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-11:1.1.1.3.0.10
	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:1.1.1.3.0.8
	perseant-exfatfs-base:1.1.1.3
	netbsd-8-3-RELEASE:1.1.1.1
	netbsd-9-4-RELEASE:1.1.1.2
	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-10:1.1.1.3.0.6
	netbsd-10-base:1.1.1.3
	netbsd-9-3-RELEASE:1.1.1.2
	gmp-6-2-1:1.1.1.3
	cjep_sun2x-base1:1.1.1.3
	cjep_sun2x:1.1.1.3.0.4
	cjep_sun2x-base:1.1.1.3
	cjep_staticlib_x-base1:1.1.1.3
	netbsd-9-2-RELEASE:1.1.1.2
	cjep_staticlib_x:1.1.1.3.0.2
	cjep_staticlib_x-base:1.1.1.3
	netbsd-9-1-RELEASE:1.1.1.2
	gmp-6-2-0:1.1.1.3
	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	2011.06.20.05.54.39;	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;
next	1.1.1.2;

1.1.1.2
date	2017.08.22.09.40.49;	author mrg;	state Exp;
branches;
next	1.1.1.3;
commitid	W5kmAIk8hwVpSb4A;

1.1.1.3
date	2020.09.27.00.27.05;	author mrg;	state Exp;
branches;
next	;
commitid	BWuUFuEU17KgrCpC;


desc
@@


1.1
log
@Initial revision
@
text
@dnl  x86-64 mpn_popcount optimized for "Core 2".

dnl  Copyright 2007 Free Software Foundation, Inc.

dnl  This file is part of the GNU MP Library.

dnl  The GNU MP Library is free software; you can redistribute it and/or modify
dnl  it under the terms of the GNU Lesser General Public License as published
dnl  by the Free Software Foundation; either version 3 of the License, or (at
dnl  your option) any later version.

dnl  The GNU MP Library is distributed in the hope that it will be useful, but
dnl  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public
dnl  License for more details.

dnl  You should have received a copy of the GNU Lesser General Public License
dnl  along with the GNU MP Library.  If not, see http://www.gnu.org/licenses/.


include(`../config.m4')

MULFUNC_PROLOGUE(mpn_popcount)
include_mpn(`x86/pentium4/sse2/popcount.asm')
@


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
@d6 1
a6 1
dnl
d8 4
a11 14
dnl  it under the terms of either:
dnl
dnl    * the GNU Lesser General Public License as published by the Free
dnl      Software Foundation; either version 3 of the License, or (at your
dnl      option) any later version.
dnl
dnl  or
dnl
dnl    * the GNU General Public License as published by the Free Software
dnl      Foundation; either version 2 of the License, or (at your option) any
dnl      later version.
dnl
dnl  or both in parallel, as here.
dnl
d14 5
a18 6
dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
dnl  for more details.
dnl
dnl  You should have received copies of the GNU General Public License and the
dnl  GNU Lesser General Public License along with the GNU MP Library.  If not,
dnl  see https://www.gnu.org/licenses/.
@


1.1.1.3
log
@initial import of GMP 6.2.0.  changes include:

- Bug fixes to gmp_snprintf, conversion to double, mpz_powm,
  and mpf_set_str.
- New functions for factorial, primorial, fibonacci, mpz_2fac_ui,
  and mpz_mfac_uiui.
- MIPS r6 cores are now supported.
- Various speeds ups.
@
text
@d1 1
a1 1
dnl  AMD64 SSSE3 mpn_popcount -- population count.
d3 1
a3 1
dnl  Copyright 2010-2017 Free Software Foundation, Inc.
d34 2
a35 152
C		    cycles/limb	  good for cpu?
C AMD K8,K9		n/a
C AMD K10		n/a
C AMD bd1	     1.79-1.91		n
C AMD bd2	     1.73-1.85		n
C AMD bd3		 ?
C AMD bd4	     1.73-1.85		n
C AMD zen		 1.47		n
C AMD bobcat		 8.0		n
C AMD jaguar		 4.78		n
C Intel P4		n/a
C Intel CNR		 3.75
C Intel PNR		 2.61		y
C Intel NHM		 2.03		n
C Intel SBR		 1.87		n
C Intel IBR	     1.52-1.58		n
C Intel HWL	     1.52-1.58		n
C Intel BWL	     1.52-1.58		n
C Intel SKL		 1.51		n
C Intel atom		12.3		n
C Intel SLM		 9.1		n
C VIA nano		 ?

C TODO
C  * This was hand-written without too much thought about optimal insn
C    selection; check to see of it can be improved.
C  * Consider doing some instruction scheduling.

define(`up',		`%rdi')
define(`n',		`%rsi')

ASM_START()
	TEXT
	ALIGN(32)
PROLOGUE(mpn_popcount)
	lea	L(cnsts)(%rip), %r9

ifdef(`PIC', `define(`OFF1',32) define(`OFF2',48)',
	     `define(`OFF1',64) define(`OFF2',80)')
	movdqa	OFF1`'(%r9), %xmm7
	movdqa	OFF2`'(%r9), %xmm6
	pxor	%xmm4, %xmm4
	pxor	%xmm5, %xmm5
	pxor	%xmm8, %xmm8

	mov	R32(n), R32(%rax)
	and	$7, R32(%rax)
ifdef(`PIC',`
	movslq	(%r9,%rax,4), %rax
	add	%r9, %rax
	jmp	*%rax
',`
	jmp	*(%r9,%rax,8)
')

L(1):	movq	(up), %xmm1
	add	$8, up
	jmp	L(e1)

L(2):	add	$-48, up
	jmp	L(e2)

L(3):	movq	(up), %xmm1
	add	$-40, up
	jmp	L(e3)

L(4):	add	$-32, up
	jmp	L(e4)

L(5):	movq	(up), %xmm1
	add	$-24, up
	jmp	L(e5)

L(6):	add	$-16, up
	jmp	L(e6)

L(7):	movq	(up), %xmm1
	add	$-8, up
	jmp	L(e7)

	ALIGN(32)
L(top):	lddqu	(up), %xmm1
L(e7):	movdqa	%xmm6, %xmm0		C copy mask register
	movdqa	%xmm7, %xmm2		C copy count register
	movdqa	%xmm7, %xmm3		C copy count register
	pand	%xmm1, %xmm0
	psrlw	$4, %xmm1
	pand	%xmm6, %xmm1
	pshufb	%xmm0, %xmm2
	pshufb	%xmm1, %xmm3
	paddb	%xmm2, %xmm3
	paddb	%xmm3, %xmm4
L(e6):	lddqu	16(up), %xmm1
L(e5):	movdqa	%xmm6, %xmm0
	movdqa	%xmm7, %xmm2
	movdqa	%xmm7, %xmm3
	pand	%xmm1, %xmm0
	psrlw	$4, %xmm1
	pand	%xmm6, %xmm1
	pshufb	%xmm0, %xmm2
	pshufb	%xmm1, %xmm3
	paddb	%xmm2, %xmm3
	paddb	%xmm3, %xmm4
L(e4):	lddqu	32(up), %xmm1
L(e3):	movdqa	%xmm6, %xmm0
	movdqa	%xmm7, %xmm2
	movdqa	%xmm7, %xmm3
	pand	%xmm1, %xmm0
	psrlw	$4, %xmm1
	pand	%xmm6, %xmm1
	pshufb	%xmm0, %xmm2
	pshufb	%xmm1, %xmm3
	paddb	%xmm2, %xmm3
	paddb	%xmm3, %xmm4
L(e2):	lddqu	48(up), %xmm1
	add	$64, up
L(e1):	movdqa	%xmm6, %xmm0
	movdqa	%xmm7, %xmm2
	movdqa	%xmm7, %xmm3
	pand	%xmm1, %xmm0
	psrlw	$4, %xmm1
	pand	%xmm6, %xmm1
	pshufb	%xmm0, %xmm2
	pshufb	%xmm1, %xmm3
	psadbw	%xmm5, %xmm4		C sum to 8 x 16-bit counts
	paddb	%xmm2, %xmm3
	paddq	%xmm4, %xmm8		C sum to 2 x 64-bit counts
	movdqa	%xmm3, %xmm4
	sub	$8, n
	jg	L(top)

	psadbw	%xmm5, %xmm4
	paddq	%xmm4, %xmm8
	pshufd	$14, %xmm8, %xmm0
	paddq	%xmm8, %xmm0
	movq	%xmm0, %rax
	ret
EPILOGUE()
DEF_OBJECT(L(cnsts),16,`JUMPTABSECT')
	JMPENT(	L(top), L(cnsts))
	JMPENT(	L(1), L(cnsts))
	JMPENT(	L(2), L(cnsts))
	JMPENT(	L(3), L(cnsts))
	JMPENT(	L(4), L(cnsts))
	JMPENT(	L(5), L(cnsts))
	JMPENT(	L(6), L(cnsts))
	JMPENT(	L(7), L(cnsts))
	.byte	0x00,0x01,0x01,0x02,0x01,0x02,0x02,0x03
	.byte	0x01,0x02,0x02,0x03,0x02,0x03,0x03,0x04
	.byte	0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f
	.byte	0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f,0x0f
END_OBJECT(L(cnsts))
@