feat: add bench_lookup bench

For now, the benchmarks on the `bench_lookup` I added are: Using `permute_expression_pair_par`: ``` Benchmarking bench-lookup/14: Warming up for 3.0000 s[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 20.425916ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 20.426375ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 20.261ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 19.694833ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 20.660875ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 19.887375ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 20.239875ms Warning: Unable to complete 10 samples in 5.0s. You may wish to increase target time to 6.8s. Benchmarking bench-lookup/14: Collecting 10 samples in estimated 6.8417 s (10 iterations)[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 20.548208ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 19.5575ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 20.678708ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 20.956375ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 20.183791ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 19.00175ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 19.986916ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 19.358875ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 21.128708ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 18.92425ms bench-lookup/14 time: [678.46 ms 686.72 ms 694.16 ms] change: [-0.7211% +1.2598% +3.1373%] (p = 0.25 > 0.05) No change in performance detected. Benchmarking bench-lookup/15: Warming up for 3.0000 s[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 40.454916ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 41.66425ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 41.290333ms Warning: Unable to complete 10 samples in 5.0s. You may wish to increase target time to 12.5s. Benchmarking bench-lookup/15: Collecting 10 samples in estimated 12.503 s (10 iterations)[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 40.871916ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 39.03175ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 44.727416ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 42.948333ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 40.489958ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 43.823041ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 39.592ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 40.593375ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 41.861708ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 45.023333ms bench-lookup/15 time: [1.2285 s 1.2341 s 1.2393 s] change: [-6.0038% -4.4123% -2.7223%] (p = 0.00 < 0.05) Performance has improved. Found 2 outliers among 10 measurements (20.00%) 1 (10.00%) low mild 1 (10.00%) high mild Benchmarking bench-lookup/16: Warming up for 3.0000 s[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 92.282041ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 90.784875ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 95.368958ms Warning: Unable to complete 10 samples in 5.0s. You may wish to increase target time to 23.9s. Benchmarking bench-lookup/16: Collecting 10 samples in estimated 23.937 s (10 iterations)[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 93.599166ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 95.992583ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 91.913625ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 89.482625ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 90.111875ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 86.671916ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 96.854666ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 102.468125ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 97.830583ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 87.925708ms bench-lookup/16 time: [2.3417 s 2.3644 s 2.3901 s] change: [+2.2283% +4.1485% +6.0108%] (p = 0.00 < 0.05) Performance has regressed. Found 1 outliers among 10 measurements (10.00%) 1 (10.00%) high mild Benchmarking bench-lookup/17: Warming up for 3.0000 s[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 214.102916ms Warning: Unable to complete 10 samples in 5.0s. You may wish to increase target time to 45.0s. Benchmarking bench-lookup/17: Collecting 10 samples in estimated 45.000 s (10 iterations)[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 199.65025ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 208.088875ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 208.299666ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 199.684416ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 199.761666ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 193.034458ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 202.182375ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 200.825375ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 226.314541ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 211.914291ms bench-lookup/17 time: [4.3987 s 4.4299 s 4.4605 s] change: [+0.7989% +1.9668% +3.0962%] (p = 0.01 < 0.05) Change within noise threshold. Benchmarking bench-lookup/18: Warming up for 3.0000 s[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 423.016291ms Warning: Unable to complete 10 samples in 5.0s. You may wish to increase target time to 85.7s. Benchmarking bench-lookup/18: Collecting 10 samples in estimated 85.748 s (10 iterations)[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 451.549291ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 469.336ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 429.5375ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 430.579041ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 435.976541ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 416.241875ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 423.361041ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 436.833625ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 456.685458ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 454.897541ms bench-lookup/18 time: [8.5101 s 8.5631 s 8.6175 s] change: [+0.5067% +1.6515% +2.8407%] (p = 0.02 < 0.05) Change within noise threshold. ``` Using `permute_expression_pair_seq`: ``` Benchmarking bench-lookup/14: Warming up for 3.0000 s[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 19.35325ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 19.101125ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 18.721708ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 19.291333ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 18.860208ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 18.553916ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 18.965375ms Warning: Unable to complete 10 samples in 5.0s. You may wish to increase target time to 6.9s. Benchmarking bench-lookup/14: Collecting 10 samples in estimated 6.8584 s (10 iterations)[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 19.117458ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 18.80025ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 19.169875ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 19.03325ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 18.636166ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 19.170166ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 19.000416ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 18.565958ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 18.970333ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 19.007291ms bench-lookup/14 time: [679.11 ms 687.62 ms 696.42 ms] change: [-1.5707% +0.1313% +1.8844%] (p = 0.89 > 0.05) No change in performance detected. Benchmarking bench-lookup/15: Warming up for 3.0000 s[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 41.634625ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 40.915958ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 40.774625ms Warning: Unable to complete 10 samples in 5.0s. You may wish to increase target time to 12.6s. Benchmarking bench-lookup/15: Collecting 10 samples in estimated 12.569 s (10 iterations)[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 41.548583ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 41.074333ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 41.807125ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 41.106458ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 41.222541ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 41.021458ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 41.411666ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 41.024416ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 41.636541ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 41.869166ms bench-lookup/15 time: [1.2474 s 1.2597 s 1.2711 s] change: [+0.9856% +2.0736% +3.1604%] (p = 0.00 < 0.05) Change within noise threshold. Benchmarking bench-lookup/16: Warming up for 3.0000 s[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 90.202208ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 89.318083ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 88.717125ms Warning: Unable to complete 10 samples in 5.0s. You may wish to increase target time to 23.8s. Benchmarking bench-lookup/16: Collecting 10 samples in estimated 23.789 s (10 iterations)[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 89.929041ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 88.316333ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 89.588083ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 88.630916ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 88.872ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 88.961416ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 88.796833ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 89.80725ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 89.426916ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 89.039833ms bench-lookup/16 time: [2.3537 s 2.3854 s 2.4165 s] change: [-0.7038% +0.8909% +2.5108%] (p = 0.33 > 0.05) No change in performance detected. Benchmarking bench-lookup/17: Warming up for 3.0000 s[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 187.758583ms Warning: Unable to complete 10 samples in 5.0s. You may wish to increase target time to 43.2s. Benchmarking bench-lookup/17: Collecting 10 samples in estimated 43.177 s (10 iterations)[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 187.717833ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 185.975333ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 187.108625ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 187.965416ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 188.279458ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 188.287166ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 188.590291ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 186.355708ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 186.600458ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 188.600875ms bench-lookup/17 time: [4.3965 s 4.4531 s 4.5112 s] change: [-0.8127% +0.5248% +2.0814%] (p = 0.52 > 0.05) No change in performance detected. Benchmarking bench-lookup/18: Warming up for 3.0000 s[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 405.103375ms Warning: Unable to complete 10 samples in 5.0s. You may wish to increase target time to 86.2s. Benchmarking bench-lookup/18: Collecting 10 samples in estimated 86.153 s (10 iterations)[halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 406.387125ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 402.833916ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 403.729208ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 404.397583ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 404.277833ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 409.32825ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 404.037583ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 403.349875ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 405.868083ms [halo2_proofs/src/plonk/lookup/prover.rs:418] start.elapsed() = 403.907458ms bench-lookup/18 time: [8.5238 s 8.5804 s 8.6488 s] change: [-0.7212% +0.2021% +1.2400%] (p = 0.70 > 0.05) No change in performance detected. Found 1 outliers among 10 measurements (10.00%) 1 (10.00%) high mild ```
privacy-scaling-explorations · Aug 12, 2023 · e0b4479 · e0b4479
1 parent c848852
commit e0b4479
Show file tree

Hide file tree

Showing 3 changed files with 146 additions and 1 deletion.
diff --git a/halo2_proofs/Cargo.toml b/halo2_proofs/Cargo.toml
@@ -43,6 +43,10 @@ harness = false
 name = "dev_lookup"
 harness = false
 
+[[bench]]
+name = "bench_lookup"
+harness = false
+
 [[bench]]
 name = "fft"
 harness = false

diff --git a/halo2_proofs/benches/bench_lookup.rs b/halo2_proofs/benches/bench_lookup.rs
@@ -0,0 +1,137 @@
+#[macro_use]
+extern crate criterion;
+
+use ff::{Field, PrimeField};
+use halo2_proofs::circuit::{Layouter, SimpleFloorPlanner, Value};
+use halo2_proofs::plonk::*;
+use halo2_proofs::poly::commitment::ParamsProver;
+use halo2_proofs::poly::ipa::commitment::{IPACommitmentScheme, ParamsIPA};
+use halo2_proofs::poly::ipa::multiopen::ProverIPA;
+use halo2_proofs::poly::Rotation;
+use halo2_proofs::transcript::{Blake2bWrite, Challenge255, TranscriptWriterBuffer};
+use halo2curves::pasta::{pallas, EqAffine};
+use rand_core::OsRng;
+
+use std::marker::PhantomData;
+
+use criterion::{BenchmarkId, Criterion};
+
+fn criterion_benchmark(c: &mut Criterion) {
+    #[derive(Clone, Default)]
+    struct MyCircuit<F: Field> {
+        k: usize,
+        _marker: PhantomData<F>,
+    }
+
+    #[derive(Clone)]
+    struct MyConfig {
+        selector: Selector,
+        table: TableColumn,
+        advice: Column<Advice>,
+    }
+
+    impl<F: PrimeField> Circuit<F> for MyCircuit<F> {
+        type Config = MyConfig;
+        type FloorPlanner = SimpleFloorPlanner;
+        #[cfg(feature = "circuit-params")]
+        type Params = ();
+
+        fn without_witnesses(&self) -> Self {
+            Self::default()
+        }
+
+        fn configure(meta: &mut ConstraintSystem<F>) -> MyConfig {
+            let config = MyConfig {
+                selector: meta.complex_selector(),
+                table: meta.lookup_table_column(),
+                advice: meta.advice_column(),
+            };
+
+            meta.lookup("lookup", |meta| {
+                let selector = meta.query_selector(config.selector);
+                let not_selector = Expression::Constant(F::ONE) - selector.clone();
+                let advice = meta.query_advice(config.advice, Rotation::cur());
+                vec![(selector * advice + not_selector, config.table)]
+            });
+
+            config
+        }
+
+        fn synthesize(
+            &self,
+            config: MyConfig,
+            mut layouter: impl Layouter<F>,
+        ) -> Result<(), Error> {
+            layouter.assign_table(
+                || "lookup table",
+                |mut table| {
+                    for row in 0u64..(1 << (self.k - 1)) {
+                        table.assign_cell(
+                            || format!("row {}", row),
+                            config.table,
+                            row as usize,
+                            || Value::known(F::from(row)),
+                        )?;
+                    }
+
+                    Ok(())
+                },
+            )?;
+
+            layouter.assign_region(
+                || "assign values",
+                |mut region| {
+                    for offset in 0u64..(1 << self.k) - 20 {
+                        config.selector.enable(&mut region, offset as usize)?;
+                        region.assign_advice(
+                            || format!("offset {}", offset),
+                            config.advice,
+                            offset as usize,
+                            || Value::known(F::from(offset >> 1)),
+                        )?;
+                    }
+
+                    Ok(())
+                },
+            )
+        }
+    }
+
+    let k_range = 14..=18;
+
+    let mut prover_group = c.benchmark_group("bench-lookup");
+    prover_group.sample_size(10);
+    for k in k_range {
+        let circuit = MyCircuit::<pallas::Base> {
+            k: k as usize,
+            _marker: PhantomData,
+        };
+        let params = ParamsIPA::<EqAffine>::new(k);
+        let vk = keygen_vk(&params, &circuit).unwrap();
+        let pk = keygen_pk(&params, vk, &circuit).unwrap();
+        prover_group.bench_with_input(
+            BenchmarkId::from_parameter(k),
+            &(params, pk),
+            |b, (params, pk)| {
+                b.iter(|| {
+                    let mut transcript = Blake2bWrite::<_, _, Challenge255<EqAffine>>::init(vec![]);
+                    let rng = OsRng;
+                    create_proof::<IPACommitmentScheme<EqAffine>, ProverIPA<EqAffine>, _, _, _, _>(
+                        params,
+                        pk,
+                        &[circuit.clone()],
+                        &[&[]],
+                        rng,
+                        &mut transcript,
+                    )
+                    .unwrap();
+                    transcript.finalize();
+                });
+            },
+        );
+    }
+    prover_group.finish();
+}
+
+criterion_group!(benches, criterion_benchmark);
+criterion_main!(benches);
diff --git a/halo2_proofs/src/plonk/lookup/prover.rs b/halo2_proofs/src/plonk/lookup/prover.rs
@@ -412,7 +412,11 @@ fn permute_expression_pair<'params, C: CurveAffine, P: Params<'params, C>, R: Rn
             table_expression,
         );
     }*/
-    permute_expression_pair_par(pk, params, domain, rng, input_expression, table_expression)
+    let start = std::time::Instant::now();
+    let res =
+        permute_expression_pair_par(pk, params, domain, rng, input_expression, table_expression);
+    dbg!(start.elapsed());
+    res
 }
 
 fn permute_expression_pair_par<'params, C: CurveAffine, P: Params<'params, C>, R: RngCore>(