(('iabs', ('ineg', a)), ('iabs', a)),
(('fadd', a, 0.0), a),
(('iadd', a, 0), a),
+ (('usadd_4x8', a, 0), a),
+ (('usadd_4x8', a, ~0), ~0),
+ (('fadd', ('fmul', a, b), ('fmul', a, c)), ('fmul', a, ('fadd', b, c))),
+ (('iadd', ('imul', a, b), ('imul', a, c)), ('imul', a, ('iadd', b, c))),
+ (('fadd', ('fneg', a), a), 0.0),
+ (('iadd', ('ineg', a), a), 0),
+ (('iadd', ('ineg', a), ('iadd', a, b)), b),
+ (('iadd', a, ('iadd', ('ineg', a), b)), b),
+ (('fadd', ('fneg', a), ('fadd', a, b)), b),
+ (('fadd', a, ('fadd', ('fneg', a), b)), b),
(('fmul', a, 0.0), 0.0),
(('imul', a, 0), 0),
+ (('umul_unorm_4x8', a, 0), 0),
+ (('umul_unorm_4x8', a, ~0), a),
(('fmul', a, 1.0), a),
(('imul', a, 1), a),
(('fmul', a, -1.0), ('fneg', a)),
(('flrp', a, b, 1.0), b),
(('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'),
+ (('ffract', a), ('fsub', a, ('ffloor', a)), 'options->lower_ffract'),
+ (('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', ('flt', a, b)), ('fge', a, b)),
(('inot', ('fge', a, b)), ('flt', a, b)),
+ (('inot', ('feq', a, b)), ('fne', a, b)),
+ (('inot', ('fne', a, b)), ('feq', 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))),
+ (('inot', ('ieq', a, b)), ('ine', a, b)),
+ (('inot', ('ine', a, b)), ('ieq', a, 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)),
+ (('bcsel', ('inot', 'a@bool'), b, c), ('bcsel', a, c, b)),
+ (('bcsel', a, ('bcsel', a, b, c), d), ('bcsel', a, b, d)),
+ (('fmin', a, a), a),
+ (('fmax', a, a), a),
+ (('imin', a, a), a),
+ (('imax', a, a), a),
+ (('umin', a, a), a),
+ (('umax', a, a), a),
(('fmin', ('fmax', a, 0.0), 1.0), ('fsat', a), '!options->lower_fsat'),
+ (('fmax', ('fmin', a, 1.0), 0.0), ('fsat', a), '!options->lower_fsat'),
(('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', ('flt', a, c), ('flt', b, c)), ('flt', ('fmin', a, b), c)),
+ (('ior', ('fge', a, b), ('fge', a, c)), ('fge', a, ('fmin', b, c))),
+ (('ior', ('fge', a, c), ('fge', b, c)), ('fge', ('fmax', a, 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'),
+ (('fne', ('fneg', a), a), ('fne', a, 0.0)),
+ (('feq', ('fneg', a), a), ('feq', a, 0.0)),
+ # Emulating booleans
+ (('imul', ('b2i', a), ('b2i', b)), ('b2i', ('iand', a, b))),
+ (('fmul', ('b2f', a), ('b2f', b)), ('b2f', ('iand', a, b))),
+ (('fsat', ('fadd', ('b2f', a), ('b2f', b))), ('b2f', ('ior', a, b))),
+ (('iand', 'a@bool', 1.0), ('b2f', a)),
+ (('flt', ('fneg', ('b2f', a)), 0), a), # Generated by TGSI KILL_IF.
+ (('flt', ('fsub', 0.0, ('b2f', a)), 0), a), # Generated by TGSI KILL_IF.
# Comparison with the same args. Note that these are not done for
# the float versions because NaN always returns false on float
# inequalities.
# Logical and bit operations
(('fand', a, 0.0), 0.0),
(('iand', a, a), a),
+ (('iand', a, ~0), a),
(('iand', a, 0), 0),
(('ior', a, a), a),
(('ior', a, 0), a),
(('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
(('flog2', ('fexp2', a)), a), # lg2(2^a) = a
- (('flog', ('fexp', a)), a), # ln(e^a) = a
(('fpow', a, b), ('fexp2', ('fmul', ('flog2', a), b)), 'options->lower_fpow'), # a^b = 2^(lg2(a)*b)
(('fexp2', ('fmul', ('flog2', a), b)), ('fpow', a, b), '!options->lower_fpow'), # 2^(lg2(a)*b) = a^b
- (('fexp', ('fmul', ('flog', a), b)), ('fpow', a, b), '!options->lower_fpow'), # e^(ln(a)*b) = a^b
(('fpow', a, 1.0), a),
(('fpow', a, 2.0), ('fmul', a, a)),
+ (('fpow', a, 4.0), ('fmul', ('fmul', a, a), ('fmul', a, a))),
(('fpow', 2.0, a), ('fexp2', a)),
+ (('fpow', ('fpow', a, 2.2), 0.454545), a),
+ (('fpow', ('fabs', ('fpow', a, 2.2)), 0.454545), ('fabs', a)),
+ (('fsqrt', ('fexp2', a)), ('fexp2', ('fmul', 0.5, a))),
+ (('frcp', ('fexp2', a)), ('fexp2', ('fneg', a))),
+ (('frsq', ('fexp2', a)), ('fexp2', ('fmul', -0.5, a))),
+ (('flog2', ('fsqrt', a)), ('fmul', 0.5, ('flog2', a))),
+ (('flog2', ('frcp', a)), ('fneg', ('flog2', a))),
+ (('flog2', ('frsq', a)), ('fmul', -0.5, ('flog2', a))),
+ (('flog2', ('fpow', a, b)), ('fmul', b, ('flog2', a))),
+ (('fadd', ('flog2', a), ('flog2', b)), ('flog2', ('fmul', a, b))),
+ (('fadd', ('flog2', a), ('fneg', ('flog2', b))), ('flog2', ('fdiv', a, b))),
+ (('fmul', ('fexp2', a), ('fexp2', b)), ('fexp2', ('fadd', a, b))),
# Division and reciprocal
(('fdiv', 1.0, a), ('frcp', a)),
+ (('fdiv', a, b), ('fmul', a, ('frcp', b)), 'options->lower_fdiv'),
(('frcp', ('frcp', a)), a),
(('frcp', ('fsqrt', a)), ('frsq', a)),
(('fsqrt', a), ('frcp', ('frsq', a)), 'options->lower_fsqrt'),
(('frcp', ('frsq', a)), ('fsqrt', a), '!options->lower_fsqrt'),
# Boolean simplifications
- (('ine', 'a@bool', 0), 'a'),
- (('ieq', 'a@bool', 0), ('inot', 'a')),
+ (('ieq', 'a@bool', True), a),
+ (('ine', 'a@bool', True), ('inot', a)),
+ (('ine', 'a@bool', False), a),
+ (('ieq', 'a@bool', False), ('inot', 'a')),
(('bcsel', a, True, False), ('ine', a, 0)),
(('bcsel', a, False, True), ('ieq', a, 0)),
(('bcsel', True, b, c), b),
(('bcsel', a, b, b), b),
(('fcsel', a, b, b), b),
+ # Conversions
+ (('i2b', ('b2i', a)), a),
+ (('f2i', ('ftrunc', a)), ('f2i', a)),
+ (('f2u', ('ftrunc', a)), ('f2u', a)),
+
# Subtracts
- (('fsub', 0.0, ('fsub', 0.0, a)), a),
- (('isub', 0, ('isub', 0, a)), a),
+ (('fsub', a, ('fsub', 0.0, b)), ('fadd', a, b)),
+ (('isub', a, ('isub', 0, b)), ('iadd', a, b)),
+ (('ussub_4x8', a, 0), a),
+ (('ussub_4x8', a, ~0), 0),
+ (('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)),
(('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))),
+ # Misc. lowering
+ (('fmod', a, b), ('fsub', a, ('fmul', b, ('ffloor', ('fdiv', a, b)))), 'options->lower_fmod'),
+ (('uadd_carry', a, b), ('b2i', ('ult', ('iadd', a, b), a)), 'options->lower_uadd_carry'),
+ (('usub_borrow', a, b), ('b2i', ('ult', a, b)), 'options->lower_usub_borrow'),
+
+ (('bitfield_insert', 'base', 'insert', 'offset', 'bits'),
+ ('bcsel', ('ilt', 31, 'bits'), 'insert',
+ ('bfi', ('bfm', 'bits', 'offset'), 'insert', 'base')),
+ 'options->lower_bitfield_insert'),
+
+ (('ibitfield_extract', 'value', 'offset', 'bits'),
+ ('bcsel', ('ilt', 31, 'bits'), 'value',
+ ('ibfe', 'value', 'offset', 'bits')),
+ 'options->lower_bitfield_extract'),
+
+ (('ubitfield_extract', 'value', 'offset', 'bits'),
+ ('bcsel', ('ult', 31, 'bits'), 'value',
+ ('ubfe', 'value', 'offset', 'bits')),
+ 'options->lower_bitfield_extract'),
]
# 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))),
+ (('fdot2', a, b), ('fdot_replicated2', a, b), 'options->fdot_replicates'),
+ (('fdot3', a, b), ('fdot_replicated3', a, b), 'options->fdot_replicates'),
+ (('fdot4', a, b), ('fdot_replicated4', a, b), 'options->fdot_replicates'),
+ (('fdph', a, b), ('fdph_replicated', a, b), 'options->fdot_replicates'),
+]
+
print nir_algebraic.AlgebraicPass("nir_opt_algebraic", optimizations).render()
+print nir_algebraic.AlgebraicPass("nir_opt_algebraic_late",
+ late_optimizations).render()