diff options
| author | Jason Ekstrand <[email protected]> | 2016-06-18 12:30:36 -0700 |
|---|---|---|
| committer | Jason Ekstrand <[email protected]> | 2016-06-20 11:56:57 -0700 |
| commit | 68e308d85355079ad93bd4e16cba164784740fdf (patch) | |
| tree | 5be5ae4f25860f67920f373f58cfabbb46cb08c4 /src/compiler/nir | |
| parent | 895f7ddfb5c1c24d3f8269e73fc09458eddc4fdd (diff) | |
nir/algebraic: Remove imprecise flog2 optimizations
While mathematically correct, these two optimizations result in an
expression with substantially lower precision than the original. For any
positive finite floating-point value, log2(x) is well-defined and finite.
More precisely, it is in the range [-150, 150] so any sum of logarithms
log2(a) + log2(b) is also well-defined and finite as long as a and b are
both positive and finite. However, if a and b are either very small or
very large, their product may get flushed to infinity or zero causing
log2(a * b) to be nowhere close to log2(a) + log2(b).
This imprecision was causing incorrect rendering in Talos Principal because
part of its HDR rendering process involves doing 8 texture operations,
clamping the result to [0, 65000], taking a dot-product with a constant,
and then taking the log2. This is done 6 or 8 times and summed to produce
the final result which is written to a red texture. In cases where you
have a region of the screen that is very dark, it can end up getting a
result value of -inf which is not what is intended.
Signed-off-by: Jason Ekstrand <[email protected]>
Reviewed-by: Matt Turner <[email protected]>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=96425
Cc: "11.1 11.2 12.0" <[email protected]>
Diffstat (limited to 'src/compiler/nir')
| -rw-r--r-- | src/compiler/nir/nir_opt_algebraic.py | 2 |
1 files changed, 0 insertions, 2 deletions
diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py index 011263a14d7..fd228017c54 100644 --- a/src/compiler/nir/nir_opt_algebraic.py +++ b/src/compiler/nir/nir_opt_algebraic.py @@ -233,8 +233,6 @@ optimizations = [ (('~flog2', ('frcp', a)), ('fneg', ('flog2', a))), (('~flog2', ('frsq', a)), ('fmul', -0.5, ('flog2', a))), (('~flog2', ('fpow', a, b)), ('fmul', b, ('flog2', a))), - (('~fadd', ('flog2', a), ('flog2', b)), ('flog2', ('fmul', a, b))), - (('~fadd', ('flog2', a), ('fneg', ('flog2', b))), ('flog2', ('fdiv', a, b))), (('~fmul', ('fexp2', a), ('fexp2', b)), ('fexp2', ('fadd', a, b))), # Division and reciprocal (('~fdiv', 1.0, a), ('frcp', a)), |