(('flrp', a, a, b), a),
(('flrp', 0.0, a, b), ('fmul', a, b)),
(('flrp', a, b, c), ('fadd', ('fmul', c, ('fsub', b, a)), a), 'options->lower_flrp'),
+ (('fadd', ('fmul', a, ('fadd', 1.0, ('fneg', c))), ('fmul', b, c)), ('flrp', a, b, c), '!options->lower_flrp'),
+ (('fadd', a, ('fmul', c, ('fadd', b, ('fneg', a)))), ('flrp', a, b, c), '!options->lower_flrp'),
(('ffma', a, b, c), ('fadd', ('fmul', a, b), c), 'options->lower_ffma'),
(('fadd', ('fmul', a, b), c), ('ffma', a, b, c), '!options->lower_ffma'),
# Comparison simplifications
(('inot', ('fge', a, b)), ('flt', a, b)),
(('inot', ('ilt', a, b)), ('ige', a, b)),
(('inot', ('ige', a, b)), ('ilt', a, b)),
- (('flt', ('fadd', a, b), 0.0), ('flt', a, ('fneg', b))),
- (('fge', ('fadd', a, b), 0.0), ('fge', a, ('fneg', b))),
- (('feq', ('fadd', a, b), 0.0), ('feq', a, ('fneg', b))),
- (('fne', ('fadd', a, b), 0.0), ('fne', a, ('fneg', b))),
(('fge', ('fneg', ('fabs', a)), 0.0), ('feq', a, 0.0)),
(('bcsel', ('flt', a, b), a, b), ('fmin', a, b)),
(('bcsel', ('flt', a, b), b, a), ('fmax', a, b)),
(('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))),
# Emulating booleans
(('fmul', ('b2f', a), ('b2f', b)), ('b2f', ('iand', a, b))),
(('fsat', ('fadd', ('b2f', a), ('b2f', b))), ('b2f', ('ior', a, b))),
(('fpow', a, 1.0), a),
(('fpow', a, 2.0), ('fmul', a, a)),
(('fpow', 2.0, a), ('fexp2', a)),
+ (('fsqrt', ('fexp2', a)), ('fexp2', ('fmul', 0.5, a))),
+ (('fsqrt', ('fexp', a)), ('fexp', ('fmul', 0.5, a))),
+ (('frcp', ('fexp2', a)), ('fexp2', ('fneg', a))),
+ (('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),
(('iadd', a, ('isub', 0, b)), ('isub', a, b)),
(('fabs', ('fsub', 0.0, a)), ('fabs', a)),
(('iabs', ('isub', 0, a)), ('iabs', a)),
-
-# This one may not be exact
- (('feq', ('fadd', a, b), 0.0), ('feq', a, ('fneg', b))),
]
# Add optimizations to handle the case where the result of a ternary is
('bcsel', 'a', (op, 'd', 'b'), (op, 'd', 'c'))),
]
+# This section contains "late" optimizations that should be run after the
+# regular optimizations have finished. Optimizations should go here if
+# they help code generation but do not necessarily produce code that is
+# more easily optimizable.
+late_optimizations = [
+ (('flt', ('fadd', a, b), 0.0), ('flt', a, ('fneg', b))),
+ (('fge', ('fadd', a, b), 0.0), ('fge', a, ('fneg', b))),
+ (('feq', ('fadd', a, b), 0.0), ('feq', a, ('fneg', b))),
+ (('fne', ('fadd', a, b), 0.0), ('fne', a, ('fneg', b))),
+]
+
print nir_algebraic.AlgebraicPass("nir_opt_algebraic", optimizations).render()
+print nir_algebraic.AlgebraicPass("nir_opt_algebraic_late",
+ late_optimizations).render()