popcount.asm revision 1.1.1.2
1dnl PowerPC-64 mpn_popcount. 2 3dnl Copyright 2012 Free Software Foundation, Inc. 4 5dnl This file is part of the GNU MP Library. 6dnl 7dnl The GNU MP Library is free software; you can redistribute it and/or modify 8dnl it under the terms of either: 9dnl 10dnl * the GNU Lesser General Public License as published by the Free 11dnl Software Foundation; either version 3 of the License, or (at your 12dnl option) any later version. 13dnl 14dnl or 15dnl 16dnl * the GNU General Public License as published by the Free Software 17dnl Foundation; either version 2 of the License, or (at your option) any 18dnl later version. 19dnl 20dnl or both in parallel, as here. 21dnl 22dnl The GNU MP Library is distributed in the hope that it will be useful, but 23dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY 24dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License 25dnl for more details. 26dnl 27dnl You should have received copies of the GNU General Public License and the 28dnl GNU Lesser General Public License along with the GNU MP Library. If not, 29dnl see https://www.gnu.org/licenses/. 30 31include(`../config.m4') 32 33C cycles/limb 34C POWER3/PPC630 - 35C POWER4/PPC970 - 36C POWER5 - 37C POWER6 - 38C POWER7 2 39 40define(`up', r3) 41define(`n', r4) 42 43ASM_START() 44PROLOGUE(mpn_popcount) 45 addi r0, n, 1 46ifdef(`HAVE_ABI_mode32', 47` rldicl r0, r0, 63,33', C ...branch count 48` srdi r0, r0, 1') C ...for ctr 49 mtctr r0 50 51 andi. r0, n, 1 52 53 li r0, 0 54 li r12, 0 55 beq L(evn) 56 57L(odd): ld r4, 0(up) 58 addi up, up, 8 59 popcntd r0, r4 60 bdz L(e1) 61 62L(evn): ld r4, 0(up) 63 ld r5, 8(up) 64 popcntd r8, r4 65 popcntd r9, r5 66 bdz L(e2) 67 68 ld r4, 16(up) 69 ld r5, 24(up) 70 bdz L(e4) 71 addi up, up, 32 72 73L(top): add r0, r0, r8 74 popcntd r8, r4 75 ld r4, 0(up) 76 add r12, r12, r9 77 popcntd r9, r5 78 ld r5, 8(up) 79 addi up, up, 16 80 bdnz L(top) 81 82L(e4): add r0, r0, r8 83 popcntd r8, r4 84 add r12, r12, r9 85 popcntd r9, r5 86L(e2): add r0, r0, r8 87 add r12, r12, r9 88L(e1): add r3, r0, r12 89 blr 90EPILOGUE() 91