diff options
| author | Ian Romanick <[email protected]> | 2019-08-26 13:28:09 -0700 |
|---|---|---|
| committer | Ian Romanick <[email protected]> | 2019-08-28 11:38:51 -0700 |
| commit | d3fd1c761aab01e06665180ab86c9528c0b285b2 (patch) | |
| tree | 34eadbae076c5d8ed511434ee40f007778b9d0dd | |
| parent | 4662b70d23c2eed9b891e9694d956a1a2a37ab70 (diff) | |
nir/algrbraic: Don't optimize open-coded bitfield reverse when lowering is enabled
This caused a problem on Sandybridge where an open-coded
bitfieldReverse() function could be optimized to a
nir_op_bitfield_reverse that would generate an unsupported BFREV
instruction in the backend. This was encountered in some Unreal4 tech
demos in shader-db. The bug was not previously noticed because we don't
actually try to run those demos on Sandybridge.
The fixes tag is a bit a lie. The actual bug was introduced about
26,000 commits earlier in 371c4b3c48f ("nir: Recognize open-coded
bitfield_reverse."). Without the NIR lowering pass, the flag needed to
avoid the optimization does not exist. Hopefully nobody will care to
fix this on an earlier Mesa release.
Reviewed-by: Matt Turner <[email protected]>
Fixes: 7afa26d4e39 ("nir: Add lowering for nir_op_bitfield_reverse.")
| -rw-r--r-- | src/compiler/nir/nir_opt_algebraic.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py index beb7f7978f9..6f0a4393524 100644 --- a/src/compiler/nir/nir_opt_algebraic.py +++ b/src/compiler/nir/nir_opt_algebraic.py @@ -1319,7 +1319,7 @@ def bitfield_reverse(u): return step5 -optimizations += [(bitfield_reverse('x@32'), ('bitfield_reverse', 'x'))] +optimizations += [(bitfield_reverse('x@32'), ('bitfield_reverse', 'x'), '!options->lower_bitfield_reverse')] # For any float comparison operation, "cmp", if you have "a == a && a cmp b" # then the "a == a" is redundant because it's equivalent to "a is not NaN" |