Optimization Workflow:
1. BASELINE  -> Establish current behavior with tests
2. TEST      -> Add regression tests for the code you'll change
3. OPTIMIZE  -> Make the change
4. VERIFY    -> Run tests to prove correctness preserved
5. BENCHMARK -> Only now measure the improvement

undefined

undefined

undefined

undefined

undefined

**IMPORTANT**: Always document which profile was used in benchmark reports.

use criterion::{black_box, criterion_group, criterion_main, Criterion, BenchmarkId};

fn benchmark_variants(c: &mut Criterion) {
    let mut group = c.benchmark_group("processing");

    for size in [100, 1000, 10000].iter() {
        let data = generate_data(*size);

        group.bench_with_input(
            BenchmarkId::new("original", size),
            &data,
            |b, data| b.iter(|| original_impl(black_box(data))),
        );

        group.bench_with_input(
            BenchmarkId::new("optimized", size),
            &data,
            |b, data| b.iter(|| optimized_impl(black_box(data))),
        );
    }

    group.finish();
}

criterion_group!(benches, benchmark_variants);
criterion_main!(benches);

undefined

undefined

undefined

undefined

// Before: Allocates on every call
fn process(items: &[Item]) -> Vec<String> {
    items.iter().map(|i| i.name.clone()).collect()
}

// After: Reuse buffer
fn process_into(items: &[Item], output: &mut Vec<String>) {
    output.clear();
    output.extend(items.iter().map(|i| i.name.clone()));
}

// Use SmallVec for small collections
use smallvec::SmallVec;
type Tags = SmallVec<[String; 4]>; // Stack-allocated for <= 4 items

// Before: Array of Structs (AoS)
struct Entity {
    position: Vec3,
    velocity: Vec3,
    health: f32,
}
let entities: Vec<Entity>;

// After: Struct of Arrays (SoA) - better cache locality
struct Entities {
    positions: Vec<Vec3>,
    velocities: Vec<Vec3>,
    health: Vec<f32>,
}

// Process all positions together (cache-friendly)
fn update_positions(entities: &mut Entities, dt: f32) {
    for (pos, vel) in entities.positions.iter_mut().zip(&entities.velocities) {
        *pos += *vel * dt;
    }
}

use std::borrow::Cow;

// Parse without copying when possible
struct ParsedData<'a> {
    name: Cow<'a, str>,
    values: &'a [u8],
}

fn parse(input: &[u8]) -> Result<ParsedData<'_>> {
    // Borrow from input when no transformation needed
    // Only allocate when escaping/decoding required
}

// Use portable-simd or explicit intrinsics
use std::simd::{f32x8, SimdFloat};

fn sum_simd(data: &[f32]) -> f32 {
    let chunks = data.chunks_exact(8);
    let remainder = chunks.remainder();

    let sum = chunks
        .map(|chunk| f32x8::from_slice(chunk))
        .fold(f32x8::splat(0.0), |acc, x| acc + x)
        .reduce_sum();

    sum + remainder.iter().sum::<f32>()
}

// Use string interning for repeated strings
use string_interner::{StringInterner, DefaultSymbol};

struct Interned {
    interner: StringInterner,
}

impl Interned {
    fn intern(&mut self, s: &str) -> DefaultSymbol {
        self.interner.get_or_intern(s)
    }
}

// Use CompactString for small strings
use compact_str::CompactString;
let small: CompactString = "hello".into(); // No heap allocation

// Likely/unlikely branch hints
#[cold]
fn handle_error() { ... }

// Force inlining
#[inline(always)]
fn hot_function() { ... }

// Prevent inlining
#[inline(never)]
fn cold_function() { ... }

// Enable specific optimizations
#[target_feature(enable = "avx2")]
unsafe fn simd_process() { ... }

// Check struct size and alignment
println!("Size: {}", std::mem::size_of::<MyStruct>());
println!("Align: {}", std::mem::align_of::<MyStruct>());

// Optimize field ordering to reduce padding
#[repr(C)]
struct Optimized {
    large: u64,    // 8 bytes
    medium: u32,   // 4 bytes
    small: u16,    // 2 bytes
    tiny: u8,      // 1 byte
    _pad: u8,      // explicit padding
}

[ ] Regression tests added/extended for changed code paths
[ ] Tests pass BEFORE benchmarking
[ ] Benchmark script included (Criterion or hyperfine)
[ ] Before/after numbers on same machine
[ ] Build profile explicitly noted (release, release-lto, etc.)
[ ] If >50% improvement: flamegraph/perf evidence included
[ ] If unsafe code: invariants documented + tests proving them