OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

nir/opt_algebraic: Add 32-bit specifiers to a bunch of booleans

Browse Source 
Reviewed-by: Connor Abbott <cwabbott0@gmail.com>
This commit is contained in:
Jason Ekstrand
2018-11-08 18:08:37 -06:00
parent 2715080d65
commit be98b1db38
1 changed files with 54 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

108
src/compiler/nir/nir_opt_algebraic.py
View File

@@ -119,17 +119,17 @@ optimizations = [
(('~flrp', a, b, 1.0), b), (('~flrp', a, b, 1.0), b),
(('~flrp', a, a, b), a), (('~flrp', a, a, b), a),
(('~flrp', 0.0, a, b), ('fmul', a, b)), (('~flrp', 0.0, a, b), ('fmul', a, b)),
(('~flrp', a, b, ('b2f', c)), ('bcsel', c, b, a), 'options->lower_flrp32'), (('~flrp', a, b, ('b2f', 'c@32')), ('bcsel', c, b, a), 'options->lower_flrp32'),
(('~flrp', a, 0.0, c), ('fadd', ('fmul', ('fneg', a), c), a)), (('~flrp', a, 0.0, c), ('fadd', ('fmul', ('fneg', a), c), a)),
(('flrp@32', a, b, c), ('fadd', ('fmul', c, ('fsub', b, a)), a), 'options->lower_flrp32'), (('flrp@32', a, b, c), ('fadd', ('fmul', c, ('fsub', b, a)), a), 'options->lower_flrp32'),
(('flrp@64', a, b, c), ('fadd', ('fmul', c, ('fsub', b, a)), a), 'options->lower_flrp64'), (('flrp@64', a, b, c), ('fadd', ('fmul', c, ('fsub', b, a)), a), 'options->lower_flrp64'),
(('ffloor', a), ('fsub', a, ('ffract', a)), 'options->lower_ffloor'), (('ffloor', a), ('fsub', a, ('ffract', a)), 'options->lower_ffloor'),
(('ffract', a), ('fsub', a, ('ffloor', a)), 'options->lower_ffract'), (('ffract', a), ('fsub', a, ('ffloor', a)), 'options->lower_ffract'),
(('fceil', a), ('fneg', ('ffloor', ('fneg', a))), 'options->lower_fceil'), (('fceil', a), ('fneg', ('ffloor', ('fneg', a))), 'options->lower_fceil'),
(('~fadd', ('fmul', a, ('fadd', 1.0, ('fneg', ('b2f', c)))), ('fmul', b, ('b2f', c))), ('bcsel', c, b, a), 'options->lower_flrp32'), (('~fadd', ('fmul', a, ('fadd', 1.0, ('fneg', ('b2f', 'c@32')))), ('fmul', b, ('b2f', c))), ('bcsel', c, b, a), 'options->lower_flrp32'),
(('~fadd@32', ('fmul', a, ('fadd', 1.0, ('fneg', c ))), ('fmul', b, c )), ('flrp', a, b, c), '!options->lower_flrp32'), (('~fadd@32', ('fmul', a, ('fadd', 1.0, ('fneg', c ))), ('fmul', b, c )), ('flrp', a, b, c), '!options->lower_flrp32'),
(('~fadd@64', ('fmul', a, ('fadd', 1.0, ('fneg', c ))), ('fmul', b, c )), ('flrp', a, b, c), '!options->lower_flrp64'), (('~fadd@64', ('fmul', a, ('fadd', 1.0, ('fneg', c ))), ('fmul', b, c )), ('flrp', a, b, c), '!options->lower_flrp64'),
(('~fadd', a, ('fmul', ('b2f', c), ('fadd', b, ('fneg', a)))), ('bcsel', c, b, a), 'options->lower_flrp32'), (('~fadd', a, ('fmul', ('b2f', 'c@32'), ('fadd', b, ('fneg', a)))), ('bcsel', c, b, a), 'options->lower_flrp32'),
(('~fadd@32', a, ('fmul', c , ('fadd', b, ('fneg', a)))), ('flrp', a, b, c), '!options->lower_flrp32'), (('~fadd@32', a, ('fmul', c , ('fadd', b, ('fneg', a)))), ('flrp', a, b, c), '!options->lower_flrp32'),
(('~fadd@64', a, ('fmul', c , ('fadd', b, ('fneg', a)))), ('flrp', a, b, c), '!options->lower_flrp64'), (('~fadd@64', a, ('fmul', c , ('fadd', b, ('fneg', a)))), ('flrp', a, b, c), '!options->lower_flrp64'),
(('ffma', a, b, c), ('fadd', ('fmul', a, b), c), 'options->lower_ffma'), (('ffma', a, b, c), ('fadd', ('fmul', a, b), c), 'options->lower_ffma'),
@@ -169,50 +169,50 @@ optimizations = [
# b2f(a) <= 0.0 # b2f(a) <= 0.0
# b2f(a) == 0.0 because b2f(a) can only be 0 or 1 # b2f(a) == 0.0 because b2f(a) can only be 0 or 1
# inot(a) # inot(a)
(('fge', 0.0, ('b2f', a)), ('inot', a)), (('fge', 0.0, ('b2f', 'a@32')), ('inot', a)),
(('fge', ('fneg', ('b2f', a)), 0.0), ('inot', a)), (('fge', ('fneg', ('b2f', 'a@32')), 0.0), ('inot', a)),
(('fne', ('fadd', ('b2f', a), ('b2f', b)), 0.0), ('ior', a, b)), (('fne', ('fadd', ('b2f', 'a@32'), ('b2f', 'b@32')), 0.0), ('ior', a, b)),
(('fne', ('fmax', ('b2f', a), ('b2f', b)), 0.0), ('ior', a, b)), (('fne', ('fmax', ('b2f', 'a@32'), ('b2f', 'b@32')), 0.0), ('ior', a, b)),
(('fne', ('bcsel', a, 1.0, ('b2f', b)) , 0.0), ('ior', a, b)), (('fne', ('bcsel', a, 1.0, ('b2f', 'b@32')) , 0.0), ('ior', a, b)),
(('fne', ('b2f', a), ('fneg', ('b2f', b))), ('ior', a, b)), (('fne', ('b2f', 'a@32'), ('fneg', ('b2f', 'b@32'))), ('ior', a, b)),
(('fne', ('fmul', ('b2f', a), ('b2f', b)), 0.0), ('iand', a, b)), (('fne', ('fmul', ('b2f', 'a@32'), ('b2f', 'b@32')), 0.0), ('iand', a, b)),
(('fne', ('fmin', ('b2f', a), ('b2f', b)), 0.0), ('iand', a, b)), (('fne', ('fmin', ('b2f', 'a@32'), ('b2f', 'b@32')), 0.0), ('iand', a, b)),
(('fne', ('bcsel', a, ('b2f', b), 0.0) , 0.0), ('iand', a, b)), (('fne', ('bcsel', a, ('b2f', 'b@32'), 0.0) , 0.0), ('iand', a, b)),
(('fne', ('fadd', ('b2f', a), ('fneg', ('b2f', b))), 0.0), ('ixor', a, b)), (('fne', ('fadd', ('b2f', 'a@32'), ('fneg', ('b2f', 'b@32'))), 0.0), ('ixor', a, b)),
(('fne', ('b2f', a) , ('b2f', b) ), ('ixor', a, b)), (('fne', ('b2f', 'a@32') , ('b2f', 'b@32') ), ('ixor', a, b)),
(('fne', ('fneg', ('b2f', a)), ('fneg', ('b2f', b))), ('ixor', a, b)), (('fne', ('fneg', ('b2f', 'a@32')), ('fneg', ('b2f', 'b@32'))), ('ixor', a, b)),
(('feq', ('fadd', ('b2f', a), ('b2f', b)), 0.0), ('inot', ('ior', a, b))), (('feq', ('fadd', ('b2f', 'a@32'), ('b2f', 'b@32')), 0.0), ('inot', ('ior', a, b))),
(('feq', ('fmax', ('b2f', a), ('b2f', b)), 0.0), ('inot', ('ior', a, b))), (('feq', ('fmax', ('b2f', 'a@32'), ('b2f', 'b@32')), 0.0), ('inot', ('ior', a, b))),
(('feq', ('bcsel', a, 1.0, ('b2f', b)) , 0.0), ('inot', ('ior', a, b))), (('feq', ('bcsel', a, 1.0, ('b2f', 'b@32')) , 0.0), ('inot', ('ior', a, b))),
(('feq', ('b2f', a), ('fneg', ('b2f', b))), ('inot', ('ior', a, b))), (('feq', ('b2f', 'a@32'), ('fneg', ('b2f', 'b@32'))), ('inot', ('ior', a, b))),
(('feq', ('fmul', ('b2f', a), ('b2f', b)), 0.0), ('inot', ('iand', a, b))), (('feq', ('fmul', ('b2f', 'a@32'), ('b2f', 'b@32')), 0.0), ('inot', ('iand', a, b))),
(('feq', ('fmin', ('b2f', a), ('b2f', b)), 0.0), ('inot', ('iand', a, b))), (('feq', ('fmin', ('b2f', 'a@32'), ('b2f', 'b@32')), 0.0), ('inot', ('iand', a, b))),
(('feq', ('bcsel', a, ('b2f', b), 0.0) , 0.0), ('inot', ('iand', a, b))), (('feq', ('bcsel', a, ('b2f', 'b@32'), 0.0) , 0.0), ('inot', ('iand', a, b))),
(('feq', ('fadd', ('b2f', a), ('fneg', ('b2f', b))), 0.0), ('ieq', a, b)), (('feq', ('fadd', ('b2f', 'a@32'), ('fneg', ('b2f', 'b@32'))), 0.0), ('ieq', a, b)),
(('feq', ('b2f', a) , ('b2f', b) ), ('ieq', a, b)), (('feq', ('b2f', 'a@32') , ('b2f', 'b@32') ), ('ieq', a, b)),
(('feq', ('fneg', ('b2f', a)), ('fneg', ('b2f', b))), ('ieq', a, b)), (('feq', ('fneg', ('b2f', 'a@32')), ('fneg', ('b2f', 'b@32'))), ('ieq', a, b)),
# -(b2f(a) + b2f(b)) < 0 # -(b2f(a) + b2f(b)) < 0
# 0 < b2f(a) + b2f(b) # 0 < b2f(a) + b2f(b)
# 0 != b2f(a) + b2f(b) b2f must be 0 or 1, so the sum is non-negative # 0 != b2f(a) + b2f(b) b2f must be 0 or 1, so the sum is non-negative
# a || b # a || b
(('flt', ('fneg', ('fadd', ('b2f', a), ('b2f', b))), 0.0), ('ior', a, b)), (('flt', ('fneg', ('fadd', ('b2f', 'a@32'), ('b2f', 'b@32'))), 0.0), ('ior', a, b)),
(('flt', 0.0, ('fadd', ('b2f', a), ('b2f', b))), ('ior', a, b)), (('flt', 0.0, ('fadd', ('b2f', 'a@32'), ('b2f', 'b@32'))), ('ior', a, b)),
# -(b2f(a) + b2f(b)) >= 0 # -(b2f(a) + b2f(b)) >= 0
# 0 >= b2f(a) + b2f(b) # 0 >= b2f(a) + b2f(b)
# 0 == b2f(a) + b2f(b) b2f must be 0 or 1, so the sum is non-negative # 0 == b2f(a) + b2f(b) b2f must be 0 or 1, so the sum is non-negative
# !(a || b) # !(a || b)
(('fge', ('fneg', ('fadd', ('b2f', a), ('b2f', b))), 0.0), ('inot', ('ior', a, b))), (('fge', ('fneg', ('fadd', ('b2f', 'a@32'), ('b2f', 'b@32'))), 0.0), ('inot', ('ior', a, b))),
(('fge', 0.0, ('fadd', ('b2f', a), ('b2f', b))), ('inot', ('ior', a, b))), (('fge', 0.0, ('fadd', ('b2f', 'a@32'), ('b2f', 'b@32'))), ('inot', ('ior', a, b))),
# Some optimizations (below) convert things like (a < b || c < b) into # Some optimizations (below) convert things like (a < b || c < b) into
# (min(a, c) < b). However, this interfers with the previous optimizations # (min(a, c) < b). However, this interfers with the previous optimizations
# that try to remove comparisons with negated sums of b2f. This just # that try to remove comparisons with negated sums of b2f. This just
# breaks that apart. # breaks that apart.
(('flt', ('fmin', c, ('fneg', ('fadd', ('b2f', a), ('b2f', b)))), 0.0), (('flt', ('fmin', c, ('fneg', ('fadd', ('b2f', 'a@32'), ('b2f', 'b@32')))), 0.0),
('ior', ('flt', c, 0.0), ('ior', a, b))), ('ior', ('flt', c, 0.0), ('ior', a, b))),
(('~flt', ('fadd', a, b), a), ('flt', b, 0.0)), (('~flt', ('fadd', a, b), a), ('flt', b, 0.0)),
@@ -234,13 +234,13 @@ optimizations = [
# The fge in the second replacement is not a typo. I leave the proof that # The fge in the second replacement is not a typo. I leave the proof that
# "fmin(-b2f(a), b) >= 0 <=> fmin(-b2f(a), b) == 0" as an exercise for the # "fmin(-b2f(a), b) >= 0 <=> fmin(-b2f(a), b) == 0" as an exercise for the
# reader. # reader.
(('fge', ('fmin', ('fneg', ('b2f', a)), b), 0.0), ('iand', ('inot', a), ('fge', b, 0.0))), (('fge', ('fmin', ('fneg', ('b2f', 'a@32')), 'b@32'), 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', ('fmin', ('fneg', ('b2f', 'a@32')), 'b@32'), 0.0), ('iand', ('inot', a), ('fge', b, 0.0))),
(('feq', ('b2f', a), 0.0), ('inot', a)), (('feq', ('b2f', 'a@32'), 0.0), ('inot', a)),
(('fne', ('b2f', a), 0.0), a), (('fne', ('b2f', 'a@32'), 0.0), a),
(('ieq', ('b2i', a), 0), ('inot', a)), (('ieq', ('b2i', 'a@32'), 0), ('inot', a)),
(('ine', ('b2i', a), 0), a), (('ine', ('b2i', 'a@32'), 0), a),
(('fne', ('u2f', a), 0.0), ('ine', a, 0)), (('fne', ('u2f', a), 0.0), ('ine', a, 0)),
(('feq', ('u2f', a), 0.0), ('ieq', a, 0)), (('feq', ('u2f', a), 0.0), ('ieq', a, 0)),
@@ -274,10 +274,10 @@ optimizations = [
# 0.0 >= fabs(a) # 0.0 >= fabs(a)
(('fge', ('fneg', ('fabs', a)), 0.0), ('feq', a, 0.0)), (('fge', ('fneg', ('fabs', a)), 0.0), ('feq', a, 0.0)),
(('fmax', ('b2f(is_used_once)', a), ('b2f', b)), ('b2f', ('ior', a, b))), (('fmax', ('b2f(is_used_once)', 'a@32'), ('b2f', 'b@32')), ('b2f', ('ior', a, b))),
(('fmax', ('fneg(is_used_once)', ('b2f(is_used_once)', a)), ('fneg', ('b2f', b))), ('fneg', ('b2f', ('ior', a, b)))), (('fmax', ('fneg(is_used_once)', ('b2f(is_used_once)', 'a@32')), ('fneg', ('b2f', 'b@32'))), ('fneg', ('b2f', ('ior', a, b)))),
(('fmin', ('b2f(is_used_once)', a), ('b2f', b)), ('b2f', ('iand', a, b))), (('fmin', ('b2f(is_used_once)', 'a@32'), ('b2f', 'b@32')), ('b2f', ('iand', a, b))),
(('fmin', ('fneg(is_used_once)', ('b2f(is_used_once)', a)), ('fneg', ('b2f', b))), ('fneg', ('b2f', ('iand', a, b)))), (('fmin', ('fneg(is_used_once)', ('b2f(is_used_once)', 'a@32')), ('fneg', ('b2f', 'b@32'))), ('fneg', ('b2f', ('iand', a, b)))),
# fmin(b2f(a), b) # fmin(b2f(a), b)
# bcsel(a, fmin(b2f(a), b), fmin(b2f(a), b)) # bcsel(a, fmin(b2f(a), b), fmin(b2f(a), b))
@@ -286,7 +286,7 @@ optimizations = [
# #
# Since b is a constant, constant folding will eliminate the fmin and the # 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. # 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))), (('fmin', ('b2f', 'a@32'), '#b'), ('bcsel', a, ('fmin', b, 1.0), ('fmin', b, 0.0))),
(('flt', ('fadd(is_used_once)', a, ('fneg', b)), 0.0), ('flt', a, b)), (('flt', ('fadd(is_used_once)', a, ('fneg', b)), 0.0), ('flt', a, b)),
@@ -435,14 +435,14 @@ optimizations = [
(('fne', ('fneg', a), a), ('fne', a, 0.0)), (('fne', ('fneg', a), a), ('fne', a, 0.0)),
(('feq', ('fneg', a), a), ('feq', a, 0.0)), (('feq', ('fneg', a), a), ('feq', a, 0.0)),
# Emulating booleans # Emulating booleans
(('imul', ('b2i', a), ('b2i', b)), ('b2i', ('iand', a, b))), (('imul', ('b2i', 'a@32'), ('b2i', 'b@32')), ('b2i', ('iand', a, b))),
(('fmul', ('b2f', a), ('b2f', b)), ('b2f', ('iand', a, b))), (('fmul', ('b2f', 'a@32'), ('b2f', 'b@32')), ('b2f', ('iand', a, b))),
(('fsat', ('fadd', ('b2f', a), ('b2f', b))), ('b2f', ('ior', a, b))), (('fsat', ('fadd', ('b2f', 'a@32'), ('b2f', 'b@32'))), ('b2f', ('ior', a, b))),
(('iand', 'a@bool', 1.0), ('b2f', a), '!options->lower_b2f'), (('iand', 'a@bool', 1.0), ('b2f', a), '!options->lower_b2f'),
# True/False are ~0 and 0 in NIR. b2i of True is 1, and -1 is ~0 (True). # True/False are ~0 and 0 in NIR. b2i of True is 1, and -1 is ~0 (True).
(('ineg', ('b2i@32', a)), a), (('ineg', ('b2i@32', 'a@32')), a),
(('flt', ('fneg', ('b2f', a)), 0), a), # Generated by TGSI KILL_IF. (('flt', ('fneg', ('b2f', 'a@32')), 0), a), # Generated by TGSI KILL_IF.
(('flt', ('fsub', 0.0, ('b2f', a)), 0), a), # Generated by TGSI KILL_IF. (('flt', ('fsub', 0.0, ('b2f', 'a@32')), 0), a), # Generated by TGSI KILL_IF.
# Comparison with the same args. Note that these are not done for # Comparison with the same args. Note that these are not done for
# the float versions because NaN always returns false on float # the float versions because NaN always returns false on float
# inequalities. # inequalities.
@@ -523,7 +523,7 @@ optimizations = [
(('bcsel@32', a, -0.0, -1.0), ('fneg', ('b2f', ('inot', a)))), (('bcsel@32', a, -0.0, -1.0), ('fneg', ('b2f', ('inot', a)))),
(('bcsel', True, b, c), b), (('bcsel', True, b, c), b),
(('bcsel', False, b, c), c), (('bcsel', False, b, c), c),
(('bcsel', a, ('b2f(is_used_once)', b), ('b2f', c)), ('b2f', ('bcsel', a, b, c))), (('bcsel', a, ('b2f(is_used_once)', 'b@32'), ('b2f', 'c@32')), ('b2f', ('bcsel', a, b, c))),
# The result of this should be hit by constant propagation and, in the # The result of this should be hit by constant propagation and, in the
# next round of opt_algebraic, get picked up by one of the above two. # next round of opt_algebraic, get picked up by one of the above two.
(('bcsel', '#a', b, c), ('bcsel', ('ine', 'a', 0), b, c)), (('bcsel', '#a', b, c), ('bcsel', ('ine', 'a', 0), b, c)),
@@ -532,7 +532,7 @@ optimizations = [
(('fcsel', a, b, b), b), (('fcsel', a, b, b), b),
# Conversions # Conversions
(('i2b', ('b2i', a)), a), (('i2b', ('b2i', 'a@32')), a),
(('i2b', 'a@bool'), a), (('i2b', 'a@bool'), a),
(('f2i', ('ftrunc', a)), ('f2i', a)), (('f2i', ('ftrunc', a)), ('f2i', a)),
(('f2u', ('ftrunc', a)), ('f2u', a)), (('f2u', ('ftrunc', a)), ('f2u', a)),
@@ -754,8 +754,8 @@ for left, right in itertools.combinations_with_replacement(invert.keys(), 2):
('ior', (invert[left], a, b), (invert[right], c, d)))) ('ior', (invert[left], a, b), (invert[right], c, d))))
# Optimize x2yN(b2x(x)) -> b2y # Optimize x2yN(b2x(x)) -> b2y
optimizations.append((('f2b', ('b2f', a)), a)) optimizations.append((('f2b', ('b2f', 'a@32')), a))
optimizations.append((('i2b', ('b2i', a)), a)) optimizations.append((('i2b', ('b2i', 'a@32')), a))
for x, y in itertools.product(['f', 'u', 'i'], ['f', 'u', 'i']): for x, y in itertools.product(['f', 'u', 'i'], ['f', 'u', 'i']):
if x != 'f' and y != 'f' and x != y: if x != 'f' and y != 'f' and x != y:
continue continue
@@ -908,15 +908,15 @@ late_optimizations = [
(('fdot4', a, b), ('fdot_replicated4', 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'), (('fdph', a, b), ('fdph_replicated', a, b), 'options->fdot_replicates'),
(('b2f(is_used_more_than_once)', ('inot', a)), ('bcsel', a, 0.0, 1.0)), (('b2f(is_used_more_than_once)', ('inot', 'a@32')), ('bcsel', a, 0.0, 1.0)),
(('fneg(is_used_more_than_once)', ('b2f', ('inot', a))), ('bcsel', a, -0.0, -1.0)), (('fneg(is_used_more_than_once)', ('b2f', ('inot', 'a@32'))), ('bcsel', a, -0.0, -1.0)),
# we do these late so that we don't get in the way of creating ffmas # we do these late so that we don't get in the way of creating ffmas
(('fmin', ('fadd(is_used_once)', '#c', a), ('fadd(is_used_once)', '#c', b)), ('fadd', c, ('fmin', a, b))), (('fmin', ('fadd(is_used_once)', '#c', a), ('fadd(is_used_once)', '#c', b)), ('fadd', c, ('fmin', a, b))),
(('fmax', ('fadd(is_used_once)', '#c', a), ('fadd(is_used_once)', '#c', b)), ('fadd', c, ('fmax', a, b))), (('fmax', ('fadd(is_used_once)', '#c', a), ('fadd(is_used_once)', '#c', b)), ('fadd', c, ('fmax', a, b))),
# Lowered for backends without a dedicated b2f instruction # Lowered for backends without a dedicated b2f instruction
(('b2f@32', a), ('iand', a, 1.0), 'options->lower_b2f'), (('b2f@32', 'a@32'), ('iand', a, 1.0), 'options->lower_b2f'),
] ]
print(nir_algebraic.AlgebraicPass("nir_opt_algebraic", optimizations).render()) print(nir_algebraic.AlgebraicPass("nir_opt_algebraic", optimizations).render())