Papers › DevFormer: A Symmetric Transformer for Context-Aware Device Placement

DevFormer: A Symmetric Transformer for Context-Aware Device Placement

26 May 2022arXiv:2205.13225archive 2025-07-28

Haeyeon Kim, Minsu Kim, Federico Berto, Joungho Kim, Jinkyoo Park

In this paper, we present DevFormer, a novel transformer-based architecture for addressing the complex and computationally demanding problem of hardware design optimization. Despite the demonstrated efficacy of transformers in domains including natural language processing and computer vision, their use in hardware design has been limited by the scarcity of offline data. Our approach addresses this limitation by introducing strong inductive biases such as relative positional embeddings and action-permutation symmetricity that effectively capture the hardware context and enable efficient design optimization with limited offline data. We apply DevFoemer to the problem of decoupling capacitor placement and show that it outperforms state-of-the-art methods in both simulated and real hardware, leading to improved performances while reducing the number of components by more than 30%. Finally, we show that our approach achieves promising results in other offline contextual learning-based combinatorial optimization tasks.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 23 code samples harvested from 3 repositories linked to this paper: 16 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 2 repositories, 12 ran (6 with no instrument failure; 6 where Syntology's instrument failed); community (archive-listed): 4 samples from 1 repository, 4 ran (3 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

kaist-silab/devformer officialmentioned in papermentioned on GitHubpytorchMITSyntology: 13 samples, 8 ran (6 instrument-failed) · 5 unverified report
kaist-silab/dppbench officialmentioned in papermentioned on GitHubpytorchSyntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
ai4co/llm-as-hh mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution (arXiv:2402.01145; that paper's own run record: 5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
ai4co/reevo mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (1 instrument-failed) · 0 unverified report
kaist-silab/symmetric_replay mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to POMO: Policy Optimization with Multiple Optima for Reinforcement Learning (arXiv:2010.16011; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified) and Matrix Encoding Networks for Neural Combinatorial Optimization (arXiv:2106.11113; that paper's own run record: 4 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

23 samples harvested: 16 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran · our draft was wrong
2ran; the contract check could not run
9ran
7unverified

Licence: 2 of the 23 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

kaist-silab/devformer official repository 13 samples, 8 ran (6 instrument-failed) · 5 unverified
check_extension in 8 papers src/utils/data_utils.py ran · our draft was wrong fingerprinted MIT (permissive) · 01df1926cf07ac89 · report fixture: signature filename:str/0/str · returned str · level recorded 2026-09-22
format_file_size src/utils/download_anonymous_github.py ran MIT (permissive) · 0afddc8bf087bf72 · report fixture: signature size:int/0/int, decimals:int/0/int, binary_system:bool/0/bool · returned str · level recorded 2026-09-24
load_dataset in 276 papers src/utils/data_utils.py ran · our draft was wrong MIT (permissive) · 69062811f34d8ff6 · report fixture: signature filename:str/0/str · returned dict · level recorded 2026-09-24
mask_bool2long src/utils/boolmask.py ran; the contract check could not run (RAISES) MIT (permissive) · 454003b7383dce9f · report fixture: signature mask:Tensor/2/int · returned Tensor · level recorded 2026-09-24
mask_long2bool src/utils/boolmask.py ran; the contract check could not run (RAISES) MIT (permissive) · 10638ccfaa13fb59 · report fixture: signature mask:Tensor/2/int, n:NoneType/0/? · returned Tensor · level recorded 2026-09-24
mask_long_scatter src/utils/boolmask.py ran · our draft was wrong MIT (permissive) · 1a3bb2f0ebdf9a4e · report fixture: signature mask:Tensor/3/int, values:Tensor/2/int, check_unset:bool/0/bool · returned Tensor · level recorded 2026-09-24
move_to in 15 papers src/utils/functions.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 107d6628712f1a21 · report fixture: signature var:dict/0/?, device:str/0/str · returned dict · level recorded 2026-09-22
req_url src/utils/download_anonymous_github.py ran MIT (permissive) · 3996e33f11d6e05c · report fixture: signature dl_file:list/1/str, max_retry:int/0/int · returned str · level recorded 2026-09-24
backtrack in 7 papers src/utils/beam_search.py unverified MIT (permissive) · 9d5b8d4a73d01c19 · report
get_beam_search_results src/utils/beam_search.py unverified MIT (permissive) · be9c547a8e748da5 · report
get_options in 25 papers src/options.py unverified MIT (permissive) · 082646223bfd2be7 · report
load_problem in 6 papers src/utils/functions.py unverified MIT (permissive) · 303bdfb5bc7ca4ca · report
torch_load_cpu in 6 papers src/utils/functions.py unverified MIT (permissive) here; the stored copy is pointer only · 0538f709044ed305 · report
kaist-silab/dppbench official repository 6 samples, 4 ran (0 instrument-failed) · 2 unverified
DevFormerFixed src/models/devformer.py ran MIT (permissive) · 44766ff2bb80cded · report fixture: returned DevFormerFixed · level recorded 2026-09-22
GraphAttentionEncoder src/models/devformer.py ran MIT (permissive) · ee17ee53e70396c2 · report fixture: returned GraphAttentionEncoder · level recorded 2026-09-22
MultiHeadAttention in 124 papers
census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
src/models/devformer.py ran MIT (permissive) · b1e65318aee81d61 · report fixture: returned MultiHeadAttention · level recorded 2026-09-22
MultiHeadAttentionLayer in 6 papers src/models/devformer.py ran MIT (permissive) · e974ebdae8b92931 · report fixture: returned MultiHeadAttentionLayer · level recorded 2026-09-22
DevFormer src/models/devformer.py unverified MIT (permissive) · 8344a332d9a93ac4 · report
sample_many src/models/devformer.py unverified MIT (permissive) · 4fff104acbe171fa · report
ai4co/reevo community (archive-listed) 4 samples, 4 ran (1 instrument-failed) · 0 unverified
CVRP_Encoder in 6 papers problems/cvrp_lehd/VRPModel.py ran MIT (permissive) · e0e374040216e134 · report fixture: signature data_:Tensor/3/float, capacity:Tensor/0/float · returned Tensor · level recorded 2026-09-24
EncoderLayer in 73 papers problems/cvrp_lehd/VRPModel.py ran fingerprinted MIT (permissive) · 3bbb9454b0aed4ee · report fixture: signature input1:Tensor/3/float · returned Tensor · level recorded 2026-09-24
Feed_Forward_Module problems/cvrp_lehd/VRPModel.py ran fingerprinted MIT (permissive) · e4ba52635327e4e6 · report fixture: signature input1:Tensor/2/float · returned Tensor · level recorded 2026-09-24
multi_head_attention in 24 papers problems/cvrp_lehd/VRPModel.py ran · our draft was wrong MIT (permissive) · 388642e538834053 · report fixture: signature q:Tensor/4/float, k:Tensor/4/float, v:Tensor/4/float · returned Tensor · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for DevFormer (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for DevFormer (graph method: DevFormer). 5 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. CVRP_Encoder entry · level 1 · ran · e0e374040216e134
  2. EncoderLayer model · level 1 · ran · 3bbb9454b0aed4ee
  3. Feed_Forward_Module model · level 1 · ran · e4ba52635327e4e6
  4. multi_head_attention model · level 1 · ran · our draft was wrong · 388642e538834053
  5. reshape_by_heads helper · level 1 · ran · our draft was wrong · 459fe521069329c6

harvested Assembly for DevFormer (graph method: DevFormer). 11 bricks; individually on a fixture: 8 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. DevFormer entry · level 0 · unverified · 8344a332d9a93ac4
  2. CachedLookup helper · level 1 · ran · 88d0041a61c7c24e
  3. DevFormerFixed helper · level 1 · ran · 44766ff2bb80cded
  4. GraphAttentionEncoder model · level 1 · ran · ee17ee53e70396c2
  5. compute_in_batches helper · level 0 · unverified · c15e4327c52243c6
  6. sample_many helper · level 0 · unverified · 4fff104acbe171fa
  7. MultiHeadAttentionLayer model · level 1 · ran · e974ebdae8b92931
  8. do_batch_rep helper · level 1 · ran · our draft was wrong · e9cc8485dbd6af94
  9. MultiHeadAttention model · level 1 · ran · b1e65318aee81d61
  10. Normalization model · level 1 · ran · d7486b45b2dfeb02
  11. SkipConnection helper · level 1 · ran · 8101e9e48232516f

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2205.13225") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Combinatorial OptimizationMeta-Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Collaborative Distillation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections