fix: Move timers for ClientIVC breakdown

[codygunton]

#4841 improved the witness construction in the client IVC benchmarks to make use of straightforward parallelism. This PR updates the manual % breakdown script to reflect the new structure. It also fixes benchmark.sh so that it can be used inside of benchmark_client_ivc.sh in the case where the benchmarking instance is unavailable.

Result:

--------------------------------------------------------------------------------
Benchmark                      Time             CPU   Iterations UserCounters...
--------------------------------------------------------------------------------
ClientIVCBench/Full/6      29212 ms        24574 ms            1 Decider::construct_proof=1 Decider::construct_proof(t)=755.662M ECCVMComposer::create_prover=1 ECCVMComposer::create_prover(t)=3.41214G ECCVMProver::construct_proof=1 ECCVMProver::construct_proof(t)=1.77115G Goblin::merge=11 Goblin::merge(t)=128.511M GoblinTranslatorCircuitBuilder::constructor=1 GoblinTranslatorCircuitBuilder::constructor(t)=56.2447M GoblinTranslatorComposer::create_prover=1 GoblinTranslatorComposer::create_prover(t)=121.099M GoblinTranslatorProver::construct_proof=1 GoblinTranslatorProver::construct_proof(t)=920.195M ProtogalaxyProver::fold_instances=10 ProtogalaxyProver::fold_instances(t)=15.8816G ProverInstance(Circuit&)=11 ProverInstance(Circuit&)(t)=1.94818G batch_mul_with_endomorphism=30 batch_mul_with_endomorphism(t)=564.471M commit=425 commit(t)=3.96399G compute_combiner=10 compute_combiner(t)=7.19205G compute_perturbator=9 compute_perturbator(t)=1.3842G construct_circuits=6 construct_circuits(t)=4.19883G
Benchmarking lock deleted.
client_ivc_bench.json                                                         100% 2904    89.0KB/s   00:00    
function                                        ms     % sum
construct_circuits(t)                         4199    14.41%
ProverInstance(Circuit&)(t)                   1948     6.69%
ProtogalaxyProver::fold_instances(t)         15882    54.51%
Decider::construct_proof(t)                    756     2.59%
ECCVMComposer::create_prover(t)               3412    11.71%
GoblinTranslatorComposer::create_prover(t)     121     0.42%
ECCVMProver::construct_proof(t)               1771     6.08%
GoblinTranslatorProver::construct_proof(t)     920     3.16%
Goblin::merge(t)                               129     0.44%

Total time accounted for: 29137ms/29212ms = 99.74%

[AztecBot]

Benchmark results

Metrics with a significant change:

• note_successful_decrypting_time_in_ms (32): 583 (+22%)
• note_trial_decrypting_time_in_ms (8): 93.8 (+248%)
• note_trial_decrypting_time_in_ms (64): 68.9 (+96%)

Detailed results

All benchmarks are run on txs on the Benchmarking contract on the repository. Each tx consists of a batch call to create_note and increment_balance, which guarantees that each tx has a private call, a nested private call, a public call, and a nested public call, as well as an emitted private note, an unencrypted log, and public storage read and write.

This benchmark source data is available in JSON format on S3 here.

Values are compared against data from master at commit 7f216eb0 and shown if the difference exceeds 1%.

L2 block published to L1

Each column represents the number of txs on an L2 block published to L1.

Metric	8 txs	32 txs	64 txs
l1_rollup_calldata_size_in_bytes	5,668	18,820	36,356
l1_rollup_calldata_gas	66,040	238,684	468,824
l1_rollup_execution_gas	666,520	953,393	1,335,980
l2_block_processing_time_in_ms	1,321	4,793 (+1%)	8,982 (-5%)
note_successful_decrypting_time_in_ms	193 (-14%)	⚠️ 583 (+22%)	939 (-7%)
note_trial_decrypting_time_in_ms	⚠️ 93.8 (+248%)	100 (+3%)	⚠️ 68.9 (+96%)
l2_block_building_time_in_ms	12,338	48,890 (+1%)	97,361
l2_block_rollup_simulation_time_in_ms	7,339	29,239 (+1%)	58,054
l2_block_public_tx_process_time_in_ms	4,967	19,586 (+1%)	39,196 (+1%)

L2 chain processing

Each column represents the number of blocks on the L2 chain where each block has 16 txs.

Metric	5 blocks	10 blocks
node_history_sync_time_in_ms	14,226	26,250 (-6%)
note_history_successful_decrypting_time_in_ms	1,293 (+1%)	2,435 (-1%)
note_history_trial_decrypting_time_in_ms	92.6 (-19%)	154 (-19%)
node_database_size_in_bytes	18,677,840	35,573,840 (+1%)
pxe_database_size_in_bytes	29,859	59,414

Circuits stats

Stats on running time and I/O sizes collected for every circuit run across all benchmarks.

Circuit	circuit_simulation_time_in_ms	circuit_input_size_in_bytes	circuit_output_size_in_bytes
private-kernel-init	272	44,338	27,700
private-kernel-ordering	206	52,324	14,326
base-rollup	666 (+1%)	177,083	925
root-rollup	68.1	4,176	789
private-kernel-inner	359	73,197	27,700
public-kernel-app-logic	179	34,582	27,671
public-kernel-tail	91.5	34,206	27,671
merge-rollup	8.22 (-1%)	2,696	925

Tree insertion stats

The duration to insert a fixed batch of leaves into each tree type.

Metric	1 leaves	16 leaves	64 leaves	128 leaves	512 leaves	1024 leaves	2048 leaves	4096 leaves	32 leaves
batch_insert_into_append_only_tree_16_depth_ms	9.99 (+1%)	16.0 (-1%)	N/A	N/A	N/A	N/A	N/A	N/A	N/A
batch_insert_into_append_only_tree_16_depth_hash_count	16.8	31.6	N/A	N/A	N/A	N/A	N/A	N/A	N/A
batch_insert_into_append_only_tree_16_depth_hash_ms	0.583	0.494 (-1%)	N/A	N/A	N/A	N/A	N/A	N/A	N/A
batch_insert_into_append_only_tree_32_depth_ms	N/A	N/A	46.8 (+2%)	72.6 (-1%)	231 (+1%)	445	862 (-1%)	1,726 (-1%)	N/A
batch_insert_into_append_only_tree_32_depth_hash_count	N/A	N/A	96.0	159	543	1,055	2,079	4,127	N/A
batch_insert_into_append_only_tree_32_depth_hash_ms	N/A	N/A	0.481 (+2%)	0.448 (-1%)	0.421	0.417 (-1%)	0.411 (-1%)	0.414	N/A
batch_insert_into_indexed_tree_20_depth_ms	N/A	N/A	53.7	107 (+1%)	337 (+1%)	658	1,305	2,603	N/A
batch_insert_into_indexed_tree_20_depth_hash_count	N/A	N/A	104	207	691	1,363	2,707	5,395	N/A
batch_insert_into_indexed_tree_20_depth_hash_ms	N/A	N/A	0.478	0.482	0.458 (+1%)	0.453	0.453	0.454	N/A
batch_insert_into_indexed_tree_40_depth_ms	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	60.8
batch_insert_into_indexed_tree_40_depth_hash_count	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	109
batch_insert_into_indexed_tree_40_depth_hash_ms	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	0.533

Miscellaneous

Transaction sizes based on how many contract classes are registered in the tx.

Metric	0 registered classes
tx_size_in_bytes	19,191

Transaction processing duration by data writes.

Metric	0 new note hashes	1 new note hashes
tx_pxe_processing_time_ms	2,788 (-2%)	1,432

Metric	0 public data writes	1 public data writes
tx_sequencer_processing_time_ms	8.94 (+17%)	611

[Rumata888]

LGTM