1 = r43
	;;
	mov	 r17 = 1
	setf.sig f9 = r38		// n2
	xma.l	 f6 = f11, f34, f0	// t0 = LO(di * d1)
	;;
	setf.sig f10 = r37		// n1
	setf.sig f15 = r17		// 1
	xma.hu	 f8 = f11, f33, f0	// s0 = HI(di * d0)
	;;
	getf.sig r17 = f6
	getf.sig r16 = f8
	mov	 ar.lc = r35
	;;
	sub	 r18 = r0, r39		// -d1
	add	 r14 = r17, r36
	;;
	setf.sig f14 = r18		// -d1
	cmp.leu	 p8, p9 = r17, r14
	add	 r16 = r14, r16
	;;
  (p9)	adds	 r19 = 0, r0
  (p8)	adds	 r19 = -1, r0
	cmp.gtu	 p6, p7 = r14, r16
	;;
  (p6)	adds	 r19 = 1, r19
	;;
ifelse(1,1,`
	cmp.gt	 p7, p6 = r0, r19
	;;
  (p6)	adds	 r8 = -1, r8		// di--
  (p6)	sub	 r14 = r16, r39		// t0 -= d1
  (p6)	cmp.ltu	 p6, p7 = r16, r39	// cy for: t0 - d1
	;;
  (p6)	cmp.gt	 p9, p8 = 1, r19
  (p7)	cmp.gt	 p9, p8 = 0, r19
  (p6)	adds	 r19 = -1, r19		// t1 -= cy
	mov	 r16 = r14
	;;
  (p8)	adds	 r8 = -1, r8		// di--
  (p8)	sub	 r14 = r16, r39		// t0 -= d1
  (p8)	cmp.ltu	 p8, p9 = r16, r39	// cy for: t0 - d1
	;;
  (p8)	cmp.gt	 p7, p6 = 1, r19
  (p9)	cmp.gt	 p7, p6 = 0, r19
  (p8)	adds	 r19 = -1, r19		// t1 -= cy
	mov	 r16 = r14
	;;
  (p6)	adds	 r8 = -1, r8		// di--
  (p6)	sub	 r14 = r16, r39		// t0 -= d1
  (p6)	cmp.ltu	 p6, p7 = r16, r39	// cy for: t0 - d1
	;;
  (p6)	cmp.gt	 p9, p8 = 1, r19
  (p7)	cmp.gt	 p9, p8 = 0, r19
  (p6)	adds	 r19 = -1, r19		// t1 -= cy
	mov	 r16 = r14
	;;
  (p8)	adds	 r8 = -1, r8		// di--
  (p8)	sub	 r14 = r16, r39		// t0 -= d1
  (p8)	cmp.ltu	 p8, p9 = r16, r39	// cy for: t0 - d1
	;;
  (p8)	adds	 r19 = -1, r19		// t1 -= cy
	mov	 r16 = r14
',`
	cmp.gt	 p8, p9 = r0, r19
  (p8)	br.cond.dpnt .L46
.L52:
	cmp.leu	 p6, p7 = r39, r16
	sub	 r14 = r16, r39
	adds	 r8 = -1, r8
	;;
  (p7)	adds	 r19 = -1, r19
	mov	 r16 = r14
	;;
  (p7)	cmp.gt	 p8, p9 = r0, r19
  (p9)	br.cond.dptk .L52
.L46:
')
	setf.sig f32 = r8		// di
	shladd	 r32 = r35, 3, r32
a246 63

	ALIGN(16)
L(top):	nop 0
	nop 0
	cmp.gt	 p8, p9 = r33, r35
	;;
 (p8)	mov	 r37 = r0
 (p9)	ld8	 r37 = [r34], -8
	xma.hu	 f8 = f9, f32, f10	//				0,29
	xma.l	 f12 = f9, f32, f10	//				0
	;;
	getf.sig r20 = f12		// q0				4
	xma.l	 f13 = f15, f8, f9	// q += n2			4
	sub	 r8 = -1, r36		// bitnot d0
	;;
	getf.sig r18 = f13		//				8
	xma.l	 f7 = f14, f13, f10	//				8
	xma.l	 f6 = f33, f13, f33	// t0 = LO(d0*q+d0)		8
	xma.hu	 f9 = f33, f13, f33	// t1 = HI(d0*q+d0)		9
	;;
	getf.sig r38 = f7		// n1				12
	getf.sig r16 = f6		//				13
	getf.sig r19 = f9		//				14
	;;
	sub	 r38 = r38, r39		// n1 -= d1			17
	;;
	cmp.ne	 p9, p0 = r0, r0	// clear p9
	cmp.leu	 p10, p11 = r16, r37	// cy for: n0 - t0		18
	;;
	sub	 r37 = r37, r16		// n0 -= t0			19
  (p11)	sub	 r38 = r38, r19, 1	// n1 -= t1 - cy		19
  (p10)	sub	 r38 = r38, r19		// n1 -= t1			19
	;;
	cmp.gtu	 p6, p7 = r20, r38	// n1 >= q0			20
	;;
  (p7)	cmp.ltu	 p9, p0 = r8, r37	//				21
  (p6)	add	 r18 = 1, r18		//
  (p7)	add	 r37 = r37, r36		//				21
  (p7)	add	 r38 = r38, r39		//				21
	;;
	setf.sig f10 = r37		// n1				22
  (p9)	add	 r38 = 1, r38		//				22
	;;
	setf.sig f9 = r38		// n2				23
	cmp.gtu	 p6, p7 = r39, r38	//				23
  (p7)	br.cond.spnt L(fix)
L(bck):	st8	 [r32] = r18, -8
	adds	 r35 = -1, r35
	br.cloop.sptk.few L(top)
	;;

L(end):	add	r14 = 8, r34
	add	r15 = 16, r34
	mov	 b0 = r41
	;;
	st8	[r14] = r37
	st8	[r15] = r38
	mov	 ar.pfs = r42
	mov	 r8 = r40
	mov	 ar.lc = r45
	br.ret.sptk.many b0
	;;
.L51:
d248 15
a262 21
	sub	 r37 = r37, r36
  (p9)	sub	 r38 = r38, r39, 1
  (p8)	sub	 r38 = r38, r39
	adds	 r40 = 1, r0
	br .L8
	;;

L(fix):	cmp.geu	 p6, p7 = r39, r38
	cmp.leu	 p8, p9 = r36, r37
	;;
  (p8)	cmp4.ne.and.orcm p6, p7 = 0, r0
  (p6)	br.cond.dptk L(bck)
	sub	 r37 = r37, r36
  (p9)	sub	 r38 = r38, r39, 1
  (p8)	sub	 r38 = r38, r39
	adds	 r18 = 1, r18
	;;
	setf.sig f9 = r38		// n2
	setf.sig f10 = r37		// n1
	br	 L(bck)

@


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
@d1 1
a1 1
dnl  IA-64 mpn_divrem_2 -- Divide an mpn number by a normalized 2-limb number.
d3 1
a3 1
dnl  Copyright 2010, 2013 Free Software Foundation, Inc.
d9 1
a9 1
dnl  by the Free Software Foundation; either version 2.1 of the License, or (at
d18 1
a18 3
dnl  along with the GNU MP Library; see the file COPYING.LIB.  If not, write
dnl  to the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
dnl  Boston, MA 02110-1301, USA.
d22 3
a24 3
C               norm   frac
C itanium 1
C itanium 2     29     29
d28 26
a53 3
C  * Inline and interleave limb inversion code with loop setup code.
C  * We should use explicit bundling in much of the code, since it typically
C    cuts some cycles with the GNU assembler.
d55 2
a63 10
C INPUT PARAMETERS
C qp   = r32
C fn   = r33
C np   = r34
C nn   = r35
C dp   = r36

define(`f0x1', `f15')

ASM_START()
d66 3
d70 5
a74 5
`	addp4		r32 = 0, r32		C M I
	addp4		r34 = 0, r34		C M I
	addp4		r36 = 0, r36		C M I
	zxt4		r35 = r35		C I
	zxt4		r33 = r33		C I
d77 25
a101 13
	.save ar.pfs, r42
	alloc	 r42 = ar.pfs, 5, 9, 1, 0
	shladd	 r34 = r35, 3, r34
	adds	 r14 = 8, r36
	mov	 r43 = r1
	;;
	adds	 r15 = -8, r34
	ld8	 r39 = [r14]
	.save ar.lc, r45
	mov	 r45 = ar.lc
	adds	 r14 = -16, r34
	mov	 r40 = r0
	adds	 r34 = -24, r34
d103 14
a116 6
	ld8	 r38 = [r15]
	.save rp, r41
	mov	 r41 = b0
	.body
	ld8	 r36 = [r36]
	ld8	 r37 = [r14]
d118 120
a237 2
	cmp.gtu	 p6, p7 = r39, r38
  (p6)	br.cond.dptk .L8
d239 2
a240 2
	cmp.leu	 p8, p9 = r36, r37
	cmp.geu	 p6, p7 = r39, r38
d242 2
a243 7
  (p8)	cmp4.ne.and.orcm p6, p7 = 0, r0
  (p7)	br.cond.dptk .L51
.L8:
	add	 r14 = r33, r35		// un + fn
	mov	 r46 = r39		// argument to mpn_invert_limb
	;;
	adds	 r35 = -3, r14
d245 1
a245 87
	cmp.gt	 p12, p0 = r0, r35
  (p12)	br.cond.dpnt L(end)
	br.call.sptk.many b0 = mpn_invert_limb
	;;
	setf.sig f11 = r8		// di (non-final)
	setf.sig f34 = r39		// d1
	setf.sig f33 = r36		// d0
	mov	 r1 = r43
	;;
	mov	 r17 = 1
	setf.sig f9 = r38		// n2
	xma.l	 f6 = f11, f34, f0	// t0 = LO(di * d1)
	;;
	setf.sig f10 = r37		// n1
	setf.sig f15 = r17		// 1
	xma.hu	 f8 = f11, f33, f0	// s0 = HI(di * d0)
	;;
	getf.sig r17 = f6
	getf.sig r16 = f8
	mov	 ar.lc = r35
	;;
	sub	 r18 = r0, r39		// -d1
	add	 r14 = r17, r36
	;;
	setf.sig f14 = r18		// -d1
	cmp.leu	 p8, p9 = r17, r14
	add	 r16 = r14, r16
	;;
  (p9)	adds	 r19 = 0, r0
  (p8)	adds	 r19 = -1, r0
	cmp.gtu	 p6, p7 = r14, r16
	;;
  (p6)	adds	 r19 = 1, r19
	;;
ifelse(1,1,`
	cmp.gt	 p7, p6 = r0, r19
	;;
  (p6)	adds	 r8 = -1, r8		// di--
  (p6)	sub	 r14 = r16, r39		// t0 -= d1
  (p6)	cmp.ltu	 p6, p7 = r16, r39	// cy for: t0 - d1
	;;
  (p6)	cmp.gt	 p9, p8 = 1, r19
  (p7)	cmp.gt	 p9, p8 = 0, r19
  (p6)	adds	 r19 = -1, r19		// t1 -= cy
	mov	 r16 = r14
	;;
  (p8)	adds	 r8 = -1, r8		// di--
  (p8)	sub	 r14 = r16, r39		// t0 -= d1
  (p8)	cmp.ltu	 p8, p9 = r16, r39	// cy for: t0 - d1
	;;
  (p8)	cmp.gt	 p7, p6 = 1, r19
  (p9)	cmp.gt	 p7, p6 = 0, r19
  (p8)	adds	 r19 = -1, r19		// t1 -= cy
	mov	 r16 = r14
	;;
  (p6)	adds	 r8 = -1, r8		// di--
  (p6)	sub	 r14 = r16, r39		// t0 -= d1
  (p6)	cmp.ltu	 p6, p7 = r16, r39	// cy for: t0 - d1
	;;
  (p6)	cmp.gt	 p9, p8 = 1, r19
  (p7)	cmp.gt	 p9, p8 = 0, r19
  (p6)	adds	 r19 = -1, r19		// t1 -= cy
	mov	 r16 = r14
	;;
  (p8)	adds	 r8 = -1, r8		// di--
  (p8)	sub	 r14 = r16, r39		// t0 -= d1
  (p8)	cmp.ltu	 p8, p9 = r16, r39	// cy for: t0 - d1
	;;
  (p8)	adds	 r19 = -1, r19		// t1 -= cy
	mov	 r16 = r14
',`
	cmp.gt	 p8, p9 = r0, r19
  (p8)	br.cond.dpnt .L46
.L52:
	cmp.leu	 p6, p7 = r39, r16
	sub	 r14 = r16, r39
	adds	 r8 = -1, r8
	;;
  (p7)	adds	 r19 = -1, r19
	mov	 r16 = r14
	;;
  (p7)	cmp.gt	 p8, p9 = r0, r19
  (p9)	br.cond.dptk .L52
.L46:
')
	setf.sig f32 = r8		// di
	shladd	 r32 = r35, 3, r32
a246 63

	ALIGN(16)
L(top):	nop 0
	nop 0
	cmp.gt	 p8, p9 = r33, r35
	;;
 (p8)	mov	 r37 = r0
 (p9)	ld8	 r37 = [r34], -8
	xma.hu	 f8 = f9, f32, f10	//				0,29
	xma.l	 f12 = f9, f32, f10	//				0
	;;
	getf.sig r20 = f12		// q0				4
	xma.l	 f13 = f15, f8, f9	// q += n2			4
	sub	 r8 = -1, r36		// bitnot d0
	;;
	getf.sig r18 = f13		//				8
	xma.l	 f7 = f14, f13, f10	//				8
	xma.l	 f6 = f33, f13, f33	// t0 = LO(d0*q+d0)		8
	xma.hu	 f9 = f33, f13, f33	// t1 = HI(d0*q+d0)		9
	;;
	getf.sig r38 = f7		// n1				12
	getf.sig r16 = f6		//				13
	getf.sig r19 = f9		//				14
	;;
	sub	 r38 = r38, r39		// n1 -= d1			17
	;;
	cmp.ne	 p9, p0 = r0, r0	// clear p9
	cmp.leu	 p10, p11 = r16, r37	// cy for: n0 - t0		18
	;;
	sub	 r37 = r37, r16		// n0 -= t0			19
  (p11)	sub	 r38 = r38, r19, 1	// n1 -= t1 - cy		19
  (p10)	sub	 r38 = r38, r19		// n1 -= t1			19
	;;
	cmp.gtu	 p6, p7 = r20, r38	// n1 >= q0			20
	;;
  (p7)	cmp.ltu	 p9, p0 = r8, r37	//				21
  (p6)	add	 r18 = 1, r18		//
  (p7)	add	 r37 = r37, r36		//				21
  (p7)	add	 r38 = r38, r39		//				21
	;;
	setf.sig f10 = r37		// n1				22
  (p9)	add	 r38 = 1, r38		//				22
	;;
	setf.sig f9 = r38		// n2				23
	cmp.gtu	 p6, p7 = r39, r38	//				23
  (p7)	br.cond.spnt L(fix)
L(bck):	st8	 [r32] = r18, -8
	adds	 r35 = -1, r35
	br.cloop.sptk.few L(top)
	;;

L(end):	add	r14 = 8, r34
	add	r15 = 16, r34
	mov	 b0 = r41
	;;
	st8	[r14] = r37
	st8	[r15] = r38
	mov	 ar.pfs = r42
	mov	 r8 = r40
	mov	 ar.lc = r45
	br.ret.sptk.many b0
	;;
.L51:
d248 15
a262 21
	sub	 r37 = r37, r36
  (p9)	sub	 r38 = r38, r39, 1
  (p8)	sub	 r38 = r38, r39
	adds	 r40 = 1, r0
	br .L8
	;;

L(fix):	cmp.geu	 p6, p7 = r39, r38
	cmp.leu	 p8, p9 = r36, r37
	;;
  (p8)	cmp4.ne.and.orcm p6, p7 = 0, r0
  (p6)	br.cond.dptk L(bck)
	sub	 r37 = r37, r36
  (p9)	sub	 r38 = r38, r39, 1
  (p8)	sub	 r38 = r38, r39
	adds	 r18 = 1, r18
	;;
	setf.sig f9 = r38		// n2
	setf.sig f10 = r37		// n1
	br	 L(bck)

@


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
@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 7
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/.
d56 1
a57 2
	addp4		r36 = 0, r36		C M I
	nop.m		0
@