head	1.1;
branch	1.1.1;
access;
symbols
	netbsd-11-0-RC7:1.1.1.2
	netbsd-11-0-RC6:1.1.1.2
	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:1.1.1.1.0.26
	matt-nb8-mediatek-base:1.1.1.1
	gmp-6-1-2:1.1.1.2
	perseant-stdc-iso10646:1.1.1.1.0.24
	perseant-stdc-iso10646-base:1.1.1.1
	netbsd-8:1.1.1.1.0.22
	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-localcount2:1.1.1.1.0.20
	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-7-1:1.1.1.1.0.18
	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:1.1.1.1.0.16
	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:1.1.1.1.0.14
	netbsd-7-nhusb-base:1.1.1.1
	pgoyette-localcount-20160806:1.1.1.1
	pgoyette-localcount-20160726:1.1.1.1
	pgoyette-localcount:1.1.1.1.0.12
	pgoyette-localcount-base:1.1.1.1
	netbsd-7-0-1-RELEASE:1.1.1.1
	netbsd-7-0:1.1.1.1.0.10
	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
	tls-maxphys-base:1.1.1.1
	tls-maxphys:1.1.1.1.0.8
	netbsd-7:1.1.1.1.0.6
	netbsd-7-base:1.1.1.1
	yamt-pagecache:1.1.1.1.0.4
	yamt-pagecache-base9:1.1.1.1
	tls-earlyentropy:1.1.1.1.0.2
	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
	gmp-5-1-3:1.1.1.1
	gmp:1.1.1;
locks; strict;
comment	@;; @;


1.1
date	2013.11.29.07.49.48;	author mrg;	state Exp;
branches
	1.1.1.1;
next	;
commitid	L2Av4PuGmdoL39fx;

1.1.1.1
date	2013.11.29.07.49.48;	author mrg;	state Exp;
branches
	1.1.1.1.4.1
	1.1.1.1.8.1;
next	1.1.1.2;
commitid	L2Av4PuGmdoL39fx;

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

1.1.1.1.4.1
date	2013.11.29.07.49.48;	author yamt;	state dead;
branches;
next	1.1.1.1.4.2;
commitid	nx2BSsHy0NPeAxBx;

1.1.1.1.4.2
date	2014.05.22.14.09.06;	author yamt;	state Exp;
branches;
next	;
commitid	nx2BSsHy0NPeAxBx;

1.1.1.1.8.1
date	2013.11.29.07.49.48;	author tls;	state dead;
branches;
next	1.1.1.1.8.2;
commitid	jTnpym9Qu0o4R1Nx;

1.1.1.1.8.2
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_addlsh1_n -- rp[] = up[] + (vp[] << 1)
dnl  AMD64 mpn_rsblsh1_n -- rp[] = (vp[] << 1) - up[]
dnl  Optimised for Intel Atom.

dnl  Contributed to the GNU project by Torbjorn Granlund.

dnl  Copyright 2011, 2012 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 TODO
C  * This code is slightly large at 433 bytes.
C  * sublsh1_n.asm and this file use the same basic pattern.

C	     cycles/limb
C AMD K8,K9	 ?
C AMD K10	 ?
C Intel P4	 ?
C Intel core2	 ?
C Intel NHM	 ?
C Intel SBR	 ?
C Intel atom	 4.875	(4.75 is probably possible)
C VIA nano	 ?

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

ifdef(`OPERATION_addlsh1_n', `
  define(ADDSUB,	add)
  define(ADCSBB,	adc)
  define(func_n,	mpn_addlsh1_n)
  define(func_nc,	mpn_addlsh1_nc)')
ifdef(`OPERATION_rsblsh1_n', `
  define(ADDSUB,	sub)
  define(ADCSBB,	sbb)
  define(func_n,	mpn_rsblsh1_n)
  define(func_nc,	mpn_rsblsh1_nc)')

ABI_SUPPORT(DOS64)
ABI_SUPPORT(STD64)

MULFUNC_PROLOGUE(mpn_addlsh1_n mpn_addlsh1_nc mpn_rsblsh1_n mpn_rsblsh1_nc)

ASM_START()
	TEXT
	ALIGN(16)
PROLOGUE(func_n)
	FUNC_ENTRY(4)
	push	%rbp
	xor	R32(%rbp), R32(%rbp)
L(ent):	mov	R32(n), R32(%rax)
	and	$3, R32(%rax)
	jz	L(b0)
	cmp	$2, R32(%rax)
	jz	L(b2)
	jg	L(b3)

L(b1):	mov	(vp), %r8
	add	%r8, %r8
	lea	8(vp), vp
	sbb	R32(%rax), R32(%rax)	C save scy
	add	R32(%rbp), R32(%rbp)	C restore acy
	ADCSBB	(up), %r8
	mov	%r8, (rp)
	sbb	R32(%rbp), R32(%rbp)	C save acy
	lea	8(up), up
	lea	8(rp), rp
	jmp	L(b0)

L(b2):	mov	(vp), %r8
	add	%r8, %r8
	mov	8(vp), %r9
	adc	%r9, %r9
	lea	16(vp), vp
	sbb	R32(%rax), R32(%rax)	C save scy
	add	R32(%rbp), R32(%rbp)	C restore acy
	ADCSBB	(up), %r8
	mov	%r8, (rp)
	ADCSBB	8(up), %r9
	mov	%r9, 8(rp)
	sbb	R32(%rbp), R32(%rbp)	C save acy
	lea	16(up), up
	lea	16(rp), rp
	jmp	L(b0)

L(b3):	mov	(vp), %r8
	add	%r8, %r8
	mov	8(vp), %r9
	adc	%r9, %r9
	mov	16(vp), %r10
	adc	%r10, %r10
	lea	24(vp), vp
	sbb	R32(%rax), R32(%rax)	C save scy
	add	R32(%rbp), R32(%rbp)	C restore acy
	ADCSBB	(up), %r8
	mov	%r8, (rp)
	ADCSBB	8(up), %r9
	mov	%r9, 8(rp)
	ADCSBB	16(up), %r10
	mov	%r10, 16(rp)
	sbb	R32(%rbp), R32(%rbp)	C save acy
	lea	24(up), up
	lea	24(rp), rp

L(b0):	test	$4, R8(n)
	jz	L(skp)
	add	R32(%rax), R32(%rax)	C restore scy
	mov	(vp), %r8
	adc	%r8, %r8
	mov	8(vp), %r9
	adc	%r9, %r9
	mov	16(vp), %r10
	adc	%r10, %r10
	mov	24(vp), %r11
	adc	%r11, %r11
	lea	32(vp), vp
	sbb	R32(%rax), R32(%rax)	C save scy
	add	R32(%rbp), R32(%rbp)	C restore acy
	ADCSBB	(up), %r8
	mov	%r8, (rp)
	ADCSBB	8(up), %r9
	mov	%r9, 8(rp)
	ADCSBB	16(up), %r10
	mov	%r10, 16(rp)
	ADCSBB	24(up), %r11
	mov	%r11, 24(rp)
	lea	32(up), up
	lea	32(rp), rp
	sbb	R32(%rbp), R32(%rbp)	C save acy

L(skp):	cmp	$8, n
	jl	L(rtn)

	push	%r12
	push	%r13
	push	%r14
	push	%rbx
	lea	-64(rp), rp
	jmp	L(x)

	ALIGN(16)
L(top):	add	R32(%rax), R32(%rax)	C restore scy
	lea	64(rp), rp
	mov	(vp), %r8
	adc	%r8, %r8
	mov	8(vp), %r9
	adc	%r9, %r9
	mov	16(vp), %r10
	adc	%r10, %r10
	mov	24(vp), %r11
	adc	%r11, %r11
	mov	32(vp), %r12
	adc	%r12, %r12
	mov	40(vp), %r13
	adc	%r13, %r13
	mov	48(vp), %r14
	adc	%r14, %r14
	mov	56(vp), %rbx
	adc	%rbx, %rbx
	lea	64(vp), vp
	sbb	R32(%rax), R32(%rax)	C save scy
	add	R32(%rbp), R32(%rbp)	C restore acy
	ADCSBB	(up), %r8
	mov	%r8, (rp)
	ADCSBB	8(up), %r9
	mov	%r9, 8(rp)
	ADCSBB	16(up), %r10
	mov	%r10, 16(rp)
	ADCSBB	24(up), %r11
	mov	%r11, 24(rp)
	ADCSBB	32(up), %r12
	mov	%r12, 32(rp)
	ADCSBB	40(up), %r13
	mov	%r13, 40(rp)
	ADCSBB	48(up), %r14
	mov	%r14, 48(rp)
	ADCSBB	56(up), %rbx
	mov	%rbx, 56(rp)
	sbb	R32(%rbp), R32(%rbp)	C save acy
	lea	64(up), up
L(x):	sub	$8, n
	jge	L(top)

L(end):	pop	%rbx
	pop	%r14
	pop	%r13
	pop	%r12
L(rtn):
ifdef(`OPERATION_addlsh1_n',`
	add	R32(%rbp), R32(%rax)
	neg	R32(%rax)')
ifdef(`OPERATION_rsblsh1_n',`
	sub	R32(%rax), R32(%rbp)
	movslq	R32(%rbp), %rax')

	pop	%rbp
	FUNC_EXIT()
	ret
EPILOGUE()
PROLOGUE(func_nc)
	FUNC_ENTRY(4)
IFDOS(`	mov	56(%rsp), %r8	')
	push	%rbp
	neg	%r8			C set CF
	sbb	R32(%rbp), R32(%rbp)	C save acy
	jmp	L(ent)
EPILOGUE()
@


1.1.1.1
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
@@


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
@d1 3
a3 2
dnl  AMD64 mpn_addlsh1_n, mpn_rsblsh1_n optimised for Intel Atom.
dnl  Used also for AMD bd1.
d10 1
a10 1
dnl
d12 4
a15 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
d18 5
a22 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/.
a32 2
C AMD bd1	 2.3
C AMD bobcat	 ?
@


1.1.1.1.8.1
log
@file aorrlsh1_n.asm was added on branch tls-maxphys on 2014-08-19 23:59:55 +0000
@
text
@d1 226
@


1.1.1.1.8.2
log
@Rebase to HEAD as of a few days ago.
@
text
@a0 226
dnl  AMD64 mpn_addlsh1_n -- rp[] = up[] + (vp[] << 1)
dnl  AMD64 mpn_rsblsh1_n -- rp[] = (vp[] << 1) - up[]
dnl  Optimised for Intel Atom.

dnl  Contributed to the GNU project by Torbjorn Granlund.

dnl  Copyright 2011, 2012 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 TODO
C  * This code is slightly large at 433 bytes.
C  * sublsh1_n.asm and this file use the same basic pattern.

C	     cycles/limb
C AMD K8,K9	 ?
C AMD K10	 ?
C Intel P4	 ?
C Intel core2	 ?
C Intel NHM	 ?
C Intel SBR	 ?
C Intel atom	 4.875	(4.75 is probably possible)
C VIA nano	 ?

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

ifdef(`OPERATION_addlsh1_n', `
  define(ADDSUB,	add)
  define(ADCSBB,	adc)
  define(func_n,	mpn_addlsh1_n)
  define(func_nc,	mpn_addlsh1_nc)')
ifdef(`OPERATION_rsblsh1_n', `
  define(ADDSUB,	sub)
  define(ADCSBB,	sbb)
  define(func_n,	mpn_rsblsh1_n)
  define(func_nc,	mpn_rsblsh1_nc)')

ABI_SUPPORT(DOS64)
ABI_SUPPORT(STD64)

MULFUNC_PROLOGUE(mpn_addlsh1_n mpn_addlsh1_nc mpn_rsblsh1_n mpn_rsblsh1_nc)

ASM_START()
	TEXT
	ALIGN(16)
PROLOGUE(func_n)
	FUNC_ENTRY(4)
	push	%rbp
	xor	R32(%rbp), R32(%rbp)
L(ent):	mov	R32(n), R32(%rax)
	and	$3, R32(%rax)
	jz	L(b0)
	cmp	$2, R32(%rax)
	jz	L(b2)
	jg	L(b3)

L(b1):	mov	(vp), %r8
	add	%r8, %r8
	lea	8(vp), vp
	sbb	R32(%rax), R32(%rax)	C save scy
	add	R32(%rbp), R32(%rbp)	C restore acy
	ADCSBB	(up), %r8
	mov	%r8, (rp)
	sbb	R32(%rbp), R32(%rbp)	C save acy
	lea	8(up), up
	lea	8(rp), rp
	jmp	L(b0)

L(b2):	mov	(vp), %r8
	add	%r8, %r8
	mov	8(vp), %r9
	adc	%r9, %r9
	lea	16(vp), vp
	sbb	R32(%rax), R32(%rax)	C save scy
	add	R32(%rbp), R32(%rbp)	C restore acy
	ADCSBB	(up), %r8
	mov	%r8, (rp)
	ADCSBB	8(up), %r9
	mov	%r9, 8(rp)
	sbb	R32(%rbp), R32(%rbp)	C save acy
	lea	16(up), up
	lea	16(rp), rp
	jmp	L(b0)

L(b3):	mov	(vp), %r8
	add	%r8, %r8
	mov	8(vp), %r9
	adc	%r9, %r9
	mov	16(vp), %r10
	adc	%r10, %r10
	lea	24(vp), vp
	sbb	R32(%rax), R32(%rax)	C save scy
	add	R32(%rbp), R32(%rbp)	C restore acy
	ADCSBB	(up), %r8
	mov	%r8, (rp)
	ADCSBB	8(up), %r9
	mov	%r9, 8(rp)
	ADCSBB	16(up), %r10
	mov	%r10, 16(rp)
	sbb	R32(%rbp), R32(%rbp)	C save acy
	lea	24(up), up
	lea	24(rp), rp

L(b0):	test	$4, R8(n)
	jz	L(skp)
	add	R32(%rax), R32(%rax)	C restore scy
	mov	(vp), %r8
	adc	%r8, %r8
	mov	8(vp), %r9
	adc	%r9, %r9
	mov	16(vp), %r10
	adc	%r10, %r10
	mov	24(vp), %r11
	adc	%r11, %r11
	lea	32(vp), vp
	sbb	R32(%rax), R32(%rax)	C save scy
	add	R32(%rbp), R32(%rbp)	C restore acy
	ADCSBB	(up), %r8
	mov	%r8, (rp)
	ADCSBB	8(up), %r9
	mov	%r9, 8(rp)
	ADCSBB	16(up), %r10
	mov	%r10, 16(rp)
	ADCSBB	24(up), %r11
	mov	%r11, 24(rp)
	lea	32(up), up
	lea	32(rp), rp
	sbb	R32(%rbp), R32(%rbp)	C save acy

L(skp):	cmp	$8, n
	jl	L(rtn)

	push	%r12
	push	%r13
	push	%r14
	push	%rbx
	lea	-64(rp), rp
	jmp	L(x)

	ALIGN(16)
L(top):	add	R32(%rax), R32(%rax)	C restore scy
	lea	64(rp), rp
	mov	(vp), %r8
	adc	%r8, %r8
	mov	8(vp), %r9
	adc	%r9, %r9
	mov	16(vp), %r10
	adc	%r10, %r10
	mov	24(vp), %r11
	adc	%r11, %r11
	mov	32(vp), %r12
	adc	%r12, %r12
	mov	40(vp), %r13
	adc	%r13, %r13
	mov	48(vp), %r14
	adc	%r14, %r14
	mov	56(vp), %rbx
	adc	%rbx, %rbx
	lea	64(vp), vp
	sbb	R32(%rax), R32(%rax)	C save scy
	add	R32(%rbp), R32(%rbp)	C restore acy
	ADCSBB	(up), %r8
	mov	%r8, (rp)
	ADCSBB	8(up), %r9
	mov	%r9, 8(rp)
	ADCSBB	16(up), %r10
	mov	%r10, 16(rp)
	ADCSBB	24(up), %r11
	mov	%r11, 24(rp)
	ADCSBB	32(up), %r12
	mov	%r12, 32(rp)
	ADCSBB	40(up), %r13
	mov	%r13, 40(rp)
	ADCSBB	48(up), %r14
	mov	%r14, 48(rp)
	ADCSBB	56(up), %rbx
	mov	%rbx, 56(rp)
	sbb	R32(%rbp), R32(%rbp)	C save acy
	lea	64(up), up
L(x):	sub	$8, n
	jge	L(top)

L(end):	pop	%rbx
	pop	%r14
	pop	%r13
	pop	%r12
L(rtn):
ifdef(`OPERATION_addlsh1_n',`
	add	R32(%rbp), R32(%rax)
	neg	R32(%rax)')
ifdef(`OPERATION_rsblsh1_n',`
	sub	R32(%rax), R32(%rbp)
	movslq	R32(%rbp), %rax')

	pop	%rbp
	FUNC_EXIT()
	ret
EPILOGUE()
PROLOGUE(func_nc)
	FUNC_ENTRY(4)
IFDOS(`	mov	56(%rsp), %r8	')
	push	%rbp
	neg	%r8			C set CF
	sbb	R32(%rbp), R32(%rbp)	C save acy
	jmp	L(ent)
EPILOGUE()
@


1.1.1.1.4.1
log
@file aorrlsh1_n.asm was added on branch yamt-pagecache on 2014-05-22 14:09:06 +0000
@
text
@d1 226
@


1.1.1.1.4.2
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
@a0 226
dnl  AMD64 mpn_addlsh1_n -- rp[] = up[] + (vp[] << 1)
dnl  AMD64 mpn_rsblsh1_n -- rp[] = (vp[] << 1) - up[]
dnl  Optimised for Intel Atom.

dnl  Contributed to the GNU project by Torbjorn Granlund.

dnl  Copyright 2011, 2012 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 TODO
C  * This code is slightly large at 433 bytes.
C  * sublsh1_n.asm and this file use the same basic pattern.

C	     cycles/limb
C AMD K8,K9	 ?
C AMD K10	 ?
C Intel P4	 ?
C Intel core2	 ?
C Intel NHM	 ?
C Intel SBR	 ?
C Intel atom	 4.875	(4.75 is probably possible)
C VIA nano	 ?

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

ifdef(`OPERATION_addlsh1_n', `
  define(ADDSUB,	add)
  define(ADCSBB,	adc)
  define(func_n,	mpn_addlsh1_n)
  define(func_nc,	mpn_addlsh1_nc)')
ifdef(`OPERATION_rsblsh1_n', `
  define(ADDSUB,	sub)
  define(ADCSBB,	sbb)
  define(func_n,	mpn_rsblsh1_n)
  define(func_nc,	mpn_rsblsh1_nc)')

ABI_SUPPORT(DOS64)
ABI_SUPPORT(STD64)

MULFUNC_PROLOGUE(mpn_addlsh1_n mpn_addlsh1_nc mpn_rsblsh1_n mpn_rsblsh1_nc)

ASM_START()
	TEXT
	ALIGN(16)
PROLOGUE(func_n)
	FUNC_ENTRY(4)
	push	%rbp
	xor	R32(%rbp), R32(%rbp)
L(ent):	mov	R32(n), R32(%rax)
	and	$3, R32(%rax)
	jz	L(b0)
	cmp	$2, R32(%rax)
	jz	L(b2)
	jg	L(b3)

L(b1):	mov	(vp), %r8
	add	%r8, %r8
	lea	8(vp), vp
	sbb	R32(%rax), R32(%rax)	C save scy
	add	R32(%rbp), R32(%rbp)	C restore acy
	ADCSBB	(up), %r8
	mov	%r8, (rp)
	sbb	R32(%rbp), R32(%rbp)	C save acy
	lea	8(up), up
	lea	8(rp), rp
	jmp	L(b0)

L(b2):	mov	(vp), %r8
	add	%r8, %r8
	mov	8(vp), %r9
	adc	%r9, %r9
	lea	16(vp), vp
	sbb	R32(%rax), R32(%rax)	C save scy
	add	R32(%rbp), R32(%rbp)	C restore acy
	ADCSBB	(up), %r8
	mov	%r8, (rp)
	ADCSBB	8(up), %r9
	mov	%r9, 8(rp)
	sbb	R32(%rbp), R32(%rbp)	C save acy
	lea	16(up), up
	lea	16(rp), rp
	jmp	L(b0)

L(b3):	mov	(vp), %r8
	add	%r8, %r8
	mov	8(vp), %r9
	adc	%r9, %r9
	mov	16(vp), %r10
	adc	%r10, %r10
	lea	24(vp), vp
	sbb	R32(%rax), R32(%rax)	C save scy
	add	R32(%rbp), R32(%rbp)	C restore acy
	ADCSBB	(up), %r8
	mov	%r8, (rp)
	ADCSBB	8(up), %r9
	mov	%r9, 8(rp)
	ADCSBB	16(up), %r10
	mov	%r10, 16(rp)
	sbb	R32(%rbp), R32(%rbp)	C save acy
	lea	24(up), up
	lea	24(rp), rp

L(b0):	test	$4, R8(n)
	jz	L(skp)
	add	R32(%rax), R32(%rax)	C restore scy
	mov	(vp), %r8
	adc	%r8, %r8
	mov	8(vp), %r9
	adc	%r9, %r9
	mov	16(vp), %r10
	adc	%r10, %r10
	mov	24(vp), %r11
	adc	%r11, %r11
	lea	32(vp), vp
	sbb	R32(%rax), R32(%rax)	C save scy
	add	R32(%rbp), R32(%rbp)	C restore acy
	ADCSBB	(up), %r8
	mov	%r8, (rp)
	ADCSBB	8(up), %r9
	mov	%r9, 8(rp)
	ADCSBB	16(up), %r10
	mov	%r10, 16(rp)
	ADCSBB	24(up), %r11
	mov	%r11, 24(rp)
	lea	32(up), up
	lea	32(rp), rp
	sbb	R32(%rbp), R32(%rbp)	C save acy

L(skp):	cmp	$8, n
	jl	L(rtn)

	push	%r12
	push	%r13
	push	%r14
	push	%rbx
	lea	-64(rp), rp
	jmp	L(x)

	ALIGN(16)
L(top):	add	R32(%rax), R32(%rax)	C restore scy
	lea	64(rp), rp
	mov	(vp), %r8
	adc	%r8, %r8
	mov	8(vp), %r9
	adc	%r9, %r9
	mov	16(vp), %r10
	adc	%r10, %r10
	mov	24(vp), %r11
	adc	%r11, %r11
	mov	32(vp), %r12
	adc	%r12, %r12
	mov	40(vp), %r13
	adc	%r13, %r13
	mov	48(vp), %r14
	adc	%r14, %r14
	mov	56(vp), %rbx
	adc	%rbx, %rbx
	lea	64(vp), vp
	sbb	R32(%rax), R32(%rax)	C save scy
	add	R32(%rbp), R32(%rbp)	C restore acy
	ADCSBB	(up), %r8
	mov	%r8, (rp)
	ADCSBB	8(up), %r9
	mov	%r9, 8(rp)
	ADCSBB	16(up), %r10
	mov	%r10, 16(rp)
	ADCSBB	24(up), %r11
	mov	%r11, 24(rp)
	ADCSBB	32(up), %r12
	mov	%r12, 32(rp)
	ADCSBB	40(up), %r13
	mov	%r13, 40(rp)
	ADCSBB	48(up), %r14
	mov	%r14, 48(rp)
	ADCSBB	56(up), %rbx
	mov	%rbx, 56(rp)
	sbb	R32(%rbp), R32(%rbp)	C save acy
	lea	64(up), up
L(x):	sub	$8, n
	jge	L(top)

L(end):	pop	%rbx
	pop	%r14
	pop	%r13
	pop	%r12
L(rtn):
ifdef(`OPERATION_addlsh1_n',`
	add	R32(%rbp), R32(%rax)
	neg	R32(%rax)')
ifdef(`OPERATION_rsblsh1_n',`
	sub	R32(%rax), R32(%rbp)
	movslq	R32(%rbp), %rax')

	pop	%rbp
	FUNC_EXIT()
	ret
EPILOGUE()
PROLOGUE(func_nc)
	FUNC_ENTRY(4)
IFDOS(`	mov	56(%rsp), %r8	')
	push	%rbp
	neg	%r8			C set CF
	sbb	R32(%rbp), R32(%rbp)	C save acy
	jmp	L(ent)
EPILOGUE()
@