source/libs/gmp/gmp-src/mpn/x86_64/aorrlshC_n.asm

   1 dnl  AMD64 mpn_addlshC_n -- rp[] = up[] + (vp[] << C)
   2 dnl  AMD64 mpn_rsblshC_n -- rp[] = (vp[] << C) - up[]
   3
   4 dnl  Copyright 2009-2012 Free Software Foundation, Inc.
   5
   6 dnl  This file is part of the GNU MP Library.
   7 dnl
   8 dnl  The GNU MP Library is free software; you can redistribute it and/or modify
   9 dnl  it under the terms of either:
  10 dnl
  11 dnl    * the GNU Lesser General Public License as published by the Free
  12 dnl      Software Foundation; either version 3 of the License, or (at your
  13 dnl      option) any later version.
  14 dnl
  15 dnl  or
  16 dnl
  17 dnl    * the GNU General Public License as published by the Free Software
  18 dnl      Foundation; either version 2 of the License, or (at your option) any
  19 dnl      later version.
  20 dnl
  21 dnl  or both in parallel, as here.
  22 dnl
  23 dnl  The GNU MP Library is distributed in the hope that it will be useful, but
  24 dnl  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
  25 dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
  26 dnl  for more details.
  27 dnl
  28 dnl  You should have received copies of the GNU General Public License and the
  29 dnl  GNU Lesser General Public License along with the GNU MP Library.  If not,
  30 dnl  see https://www.gnu.org/licenses/.
  31
  32
  33 C            cycles/limb
  34 C AMD K8,K9      2
  35 C AMD K10        2
  36 C Intel P4       ?
  37 C Intel core2    3
  38 C Intel NHM      2.75
  39 C Intel SBR      2.55
  40 C Intel atom     ?
  41 C VIA nano       ?
  42
  43 C INPUT PARAMETERS
  44 define(`rp',    `%rdi')
  45 define(`up',    `%rsi')
  46 define(`vp',    `%rdx')
  47 define(`n',     `%rcx')
  48
  49 define(M, eval(m4_lshift(1,LSH)))
  50
  51 ABI_SUPPORT(DOS64)
  52 ABI_SUPPORT(STD64)
  53
  54 ASM_START()
  55         TEXT
  56         ALIGN(16)
  57 PROLOGUE(func)
  58         FUNC_ENTRY(4)
  59         push    %r12
  60         push    %r13
  61         push    %r14
  62         push    %r15
  63
  64         mov     (vp), %r8
  65         lea     (,%r8,M), %r12
  66         shr     $RSH, %r8
  67
  68         mov     R32(n), R32(%rax)
  69         lea     (rp,n,8), rp
  70         lea     (up,n,8), up
  71         lea     (vp,n,8), vp
  72         neg     n
  73         and     $3, R8(%rax)
  74         je      L(b00)
  75         cmp     $2, R8(%rax)
  76         jc      L(b01)
  77         je      L(b10)
  78
  79 L(b11): mov     8(vp,n,8), %r10
  80         lea     (%r8,%r10,M), %r14
  81         shr     $RSH, %r10
  82         mov     16(vp,n,8), %r11
  83         lea     (%r10,%r11,M), %r15
  84         shr     $RSH, %r11
  85         ADDSUB  (up,n,8), %r12
  86         ADCSBB  8(up,n,8), %r14
  87         ADCSBB  16(up,n,8), %r15
  88         sbb     R32(%rax), R32(%rax)              C save carry for next
  89         mov     %r12, (rp,n,8)
  90         mov     %r14, 8(rp,n,8)
  91         mov     %r15, 16(rp,n,8)
  92         add     $3, n
  93         js      L(top)
  94         jmp     L(end)
  95
  96 L(b01): mov     %r8, %r11
  97         ADDSUB  (up,n,8), %r12
  98         sbb     R32(%rax), R32(%rax)              C save carry for next
  99         mov     %r12, (rp,n,8)
 100         add     $1, n
 101         js      L(top)
 102         jmp     L(end)
 103
 104 L(b10): mov     8(vp,n,8), %r11
 105         lea     (%r8,%r11,M), %r15
 106         shr     $RSH, %r11
 107         ADDSUB  (up,n,8), %r12
 108         ADCSBB  8(up,n,8), %r15
 109         sbb     R32(%rax), R32(%rax)              C save carry for next
 110         mov     %r12, (rp,n,8)
 111         mov     %r15, 8(rp,n,8)
 112         add     $2, n
 113         js      L(top)
 114         jmp     L(end)
 115
 116 L(b00): mov     8(vp,n,8), %r9
 117         mov     16(vp,n,8), %r10
 118         jmp     L(e00)
 119
 120         ALIGN(16)
 121 L(top): mov     16(vp,n,8), %r10
 122         mov     (vp,n,8), %r8
 123         mov     8(vp,n,8), %r9
 124         lea     (%r11,%r8,M), %r12
 125         shr     $RSH, %r8
 126 L(e00): lea     (%r8,%r9,M), %r13
 127         shr     $RSH, %r9
 128         mov     24(vp,n,8), %r11
 129         lea     (%r9,%r10,M), %r14
 130         shr     $RSH, %r10
 131         lea     (%r10,%r11,M), %r15
 132         shr     $RSH, %r11
 133         add     R32(%rax), R32(%rax)              C restore carry
 134         ADCSBB  (up,n,8), %r12
 135         ADCSBB  8(up,n,8), %r13
 136         ADCSBB  16(up,n,8), %r14
 137         ADCSBB  24(up,n,8), %r15
 138         mov     %r12, (rp,n,8)
 139         mov     %r13, 8(rp,n,8)
 140         mov     %r14, 16(rp,n,8)
 141         sbb     R32(%rax), R32(%rax)              C save carry for next
 142         mov     %r15, 24(rp,n,8)
 143         add     $4, n
 144         js      L(top)
 145 L(end):
 146
 147 ifelse(ADDSUB,add,`
 148         sub     R32(%r11), R32(%rax)
 149         neg     R32(%rax)
 150 ',`
 151         add     R32(%r11), R32(%rax)
 152         movslq  R32(%rax), %rax
 153 ')
 154         pop     %r15
 155         pop     %r14
 156         pop     %r13
 157         pop     %r12
 158         FUNC_EXIT()
 159         ret
 160 EPILOGUE()