nir/algebraic: Push unary operations into source operands of fsat source

Pushing a unary operation, like fneg, into the operation that generates
its operand allows the fsat to be applied to the inner instruction
instead of on a separate instruction that performs the unary operation.
This changes

    fmul	ssa_100, ssa_99, ssa_98
    fmov.sat	ssa_101, -ssa_100

into

    fmul.sat	ssa_100, -ssa_99, ssa_98

Ice Lake, Skylake, and Broadwell had similar results. (Ice Lake shown)
total instructions in shared programs: 17228658 -> 17228584 (<.01%)
instructions in affected programs: 3163 -> 3089 (-2.34%)
helped: 49
HURT: 0
helped stats (abs) min: 1 max: 2 x̄: 1.51 x̃: 2
helped stats (rel) min: 0.58% max: 9.09% x̄: 3.69% x̃: 3.51%
95% mean confidence interval for instructions value: -1.66 -1.37
95% mean confidence interval for instructions %-change: -4.37% -3.00%
Instructions are helped.

total cycles in shared programs: 360937144 -> 360936431 (<.01%)
cycles in affected programs: 24029 -> 23316 (-2.97%)
helped: 47
HURT: 2
helped stats (abs) min: 4 max: 18 x̄: 15.34 x̃: 16
helped stats (rel) min: 0.69% max: 6.18% x̄: 3.78% x̃: 4.27%
HURT stats (abs)   min: 4 max: 4 x̄: 4.00 x̃: 4
HURT stats (rel)   min: 0.34% max: 0.67% x̄: 0.50% x̃: 0.50%
95% mean confidence interval for cycles value: -16.05 -13.05
95% mean confidence interval for cycles %-change: -4.07% -3.15%
Cycles are helped.

All Gen7 and earlier platforms had similar results. (Haswell shown)
total instructions in shared programs: 13536059 -> 13535884 (<.01%)
instructions in affected programs: 8797 -> 8622 (-1.99%)
helped: 150
HURT: 0
helped stats (abs) min: 1 max: 2 x̄: 1.17 x̃: 1
helped stats (rel) min: 0.40% max: 11.11% x̄: 3.51% x̃: 1.96%
95% mean confidence interval for instructions value: -1.23 -1.11
95% mean confidence interval for instructions %-change: -3.97% -3.05%
Instructions are helped.

total cycles in shared programs: 357696119 -> 357694193 (<.01%)
cycles in affected programs: 50216 -> 48290 (-3.84%)
helped: 109
HURT: 14
helped stats (abs) min: 2 max: 92 x̄: 18.97 x̃: 16
helped stats (rel) min: 0.26% max: 19.09% x̄: 7.37% x̃: 5.37%
HURT stats (abs)   min: 2 max: 26 x̄: 10.14 x̃: 5
HURT stats (rel)   min: 0.18% max: 4.73% x̄: 1.84% x̃: 0.92%
95% mean confidence interval for cycles value: -19.27 -12.05
95% mean confidence interval for cycles %-change: -7.34% -5.31%
Cycles are helped.

Reviewed-by: Matt Turner <mattst88@gmail.com>

diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py
index bdf432b..c488b2c 100644 (file)
--- a/src/compiler/nir/nir_opt_algebraic.py
+++ b/src/compiler/nir/nir_opt_algebraic.py
@@ -375,6 +375,9 @@ optimizations = [
    (('fsat', ('b2f', a)), ('b2f', a)),
    (('fsat', a), ('fmin', ('fmax', a, 0.0), 1.0), 'options->lower_fsat'),
    (('fsat', ('fsat', a)), ('fsat', a)),
+   (('fsat', ('fneg(is_used_once)', ('fadd(is_used_once)', a, b))), ('fsat', ('fadd', ('fneg', a), ('fneg', b))), '!options->lower_negate && !options->lower_fsat'),
+   (('fsat', ('fneg(is_used_once)', ('fmul(is_used_once)', a, b))), ('fsat', ('fmul', ('fneg', a), b)), '!options->lower_negate && !options->lower_fsat'),
+   (('fsat', ('fabs(is_used_once)', ('fmul(is_used_once)', a, b))), ('fsat', ('fmul', ('fabs', a), ('fabs', b))), '!options->lower_fsat'),
    (('fmin', ('fmax', ('fmin', ('fmax', a, b), c), b), c), ('fmin', ('fmax', a, b), c)),
    (('imin', ('imax', ('imin', ('imax', a, b), c), b), c), ('imin', ('imax', a, b), c)),
    (('umin', ('umax', ('umin', ('umax', a, b), c), b), c), ('umin', ('umax', a, b), c)),
@@ -698,7 +701,7 @@ optimizations.extend([
    (('iabs', ('isub', 0, a)), ('iabs', a)),
 
    # Propagate negation up multiplication chains
-   (('fmul', ('fneg', a), b), ('fneg', ('fmul', a, b))),
+   (('fmul(is_used_by_non_fsat)', ('fneg', a), b), ('fneg', ('fmul', a, b))),
    (('imul', ('ineg', a), b), ('ineg', ('imul', a, b))),
 
    # Propagate constants up multiplication chains

diff --git a/src/compiler/nir/nir_search_helpers.h b/src/compiler/nir/nir_search_helpers.h
index 1624508..91d638a 100644 (file)
--- a/src/compiler/nir/nir_search_helpers.h
+++ b/src/compiler/nir/nir_search_helpers.h
@@ -193,4 +193,23 @@ is_not_used_by_if(nir_alu_instr *instr)
    return list_empty(&instr->dest.dest.ssa.if_uses);
 }
 
+static inline bool
+is_used_by_non_fsat(nir_alu_instr *instr)
+{
+   nir_foreach_use(src, &instr->dest.dest.ssa) {
+      const nir_instr *const user_instr = src->parent_instr;
+
+      if (user_instr->type != nir_instr_type_alu)
+         return true;
+
+      const nir_alu_instr *const user_alu = nir_instr_as_alu(user_instr);
+
+      assert(instr != user_alu);
+      if (user_alu->op != nir_op_fsat)
+         return true;
+   }
+
+   return false;
+}
+
 #endif /* _NIR_SEARCH_ */