github.com/aergoio/aergo@v1.3.1/libtool/src/gmp-6.1.2/mpn/x86/p6/README (about) 1 Copyright 2000, 2001 Free Software Foundation, Inc. 2 3 This file is part of the GNU MP Library. 4 5 The GNU MP Library is free software; you can redistribute it and/or modify 6 it under the terms of either: 7 8 * the GNU Lesser General Public License as published by the Free 9 Software Foundation; either version 3 of the License, or (at your 10 option) any later version. 11 12 or 13 14 * the GNU General Public License as published by the Free Software 15 Foundation; either version 2 of the License, or (at your option) any 16 later version. 17 18 or both in parallel, as here. 19 20 The GNU MP Library is distributed in the hope that it will be useful, but 21 WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY 22 or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License 23 for more details. 24 25 You should have received copies of the GNU General Public License and the 26 GNU Lesser General Public License along with the GNU MP Library. If not, 27 see https://www.gnu.org/licenses/. 28 29 30 31 32 33 INTEL P6 MPN SUBROUTINES 34 35 36 37 This directory contains code optimized for Intel P6 class CPUs, meaning 38 PentiumPro, Pentium II and Pentium III. The mmx and p3mmx subdirectories 39 have routines using MMX instructions. 40 41 42 43 STATUS 44 45 Times for the loops, with all code and data in L1 cache, are as follows. 46 Some of these might be able to be improved. 47 48 cycles/limb 49 50 mpn_add_n/sub_n 3.7 51 52 mpn_copyi 0.75 53 mpn_copyd 1.75 (or 0.75 if no overlap) 54 55 mpn_divrem_1 39.0 56 mpn_mod_1 21.5 57 mpn_divexact_by3 8.5 58 59 mpn_mul_1 5.5 60 mpn_addmul/submul_1 6.35 61 62 mpn_l/rshift 2.5 63 64 mpn_mul_basecase 8.2 cycles/crossproduct (approx) 65 mpn_sqr_basecase 4.0 cycles/crossproduct (approx) 66 or 7.75 cycles/triangleproduct (approx) 67 68 Pentium II and III have MMX and get the following improvements. 69 70 mpn_divrem_1 25.0 integer part, 17.5 fractional part 71 72 mpn_l/rshift 1.75 73 74 75 76 77 NOTES 78 79 Write-allocate L1 data cache means prefetching of destinations is unnecessary. 80 81 Mispredicted branches have a penalty of between 9 and 15 cycles, and even up 82 to 26 cycles depending how far speculative execution has gone. The 9 cycle 83 minimum penalty comes from the issue pipeline being 9 stages. 84 85 A copy with rep movs seems to copy 16 bytes at a time, since speeds for 4, 86 5, 6 or 7 limb operations are all the same. The 0.75 cycles/limb would be 3 87 cycles per 16 byte block. 88 89 90 91 92 CODING 93 94 Instructions in general code have been shown grouped if they can execute 95 together, which means up to three instructions with no successive 96 dependencies, and with only the first being a multiple micro-op. 97 98 P6 has out-of-order execution, so the groupings are really only showing 99 dependent paths where some shuffling might allow some latencies to be 100 hidden. 101 102 103 104 105 REFERENCES 106 107 "Intel Architecture Optimization Reference Manual", 1999, revision 001 dated 108 02/99, order number 245127 (order number 730795-001 is in the document too). 109 Available on-line: 110 111 http://download.intel.com/design/PentiumII/manuals/245127.htm 112 113 "Intel Architecture Optimization Manual", 1997, order number 242816. This 114 is an older document mostly about P5 and not as good as the above. 115 Available on-line: 116 117 http://download.intel.com/design/PentiumII/manuals/242816.htm 118 119 120 121 ---------------- 122 Local variables: 123 mode: text 124 fill-column: 76 125 End: