diff options
| author | Rob Clark <robclark@freedesktop.org> | 2015-03-31 11:25:19 -0400 |
|---|---|---|
| committer | Rob Clark <robclark@freedesktop.org> | 2015-04-05 08:56:24 -0400 |
| commit | 6829d76e0285f9ed8091990b908d2e7dc37c5218 (patch) | |
| tree | f41184ad8f9bd67fcb26719be4601779f5a97130 /src/glsl | |
| parent | 24b78fe54e1498dc3f66cb616561894039806642 (diff) | |
| download | external_mesa3d-6829d76e0285f9ed8091990b908d2e7dc37c5218.zip external_mesa3d-6829d76e0285f9ed8091990b908d2e7dc37c5218.tar.gz external_mesa3d-6829d76e0285f9ed8091990b908d2e7dc37c5218.tar.bz2 | |
nir: add option to lower slt/sge/seq/sne
In freedreno these get implemented as the matching f* instruction plus a
u2f to convert the result to float 1.0/0.0. But less lines of code to
just let nir_opt_algebraic handle this for us, plus opens up some small
window for other opt passes to improve (ie. if some shader ended up with
both a flt and slt with same src args, for example).
v2: use b2f rather than u2f
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Diffstat (limited to 'src/glsl')
| -rw-r--r-- | src/glsl/nir/nir.h | 3 | ||||
| -rw-r--r-- | src/glsl/nir/nir_opt_algebraic.py | 4 |
2 files changed, 7 insertions, 0 deletions
diff --git a/src/glsl/nir/nir.h b/src/glsl/nir/nir.h index 199ecc0..167e3be 100644 --- a/src/glsl/nir/nir.h +++ b/src/glsl/nir/nir.h @@ -1382,6 +1382,9 @@ typedef struct nir_shader_compiler_options { /** lowers fneg and ineg to fsub and isub. */ bool lower_negate; + /* lower {slt,sge,seq,sne} to {flt,fge,feq,fne} + b2f: */ + bool lower_scmp; + /** * Does the driver support real 32-bit integers? (Otherwise, integers * are simulated by floats.) diff --git a/src/glsl/nir/nir_opt_algebraic.py b/src/glsl/nir/nir_opt_algebraic.py index 60d1160..a8c1745 100644 --- a/src/glsl/nir/nir_opt_algebraic.py +++ b/src/glsl/nir/nir_opt_algebraic.py @@ -96,6 +96,10 @@ optimizations = [ (('fmin', ('fmax', ('fmin', ('fmax', a, 0.0), 1.0), 0.0), 1.0), ('fmin', ('fmax', a, 0.0), 1.0)), (('ior', ('flt', a, b), ('flt', a, c)), ('flt', a, ('fmax', b, c))), (('ior', ('fge', a, b), ('fge', a, c)), ('fge', a, ('fmin', b, c))), + (('slt', a, b), ('b2f', ('flt', a, b)), 'options->lower_scmp'), + (('sge', a, b), ('b2f', ('fge', a, b)), 'options->lower_scmp'), + (('seq', a, b), ('b2f', ('feq', a, b)), 'options->lower_scmp'), + (('sne', a, b), ('b2f', ('fne', a, b)), 'options->lower_scmp'), # Emulating booleans (('fmul', ('b2f', a), ('b2f', b)), ('b2f', ('iand', a, b))), (('fsat', ('fadd', ('b2f', a), ('b2f', b))), ('b2f', ('ior', a, b))), |