From cceb50e14ed653518c67f84f4d86886a7a237025 Mon Sep 17 00:00:00 2001
From: Ian Romanick <ian.d.romanick@intel.com>
Date: Tue, 19 Jul 2016 17:47:38 -0700
Subject: nir/algebraic: Optimize common array indexing sequence

Some shaders include code that looks like:

   uniform int i;
   uniform vec4 bones[...];

   foo(bones[i * 3], bones[i * 3 + 1], bones[i * 3 + 2]);

CSE would do some work on this:

   x = i * 3
   foo(bones[x], bones[x + 1], bones[x + 2]);

The compiler may then add '<< 4 + base' to the index calculations.
This results in expressions like

   x = i * 3
   foo(bones[x << 4], bones[(x + 1) << 4], bones[(x + 2) << 4]);

Just rearranging the math to produce (i * 48) + 16 saves an
instruction, and it allows CSE to do more work.

   x = i * 48;
   foo(bones[x], bones[x + 16], bones[x + 32]);

So, ~6 instructions becomes ~3.

Some individual shader-db results look pretty bad.  However, I have a
really, really hard time believing the change in estimated cycles in,
for example, 3dmmes-taiji/51.shader_test after looking that change in
the generated code.

G45
total instructions in shared programs: 4020840 -> 4010070 (-0.27%)
instructions in affected programs: 177460 -> 166690 (-6.07%)
helped: 894
HURT: 0

total cycles in shared programs: 98829000 -> 98784990 (-0.04%)
cycles in affected programs: 3936648 -> 3892638 (-1.12%)
helped: 894
HURT: 0

Ironlake
total instructions in shared programs: 6418887 -> 6408117 (-0.17%)
instructions in affected programs: 177460 -> 166690 (-6.07%)
helped: 894
HURT: 0

total cycles in shared programs: 143504542 -> 143460532 (-0.03%)
cycles in affected programs: 3936648 -> 3892638 (-1.12%)
helped: 894
HURT: 0

Sandy Bridge
total instructions in shared programs: 8357887 -> 8339251 (-0.22%)
instructions in affected programs: 432715 -> 414079 (-4.31%)
helped: 2795
HURT: 0

total cycles in shared programs: 118284184 -> 118207412 (-0.06%)
cycles in affected programs: 6114626 -> 6037854 (-1.26%)
helped: 2478
HURT: 317

Ivy Bridge
total instructions in shared programs: 7669390 -> 7653822 (-0.20%)
instructions in affected programs: 388234 -> 372666 (-4.01%)
helped: 2795
HURT: 0

total cycles in shared programs: 68381982 -> 68263684 (-0.17%)
cycles in affected programs: 1972658 -> 1854360 (-6.00%)
helped: 2458
HURT: 307

Haswell
total instructions in shared programs: 7082636 -> 7067068 (-0.22%)
instructions in affected programs: 388234 -> 372666 (-4.01%)
helped: 2795
HURT: 0

total cycles in shared programs: 68282020 -> 68164158 (-0.17%)
cycles in affected programs: 1891820 -> 1773958 (-6.23%)
helped: 2459
HURT: 261

Broadwell
total instructions in shared programs: 9002466 -> 8985875 (-0.18%)
instructions in affected programs: 658784 -> 642193 (-2.52%)
helped: 2795
HURT: 5

total cycles in shared programs: 78503092 -> 78450404 (-0.07%)
cycles in affected programs: 2873304 -> 2820616 (-1.83%)
helped: 2275
HURT: 415

Skylake
total instructions in shared programs: 9156978 -> 9140387 (-0.18%)
instructions in affected programs: 682625 -> 666034 (-2.43%)
helped: 2795
HURT: 5

total cycles in shared programs: 75591392 -> 75550574 (-0.05%)
cycles in affected programs: 3192120 -> 3151302 (-1.28%)
helped: 2271
HURT: 425

Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Thomas Helland <thomashelland90@gmail.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
---
 src/compiler/nir/nir_opt_algebraic.py | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'src/compiler/nir')

diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py
index 0f0896be5df..37cb700d6ac 100644
--- a/src/compiler/nir/nir_opt_algebraic.py
+++ b/src/compiler/nir/nir_opt_algebraic.py
@@ -119,6 +119,17 @@ optimizations = [
    (('~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'),
    (('~fadd', ('fmul', a, b), c), ('ffma', a, b, c), 'options->fuse_ffma'),
+
+   # (a * #b + #c) << #d
+   # ((a * #b) << #d) + (#c << #d)
+   # (a * (#b << #d)) + (#c << #d)
+   (('ishl', ('iadd', ('imul', a, '#b'), '#c'), '#d'),
+    ('iadd', ('imul', a, ('ishl', b, d)), ('ishl', c, d))),
+
+   # (a * #b) << #c
+   # a * (#b << #c)
+   (('ishl', ('imul', a, '#b'), '#c'), ('imul', a, ('ishl', b, c))),
+
    # Comparison simplifications
    (('~inot', ('flt', a, b)), ('fge', a, b)),
    (('~inot', ('fge', a, b)), ('flt', a, b)),
-- 
cgit v1.2.3