github.com/aergoio/aergo@v1.3.1/libtool/src/gmp-6.1.2/mpn/pa64/README (about) 1 Copyright 1999, 2001, 2002, 2004 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 This directory contains mpn functions for 64-bit PA-RISC 2.0. 33 34 PIPELINE SUMMARY 35 36 The PA8x00 processors have an orthogonal 4-way out-of-order pipeline. Each 37 cycle two ALU operations and two MEM operations can issue, but just one of the 38 MEM operations may be a store. The two ALU operations can be almost any 39 combination of non-memory operations. Unlike every other processor, integer 40 and fp operations are completely equal here; they both count as just ALU 41 operations. 42 43 Unfortunately, some operations cause hickups in the pipeline. Combining 44 carry-consuming operations like ADD,DC with operations that does not set carry 45 like ADD,L cause long delays. Skip operations also seem to cause hickups. If 46 several ADD,DC are issued consecutively, or if plain carry-generating ADD feed 47 ADD,DC, stalling does not occur. We can effectively issue two ADD,DC 48 operations/cycle. 49 50 Latency scheduling is not as important as making sure to have a mix of ALU and 51 MEM operations, but for full pipeline utilization, it is still a good idea to 52 do some amount of latency scheduling. 53 54 Like for all other processors, RAW memory scheduling is critically important. 55 Since integer multiplication takes place in the floating-point unit, the GMP 56 code needs to handle this problem frequently. 57 58 STATUS 59 60 * mpn_lshift and mpn_rshift run at 1.5 cycles/limb on PA8000 and at 1.0 61 cycles/limb on PA8500. With latency scheduling, the numbers could 62 probably be improved to 1.0 cycles/limb for all PA8x00 chips. 63 64 * mpn_add_n and mpn_sub_n run at 2.0 cycles/limb on PA8000 and at about 65 1.6875 cycles/limb on PA8500. With latency scheduling, this could 66 probably be improved to get close to 1.5 cycles/limb. A problem is the 67 stalling of carry-inputting instructions after instructions that do not 68 write to carry. 69 70 * mpn_mul_1, mpn_addmul_1, and mpn_submul_1 run at between 5.625 and 6.375 71 on PA8500 and later, and about a cycle/limb slower on older chips. The 72 code uses ADD,DC for adjacent limbs, and relies heavily on reordering. 73 74 75 REFERENCES 76 77 Hewlett Packard, "64-Bit Runtime Architecture for PA-RISC 2.0", version 3.3, 78 October 1997.