head	1.2;
access;
symbols
	perseant-exfatfs-base-20250801:1.2
	perseant-exfatfs-base-20240630:1.2
	perseant-exfatfs:1.2.0.8
	perseant-exfatfs-base:1.2
	netbsd-8-3-RELEASE:1.1.1.2
	cjep_sun2x:1.2.0.6
	cjep_sun2x-base:1.2
	cjep_staticlib_x-base1:1.2
	cjep_staticlib_x:1.2.0.4
	cjep_staticlib_x-base:1.2
	phil-wifi-20200421:1.2
	phil-wifi-20200411:1.2
	phil-wifi-20200406:1.2
	netbsd-8-2-RELEASE:1.1.1.2
	netbsd-8-1-RELEASE:1.1.1.2
	netbsd-8-1-RC1:1.1.1.2
	pgoyette-compat-merge-20190127:1.2
	pgoyette-compat-20190127:1.2
	pgoyette-compat-20190118:1.2
	pgoyette-compat-1226:1.2
	pgoyette-compat-1126:1.2
	pgoyette-compat-1020:1.2
	pgoyette-compat-0930:1.2
	pgoyette-compat-0906:1.2
	netbsd-7-2-RELEASE:1.1.1.2
	pgoyette-compat-0728:1.2
	netbsd-8-0-RELEASE:1.1.1.2
	pgoyette-compat-0625:1.2
	netbsd-8-0-RC2:1.1.1.2
	pgoyette-compat-0521:1.2
	pgoyette-compat-0502:1.2
	pgoyette-compat-0422:1.2
	netbsd-8-0-RC1:1.1.1.2
	pgoyette-compat-0415:1.2
	pgoyette-compat-0407:1.2
	pgoyette-compat-0330:1.2
	pgoyette-compat-0322:1.2
	pgoyette-compat-0315:1.2
	netbsd-7-1-2-RELEASE:1.1.1.2
	pgoyette-compat:1.2.0.2
	pgoyette-compat-base:1.2
	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
	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	@;; @;


1.2
date	2017.08.22.09.55.46;	author mrg;	state dead;
branches;
next	1.1;
commitid	DVNRZh45aSIRZb4A;

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	;
commitid	L2Av4PuGmdoL39fx;

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
@@


1.2
log
@merge GMP 6.1.2.
@
text
@dnl  AMD64 mpn_mul_basecase.

dnl  Contributed to the GNU project by Torbjorn Granlund and David Harvey.

dnl  Copyright 2008 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 K8,K9:	 2.375
C K10:		 2.375
C P4:		 ?
C P6-15:	 4.45

C The inner loops of this code are the result of running a code generation and
C optimization tool suite written by David Harvey and Torbjorn Granlund.

C TODO
C  * Use fewer registers.  (how??? I can't see it -- david)
C  * Avoid some "mov $0,r" and instead use "xor r,r".
C  * Can the top of each L(addmul_outer_n) prologue be folded into the
C    mul_1/mul_2 prologues, saving a LEA (%rip)? It would slow down the
C    case where vn = 1 or 2; is it worth it?

C INPUT PARAMETERS
define(`rp',      `%rdi')
define(`up',      `%rsi')
define(`un_param',`%rdx')
define(`vp',      `%rcx')
define(`vn',      `%r8')

define(`v0', `%r12')
define(`v1', `%r9')

define(`w0', `%rbx')
define(`w1', `%r15')
define(`w2', `%rbp')
define(`w3', `%r10')

define(`n',  `%r11')
define(`outer_addr', `%r14')
define(`un',  `%r13')

ASM_START()
	TEXT
	ALIGN(16)
PROLOGUE(mpn_mul_basecase)
	push	%rbx
	push	%rbp
	push	%r12
	push	%r13
	push	%r14
	push	%r15

	xor	R32(un), R32(un)
	mov	(up), %rax
	mov	(vp), v0

	sub	un_param, un		C rdx used by mul
	mov	un, n
	mov	R32(un_param), R32(w0)

	lea	(rp,un_param,8), rp
	lea	(up,un_param,8), up

	mul	v0

	test	$1, R8(vn)
	jz	L(mul_2)

C ===========================================================
C     mul_1 for vp[0] if vn is odd

L(mul_1):
	and	$3, R32(w0)
	jz	L(mul_1_prologue_0)
	cmp	$2, R32(w0)
	jc	L(mul_1_prologue_1)
	jz	L(mul_1_prologue_2)
	jmp	L(mul_1_prologue_3)

L(mul_1_prologue_0):
	mov	%rax, w2
	mov	%rdx, w3		C note: already w0 == 0
	lea	L(addmul_outer_0)(%rip), outer_addr
	jmp	L(mul_1_entry_0)

L(mul_1_prologue_1):
	cmp	$-1, un
	jne	2f
	mov	%rax, -8(rp)
	mov	%rdx, (rp)
	jmp	L(ret)
2:	add	$1, n
	lea	L(addmul_outer_1)(%rip), outer_addr
	mov	%rax, w1
	mov	%rdx, w2
	xor	R32(w3), R32(w3)
	mov	(up,n,8), %rax
	jmp	L(mul_1_entry_1)

L(mul_1_prologue_2):
	add	$-2, n
	lea	L(addmul_outer_2)(%rip), outer_addr
	mov	%rax, w0
	mov	%rdx, w1
	mov	24(up,n,8), %rax
	xor	R32(w2), R32(w2)
	xor	R32(w3), R32(w3)
	jmp	L(mul_1_entry_2)

L(mul_1_prologue_3):
	add	$-1, n
	lea	L(addmul_outer_3)(%rip), outer_addr
	mov	%rax, w3
	mov	%rdx, w0
	jmp	L(mul_1_entry_3)


	C this loop is 10 c/loop = 2.5 c/l on K8, for all up/rp alignments

	ALIGN(16)
L(mul_1_top):
	mov	w0, -16(rp,n,8)
	add	%rax, w1
	mov	(up,n,8), %rax
	adc	%rdx, w2
L(mul_1_entry_1):
	xor	R32(w0), R32(w0)
	mul	v0
	mov	w1, -8(rp,n,8)
	add	%rax, w2
	adc	%rdx, w3
L(mul_1_entry_0):
	mov	8(up,n,8), %rax
	mul	v0
	mov	w2, (rp,n,8)
	add	%rax, w3
	adc	%rdx, w0
L(mul_1_entry_3):
	mov	16(up,n,8), %rax
	mul	v0
	mov	w3, 8(rp,n,8)
	xor	R32(w2), R32(w2)	C zero
	mov	w2, w3			C zero
	add	%rax, w0
	mov	24(up,n,8), %rax
	mov	w2, w1			C zero
	adc	%rdx, w1
L(mul_1_entry_2):
	mul	v0
	add	$4, n
	js	L(mul_1_top)

	mov	w0, -16(rp)
	add	%rax, w1
	mov	w1, -8(rp)
	adc	%rdx, w2
	mov	w2, (rp)

	add	$-1, vn			C vn -= 1
	jz	L(ret)

	mov	8(vp), v0
	mov	16(vp), v1

	lea	8(vp), vp		C vp += 1
	lea	8(rp), rp		C rp += 1

	jmp	*outer_addr

C ===========================================================
C     mul_2 for vp[0], vp[1] if vn is even

	ALIGN(16)
L(mul_2):
	mov	8(vp), v1

	and	$3, R32(w0)
	jz	L(mul_2_prologue_0)
	cmp	$2, R32(w0)
	jz	L(mul_2_prologue_2)
	jc	L(mul_2_prologue_1)

L(mul_2_prologue_3):
	lea	L(addmul_outer_3)(%rip), outer_addr
	add	$2, n
	mov	%rax, -16(rp,n,8)
	mov	%rdx, w2
	xor	R32(w3), R32(w3)
	xor	R32(w0), R32(w0)
	mov	-16(up,n,8), %rax
	jmp	L(mul_2_entry_3)

	ALIGN(16)
L(mul_2_prologue_0):
	add	$3, n
	mov	%rax, w0
	mov	%rdx, w1
	xor	R32(w2), R32(w2)
	mov	-24(up,n,8), %rax
	lea	L(addmul_outer_0)(%rip), outer_addr
	jmp	L(mul_2_entry_0)

	ALIGN(16)
L(mul_2_prologue_1):
	mov	%rax, w3
	mov	%rdx, w0
	xor	R32(w1), R32(w1)
	lea	L(addmul_outer_1)(%rip), outer_addr
	jmp	L(mul_2_entry_1)

	ALIGN(16)
L(mul_2_prologue_2):
	add	$1, n
	lea	L(addmul_outer_2)(%rip), outer_addr
	mov	$0, R32(w0)
	mov	$0, R32(w1)
	mov	%rax, w2
	mov	-8(up,n,8), %rax
	mov	%rdx, w3
	jmp	L(mul_2_entry_2)

	C this loop is 18 c/loop = 2.25 c/l on K8, for all up/rp alignments

	ALIGN(16)
L(mul_2_top):
	mov	-32(up,n,8), %rax
	mul	v1
	add	%rax, w0
	adc	%rdx, w1
	mov	-24(up,n,8), %rax
	xor	R32(w2), R32(w2)
	mul	v0
	add	%rax, w0
	mov	-24(up,n,8), %rax
	adc	%rdx, w1
	adc	$0, R32(w2)
L(mul_2_entry_0):
	mul	v1
	add	%rax, w1
	mov	w0, -24(rp,n,8)
	adc	%rdx, w2
	mov	-16(up,n,8), %rax
	mul	v0
	mov	$0, R32(w3)
	add	%rax, w1
	adc	%rdx, w2
	mov	-16(up,n,8), %rax
	adc	$0, R32(w3)
	mov	$0, R32(w0)
	mov	w1, -16(rp,n,8)
L(mul_2_entry_3):
	mul	v1
	add	%rax, w2
	mov	-8(up,n,8), %rax
	adc	%rdx, w3
	mov	$0, R32(w1)
	mul	v0
	add	%rax, w2
	mov	-8(up,n,8), %rax
	adc	%rdx, w3
	adc	R32(w1), R32(w0)	C adc $0, w0
L(mul_2_entry_2):
	mul	v1
	add	%rax, w3
	mov	w2, -8(rp,n,8)
	adc	%rdx, w0
	mov	(up,n,8), %rax
	mul	v0
	add	%rax, w3
	adc	%rdx, w0
	adc	$0, R32(w1)
L(mul_2_entry_1):
	add	$4, n
	mov	w3, -32(rp,n,8)
	js	L(mul_2_top)

	mov	-32(up,n,8), %rax
	mul	v1
	add	%rax, w0
	mov	w0, (rp)
	adc	%rdx, w1
	mov	w1, 8(rp)

	add	$-2, vn			C vn -= 2
	jz	L(ret)

	mov	16(vp), v0
	mov	24(vp), v1

	lea	16(vp), vp		C vp += 2
	lea	16(rp), rp		C rp += 2

	jmp	*outer_addr


C ===========================================================
C     addmul_2 for remaining vp's

	C in the following prologues, we reuse un to store the
	C adjusted value of n that is reloaded on each iteration

L(addmul_outer_0):
	add	$3, un
	lea	0(%rip), outer_addr

	mov	un, n
	mov	-24(up,un,8), %rax
	mul	v0
	mov	%rax, w0
	mov	-24(up,un,8), %rax
	mov	%rdx, w1
	xor	R32(w2), R32(w2)
	jmp	L(addmul_entry_0)

L(addmul_outer_1):
	mov	un, n
	mov	(up,un,8), %rax
	mul	v0
	mov	%rax, w3
	mov	(up,un,8), %rax
	mov	%rdx, w0
	xor	R32(w1), R32(w1)
	jmp	L(addmul_entry_1)

L(addmul_outer_2):
	add	$1, un
	lea	0(%rip), outer_addr

	mov	un, n
	mov	-8(up,un,8), %rax
	mul	v0
	xor	R32(w0), R32(w0)
	mov	%rax, w2
	xor	R32(w1), R32(w1)
	mov	%rdx, w3
	mov	-8(up,un,8), %rax
	jmp	L(addmul_entry_2)

L(addmul_outer_3):
	add	$2, un
	lea	0(%rip), outer_addr

	mov	un, n
	mov	-16(up,un,8), %rax
	xor	R32(w3), R32(w3)
	mul	v0
	mov	%rax, w1
	mov	-16(up,un,8), %rax
	mov	%rdx, w2
	jmp	L(addmul_entry_3)

	C this loop is 19 c/loop = 2.375 c/l on K8, for all up/rp alignments

	ALIGN(16)
L(addmul_top):
	add	w3, -32(rp,n,8)
	adc	%rax, w0
	mov	-24(up,n,8), %rax
	adc	%rdx, w1
	xor	R32(w2), R32(w2)
	mul	v0
	add	%rax, w0
	mov	-24(up,n,8), %rax
	adc	%rdx, w1
	adc	R32(w2), R32(w2)	C adc $0, w2
L(addmul_entry_0):
	mul	v1
	xor	R32(w3), R32(w3)
	add	w0, -24(rp,n,8)
	adc	%rax, w1
	mov	-16(up,n,8), %rax
	adc	%rdx, w2
	mul	v0
	add	%rax, w1
	mov	-16(up,n,8), %rax
	adc	%rdx, w2
	adc	$0, R32(w3)
L(addmul_entry_3):
	mul	v1
	add	w1, -16(rp,n,8)
	adc	%rax, w2
	mov	-8(up,n,8), %rax
	adc	%rdx, w3
	mul	v0
	xor	R32(w0), R32(w0)
	add	%rax, w2
	adc	%rdx, w3
	mov	$0, R32(w1)
	mov	-8(up,n,8), %rax
	adc	R32(w1), R32(w0)	C adc $0, w0
L(addmul_entry_2):
	mul	v1
	add	w2, -8(rp,n,8)
	adc	%rax, w3
	adc	%rdx, w0
	mov	(up,n,8), %rax
	mul	v0
	add	%rax, w3
	mov	(up,n,8), %rax
	adc	%rdx, w0
	adc	$0, R32(w1)
L(addmul_entry_1):
	mul	v1
	add	$4, n
	js	L(addmul_top)

	add	w3, -8(rp)
	adc	%rax, w0
	mov	w0, (rp)
	adc	%rdx, w1
	mov	w1, 8(rp)

	add	$-2, vn			C vn -= 2
	jz	L(ret)

	lea	16(rp), rp		C rp += 2
	lea	16(vp), vp		C vp += 2

	mov	(vp), v0
	mov	8(vp), v1

	jmp	*outer_addr

	ALIGN(16)
L(ret):	pop	%r15
	pop	%r14
	pop	%r13
	pop	%r12
	pop	%rbp
	pop	%rbx
	ret

EPILOGUE()
@


1.1
log
@Initial revision
@
text
@@


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
@d5 1
a5 1
dnl  Copyright 2008, 2012 Free Software Foundation, Inc.
d25 4
a28 7
C AMD K8,K9	 2.375
C AMD K10	 2.375
C Intel P4	15-16
C Intel core2	 4.45
C Intel corei	 4.35
C Intel atom	 ?
C VIA nano	 4.5
a58 3
ABI_SUPPORT(DOS64)
ABI_SUPPORT(STD64)

a62 2
	FUNC_ENTRY(4)
IFDOS(`	mov	56(%rsp), %r8d	')
d95 1
a95 7

L(mul_1_prologue_3):
	add	$-1, n
	lea	L(addmul_outer_3)(%rip), outer_addr
	mov	%rax, w3
	mov	%rdx, w0
	jmp	L(mul_1_entry_3)
d127 7
d294 1
a294 1
	mov	-32(up,n,8), %rax	C FIXME: n is constant
a447 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
@d5 1
a5 1
dnl  Copyright 2008, 2012 Free Software Foundation, Inc.
d25 4
a28 7
C AMD K8,K9	 2.375
C AMD K10	 2.375
C Intel P4	15-16
C Intel core2	 4.45
C Intel corei	 4.35
C Intel atom	 ?
C VIA nano	 4.5
a58 3
ABI_SUPPORT(DOS64)
ABI_SUPPORT(STD64)

a62 2
	FUNC_ENTRY(4)
IFDOS(`	mov	56(%rsp), %r8d	')
d95 1
a95 7

L(mul_1_prologue_3):
	add	$-1, n
	lea	L(addmul_outer_3)(%rip), outer_addr
	mov	%rax, w3
	mov	%rdx, w0
	jmp	L(mul_1_entry_3)
d127 7
d294 1
a294 1
	mov	-32(up,n,8), %rax	C FIXME: n is constant
a447 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
@d5 1
a5 1
dnl  Copyright 2008, 2012 Free Software Foundation, Inc.
d25 4
a28 7
C AMD K8,K9	 2.375
C AMD K10	 2.375
C Intel P4	15-16
C Intel core2	 4.45
C Intel corei	 4.35
C Intel atom	 ?
C VIA nano	 4.5
a58 3
ABI_SUPPORT(DOS64)
ABI_SUPPORT(STD64)

a62 2
	FUNC_ENTRY(4)
IFDOS(`	mov	56(%rsp), %r8d	')
d95 1
a95 7

L(mul_1_prologue_3):
	add	$-1, n
	lea	L(addmul_outer_3)(%rip), outer_addr
	mov	%rax, w3
	mov	%rdx, w0
	jmp	L(mul_1_entry_3)
d127 7
d294 1
a294 1
	mov	-32(up,n,8), %rax	C FIXME: n is constant
a447 1
	FUNC_EXIT()
@