fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2025-12-31 03:20:09 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

nir/algebraic: Make some notes about comparison rearrangements versus infinity

Browse source 
The original comment was a little terse and a little incorrect.  The
rearrangements are fine w.r.t. NaN.  However, they produce incorrect
results if one operand is +Inf and the other is -Inf.

A later commit, "nir/algebraic: Add some compare-with-zero optimizations
that are exact", will add some more patterns here.  It may be reasonable
to squash this commit (forward) into that commit.

v2: Fix some incorrect comparisons operators in the comment (<= vs >=).
Add commentary that subtraction works like addition w.r.t. NaN.  Both
noticed / suggested by Caio.

Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6358>
This commit is contained in:
Ian Romanick 2020-07-07 17:30:42 -07:00 • committed by Marge Bot
parent 363efc2823
commit aec0547838
1 changed files with 21 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

23
src/compiler/nir/nir_opt_algebraic.py
View file

@ -2053,8 +2053,27 @@ before_ffma_optimizations = [
# they help code generation but do not necessarily produce code that is
# more easily optimizable.
late_optimizations = [
# Most of these optimizations aren't quite safe when you get infinity or
# Nan involved but the first one should be fine.
# The rearrangements are fine w.r.t. NaN. However, they produce incorrect
# results if one operand is +Inf and the other is -Inf.
#
# 1. Inf + -Inf = NaN
# 2. ∀x: x + NaN = NaN and x - NaN = NaN
# 3. ∀x: x != NaN = true
# 4. ∀x, ∀ cmp ∈ {<, >, ≤, ≥, =}: x cmp NaN = false
#
# a=Inf, b=-Inf a=-Inf, b=Inf a=NaN b=NaN
# (a+b) < 0 false false false false
# a < -b false false false false
# -(a+b) < 0 false false false false
# -a < b false false false false
# (a+b) >= 0 false false false false
# a >= -b true true false false
# -(a+b) >= 0 false false false false
# -a >= b true true false false
# (a+b) == 0 false false false false
# a == -b true true false false
# (a+b) != 0 true true true true
# a != -b false false true true
(('flt', ('fadd', a, b), 0.0), ('flt', a, ('fneg', b))),
(('flt', ('fneg', ('fadd', a, b)), 0.0), ('flt', ('fneg', a), b)),
(('~fge', ('fadd', a, b), 0.0), ('fge', a, ('fneg', b))),