dnl PowerPC-64 mpn_invert_limb -- Invert a normalized limb. dnl Copyright 2004, 2005, 2006, 2008, 2010 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 (approximate) C POWER3/PPC630 80 C POWER4/PPC970 86 C POWER5 86 C POWER6 170 C POWER7 66 ASM_START() PROLOGUE(mpn_invert_limb) LEAL( r12, approx_tab) srdi r9, r3, 32 rlwinm r9, r9, 10, 23, 30 C (d >> 55) & 0x1fe srdi r10, r3, 24 C d >> 24 lis r11, 0x1000 rldicl r8, r3, 0, 63 C d mod 2 addi r10, r10, 1 C d40 sldi r11, r11, 32 C 2^60 srdi r7, r3, 1 C d/2 add r7, r7, r8 C d63 = ceil(d/2) neg r8, r8 C mask = -(d mod 2) lhzx r0, r9, r12 mullw r9, r0, r0 C v0*v0 sldi r6, r0, 11 C v0 << 11 addi r0, r6, -1 C (v0 << 11) - 1 mulld r9, r9, r10 C v0*v0*d40 srdi r9, r9, 40 C v0*v0*d40 >> 40 subf r9, r9, r0 C v1 = (v0 << 11) - (v0*v0*d40 >> 40) - 1 mulld r0, r9, r10 C v1*d40 sldi r6, r9, 13 C v1 << 13 subf r0, r0, r11 C 2^60 - v1*d40 mulld r0, r0, r9 C v1 * (2^60 - v1*d40) srdi r0, r0, 47 C v1 * (2^60 - v1*d40) >> 47 add r0, r0, r6 C v2 = (v1 << 13) + (v1 * (2^60 - v1*d40) >> 47) mulld r11, r0, r7 C v2 * d63 srdi r10, r0, 1 C v2 >> 1 sldi r9, r0, 31 C v2 << 31 and r8, r10, r8 C (v2 >> 1) & mask subf r8, r11, r8 C ((v2 >> 1) & mask) - v2 * d63 mulhdu r0, r8, r0 C p1 = v2 * (((v2 >> 1) & mask) - v2 * d63) srdi r0, r0, 1 C p1 >> 1 add r0, r0, r9 C v3 = (v2 << 31) + (p1 >> 1) nop mulhdu r9, r0, r3 mulld r11, r0, r3 addc r10, r11, r3 adde r3, r9, r3 subf r3, r3, r0 blr EPILOGUE() DEF_OBJECT(approx_tab) .short 0x7fd,0x7f5,0x7ed,0x7e5,0x7dd,0x7d5,0x7ce,0x7c6 .short 0x7bf,0x7b7,0x7b0,0x7a8,0x7a1,0x79a,0x792,0x78b .short 0x784,0x77d,0x776,0x76f,0x768,0x761,0x75b,0x754 .short 0x74d,0x747,0x740,0x739,0x733,0x72c,0x726,0x720 .short 0x719,0x713,0x70d,0x707,0x700,0x6fa,0x6f4,0x6ee .short 0x6e8,0x6e2,0x6dc,0x6d6,0x6d1,0x6cb,0x6c5,0x6bf .short 0x6ba,0x6b4,0x6ae,0x6a9,0x6a3,0x69e,0x698,0x693 .short 0x68d,0x688,0x683,0x67d,0x678,0x673,0x66e,0x669 .short 0x664,0x65e,0x659,0x654,0x64f,0x64a,0x645,0x640 .short 0x63c,0x637,0x632,0x62d,0x628,0x624,0x61f,0x61a .short 0x616,0x611,0x60c,0x608,0x603,0x5ff,0x5fa,0x5f6 .short 0x5f1,0x5ed,0x5e9,0x5e4,0x5e0,0x5dc,0x5d7,0x5d3 .short 0x5cf,0x5cb,0x5c6,0x5c2,0x5be,0x5ba,0x5b6,0x5b2 .short 0x5ae,0x5aa,0x5a6,0x5a2,0x59e,0x59a,0x596,0x592 .short 0x58e,0x58a,0x586,0x583,0x57f,0x57b,0x577,0x574 .short 0x570,0x56c,0x568,0x565,0x561,0x55e,0x55a,0x556 .short 0x553,0x54f,0x54c,0x548,0x545,0x541,0x53e,0x53a .short 0x537,0x534,0x530,0x52d,0x52a,0x526,0x523,0x520 .short 0x51c,0x519,0x516,0x513,0x50f,0x50c,0x509,0x506 .short 0x503,0x500,0x4fc,0x4f9,0x4f6,0x4f3,0x4f0,0x4ed .short 0x4ea,0x4e7,0x4e4,0x4e1,0x4de,0x4db,0x4d8,0x4d5 .short 0x4d2,0x4cf,0x4cc,0x4ca,0x4c7,0x4c4,0x4c1,0x4be .short 0x4bb,0x4b9,0x4b6,0x4b3,0x4b0,0x4ad,0x4ab,0x4a8 .short 0x4a5,0x4a3,0x4a0,0x49d,0x49b,0x498,0x495,0x493 .short 0x490,0x48d,0x48b,0x488,0x486,0x483,0x481,0x47e .short 0x47c,0x479,0x477,0x474,0x472,0x46f,0x46d,0x46a .short 0x468,0x465,0x463,0x461,0x45e,0x45c,0x459,0x457 .short 0x455,0x452,0x450,0x44e,0x44b,0x449,0x447,0x444 .short 0x442,0x440,0x43e,0x43b,0x439,0x437,0x435,0x432 .short 0x430,0x42e,0x42c,0x42a,0x428,0x425,0x423,0x421 .short 0x41f,0x41d,0x41b,0x419,0x417,0x414,0x412,0x410 .short 0x40e,0x40c,0x40a,0x408,0x406,0x404,0x402,0x400 END_OBJECT(approx_tab) ASM_END()