From 4d35683d91e3d61bf14b76d801bf6ae17237e162 Mon Sep 17 00:00:00 2001 From: Ian Romanick Date: Wed, 19 Oct 2016 08:53:10 -0700 Subject: [PATCH] nir: Optimize integer division and modulus with 1 The previous power-of-two rules didn't catch idiv (because i965 doesn't set lower_idiv) and imod cases. The udiv and umod cases should have been caught, but I included them for orthogonality. This fixes silly code observed from compute shaders with local_size_[xy] = 1. Signed-off-by: Ian Romanick Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=98299 Reviewed-by: Jordan Justen Reviewed-by: Jason Ekstrand --- src/compiler/nir/nir_opt_algebraic.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py index 2de8050f853..82d92f42932 100644 --- a/src/compiler/nir/nir_opt_algebraic.py +++ b/src/compiler/nir/nir_opt_algebraic.py @@ -66,6 +66,10 @@ optimizations = [ (('imul', a, '#b@32(is_pos_power_of_two)'), ('ishl', a, ('find_lsb', b))), (('imul', a, '#b@32(is_neg_power_of_two)'), ('ineg', ('ishl', a, ('find_lsb', ('iabs', b))))), + (('udiv', a, 1), a), + (('idiv', a, 1), a), + (('umod', a, 1), 0), + (('imod', a, 1), 0), (('udiv', a, '#b@32(is_pos_power_of_two)'), ('ushr', a, ('find_lsb', b))), (('idiv', a, '#b@32(is_pos_power_of_two)'), ('imul', ('isign', a), ('ushr', ('iabs', a), ('find_lsb', b))), 'options->lower_idiv'), (('idiv', a, '#b@32(is_neg_power_of_two)'), ('ineg', ('imul', ('isign', a), ('ushr', ('iabs', a), ('find_lsb', ('iabs', b))))), 'options->lower_idiv'), -- 2.30.2