src/mesa/drivers/dri/i965/brw_nir_trig_workarounds.py

   1 #
   2 # Copyright (C) 2016 Intel Corporation
   3 #
   4 # Permission is hereby granted, free of charge, to any person obtaining a
   5 # copy of this software and associated documentation files (the "Software"),
   6 # to deal in the Software without restriction, including without limitation
   7 # the rights to use, copy, modify, merge, publish, distribute, sublicense,
   8 # and/or sell copies of the Software, and to permit persons to whom the
   9 # Software is furnished to do so, subject to the following conditions:
  10 #
  11 # The above copyright notice and this permission notice (including the next
  12 # paragraph) shall be included in all copies or substantial portions of the
  13 # Software.
  14 #
  15 # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  16 # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  17 # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
  18 # THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  19 # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
  20 # FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
  21 # IN THE SOFTWARE.
  22
  23 import nir_algebraic
  24
  25 # Prior to Kaby Lake, The SIN and COS instructions on Intel hardware can
  26 # produce values slightly outside of the [-1.0, 1.0] range for a small set of
  27 # values.  Obviously, this can break everyone's expectations about trig
  28 # functions.  This appears to be fixed in Kaby Lake.
  29 #
  30 # According to an internal presentation, the COS instruction can produce
  31 # a value up to 1.000027 for inputs in the range (0.08296, 0.09888).  One
  32 # suggested workaround is to multiply by 0.99997, scaling down the
  33 # amplitude slightly.  Apparently this also minimizes the error function,
  34 # reducing the maximum error from 0.00006 to about 0.00003.
  35
  36 trig_workarounds = [
  37    (('fsin', 'x'), ('fmul', ('fsin', 'x'), 0.99997)),
  38    (('fcos', 'x'), ('fmul', ('fcos', 'x'), 0.99997)),
  39 ]
  40
  41 print '#include "brw_nir.h"'
  42 print nir_algebraic.AlgebraicPass("brw_nir_apply_trig_workarounds",
  43                                   trig_workarounds).render()