nir: Fix typo in "ushr by 0" algebraic replacement

[mesa.git] / src / glsl / nir / nir_opt_algebraic.py

diff --git a/src/glsl/nir/nir_opt_algebraic.py b/src/glsl/nir/nir_opt_algebraic.py
index db2fe0372062cd4e1dc720ddf72a86272cee3ed2..cdb19241c43634cd5e071a3829363d81f27d4dbc 100644 (file)
--- a/src/glsl/nir/nir_opt_algebraic.py
+++ b/src/glsl/nir/nir_opt_algebraic.py
@@ -94,6 +94,12 @@ optimizations = [
    (('fsat', a), ('fmin', ('fmax', a, 0.0), 1.0), 'options->lower_fsat'),
    (('fsat', ('fsat', a)), ('fsat', a)),
    (('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))),
@@ -127,7 +133,7 @@ optimizations = [
    (('ishr', 0, a), 0),
    (('ishr', a, 0), a),
    (('ushr', 0, a), 0),
-   (('ushr', a, 0), 0),
+   (('ushr', a, 0), a),
    # Exponential/logarithmic identities
    (('fexp2', ('flog2', a)), a), # 2^lg2(a) = a
    (('fexp',  ('flog',  a)), a), # e^ln(a)  = a
@@ -145,6 +151,20 @@ optimizations = [
    (('frcp', ('fexp', a)), ('fexp', ('fneg', a))),
    (('frsq', ('fexp2', a)), ('fexp2', ('fmul', -0.5, a))),
    (('frsq', ('fexp', a)), ('fexp', ('fmul', -0.5, a))),
+   (('flog2', ('fsqrt', a)), ('fmul', 0.5, ('flog2', a))),
+   (('flog', ('fsqrt', a)), ('fmul', 0.5, ('flog', a))),
+   (('flog2', ('frcp', a)), ('fneg', ('flog2', a))),
+   (('flog', ('frcp', a)), ('fneg', ('flog', a))),
+   (('flog2', ('frsq', a)), ('fmul', -0.5, ('flog2', a))),
+   (('flog', ('frsq', a)), ('fmul', -0.5, ('flog', a))),
+   (('flog2', ('fpow', a, b)), ('fmul', b, ('flog2', a))),
+   (('flog', ('fpow', a, b)), ('fmul', b, ('flog', a))),
+   (('fadd', ('flog2', a), ('flog2', b)), ('flog2', ('fmul', a, b))),
+   (('fadd', ('flog', a), ('flog', b)), ('flog', ('fmul', a, b))),
+   (('fadd', ('flog2', a), ('fneg', ('flog2', b))), ('flog2', ('fdiv', a, b))),
+   (('fadd', ('flog', a), ('fneg', ('flog', b))), ('flog', ('fdiv', a, b))),
+   (('fmul', ('fexp2', a), ('fexp2', b)), ('fexp2', ('fadd', a, b))),
+   (('fmul', ('fexp', a), ('fexp', b)), ('fexp', ('fadd', a, b))),
    # Division and reciprocal
    (('fdiv', 1.0, a), ('frcp', a)),
    (('frcp', ('frcp', a)), a),
@@ -165,11 +185,15 @@ optimizations = [
    (('bcsel', a, b, b), b),
    (('fcsel', a, b, b), b),
 
+   # Conversions
+   (('f2i', ('ftrunc', a)), ('f2i', a)),
+   (('f2u', ('ftrunc', a)), ('f2u', a)),
+
    # Subtracts
    (('fsub', a, ('fsub', 0.0, b)), ('fadd', a, b)),
    (('isub', a, ('isub', 0, b)), ('iadd', a, b)),
-   (('fsub', a, b), ('fadd', a, ('fneg', b)), '!options->lower_negate'),
-   (('isub', a, b), ('iadd', a, ('ineg', b)), '!options->lower_negate'),
+   (('fsub', a, b), ('fadd', a, ('fneg', b)), 'options->lower_sub'),
+   (('isub', a, b), ('iadd', a, ('ineg', b)), 'options->lower_sub'),
    (('fneg', a), ('fsub', 0.0, a), 'options->lower_negate'),
    (('ineg', a), ('isub', 0, a), 'options->lower_negate'),
    (('fadd', a, ('fsub', 0.0, b)), ('fsub', a, b)),