SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.02009 · 2020

S3NAS: Fast NPU-aware Neural Architecture Search Methodology

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2009.02009.json · badge: /api/ran/2009.02009.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
cap-lab/S3NAS canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
get_representatives Ran
ran on a synthesized input
cap-lab/S3NAS/etc_utils/excitation_csvs_to_rank_json.py
code served (permissive licence) · get_code("7d03067f96dcd2b2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import pandas as pd
import tempfile
import os

# Create a temporary CSV file with sample data
temp_dir = tempfile.mkdtemp()
csv_file = os.path.join(temp_dir, "test_data.csv")

# Create a simple DataFrame and save it to CSV
data = {
    'col1': [1.0, 2.0, 3.0, 4.0, 5.0],
    'col2': [2.0, 4.0, 6.0, 8.0, 10.0],
    'col3': [1.5, 3.0, 4.5, 6.0, 7.5]
}
df = pd.DataFrame(data)
df.index.name = 'index'
df.to_csv(csv_file)

ARGS = {
    'csv_file': csv_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
is_script Ran
ran on a synthesized input
cap-lab/S3NAS/tester.py
code served (permissive licence) · get_code("eb56a6738859716f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

def is_script(script_filename):
    if script_filename[-3:] == '.sh':
        return True
    else:
        return False

ARGS = {
    'script_filename': 'test_script.sh'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
parse_gparams_from_model_args Ran
ran on a synthesized input
cap-lab/S3NAS/graph/net_builder.py
code served (permissive licence) · get_code("c5de8384058db87c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function parse_gparams_from_model_args takes a model_args dict
# and extracts activation function parameters from it.
# It looks for keys: 'act_fn', 'se_inner_act_fn', 'se_gating_fn'
# and returns a dict with only those keys that exist and have truthy values.

# Create a model_args dict with some of these keys
model_args = {
    'act_fn': 'relu',
    'se_inner_act_fn': 'sigmoid',
    # 'se_gating_fn' is intentionally omitted to test the get() behavior
    'other_key': 'should_not_appear'
}

ARGS = {
    'model_args': model_args
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
build_dataset Not yet run
unverified (harvested, no recorded run)
cap-lab/S3NAS/etc_utils/extract_se_excitations.py
code served (permissive licence) · get_code("7717e3acb98c2064")
How it ran

no invocation recorded.

get_latency Not yet run
unverified (harvested, no recorded run)
cap-lab/S3NAS/etc_utils/print_latency_from_tb.py
code served (permissive licence) · get_code("89d46883898f8a86")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

As the application area of convolutional neural networks (CNN) is growing in embedded devices, it becomes popular to use a hardware CNN accelerator, called neural processing unit (NPU), to achieve higher performance per watt than CPUs or GPUs. Recently, automated neural architecture search (NAS) emerges as the default technique to find a state-of-the-art CNN architecture with higher accuracy than manually-designed architectures for image classification. In this paper, we present a fast NPU-aware NAS methodology, called S3NAS, to find a CNN architecture with higher accuracy than the existing ones under a given latency constraint. It consists of three steps: supernet design, Single-Path NAS for fast architecture exploration, and scaling. To widen the search space of the supernet structure that consists of stages, we allow stages to have a different number of blocks and blocks to have parallel layers of different kernel sizes. For a fast neural architecture search, we apply a modified Single-Path NAS technique to the proposed supernet structure. In this step, we assume a shorter latency constraint than the required to reduce the search space and the search time. The last step is to scale up the network maximally within the latency constraint. For accurate latency estimation, an analytical latency estimator is devised, based on a cycle-level NPU simulator that runs an entire CNN considering the memory access overhead accurately. With the proposed methodology, we are able to find a network in 3 hours using TPUv3, which shows 82.72% top-1 accuracy on ImageNet with 11.66 ms latency. Code are released at https://github.com/cap-lab/S3NAS

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2009.02009")
get_code_for_paper("2009.02009")
have("2009.02009")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2009.02009.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2009.02009.svg)](https://syntology.ai/paper/2009.02009)

Connect an agent — have() is free.