nir/range-analysis: Range tracking for fpow

One shader from Metro Last Light and the rest from Rochard.  In the
Rochard cases, something like:

    min(1.0, max(pow(saturate(x), y), z))

was transformed to

    saturate(max(pow(saturate(x), y), z))

because the result of the pow must be >= 0.

The Metro Last Light case was similar.  An instance of

    min(pow(abs(x), y), 1.0)

became

    saturate(pow(abs(x), y))

v2: Fix some comments.  Suggested by Caio.

v3: Fix setting is_intgral when the exponent might be negative.  See
also Mesa MR !1778.

Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
All Intel platforms had similar results. (Ice Lake shown)
total instructions in shared programs: 16280670 -> 16280659 (<.01%)
instructions in affected programs: 1130 -> 1119 (-0.97%)
helped: 11
HURT: 0
helped stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
helped stats (rel) min: 0.72% max: 1.43% x̄: 1.03% x̃: 0.97%
95% mean confidence interval for instructions value: -1.00 -1.00
95% mean confidence interval for instructions %-change: -1.19% -0.86%
Instructions are helped.

total cycles in shared programs: 367168430 -> 367168270 (<.01%)
cycles in affected programs: 10281 -> 10121 (-1.56%)
helped: 10
HURT: 1
helped stats (abs) min: 16 max: 18 x̄: 17.00 x̃: 17
helped stats (rel) min: 1.31% max: 2.43% x̄: 1.79% x̃: 1.70%
HURT stats (abs)   min: 10 max: 10 x̄: 10.00 x̃: 10
HURT stats (rel)   min: 3.10% max: 3.10% x̄: 3.10% x̃: 3.10%
95% mean confidence interval for cycles value: -20.06 -9.04
95% mean confidence interval for cycles %-change: -2.36% -0.32%
Cycles are helped.

diff --git a/src/compiler/nir/nir_range_analysis.c b/src/compiler/nir/nir_range_analysis.c
index 6dfaea167ac3de1482969a05dbb5eac623388969..7fbf4217239fc11b4dfb8d1e36e934a9db5c0ccd 100644 (file)
--- a/src/compiler/nir/nir_range_analysis.c
+++ b/src/compiler/nir/nir_range_analysis.c
@@ -31,6 +31,12 @@
  * the result.
  */
 
+static bool
+is_not_negative(enum ssa_ranges r)
+{
+   return r == gt_zero || r == ge_zero || r == eq_zero;
+}
+
 static void *
 pack_data(const struct ssa_result_range r)
 {
@@ -722,6 +728,66 @@ analyze_expression(const nir_alu_instr *instr, unsigned src,
       r = (struct ssa_result_range){le_zero, false};
       break;
 
+   case nir_op_fpow: {
+      /* Due to flush-to-zero semanatics of floating-point numbers with very
+       * small mangnitudes, we can never really be sure a result will be
+       * non-zero.
+       *
+       * NIR uses pow() and powf() to constant evaluate nir_op_fpow.  The man
+       * page for that function says:
+       *
+       *    If y is 0, the result is 1.0 (even if x is a NaN).
+       *
+       * gt_zero: pow(*, eq_zero)
+       *        | pow(eq_zero, lt_zero)   # 0^-y = +inf
+       *        | pow(eq_zero, le_zero)   # 0^-y = +inf or 0^0 = 1.0
+       *        ;
+       *
+       * eq_zero: pow(eq_zero, gt_zero)
+       *        ;
+       *
+       * ge_zero: pow(gt_zero, gt_zero)
+       *        | pow(gt_zero, ge_zero)
+       *        | pow(gt_zero, lt_zero)
+       *        | pow(gt_zero, le_zero)
+       *        | pow(gt_zero, ne_zero)
+       *        | pow(gt_zero, unknown)
+       *        | pow(ge_zero, gt_zero)
+       *        | pow(ge_zero, ge_zero)
+       *        | pow(ge_zero, lt_zero)
+       *        | pow(ge_zero, le_zero)
+       *        | pow(ge_zero, ne_zero)
+       *        | pow(ge_zero, unknown)
+       *        | pow(eq_zero, ge_zero)  # 0^0 = 1.0 or 0^+y = 0.0
+       *        | pow(eq_zero, ne_zero)  # 0^-y = +inf or 0^+y = 0.0
+       *        | pow(eq_zero, unknown)  # union of all other y cases
+       *        ;
+       *
+       * All other cases are unknown.
+       *
+       * We could do better if the right operand is a constant, integral
+       * value.
+       */
+      static const enum ssa_ranges table[last_range + 1][last_range + 1] = {
+         /* left\right   unknown  lt_zero  le_zero  gt_zero  ge_zero  ne_zero  eq_zero */
+         /* unknown */ { _______, _______, _______, _______, _______, _______, gt_zero },
+         /* lt_zero */ { _______, _______, _______, _______, _______, _______, gt_zero },
+         /* le_zero */ { _______, _______, _______, _______, _______, _______, gt_zero },
+         /* gt_zero */ { ge_zero, ge_zero, ge_zero, ge_zero, ge_zero, ge_zero, gt_zero },
+         /* ge_zero */ { ge_zero, ge_zero, ge_zero, ge_zero, ge_zero, ge_zero, gt_zero },
+         /* ne_zero */ { _______, _______, _______, _______, _______, _______, gt_zero },
+         /* eq_zero */ { ge_zero, gt_zero, gt_zero, eq_zero, ge_zero, ge_zero, gt_zero },
+      };
+
+      const struct ssa_result_range left = analyze_expression(alu, 0, ht);
+      const struct ssa_result_range right = analyze_expression(alu, 1, ht);
+
+      r.is_integral = left.is_integral && right.is_integral &&
+                      is_not_negative(right.range);
+      r.range = table[left.range][right.range];
+      break;
+   }
+
    case nir_op_ffma: {
       const struct ssa_result_range first = analyze_expression(alu, 0, ht);
       const struct ssa_result_range second = analyze_expression(alu, 1, ht);