"Fossies" - the Fresh Open Source Software Archive

Member "gmp-6.2.1/mpn/sparc32/README" (14 Nov 2020, 2586 Bytes) of package /linux/misc/gmp-6.2.1.tar.xz:


As a special service "Fossies" has tried to format the requested text file into HTML format (style: standard) with prefixed line numbers. Alternatively you can here view or download the uninterpreted source code file.

    1 Copyright 1996, 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 This directory contains mpn functions for various SPARC chips.  Code that
   34 runs only on version 8 SPARC implementations, is in the v8 subdirectory.
   35 
   36 RELEVANT OPTIMIZATION ISSUES
   37 
   38   Load and Store timing
   39 
   40 On most early SPARC implementations, the ST instructions takes multiple
   41 cycles, while a STD takes just a single cycle more than an ST.  For the CPUs
   42 in SPARCstation I and II, the times are 3 and 4 cycles, respectively.
   43 Therefore, combining two ST instructions into a STD when possible is a
   44 significant optimization.
   45 
   46 Later SPARC implementations have single cycle ST.
   47 
   48 For SuperSPARC, we can perform just one memory instruction per cycle, even
   49 if up to two integer instructions can be executed in its pipeline.  For
   50 programs that perform so many memory operations that there are not enough
   51 non-memory operations to issue in parallel with all memory operations, using
   52 LDD and STD when possible helps.
   53 
   54 UltraSPARC-1/2 has very slow integer multiplication.  In the v9 subdirectory,
   55 we therefore use floating-point multiplication.
   56 
   57 STATUS
   58 
   59 1. On a SuperSPARC, mpn_lshift and mpn_rshift run at 3 cycles/limb, or 2.5
   60    cycles/limb asymptotically.  We could optimize speed for special counts
   61    by using ADDXCC.
   62 
   63 2. On a SuperSPARC, mpn_add_n and mpn_sub_n runs at 2.5 cycles/limb, or 2
   64    cycles/limb asymptotically.
   65 
   66 3. mpn_mul_1 runs at what is believed to be optimal speed.
   67 
   68 4. On SuperSPARC, mpn_addmul_1 and mpn_submul_1 could both be improved by a
   69    cycle by avoiding one of the add instructions.  See a29k/addmul_1.
   70 
   71 The speed of the code for other SPARC implementations is uncertain.