radv: UseEnumerateInstanceVersion for the default version.

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

diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py
index d94536439c8fb1cd7620fc4d7c4a313b56ccc6f5..96232f0e549c5707b5c4072ac4464cff5cc676be 100644 (file)
--- a/src/compiler/nir/nir_opt_algebraic.py
+++ b/src/compiler/nir/nir_opt_algebraic.py
@@ -24,6 +24,7 @@
 #    Jason Ekstrand (jason@jlekstrand.net)
 
 import nir_algebraic
+import itertools
 
 # Convenience variables
 a = 'a'
@@ -124,6 +125,14 @@ optimizations = [
    (('ffma', a, b, c), ('fadd', ('fmul', a, b), c), 'options->lower_ffma'),
    (('~fadd', ('fmul', a, b), c), ('ffma', a, b, c), 'options->fuse_ffma'),
 
+   (('fdot4', ('vec4', a, b,   c,   1.0), d), ('fdph',  ('vec3', a, b, c), d)),
+   (('fdot4', ('vec4', a, 0.0, 0.0, 0.0), b), ('fmul', a, b)),
+   (('fdot4', ('vec4', a, b,   0.0, 0.0), c), ('fdot2', ('vec2', a, b), c)),
+   (('fdot4', ('vec4', a, b,   c,   0.0), d), ('fdot3', ('vec3', a, b, c), d)),
+
+   (('fdot3', ('vec3', a, 0.0, 0.0), b), ('fmul', a, b)),
+   (('fdot3', ('vec3', a, b,   0.0), c), ('fdot2', ('vec2', a, b), c)),
+
    # (a * #b + #c) << #d
    # ((a * #b) << #d) + (#c << #d)
    # (a * (#b << #d)) + (#c << #d)
@@ -152,6 +161,15 @@ optimizations = [
 
    (('fge', ('fneg', ('b2f', a)), 0.0), ('inot', a)),
 
+   (('~flt', ('fadd', a, b), a), ('flt', b, 0.0)),
+   (('~fge', ('fadd', a, b), a), ('fge', b, 0.0)),
+   (('~feq', ('fadd', a, b), a), ('feq', b, 0.0)),
+   (('~fne', ('fadd', a, b), a), ('fne', b, 0.0)),
+
+   # Cannot remove the addition from ilt or ige due to overflow.
+   (('ieq', ('iadd', a, b), a), ('ieq', b, 0)),
+   (('ine', ('iadd', a, b), a), ('ine', b, 0)),
+
    # fmin(-b2f(a), b) >= 0.0
    # -b2f(a) >= 0.0 && b >= 0.0
    # -b2f(a) == 0.0 && b >= 0.0    -b2f can only be 0 or -1, never >0
@@ -165,6 +183,11 @@ optimizations = [
    (('fge', ('fmin', ('fneg', ('b2f', a)), b), 0.0), ('iand', ('inot', a), ('fge', b, 0.0))),
    (('feq', ('fmin', ('fneg', ('b2f', a)), b), 0.0), ('iand', ('inot', a), ('fge', b, 0.0))),
 
+   (('feq', ('b2f', a), 0.0), ('inot', a)),
+   (('fne', ('b2f', a), 0.0), a),
+   (('ieq', ('b2i', a), 0),   ('inot', a)),
+   (('ine', ('b2i', a), 0),   a),
+
    # 0.0 < fabs(a)
    # fabs(a) > 0.0
    # fabs(a) != 0.0 because fabs(a) must be >= 0
@@ -176,9 +199,16 @@ optimizations = [
    (('fmin',                        ('b2f(is_used_once)', a),           ('b2f', b)),           ('b2f', ('iand', a, b))),
    (('fmin', ('fneg(is_used_once)', ('b2f(is_used_once)', a)), ('fneg', ('b2f', b))), ('fneg', ('b2f', ('iand', a, b)))),
 
-   # ignore this opt when the result is used by a bcsel or if so we can make
-   # use of conditional modifiers on supported hardware.
-   (('flt(is_not_used_by_conditional)', ('fadd(is_used_once)', a, ('fneg', b)), 0.0), ('flt', a, b)),
+   # fmin(b2f(a), b)
+   # bcsel(a, fmin(b2f(a), b), fmin(b2f(a), b))
+   # bcsel(a, fmin(b2f(True), b), fmin(b2f(False), b))
+   # bcsel(a, fmin(1.0, b), fmin(0.0, b))
+   #
+   # Since b is a constant, constant folding will eliminate the fmin and the
+   # fmax.  If b is > 1.0, the bcsel will be replaced with a b2f.
+   (('fmin', ('b2f', a), '#b'), ('bcsel', a, ('fmin', b, 1.0), ('fmin', b, 0.0))),
+
+   (('flt', ('fadd(is_used_once)', a, ('fneg', b)), 0.0), ('flt', a, b)),
 
    (('fge', ('fneg', ('fabs', a)), 0.0), ('feq', a, 0.0)),
    (('~bcsel', ('flt', b, a), b, a), ('fmin', a, b)),
@@ -382,6 +412,7 @@ optimizations = [
 
    # Conversions
    (('i2b', ('b2i', a)), a),
+   (('i2b', 'a@bool'), a),
    (('f2i32', ('ftrunc', a)), ('f2i32', a)),
    (('f2u32', ('ftrunc', a)), ('f2u32', a)),
    (('i2b', ('ineg', a)), ('i2b', a)),
@@ -536,6 +567,14 @@ optimizations = [
      'options->lower_unpack_snorm_4x8'),
 ]
 
+invert = {'feq': 'fne', 'fne': 'feq', 'fge': 'flt', 'flt': 'fge' }
+
+for left, right in list(itertools.combinations(invert.keys(), 2)) + zip(invert.keys(), invert.keys()):
+   optimizations.append((('inot', ('ior(is_used_once)', (left, a, b), (right, c, d))),
+                         ('iand', (invert[left], a, b), (invert[right], c, d))))
+   optimizations.append((('inot', ('iand(is_used_once)', (left, a, b), (right, c, d))),
+                         ('ior', (invert[left], a, b), (invert[right], c, d))))
+
 def fexp2i(exp, bits):
    # We assume that exp is already in the right range.
    if bits == 32: