ChipletPart: Cost-Aware Partitioning for 2.5D Systems Article Swipe
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2507.19819
Industry adoption of chiplets has been increasing as a cost-effective option for making larger high-performance systems. Consequently, partitioning large systems into chiplets is increasingly important. In this work, we introduce ChipletPart - a cost-driven 2.5D system partitioner that addresses the unique constraints of chiplet systems, including complex objective functions, limited reach of inter-chiplet I/O transceivers, and the assignment of heterogeneous manufacturing technologies to different chiplets. ChipletPart integrates a sophisticated chiplet cost model with its underlying genetic algorithm-based technology assignment and partitioning methodology, along with a simulated annealing-based chiplet floorplanner. Our results show that: (i) ChipletPart reduces chiplet cost by up to 58% (20% geometric mean) compared to state-of-the-art min-cut partitioners, which often yield floorplan-infeasible solutions; (ii) ChipletPart generates partitions with up to 47% (6% geometric mean) lower cost as compared to the prior work Floorplet; and (iii) for the testcases we study, heterogeneous integration reduces cost by up to 43% (15% geometric mean) compared to homogeneous implementations. Additionally, we explore Bayesian optimization (BO) for finding low cost and floorplan-feasible chiplet solutions with technology assignments. On some testcases, our BO framework achieves better system cost (up to 5.3% improvement) with higher runtime overhead (up to 4x) compared to our GA framework. We also present case studies that show how changes in packaging and inter-chiplet signaling technologies can affect partitioning solutions. Finally, we make ChipletPart, the underlying chiplet cost model, and a chiplet testcase generator available as open-source tools for the community.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2507.19819
- https://arxiv.org/pdf/2507.19819
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4416174531
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4416174531Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2507.19819Digital Object Identifier
- Title
-
ChipletPart: Cost-Aware Partitioning for 2.5D SystemsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-07-26Full publication date if available
- Authors
-
Alexander Graening, Puneet Gupta, Andrew B. Kahng, Bodhisatta PramanikList of authors in order
- Landing page
-
https://arxiv.org/abs/2507.19819Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2507.19819Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2507.19819Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4416174531 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2507.19819 |
| ids.doi | https://doi.org/10.48550/arxiv.2507.19819 |
| ids.openalex | https://openalex.org/W4416174531 |
| fwci | |
| type | preprint |
| title | ChipletPart: Cost-Aware Partitioning for 2.5D Systems |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2507.19819 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2507.19819 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2507.19819 |
| locations[1].id | doi:10.48550/arxiv.2507.19819 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2507.19819 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5039211292 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Alexander Graening |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Graening, Alexander |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5084229134 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-6188-1134 |
| authorships[1].author.display_name | Puneet Gupta |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Gupta, Puneet |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5113527355 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Andrew B. Kahng |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Kahng, Andrew B. |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5063613522 |
| authorships[3].author.orcid | https://orcid.org/0009-0004-6014-1048 |
| authorships[3].author.display_name | Bodhisatta Pramanik |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Pramanik, Bodhisatta |
| authorships[3].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2507.19819 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | ChipletPart: Cost-Aware Partitioning for 2.5D Systems |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-28T07:02:26.514252 |
| primary_topic | |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2507.19819 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2507.19819 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2507.19819 |
| primary_location.id | pmh:oai:arXiv.org:2507.19819 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2507.19819 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2507.19819 |
| publication_date | 2025-07-26 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.- | 31 |
| abstract_inverted_index.a | 8, 32, 67, 84, 229 |
| abstract_inverted_index.BO | 178 |
| abstract_inverted_index.GA | 198 |
| abstract_inverted_index.In | 25 |
| abstract_inverted_index.On | 174 |
| abstract_inverted_index.We | 200 |
| abstract_inverted_index.as | 7, 128, 234 |
| abstract_inverted_index.by | 98, 146 |
| abstract_inverted_index.in | 209 |
| abstract_inverted_index.is | 22 |
| abstract_inverted_index.of | 2, 42, 51, 58 |
| abstract_inverted_index.to | 62, 100, 106, 121, 130, 148, 154, 185, 193, 196 |
| abstract_inverted_index.up | 99, 120, 147 |
| abstract_inverted_index.we | 28, 140, 158, 220 |
| abstract_inverted_index.(6% | 123 |
| abstract_inverted_index.(i) | 93 |
| abstract_inverted_index.(up | 184, 192 |
| abstract_inverted_index.43% | 149 |
| abstract_inverted_index.47% | 122 |
| abstract_inverted_index.4x) | 194 |
| abstract_inverted_index.58% | 101 |
| abstract_inverted_index.I/O | 53 |
| abstract_inverted_index.Our | 89 |
| abstract_inverted_index.and | 55, 79, 135, 167, 211, 228 |
| abstract_inverted_index.can | 215 |
| abstract_inverted_index.for | 11, 137, 163, 237 |
| abstract_inverted_index.has | 4 |
| abstract_inverted_index.how | 207 |
| abstract_inverted_index.its | 73 |
| abstract_inverted_index.low | 165 |
| abstract_inverted_index.our | 177, 197 |
| abstract_inverted_index.the | 39, 56, 131, 138, 223, 238 |
| abstract_inverted_index.(15% | 150 |
| abstract_inverted_index.(20% | 102 |
| abstract_inverted_index.(BO) | 162 |
| abstract_inverted_index.(ii) | 115 |
| abstract_inverted_index.2.5D | 34 |
| abstract_inverted_index.5.3% | 186 |
| abstract_inverted_index.also | 201 |
| abstract_inverted_index.been | 5 |
| abstract_inverted_index.case | 203 |
| abstract_inverted_index.cost | 70, 97, 127, 145, 166, 183, 226 |
| abstract_inverted_index.into | 20 |
| abstract_inverted_index.make | 221 |
| abstract_inverted_index.show | 91, 206 |
| abstract_inverted_index.some | 175 |
| abstract_inverted_index.that | 37, 205 |
| abstract_inverted_index.this | 26 |
| abstract_inverted_index.with | 72, 83, 119, 171, 188 |
| abstract_inverted_index.work | 133 |
| abstract_inverted_index.(iii) | 136 |
| abstract_inverted_index.along | 82 |
| abstract_inverted_index.large | 18 |
| abstract_inverted_index.lower | 126 |
| abstract_inverted_index.mean) | 104, 125, 152 |
| abstract_inverted_index.model | 71 |
| abstract_inverted_index.often | 111 |
| abstract_inverted_index.prior | 132 |
| abstract_inverted_index.reach | 50 |
| abstract_inverted_index.that: | 92 |
| abstract_inverted_index.tools | 236 |
| abstract_inverted_index.which | 110 |
| abstract_inverted_index.work, | 27 |
| abstract_inverted_index.yield | 112 |
| abstract_inverted_index.affect | 216 |
| abstract_inverted_index.better | 181 |
| abstract_inverted_index.higher | 189 |
| abstract_inverted_index.larger | 13 |
| abstract_inverted_index.making | 12 |
| abstract_inverted_index.model, | 227 |
| abstract_inverted_index.option | 10 |
| abstract_inverted_index.study, | 141 |
| abstract_inverted_index.system | 35, 182 |
| abstract_inverted_index.unique | 40 |
| abstract_inverted_index.changes | 208 |
| abstract_inverted_index.chiplet | 43, 69, 87, 96, 169, 225, 230 |
| abstract_inverted_index.complex | 46 |
| abstract_inverted_index.explore | 159 |
| abstract_inverted_index.finding | 164 |
| abstract_inverted_index.genetic | 75 |
| abstract_inverted_index.limited | 49 |
| abstract_inverted_index.min-cut | 108 |
| abstract_inverted_index.present | 202 |
| abstract_inverted_index.reduces | 95, 144 |
| abstract_inverted_index.results | 90 |
| abstract_inverted_index.runtime | 190 |
| abstract_inverted_index.studies | 204 |
| abstract_inverted_index.systems | 19 |
| abstract_inverted_index.Bayesian | 160 |
| abstract_inverted_index.Finally, | 219 |
| abstract_inverted_index.Industry | 0 |
| abstract_inverted_index.achieves | 180 |
| abstract_inverted_index.adoption | 1 |
| abstract_inverted_index.chiplets | 3, 21 |
| abstract_inverted_index.compared | 105, 129, 153, 195 |
| abstract_inverted_index.overhead | 191 |
| abstract_inverted_index.systems, | 44 |
| abstract_inverted_index.systems. | 15 |
| abstract_inverted_index.testcase | 231 |
| abstract_inverted_index.addresses | 38 |
| abstract_inverted_index.available | 233 |
| abstract_inverted_index.chiplets. | 64 |
| abstract_inverted_index.different | 63 |
| abstract_inverted_index.framework | 179 |
| abstract_inverted_index.generates | 117 |
| abstract_inverted_index.generator | 232 |
| abstract_inverted_index.geometric | 103, 124, 151 |
| abstract_inverted_index.including | 45 |
| abstract_inverted_index.introduce | 29 |
| abstract_inverted_index.objective | 47 |
| abstract_inverted_index.packaging | 210 |
| abstract_inverted_index.signaling | 213 |
| abstract_inverted_index.simulated | 85 |
| abstract_inverted_index.solutions | 170 |
| abstract_inverted_index.testcases | 139 |
| abstract_inverted_index.Floorplet; | 134 |
| abstract_inverted_index.assignment | 57, 78 |
| abstract_inverted_index.community. | 239 |
| abstract_inverted_index.framework. | 199 |
| abstract_inverted_index.functions, | 48 |
| abstract_inverted_index.important. | 24 |
| abstract_inverted_index.increasing | 6 |
| abstract_inverted_index.integrates | 66 |
| abstract_inverted_index.partitions | 118 |
| abstract_inverted_index.solutions. | 218 |
| abstract_inverted_index.solutions; | 114 |
| abstract_inverted_index.technology | 77, 172 |
| abstract_inverted_index.testcases, | 176 |
| abstract_inverted_index.underlying | 74, 224 |
| abstract_inverted_index.ChipletPart | 30, 65, 94, 116 |
| abstract_inverted_index.constraints | 41 |
| abstract_inverted_index.cost-driven | 33 |
| abstract_inverted_index.homogeneous | 155 |
| abstract_inverted_index.integration | 143 |
| abstract_inverted_index.open-source | 235 |
| abstract_inverted_index.partitioner | 36 |
| abstract_inverted_index.ChipletPart, | 222 |
| abstract_inverted_index.assignments. | 173 |
| abstract_inverted_index.improvement) | 187 |
| abstract_inverted_index.increasingly | 23 |
| abstract_inverted_index.methodology, | 81 |
| abstract_inverted_index.optimization | 161 |
| abstract_inverted_index.partitioning | 17, 80, 217 |
| abstract_inverted_index.technologies | 61, 214 |
| abstract_inverted_index.Additionally, | 157 |
| abstract_inverted_index.Consequently, | 16 |
| abstract_inverted_index.floorplanner. | 88 |
| abstract_inverted_index.heterogeneous | 59, 142 |
| abstract_inverted_index.inter-chiplet | 52, 212 |
| abstract_inverted_index.manufacturing | 60 |
| abstract_inverted_index.partitioners, | 109 |
| abstract_inverted_index.sophisticated | 68 |
| abstract_inverted_index.transceivers, | 54 |
| abstract_inverted_index.cost-effective | 9 |
| abstract_inverted_index.algorithm-based | 76 |
| abstract_inverted_index.annealing-based | 86 |
| abstract_inverted_index.high-performance | 14 |
| abstract_inverted_index.implementations. | 156 |
| abstract_inverted_index.state-of-the-art | 107 |
| abstract_inverted_index.floorplan-feasible | 168 |
| abstract_inverted_index.floorplan-infeasible | 113 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |