From ec16f935fe391fa452952b3765ad00b403aac491 Mon Sep 17 00:00:00 2001 From: Ian Romanick Date: Wed, 19 Feb 2020 12:47:21 -0800 Subject: [PATCH] nir/algebraic: Mark comparisons generated from lowered fsign precise This prevents other transformations from converting them to 'a != 0'. For example, both of these transformations can do this: (('~flt', 0.0, ('fabs', a)), ('fne', a, 0.0)), (('~flt', ('fneg', ('fabs', a)), 0.0), ('fne', a, 0.0)), Both fsign(fabs(NaN)) and fsign(fneg(fabs(NaN))) should produce zero, but, since 'NaN != 0.0' is true, cascading these transformations could cause them to generate 1.0 or -1.0 respecively. No shader-db or fossil-db changes on any Intel platform. Reviewed-by: Caio Marcelo de Oliveira Filho Part-of: --- src/compiler/nir/nir_opt_algebraic.py | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py index 1a725a74f65..142bf99f201 100644 --- a/src/compiler/nir/nir_opt_algebraic.py +++ b/src/compiler/nir/nir_opt_algebraic.py @@ -572,8 +572,9 @@ optimizations.extend([ # SignedZeroInfNanPreserve is set, but we don't currently have any way of # representing this in the optimizations other than the usual ~. (('~fmax', ('fmin', a, 0.0), -1.0), ('fneg', ('fsat', ('fneg', a))), '!options->lower_fsat'), - # fsat(fsign(NaN)) = fsat(0) = 0, and b2f(0 < NaN) = b2f(False) = 0. - (('fsat', ('fsign', a)), ('b2f', ('flt', 0.0, a))), + # fsat(fsign(NaN)) = fsat(0) = 0, and b2f(0 < NaN) = b2f(False) = 0. Mark + # the new comparison precise to prevent it being changed to 'a != 0'. + (('fsat', ('fsign', a)), ('b2f', ('!flt', 0.0, a))), (('fsat', ('b2f', a)), ('b2f', a)), (('fsat', a), ('fmin', ('fmax', a, 0.0), 1.0), 'options->lower_fsat'), (('fsat', ('fsat', a)), ('fsat', a)), @@ -1576,7 +1577,9 @@ optimizations.extend([ (('imin', ('imax', a, -1), 1), ('isign', a), '!options->lower_isign'), (('imax', ('imin', a, 1), -1), ('isign', a), '!options->lower_isign'), # float(0 < NaN) - float(NaN < 0) = float(False) - float(False) = 0 - 0 = 0 - (('fsign', a), ('fsub', ('b2f', ('flt', 0.0, a)), ('b2f', ('flt', a, 0.0))), 'options->lower_fsign'), + # Mark the new comparisons precise to prevent them being changed to 'a != + # 0' or 'a == 0'. + (('fsign', a), ('fsub', ('b2f', ('!flt', 0.0, a)), ('b2f', ('!flt', a, 0.0))), 'options->lower_fsign'), # Address/offset calculations: # Drivers supporting imul24 should use the nir_lower_amul() pass, this