foxhunt/ml/benches/inference_bench.rs

//! ML Inference Performance Benchmarks
//!
//! Validates ML model inference latency targets for HFT trading system.
//!
//! Performance Targets:
//! - Ensemble inference: <300ms
//! - Single model inference: <100ms
//! - Feature preparation: <10ms
//! - Model switching: <50ms
#![allow(unused_crate_dependencies)]

use criterion::{black_box, criterion_group, criterion_main, BatchSize, Criterion};
use std::time::Duration;

/// Simulated market features for inference
#[derive(Clone)]
struct MarketFeatures {
    prices: Vec<f64>,
    volumes: Vec<f64>,
    #[allow(dead_code)]
    order_book_depth: Vec<(f64, f64)>, // (bid, ask) pairs
    #[allow(dead_code)]
    timestamp_features: Vec<f64>,
}

impl MarketFeatures {
    fn new() -> Self {
        Self {
            prices: vec![150.0; 60], // 60 time steps
            volumes: vec![1000.0; 60],
            order_book_depth: vec![(149.9, 150.1); 10],
            timestamp_features: vec![0.0, 0.1, 0.2, 0.3, 0.4],
        }
    }
}

/// Mock ensemble inference
struct MockEnsembleInference {
    model_count: usize,
}

impl MockEnsembleInference {
    fn new(model_count: usize) -> Self {
        Self { model_count }
    }

    fn predict(&self, features: &MarketFeatures) -> f64 {
        // Simulate ensemble inference with some computation
        let mut result = 0.0;
        for _ in 0..self.model_count {
            // Simulate model inference
            for &price in &features.prices {
                result += (price * 0.001).tanh();
            }
            for &vol in &features.volumes {
                result += (vol * 0.0001).ln();
            }
        }
        result / self.model_count as f64
    }
}

/// Benchmark ensemble inference
fn bench_ensemble_inference(c: &mut Criterion) {
    let ensemble = MockEnsembleInference::new(5); // 5 models in ensemble
    let features = MarketFeatures::new();

    c.bench_function("ensemble_inference_5_models", |b| {
        b.iter_batched(
            || features.clone(),
            |features| black_box(ensemble.predict(&features)),
            BatchSize::SmallInput,
        )
    });

    // Test different ensemble sizes
    let mut group = c.benchmark_group("ensemble_size_comparison");
    for size in [1, 3, 5, 7, 10] {
        let ensemble = MockEnsembleInference::new(size);
        group.bench_function(format!("{}_models", size), |b| {
            b.iter_batched(
                || features.clone(),
                |features| black_box(ensemble.predict(&features)),
                BatchSize::SmallInput,
            )
        });
    }
    group.finish();
}

/// Benchmark feature preparation
fn bench_feature_preparation(c: &mut Criterion) {
    let prices = vec![150.0 + (0..100).map(|i| i as f64 * 0.1).sum::<f64>(); 100];
    let volumes = vec![1000.0; 100];

    c.bench_function("feature_preparation", |b| {
        b.iter(|| {
            let features = MarketFeatures {
                prices: black_box(&prices).to_vec(),
                volumes: black_box(&volumes).to_vec(),
                order_book_depth: vec![(149.9, 150.1); 10],
                timestamp_features: vec![0.0; 5],
            };
            black_box(features)
        })
    });

    // Test feature normalization
    c.bench_function("feature_normalization", |b| {
        b.iter(|| {
            let normalized: Vec<f64> = prices
                .iter()
                .map(|&p| {
                    let mean = 150.0;
                    let std = 10.0;
                    (p - mean) / std
                })
                .collect();
            black_box(normalized)
        })
    });
}

/// Benchmark single model inference
fn bench_single_model_inference(c: &mut Criterion) {
    let model = MockEnsembleInference::new(1);
    let features = MarketFeatures::new();

    c.bench_function("single_model_inference", |b| {
        b.iter_batched(
            || features.clone(),
            |features| black_box(model.predict(&features)),
            BatchSize::SmallInput,
        )
    });
}

/// Benchmark batch inference
fn bench_batch_inference(c: &mut Criterion) {
    let model = MockEnsembleInference::new(5);
    let batch: Vec<MarketFeatures> = (0..10).map(|_| MarketFeatures::new()).collect();

    c.bench_function("batch_inference_10_samples", |b| {
        b.iter_batched(
            || batch.clone(),
            |batch| {
                batch
                    .iter()
                    .map(|features| model.predict(features))
                    .collect::<Vec<_>>()
            },
            BatchSize::SmallInput,
        )
    });

    // Test different batch sizes
    let mut group = c.benchmark_group("batch_size_comparison");
    for batch_size in [1, 5, 10, 20, 50] {
        let batch: Vec<MarketFeatures> = (0..batch_size).map(|_| MarketFeatures::new()).collect();
        group.bench_function(format!("batch_{}", batch_size), |b| {
            b.iter_batched(
                || batch.clone(),
                |batch| {
                    batch
                        .iter()
                        .map(|features| model.predict(features))
                        .collect::<Vec<_>>()
                },
                BatchSize::SmallInput,
            )
        });
    }
    group.finish();
}

criterion_group! {
    name = ml_inference_benchmarks;
    config = Criterion::default()
        .measurement_time(Duration::from_secs(10))
        .sample_size(100)
        .warm_up_time(Duration::from_secs(3));
    targets =
        bench_ensemble_inference,
        bench_single_model_inference,
        bench_feature_preparation,
        bench_batch_inference
}

criterion_main!(ml_inference_benchmarks);

#[cfg(test)]
mod performance_tests {
    use super::*;
    use std::time::Instant;

    #[test]
    fn test_ensemble_inference_latency() {
        let ensemble = MockEnsembleInference::new(5);
        let features = MarketFeatures::new();

        let iterations = 100;
        let start = Instant::now();

        for _ in 0..iterations {
            black_box(ensemble.predict(&features));
        }

        let duration = start.elapsed();
        let avg_duration_ms = duration.as_millis() / iterations;

        // Target: <300ms for ensemble inference
        assert!(
            avg_duration_ms < 300,
            "Ensemble inference too slow: {}ms average (target: <300ms)",
            avg_duration_ms
        );

        println!("✓ Ensemble inference: {}ms average", avg_duration_ms);
    }

    #[test]
    fn test_single_model_latency() {
        let model = MockEnsembleInference::new(1);
        let features = MarketFeatures::new();

        let iterations = 100;
        let start = Instant::now();

        for _ in 0..iterations {
            black_box(model.predict(&features));
        }

        let duration = start.elapsed();
        let avg_duration_ms = duration.as_millis() / iterations;

        // Target: <100ms for single model
        assert!(
            avg_duration_ms < 100,
            "Single model inference too slow: {}ms average (target: <100ms)",
            avg_duration_ms
        );

        println!("✓ Single model inference: {}ms average", avg_duration_ms);
    }

    #[test]
    fn test_feature_preparation_latency() {
        let prices = vec![150.0; 100];
        let volumes = vec![1000.0; 100];

        let iterations = 1000;
        let start = Instant::now();

        for _ in 0..iterations {
            let features = MarketFeatures {
                prices: prices.clone(),
                volumes: volumes.clone(),
                order_book_depth: vec![(149.9, 150.1); 10],
                timestamp_features: vec![0.0; 5],
            };
            black_box(features);
        }

        let duration = start.elapsed();
        let avg_duration_us = duration.as_micros() / iterations;

        // Target: <10ms (10000μs) for feature preparation
        assert!(
            avg_duration_us < 10000,
            "Feature preparation too slow: {}μs average (target: <10000μs)",
            avg_duration_us
        );

        println!("✓ Feature preparation: {}μs average", avg_duration_us);
    }

    #[test]
    fn test_batch_inference_throughput() {
        let model = MockEnsembleInference::new(5);
        let batch: Vec<MarketFeatures> = (0..10).map(|_| MarketFeatures::new()).collect();

        let iterations = 10;
        let start = Instant::now();

        for _ in 0..iterations {
            let results: Vec<f64> = batch.iter().map(|f| model.predict(f)).collect();
            black_box(results);
        }

        let duration = start.elapsed();
        let total_predictions = iterations * 10;
        let avg_per_prediction_ms = duration.as_millis() / total_predictions;

        println!(
            "✓ Batch inference throughput: {}ms per prediction (batch size: 10)",
            avg_per_prediction_ms
        );
        println!(
            "  Total: {} predictions in {:?}",
            total_predictions, duration
        );
    }
}