Merge branch 'perf/true-peak-early-out'

src/dsp/limiter.rs

@@ -9,7 +9,7 @@
 //! Detection is stereo-linked (one gain for all channels). This stage limits **sample** peaks at
 //! the base rate; true-peak (inter-sample) limiting via oversampling is a later addition.
 
-use super::oversampler::Oversampler;
+use super::oversampler::{self, Oversampler};
 
 const MAX_CHANNELS: usize = 2;
 /// Fixed look-ahead — also this stage's constant latency contribution.
@@ -121,6 +121,10 @@ pub struct Limiter {
     margin_gain: f32,
     /// 4× interpolator for true-peak (inter-sample) detection.
     oversampler: Oversampler,
+    /// Sliding max of the sample peak over the interpolator's FIR support, which bounds what
+    /// its next evaluation can possibly return. Lets `process` skip the evaluation entirely
+    /// when that bound is already under the ceiling.
+    support_max: SlidingMax,
 }
 
 impl Default for Limiter {
@@ -135,6 +139,7 @@ impl Default for Limiter {
             attack_coef: 0.0,
             margin_gain: 1.0,
             oversampler: Oversampler::new(),
+            support_max: SlidingMax::new(),
         }
     }
 }
@@ -153,6 +158,7 @@ impl Limiter {
         let channels = num_channels.clamp(1, MAX_CHANNELS);
         self.delay = vec![vec![0.0; self.capacity]; channels];
         self.sliding_max.prepare(self.capacity);
+        self.support_max.prepare(oversampler::SUPPORT_LEN);
         self.oversampler.prepare(channels);
         self.reset();
     }
@@ -162,6 +168,7 @@ impl Limiter {
             ch.iter_mut().for_each(|s| *s = 0.0);
         }
         self.sliding_max.reset();
+        self.support_max.reset();
         self.oversampler.reset();
         self.write_pos = 0;
         self.gain = 1.0;
@@ -190,11 +197,28 @@ impl Limiter {
         for &x in &input[..n] {
             sample_peak = sample_peak.max(x.abs());
         }
-        let peak = sample_peak.max(self.oversampler.max_true_peak(&input[..n]));
 
         // Target a hair below the ceiling so the (slightly under-read) true peak stays under it.
         let target_ceiling = ceiling * self.margin_gain;
 
+        // The polyphase evaluation is ~PHASES*TAPS multiply-adds per channel and runs on every
+        // sample, which makes it the most expensive single thing in the chain. It is also
+        // skippable: the interpolator is linear, so over its FIR support
+        //     |true peak| <= peak_gain * max|history|
+        // and when that bound sits under the ceiling the true peak provably cannot reach it.
+        // The limiter's target would be 1.0 for this sample either way, so feeding the sample
+        // peak instead cannot change the outcome - `sliding_max` still sees any genuinely loud
+        // neighbour through that neighbour's own evaluation.
+        //
+        // The history must still be fed on every sample, or later evaluations read holes.
+        self.oversampler.push(&input[..n]);
+        let support_max = self.support_max.push(sample_peak);
+        let peak = if support_max * self.oversampler.peak_gain() <= target_ceiling {
+            sample_peak
+        } else {
+            sample_peak.max(self.oversampler.evaluate(n))
+        };
+
         // Write into the ring.
         for ch in 0..n {
             self.delay[ch][self.write_pos] = input[ch];

src/dsp/oversampler.rs

@@ -17,6 +17,9 @@
 
 const PHASES: usize = 4;
 const TAPS_PER_PHASE: usize = 12;
+/// Length of the FIR support, i.e. how many past input frames an evaluation reads. A caller
+/// bounding the true peak needs the max over exactly this many frames.
+pub const SUPPORT_LEN: usize = TAPS_PER_PHASE;
 const MAX_CHANNELS: usize = 2;
 
 /// Build the normalised polyphase coefficients: a windowed-sinc prototype split into `PHASES`
@@ -53,17 +56,32 @@ fn build_coefficients() -> [[f32; TAPS_PER_PHASE]; PHASES] {
     coeffs
 }
 
+/// Largest L1 norm across phases: `max_phase sum |c|`. Bounds the interpolator's output for a
+/// bounded input, which is what makes the [`Oversampler::peak_gain`] early-out sound.
+fn build_peak_gain(coeffs: &[[f32; TAPS_PER_PHASE]; PHASES]) -> f32 {
+    coeffs
+        .iter()
+        .map(|row| row.iter().map(|c| c.abs()).sum::<f32>())
+        .fold(0.0f32, f32::max)
+}
+
 pub struct Oversampler {
     coeffs: [[f32; TAPS_PER_PHASE]; PHASES],
     /// Per-channel circular history of the last `TAPS_PER_PHASE` input samples.
     history: Vec<[f32; TAPS_PER_PHASE]>,
     pos: usize,
+    /// Largest L1 norm across the phases. Since every interpolated sample is a dot product of
+    /// one phase with the history, `|interpolated| <= peak_gain * max|history|` - a hard bound,
+    /// which lets a caller prove the true peak cannot reach a ceiling without evaluating it.
+    peak_gain: f32,
 }
 
 impl Default for Oversampler {
     fn default() -> Self {
+        let coeffs = build_coefficients();
         Self {
-            coeffs: build_coefficients(),
+            peak_gain: build_peak_gain(&coeffs),
+            coeffs,
             history: Vec::new(),
             pos: 0,
         }
@@ -90,19 +108,38 @@ impl Oversampler {
 
     /// Feed one input frame; return the maximum inter-sample magnitude across all channels and the
     /// 4× grid (the reconstructed samples are not kept).
-    pub fn max_true_peak(&mut self, input: &[f32]) -> f32 {
+    /// Upper bound on `|interpolated|` for an input bounded by 1.0. See [`Self::peak_gain`].
+    #[inline(always)]
+    pub fn peak_gain(&self) -> f32 {
+        self.peak_gain
+    }
+
+    /// Feed one input frame into the history. Cheap - a write per channel plus a counter.
+    /// Must be called for EVERY frame even when [`Self::evaluate`] is skipped, or the FIR
+    /// history develops holes and later evaluations read stale samples.
+    #[inline]
+    pub fn push(&mut self, input: &[f32]) {
         let n = input.len().min(self.history.len());
         let slot = self.pos % TAPS_PER_PHASE;
         for ch in 0..n {
             self.history[ch][slot] = input[ch];
         }
+        self.pos += 1;
+    }
 
-        // The tap index only depends on `pos` and `k`, not on `phase` or `ch` — hoist it out of
+    /// The actual polyphase evaluation: `PHASES * TAPS_PER_PHASE` multiply-adds per channel.
+    /// This is the expensive half, and the only half a caller can skip.
+    #[inline]
+    pub fn evaluate(&self, channels: usize) -> f32 {
+        let n = channels.min(self.history.len());
+        // The tap index only depends on `pos` and `k`, not on `phase` or `ch` - hoist it out of
         // those loops instead of recomputing (and re-dividing) it PHASES*MAX_CHANNELS times over.
+        // `pos` already advanced past the newest sample in push(), hence the -1.
+        let base = self.pos + TAPS_PER_PHASE - 1;
         let mut idx = [0usize; TAPS_PER_PHASE];
         for (k, slot) in idx.iter_mut().enumerate() {
             // k = 0 is the newest sample, increasing k goes back in time.
-            *slot = (self.pos + TAPS_PER_PHASE - k) % TAPS_PER_PHASE;
+            *slot = (base - k) % TAPS_PER_PHASE;
         }
 
         let mut peak = 0.0f32;
@@ -116,10 +153,18 @@ impl Oversampler {
                 peak = peak.max(acc.abs());
             }
         }
-
-        self.pos += 1;
         peak
     }
+
+    /// Push a frame and evaluate it unconditionally. The real path splits these so the
+    /// evaluation can be skipped (see `Limiter::process`); this is kept for tests that want
+    /// the true peak of every frame regardless of any ceiling.
+    #[cfg(test)]
+    pub fn max_true_peak(&mut self, input: &[f32]) -> f32 {
+        let n = input.len().min(self.history.len());
+        self.push(input);
+        self.evaluate(n)
+    }
 }
 
 #[cfg(test)]
@@ -153,4 +198,38 @@ mod tests {
         }
         assert!((last - 0.5).abs() < 0.02, "amplitude not preserved: {last}");
     }
-}
+
+    /// The early-out in `Limiter::process` is only sound if `evaluate()` can never exceed
+    /// `peak_gain * max|history|`. Assert that directly against adversarial input - full-scale
+    /// square waves and alternating impulses maximise the interpolator's overshoot.
+    #[test]
+    fn evaluate_never_exceeds_peak_gain_bound() {
+        let mut os = Oversampler::default();
+        os.prepare(2);
+        let mut rng: u32 = 0xC0FF_EE01;
+        let mut worst_ratio = 0.0f32;
+        for i in 0..20_000 {
+            rng = rng.wrapping_mul(1_664_525).wrapping_add(1_013_904_223);
+            // Mix of adversarial shapes: alternating full scale, impulses, and noise.
+            let x = match i % 3 {
+                0 => if (i / 3) % 2 == 0 { 1.0 } else { -1.0 },
+                1 => if i % 97 == 0 { 1.0 } else { 0.0 },
+                _ => (rng >> 8) as f32 / (1 << 23) as f32 - 1.0,
+            };
+            let frame = [x, -x];
+            os.push(&frame);
+            let got = os.evaluate(2);
+            // Bound uses the max over the FIR support, which for these inputs is at most 1.0.
+            let bound = os.peak_gain() * 1.0;
+            assert!(
+                got <= bound + 1e-4,
+                "evaluate() = {got} exceeded peak_gain bound {bound} at i={i}"
+            );
+            if bound > 0.0 {
+                worst_ratio = worst_ratio.max(got / bound);
+            }
+        }
+        // Sanity: the bound must be reachable enough to be useful, not vacuously huge.
+        assert!(worst_ratio > 0.3, "bound looks far too loose (worst ratio {worst_ratio})");
+    }
+}

src/lib.rs

@@ -216,6 +216,43 @@ impl Plugin for Codename206 {
         let mut gr = [0.0f32; meters::NUM_CHANNELS];
         let mut lim_gr = 0.0f32;
 
+        // Params only change on block boundaries here (we do not split blocks on events), so a
+        // smoother that is idle now stays idle for this whole block. When every smoother feeding
+        // a channel is idle - the overwhelming common case, i.e. nobody is touching a knob -
+        // its per-sample values are constants, so lift them out of the sample loop entirely.
+        // That removes 5 Smoother::next() calls and a db_to_gain per channel per sample.
+        let chan_static = |p: &params::CompressorParams| {
+            !p.pre_gain_db.smoothed.is_smoothing()
+                && !p.makeup_db.smoothed.is_smoothing()
+                && !p.mix.smoothed.is_smoothing()
+                && !p.low_slope.smoothed.is_smoothing()
+                && !p.low_curve.smoothed.is_smoothing()
+        };
+        let band_static = [
+            chan_static(&self.params.low),
+            chan_static(&self.params.mid),
+            chan_static(&self.params.high),
+        ];
+        let all_static = chan_static(&self.params.all);
+        let mut band_pre = [1.0f32; 3];
+        for b in 0..3 {
+            if band_static[b] {
+                band_pre[b] = util::db_to_gain_fast(band_params[b].pre_gain_db.smoothed.next());
+                band_set[b].makeup_db = band_params[b].makeup_db.smoothed.next();
+                band_set[b].mix = band_params[b].mix.smoothed.next();
+                band_set[b].low_slope = band_params[b].low_slope.smoothed.next();
+                band_set[b].low_curve = band_params[b].low_curve.smoothed.next();
+            }
+        }
+        let mut all_pre_static = 1.0f32;
+        if all_static {
+            all_pre_static = util::db_to_gain_fast(self.params.all.pre_gain_db.smoothed.next());
+            all_set.makeup_db = self.params.all.makeup_db.smoothed.next();
+            all_set.mix = self.params.all.mix.smoothed.next();
+            all_set.low_slope = self.params.all.low_slope.smoothed.next();
+            all_set.low_curve = self.params.all.low_curve.smoothed.next();
+        }
+
         let mut in_frame = [0.0f32; 2];
         let mut band_in = [[0.0f32; 2]; 3];
         let mut band_out = [[0.0f32; 2]; 3];
@@ -243,14 +280,18 @@ impl Plugin for Codename206 {
             for b in 0..3 {
                 // `_fast` skips the below-(-100dB) branch, which pre_gain_db's -24..+36 range
                 // never reaches, in exchange for a cheaper exp() instead of a general powf().
-                let pre = util::db_to_gain_fast(band_params[b].pre_gain_db.smoothed.next());
+                let pre = if band_static[b] {
+                    band_pre[b]
+                } else {
+                    band_set[b].makeup_db = band_params[b].makeup_db.smoothed.next();
+                    band_set[b].mix = band_params[b].mix.smoothed.next();
+                    band_set[b].low_slope = band_params[b].low_slope.smoothed.next();
+                    band_set[b].low_curve = band_params[b].low_curve.smoothed.next();
+                    util::db_to_gain_fast(band_params[b].pre_gain_db.smoothed.next())
+                };
                 for ch in 0..n {
                     band_in[b][ch] *= pre;
                 }
-                band_set[b].makeup_db = band_params[b].makeup_db.smoothed.next();
-                band_set[b].mix = band_params[b].mix.smoothed.next();
-                band_set[b].low_slope = band_params[b].low_slope.smoothed.next();
-                band_set[b].low_curve = band_params[b].low_curve.smoothed.next();
                 self.comps[b].process(&band_in[b][..n], &mut band_out[b][..n], &band_set[b]);
                 for ch in 0..n {
                     summed[ch] += band_out[b][ch];
@@ -274,14 +315,18 @@ impl Plugin for Codename206 {
             }
 
             // 'All' aggregate channel over the summed bands (driven before its compressor).
-            let all_pre = util::db_to_gain_fast(self.params.all.pre_gain_db.smoothed.next());
+            let all_pre = if all_static {
+                all_pre_static
+            } else {
+                all_set.makeup_db = self.params.all.makeup_db.smoothed.next();
+                all_set.mix = self.params.all.mix.smoothed.next();
+                all_set.low_slope = self.params.all.low_slope.smoothed.next();
+                all_set.low_curve = self.params.all.low_curve.smoothed.next();
+                util::db_to_gain_fast(self.params.all.pre_gain_db.smoothed.next())
+            };
             for ch in 0..n {
                 summed[ch] *= all_pre;
             }
-            all_set.makeup_db = self.params.all.makeup_db.smoothed.next();
-            all_set.mix = self.params.all.mix.smoothed.next();
-            all_set.low_slope = self.params.all.low_slope.smoothed.next();
-            all_set.low_curve = self.params.all.low_curve.smoothed.next();
             self.comps[ALL].process(&summed[..n], &mut out_frame[..n], &all_set);
 
             // Output brickwall limiter.