nir/algebraic: Add some optimizations for D3D-style Booleans

D3D Booleans use a 32-bit 0/-1 representation.  Because this previously
matched NIR exactly, we didn't have to really optimize for it.  Now that
we have 1-bit Booleans, we need some specific optimizations to chew
through the D3D12-style Booleans.

Shader-db results on Kaby Lake:

    total instructions in shared programs: 15136811 -> 14967944 (-1.12%)
    instructions in affected programs: 2457021 -> 2288154 (-6.87%)
    helped: 8318
    HURT: 10

    total cycles in shared programs: 373544524 -> 359701825 (-3.71%)
    cycles in affected programs: 151029683 -> 137186984 (-9.17%)
    helped: 7749
    HURT: 682

    total loops in shared programs: 4431 -> 4399 (-0.72%)
    loops in affected programs: 32 -> 0
    helped: 21
    HURT: 0

    total spills in shared programs: 10290 -> 10051 (-2.32%)
    spills in affected programs: 2532 -> 2293 (-9.44%)
    helped: 18
    HURT: 18

    total fills in shared programs: 22203 -> 21732 (-2.12%)
    fills in affected programs: 3319 -> 2848 (-14.19%)
    helped: 18
    HURT: 18

Note that a large chunk of the improvement fixing regressions caused by
switching to 1-bit Booleans.  Previously, our ability to optimize D3D
booleans was improved by using the D3D representation directly in NIR.
Now that NIR does 1-bit bools, we need a few more optimizations.

Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Eric Anholt <eric@anholt.net>
Tested-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>

diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py
index 3c8af4692b5157a0c07cbdb215ec9a1226e4499c..506d45e55b5423e8212aa29bb96976b7352a8046 100644 (file)
--- a/src/compiler/nir/nir_opt_algebraic.py
+++ b/src/compiler/nir/nir_opt_algebraic.py
@@ -534,6 +534,19 @@ optimizations = [
    (('bcsel', a, b, b), b),
    (('fcsel', a, b, b), b),
 
+   # D3D Boolean emulation
+   (('bcsel', a, -1, 0), ('ineg', ('b2i', 'a@1'))),
+   (('bcsel', a, 0, -1), ('ineg', ('b2i', ('inot', a)))),
+   (('iand', ('ineg', ('b2i', 'a@1')), ('ineg', ('b2i', 'b@1'))),
+    ('ineg', ('b2i', ('iand', a, b)))),
+   (('ior', ('ineg', ('b2i','a@1')), ('ineg', ('b2i', 'b@1'))),
+    ('ineg', ('b2i', ('ior', a, b)))),
+   (('ieq', ('ineg', ('b2i', 'a@1')), 0), ('inot', a)),
+   (('ieq', ('ineg', ('b2i', 'a@1')), -1), a),
+   (('ine', ('ineg', ('b2i', 'a@1')), 0), a),
+   (('ine', ('ineg', ('b2i', 'a@1')), -1), ('inot', a)),
+   (('iand', ('ineg', ('b2i', a)), '1.0@32'), ('b2f', a)),
+
    # Conversions
    (('i2b32', ('b2i', 'a@32')), a),
    (('f2i', ('ftrunc', a)), ('f2i', a)),