nir/algebraic: Reassociate fadd into fmul in DPH-like pattern

Moving the add to the other end of the sequence allows it to be fused
into an FMA.

Ice Lake
total instructions in shared programs: 17173074 -> 16933147 (-1.40%)
instructions in affected programs: 7938745 -> 7698818 (-3.02%)
helped: 35583
HURT: 90
helped stats (abs) min: 1 max: 716 x̄: 6.75 x̃: 6
helped stats (rel) min: 0.10% max: 53.04% x̄: 5.29% x̃: 3.45%
HURT stats (abs)   min: 1 max: 41 x̄: 2.46 x̃: 1
HURT stats (rel)   min: 0.32% max: 8.33% x̄: 1.41% x̃: 0.77%
95% mean confidence interval for instructions value: -6.80 -6.65
95% mean confidence interval for instructions %-change: -5.32% -5.22%
Instructions are helped.

total cycles in shared programs: 360881386 -> 359533568 (-0.37%)
cycles in affected programs: 189489144 -> 188141326 (-0.71%)
helped: 27250
HURT: 6707
helped stats (abs) min: 1 max: 21997 x̄: 62.15 x̃: 16
helped stats (rel) min: <.01% max: 70.69% x̄: 4.04% x̃: 2.35%
HURT stats (abs)   min: 1 max: 3507 x̄: 51.56 x̃: 14
HURT stats (rel)   min: <.01% max: 77.26% x̄: 2.72% x̃: 1.27%
95% mean confidence interval for cycles value: -44.70 -34.68
95% mean confidence interval for cycles %-change: -2.75% -2.65%
Cycles are helped.

total spills in shared programs: 8943 -> 8829 (-1.27%)
spills in affected programs: 625 -> 511 (-18.24%)
helped: 6
HURT: 3

total fills in shared programs: 21815 -> 21719 (-0.44%)
fills in affected programs: 1653 -> 1557 (-5.81%)
helped: 7
HURT: 10

LOST:   11
GAINED: 3

Skylake and Broadwell had similar results. (Skylake shown)
total instructions in shared programs: 15271996 -> 15040882 (-1.51%)
instructions in affected programs: 7193699 -> 6962585 (-3.21%)
helped: 33985
HURT: 30
helped stats (abs) min: 1 max: 260 x̄: 6.80 x̃: 6
helped stats (rel) min: 0.10% max: 30.00% x̄: 5.54% x̃: 3.85%
HURT stats (abs)   min: 1 max: 41 x̄: 4.00 x̃: 3
HURT stats (rel)   min: 0.20% max: 2.16% x̄: 1.46% x̃: 1.72%
95% mean confidence interval for instructions value: -6.87 -6.72
95% mean confidence interval for instructions %-change: -5.59% -5.48%
Instructions are helped.

total cycles in shared programs: 355520785 -> 354253799 (-0.36%)
cycles in affected programs: 185869148 -> 184602162 (-0.68%)
helped: 25824
HURT: 6287
helped stats (abs) min: 1 max: 21997 x̄: 61.66 x̃: 16
helped stats (rel) min: <.01% max: 42.05% x̄: 4.18% x̃: 2.41%
HURT stats (abs)   min: 1 max: 3327 x̄: 51.76 x̃: 14
HURT stats (rel)   min: <.01% max: 101.62% x̄: 2.80% x̃: 1.28%
95% mean confidence interval for cycles value: -44.70 -34.21
95% mean confidence interval for cycles %-change: -2.87% -2.76%
Cycles are helped.

total spills in shared programs: 8835 -> 8818 (-0.19%)
spills in affected programs: 613 -> 596 (-2.77%)
helped: 5
HURT: 2

total fills in shared programs: 21738 -> 21744 (0.03%)
fills in affected programs: 1348 -> 1354 (0.45%)
helped: 5
HURT: 11

LOST:   0
GAINED: 12

Haswell
total instructions in shared programs: 13447102 -> 13381508 (-0.49%)
instructions in affected programs: 3770735 -> 3705141 (-1.74%)
helped: 11999
HURT: 29
helped stats (abs) min: 1 max: 409 x̄: 5.60 x̃: 3
helped stats (rel) min: 0.10% max: 20.00% x̄: 2.38% x̃: 1.87%
HURT stats (abs)   min: 3 max: 750 x̄: 54.90 x̃: 3
HURT stats (rel)   min: 0.12% max: 125.30% x̄: 9.96% x̃: 1.82%
95% mean confidence interval for instructions value: -5.71 -5.19
95% mean confidence interval for instructions %-change: -2.39% -2.30%
Instructions are helped.

total cycles in shared programs: 376342236 -> 375690458 (-0.17%)
cycles in affected programs: 155699021 -> 155047243 (-0.42%)
helped: 8397
HURT: 2876
helped stats (abs) min: 1 max: 20248 x̄: 109.87 x̃: 18
helped stats (rel) min: <.01% max: 40.71% x̄: 2.23% x̃: 1.49%
HURT stats (abs)   min: 1 max: 15414 x̄: 94.15 x̃: 22
HURT stats (rel)   min: <.01% max: 432.49% x̄: 3.15% x̃: 1.41%
95% mean confidence interval for cycles value: -67.64 -48.00
95% mean confidence interval for cycles %-change: -0.99% -0.74%
Cycles are helped.

total spills in shared programs: 23134 -> 23184 (0.22%)
spills in affected programs: 1675 -> 1725 (2.99%)
helped: 13
HURT: 11

total fills in shared programs: 34550 -> 34686 (0.39%)
fills in affected programs: 1421 -> 1557 (9.57%)
helped: 13
HURT: 11

LOST:   0
GAINED: 11

Ivy Bridge
total instructions in shared programs: 12019642 -> 11987285 (-0.27%)
instructions in affected programs: 1532236 -> 1499879 (-2.11%)
helped: 5522
HURT: 110
helped stats (abs) min: 1 max: 312 x̄: 6.22 x̃: 3
helped stats (rel) min: 0.16% max: 20.00% x̄: 2.46% x̃: 1.88%
HURT stats (abs)   min: 1 max: 750 x̄: 18.07 x̃: 3
HURT stats (rel)   min: 0.09% max: 125.30% x̄: 3.42% x̃: 1.15%
95% mean confidence interval for instructions value: -6.25 -5.24
95% mean confidence interval for instructions %-change: -2.43% -2.26%
Instructions are helped.

total cycles in shared programs: 180214667 -> 179761900 (-0.25%)
cycles in affected programs: 31448723 -> 30995956 (-1.44%)
helped: 7191
HURT: 2838
helped stats (abs) min: 1 max: 17680 x̄: 88.47 x̃: 17
helped stats (rel) min: <.01% max: 50.45% x̄: 2.16% x̃: 1.40%
HURT stats (abs)   min: 1 max: 15540 x̄: 64.63 x̃: 24
HURT stats (rel)   min: 0.02% max: 435.17% x̄: 3.10% x̃: 1.51%
95% mean confidence interval for cycles value: -53.34 -36.95
95% mean confidence interval for cycles %-change: -0.81% -0.53%
Cycles are helped.

total spills in shared programs: 3599 -> 3642 (1.19%)
spills in affected programs: 1180 -> 1223 (3.64%)
helped: 12
HURT: 2

total fills in shared programs: 4031 -> 4162 (3.25%)
fills in affected programs: 876 -> 1007 (14.95%)
helped: 12
HURT: 2

LOST:   6
GAINED: 5

Sandy Bridge
total instructions in shared programs: 10850686 -> 10822890 (-0.26%)
instructions in affected programs: 1247986 -> 1220190 (-2.23%)
helped: 4699
HURT: 102
helped stats (abs) min: 1 max: 104 x̄: 6.02 x̃: 3
helped stats (rel) min: 0.15% max: 17.65% x̄: 2.44% x̃: 1.88%
HURT stats (abs)   min: 1 max: 16 x̄: 4.70 x̃: 3
HURT stats (rel)   min: 0.09% max: 3.85% x̄: 1.11% x̃: 1.10%
95% mean confidence interval for instructions value: -6.10 -5.47
95% mean confidence interval for instructions %-change: -2.42% -2.30%
Instructions are helped.

total cycles in shared programs: 154044149 -> 153920095 (-0.08%)
cycles in affected programs: 26037392 -> 25913338 (-0.48%)
helped: 5974
HURT: 2521
helped stats (abs) min: 1 max: 1802 x̄: 35.42 x̃: 16
helped stats (rel) min: <.01% max: 35.80% x̄: 1.43% x̃: 0.84%
HURT stats (abs)   min: 1 max: 862 x̄: 34.73 x̃: 20
HURT stats (rel)   min: 0.01% max: 36.33% x̄: 1.67% x̃: 0.85%
95% mean confidence interval for cycles value: -16.31 -12.90
95% mean confidence interval for cycles %-change: -0.56% -0.45%
Cycles are helped.

total spills in shared programs: 2876 -> 2957 (2.82%)
spills in affected programs: 592 -> 673 (13.68%)
helped: 6
HURT: 35

total fills in shared programs: 3157 -> 3134 (-0.73%)
fills in affected programs: 402 -> 379 (-5.72%)
helped: 6
HURT: 0

LOST:   5
GAINED: 11

Reviewed-by: Matt Turner <[email protected]>

2 files changed, 36 insertions, 0 deletions

diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py
index fa940429281..09eaeaf3f23 100644
--- a/src/compiler/nir/nir_opt_algebraic.py
+++ b/src/compiler/nir/nir_opt_algebraic.py
@@ -1250,6 +1250,18 @@ late_optimizations = [
    (('fmax', ('fadd(is_used_once)', '#c', a), ('fadd(is_used_once)', '#c', b)), ('fadd', c, ('fmax', a, b))),
 
    (('bcsel', a, 0, ('b2f32', ('inot', 'b@bool'))), ('b2f32', ('inot', ('ior', a, b)))),
+
+   # Things that look like DPH in the source shader may get expanded to
+   # something that looks like dot(v1.xyz, v2.xyz) + v1.w by the time it gets
+   # to NIR.  After FFMA is generated, this can look like:
+   #
+   #    fadd(ffma(v1.z, v2.z, ffma(v1.y, v2.y, fmul(v1.x, v2.x))), v1.w)
+   #
+   # Reassociate the last addition into the first multiplication.
+   (('~fadd', ('ffma(is_used_once)', a, b, ('ffma', c, d, ('fmul', 'e(is_not_const_and_not_fsign)', 'f(is_not_const_and_not_fsign)'))), 'g(is_not_const)'),
+    ('ffma', a, b, ('ffma', c, d, ('ffma', e, 'f', 'g'))), '!options->intel_vec4'),
+   (('~fadd', ('ffma(is_used_once)', a, b,                ('fmul', 'e(is_not_const_and_not_fsign)', 'f(is_not_const_and_not_fsign)') ), 'g(is_not_const)'),
+    ('ffma', a, b,                ('ffma', e, 'f', 'g') ), '!options->intel_vec4'),
 ]
 
 print(nir_algebraic.AlgebraicPass("nir_opt_algebraic", optimizations).render())
diff --git a/src/compiler/nir/nir_search_helpers.h b/src/compiler/nir/nir_search_helpers.h
index 658ed2b1d5b..7c19cd3fdfe 100644
--- a/src/compiler/nir/nir_search_helpers.h
+++ b/src/compiler/nir/nir_search_helpers.h
@@ -190,6 +190,30 @@ is_not_fmul(nir_alu_instr *instr, unsigned src,
 }
 
 static inline bool
+is_fsign(nir_alu_instr *instr, unsigned src,
+         UNUSED unsigned num_components, UNUSED const uint8_t *swizzle)
+{
+   nir_alu_instr *src_alu =
+      nir_src_as_alu_instr(instr->src[src].src);
+
+   if (src_alu == NULL)
+      return false;
+
+   if (src_alu->op == nir_op_fneg)
+      src_alu = nir_src_as_alu_instr(src_alu->src[0].src);
+
+   return src_alu->op == nir_op_fsign;
+}
+
+static inline bool
+is_not_const_and_not_fsign(nir_alu_instr *instr, unsigned src,
+                           unsigned num_components, const uint8_t *swizzle)
+{
+   return is_not_const(instr, src, num_components, swizzle) &&
+          !is_fsign(instr, src, num_components, swizzle);
+}
+
+static inline bool
 is_used_once(nir_alu_instr *instr)
 {
    bool zero_if_use = list_empty(&instr->dest.dest.ssa.if_uses);