TopSort: A High-Performance Two-Phase Sorting Accelerator Optimized on HBM-based FPGAs Article Swipe
Weikang Qiao
,
Licheng Guo
,
Zhenman Fang
,
Mau-Chung Frank Chang
,
Jason Cong
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2205.07991
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2205.07991
The emergence of high-bandwidth memory (HBM) brings new opportunities to boost the performance of sorting acceleration on FPGAs, which was conventionally bounded by the available off-chip memory bandwidth. However, it is nontrivial for designers to fully utilize this immense bandwidth. First, the existing sorter designs cannot be directly scaled at the increasing rate of available off-chip bandwidth, as the required on-chip resource usage grows at a much faster rate and would bound the sorting performance in turn. Second, designers need an in-depth understanding of HBM characteristics to effectively utilize the HBM bandwidth. To tackle these challenges, we present TopSort, a novel two-phase sorting solution optimized for HBM-based FPGAs. In the first phase, 16 merge trees work in parallel to fully utilize 32 HBM channels. In the second phase, TopSort reuses the logic from phase one to form a wider merge tree to merge the partially sorted results from phase one. TopSort also adopts HBM-specific optimizations to reduce resource overhead and improve bandwidth utilization. TopSort can sort up to 4 GB data using all 32 HBM channels, with an overall sorting performance of 15.6 GB/s. TopSort is 6.7x and 2.2x faster than state-of-the-art CPU and FPGA sorters.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2205.07991
- https://arxiv.org/pdf/2205.07991
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4307695148
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4307695148Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2205.07991Digital Object Identifier
- Title
-
TopSort: A High-Performance Two-Phase Sorting Accelerator Optimized on HBM-based FPGAsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-05-16Full publication date if available
- Authors
-
Weikang Qiao, Licheng Guo, Zhenman Fang, Mau-Chung Frank Chang, Jason CongList of authors in order
- Landing page
-
https://arxiv.org/abs/2205.07991Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2205.07991Direct 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/2205.07991Direct OA link when available
- Concepts
-
Merge sort, Computer science, Merge (version control), Field-programmable gate array, Bandwidth (computing), Chip, sort, Embedded system, Sorting, Parallel computing, Sorting algorithm, Algorithm, Computer network, Telecommunications, Information retrievalTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4307695148 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2205.07991 |
| ids.doi | https://doi.org/10.48550/arxiv.2205.07991 |
| ids.openalex | https://openalex.org/W4307695148 |
| fwci | |
| type | preprint |
| title | TopSort: A High-Performance Two-Phase Sorting Accelerator Optimized on HBM-based FPGAs |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10829 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9997000098228455 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1705 |
| topics[0].subfield.display_name | Computer Networks and Communications |
| topics[0].display_name | Interconnection Networks and Systems |
| topics[1].id | https://openalex.org/T10054 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9991999864578247 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1708 |
| topics[1].subfield.display_name | Hardware and Architecture |
| topics[1].display_name | Parallel Computing and Optimization Techniques |
| topics[2].id | https://openalex.org/T11269 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9980999827384949 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Algorithms and Data Compression |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C35555965 |
| concepts[0].level | 4 |
| concepts[0].score | 0.8222298622131348 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q189057 |
| concepts[0].display_name | Merge sort |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7594339847564697 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C197129107 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6698793768882751 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1921621 |
| concepts[2].display_name | Merge (version control) |
| concepts[3].id | https://openalex.org/C42935608 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6592950224876404 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q190411 |
| concepts[3].display_name | Field-programmable gate array |
| concepts[4].id | https://openalex.org/C2776257435 |
| concepts[4].level | 2 |
| concepts[4].score | 0.6117892861366272 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q1576430 |
| concepts[4].display_name | Bandwidth (computing) |
| concepts[5].id | https://openalex.org/C165005293 |
| concepts[5].level | 2 |
| concepts[5].score | 0.4755396842956543 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1074500 |
| concepts[5].display_name | Chip |
| concepts[6].id | https://openalex.org/C88548561 |
| concepts[6].level | 2 |
| concepts[6].score | 0.47133755683898926 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q347599 |
| concepts[6].display_name | sort |
| concepts[7].id | https://openalex.org/C149635348 |
| concepts[7].level | 1 |
| concepts[7].score | 0.4063534736633301 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q193040 |
| concepts[7].display_name | Embedded system |
| concepts[8].id | https://openalex.org/C111696304 |
| concepts[8].level | 2 |
| concepts[8].score | 0.387321412563324 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2303697 |
| concepts[8].display_name | Sorting |
| concepts[9].id | https://openalex.org/C173608175 |
| concepts[9].level | 1 |
| concepts[9].score | 0.3708139657974243 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q232661 |
| concepts[9].display_name | Parallel computing |
| concepts[10].id | https://openalex.org/C108094655 |
| concepts[10].level | 3 |
| concepts[10].score | 0.32419759035110474 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q181593 |
| concepts[10].display_name | Sorting algorithm |
| concepts[11].id | https://openalex.org/C11413529 |
| concepts[11].level | 1 |
| concepts[11].score | 0.16917133331298828 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[11].display_name | Algorithm |
| concepts[12].id | https://openalex.org/C31258907 |
| concepts[12].level | 1 |
| concepts[12].score | 0.11295449733734131 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q1301371 |
| concepts[12].display_name | Computer network |
| concepts[13].id | https://openalex.org/C76155785 |
| concepts[13].level | 1 |
| concepts[13].score | 0.087105393409729 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q418 |
| concepts[13].display_name | Telecommunications |
| concepts[14].id | https://openalex.org/C23123220 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q816826 |
| concepts[14].display_name | Information retrieval |
| keywords[0].id | https://openalex.org/keywords/merge-sort |
| keywords[0].score | 0.8222298622131348 |
| keywords[0].display_name | Merge sort |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7594339847564697 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/merge |
| keywords[2].score | 0.6698793768882751 |
| keywords[2].display_name | Merge (version control) |
| keywords[3].id | https://openalex.org/keywords/field-programmable-gate-array |
| keywords[3].score | 0.6592950224876404 |
| keywords[3].display_name | Field-programmable gate array |
| keywords[4].id | https://openalex.org/keywords/bandwidth |
| keywords[4].score | 0.6117892861366272 |
| keywords[4].display_name | Bandwidth (computing) |
| keywords[5].id | https://openalex.org/keywords/chip |
| keywords[5].score | 0.4755396842956543 |
| keywords[5].display_name | Chip |
| keywords[6].id | https://openalex.org/keywords/sort |
| keywords[6].score | 0.47133755683898926 |
| keywords[6].display_name | sort |
| keywords[7].id | https://openalex.org/keywords/embedded-system |
| keywords[7].score | 0.4063534736633301 |
| keywords[7].display_name | Embedded system |
| keywords[8].id | https://openalex.org/keywords/sorting |
| keywords[8].score | 0.387321412563324 |
| keywords[8].display_name | Sorting |
| keywords[9].id | https://openalex.org/keywords/parallel-computing |
| keywords[9].score | 0.3708139657974243 |
| keywords[9].display_name | Parallel computing |
| keywords[10].id | https://openalex.org/keywords/sorting-algorithm |
| keywords[10].score | 0.32419759035110474 |
| keywords[10].display_name | Sorting algorithm |
| keywords[11].id | https://openalex.org/keywords/algorithm |
| keywords[11].score | 0.16917133331298828 |
| keywords[11].display_name | Algorithm |
| keywords[12].id | https://openalex.org/keywords/computer-network |
| keywords[12].score | 0.11295449733734131 |
| keywords[12].display_name | Computer network |
| keywords[13].id | https://openalex.org/keywords/telecommunications |
| keywords[13].score | 0.087105393409729 |
| keywords[13].display_name | Telecommunications |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2205.07991 |
| 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/2205.07991 |
| 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/2205.07991 |
| locations[1].id | doi:10.48550/arxiv.2205.07991 |
| 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.2205.07991 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5003981003 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-1946-2021 |
| authorships[0].author.display_name | Weikang Qiao |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Qiao, Weikang |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5032647120 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-0705-9510 |
| authorships[1].author.display_name | Licheng Guo |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Guo, Licheng |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5065889904 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-0603-9697 |
| authorships[2].author.display_name | Zhenman Fang |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Fang, Zhenman |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5051454330 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-2934-9359 |
| authorships[3].author.display_name | Mau-Chung Frank Chang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Chang, Mau-Chung Frank |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5016776689 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-2887-6963 |
| authorships[4].author.display_name | Jason Cong |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Cong, Jason |
| authorships[4].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2205.07991 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2022-11-05T00:00:00 |
| display_name | TopSort: A High-Performance Two-Phase Sorting Accelerator Optimized on HBM-based FPGAs |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10829 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9997000098228455 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1705 |
| primary_topic.subfield.display_name | Computer Networks and Communications |
| primary_topic.display_name | Interconnection Networks and Systems |
| related_works | https://openalex.org/W2085265870, https://openalex.org/W2362374543, https://openalex.org/W2348196682, https://openalex.org/W2977813765, https://openalex.org/W3038595913, https://openalex.org/W2267918355, https://openalex.org/W2908348257, https://openalex.org/W29303620, https://openalex.org/W2054358146, https://openalex.org/W2945185559 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2205.07991 |
| 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/2205.07991 |
| 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/2205.07991 |
| primary_location.id | pmh:oai:arXiv.org:2205.07991 |
| 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/2205.07991 |
| 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/2205.07991 |
| publication_date | 2022-05-16 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.4 | 168 |
| abstract_inverted_index.a | 65, 99, 137 |
| abstract_inverted_index.16 | 112 |
| abstract_inverted_index.32 | 121, 173 |
| abstract_inverted_index.GB | 169 |
| abstract_inverted_index.In | 108, 124 |
| abstract_inverted_index.To | 92 |
| abstract_inverted_index.an | 80, 177 |
| abstract_inverted_index.as | 57 |
| abstract_inverted_index.at | 49, 64 |
| abstract_inverted_index.be | 46 |
| abstract_inverted_index.by | 22 |
| abstract_inverted_index.in | 75, 116 |
| abstract_inverted_index.is | 30, 185 |
| abstract_inverted_index.it | 29 |
| abstract_inverted_index.of | 2, 13, 53, 83, 181 |
| abstract_inverted_index.on | 16 |
| abstract_inverted_index.to | 9, 34, 86, 118, 135, 141, 155, 167 |
| abstract_inverted_index.up | 166 |
| abstract_inverted_index.we | 96 |
| abstract_inverted_index.CPU | 192 |
| abstract_inverted_index.HBM | 84, 90, 122, 174 |
| abstract_inverted_index.The | 0 |
| abstract_inverted_index.all | 172 |
| abstract_inverted_index.and | 69, 159, 187, 193 |
| abstract_inverted_index.can | 164 |
| abstract_inverted_index.for | 32, 105 |
| abstract_inverted_index.new | 7 |
| abstract_inverted_index.one | 134 |
| abstract_inverted_index.the | 11, 23, 41, 50, 58, 72, 89, 109, 125, 130, 143 |
| abstract_inverted_index.was | 19 |
| abstract_inverted_index.15.6 | 182 |
| abstract_inverted_index.2.2x | 188 |
| abstract_inverted_index.6.7x | 186 |
| abstract_inverted_index.FPGA | 194 |
| abstract_inverted_index.also | 151 |
| abstract_inverted_index.data | 170 |
| abstract_inverted_index.form | 136 |
| abstract_inverted_index.from | 132, 147 |
| abstract_inverted_index.much | 66 |
| abstract_inverted_index.need | 79 |
| abstract_inverted_index.one. | 149 |
| abstract_inverted_index.rate | 52, 68 |
| abstract_inverted_index.sort | 165 |
| abstract_inverted_index.than | 190 |
| abstract_inverted_index.this | 37 |
| abstract_inverted_index.tree | 140 |
| abstract_inverted_index.with | 176 |
| abstract_inverted_index.work | 115 |
| abstract_inverted_index.(HBM) | 5 |
| abstract_inverted_index.GB/s. | 183 |
| abstract_inverted_index.boost | 10 |
| abstract_inverted_index.bound | 71 |
| abstract_inverted_index.first | 110 |
| abstract_inverted_index.fully | 35, 119 |
| abstract_inverted_index.grows | 63 |
| abstract_inverted_index.logic | 131 |
| abstract_inverted_index.merge | 113, 139, 142 |
| abstract_inverted_index.novel | 100 |
| abstract_inverted_index.phase | 133, 148 |
| abstract_inverted_index.these | 94 |
| abstract_inverted_index.trees | 114 |
| abstract_inverted_index.turn. | 76 |
| abstract_inverted_index.usage | 62 |
| abstract_inverted_index.using | 171 |
| abstract_inverted_index.which | 18 |
| abstract_inverted_index.wider | 138 |
| abstract_inverted_index.would | 70 |
| abstract_inverted_index.FPGAs, | 17 |
| abstract_inverted_index.FPGAs. | 107 |
| abstract_inverted_index.First, | 40 |
| abstract_inverted_index.adopts | 152 |
| abstract_inverted_index.brings | 6 |
| abstract_inverted_index.cannot | 45 |
| abstract_inverted_index.faster | 67, 189 |
| abstract_inverted_index.memory | 4, 26 |
| abstract_inverted_index.phase, | 111, 127 |
| abstract_inverted_index.reduce | 156 |
| abstract_inverted_index.reuses | 129 |
| abstract_inverted_index.scaled | 48 |
| abstract_inverted_index.second | 126 |
| abstract_inverted_index.sorted | 145 |
| abstract_inverted_index.sorter | 43 |
| abstract_inverted_index.tackle | 93 |
| abstract_inverted_index.Second, | 77 |
| abstract_inverted_index.TopSort | 128, 150, 163, 184 |
| abstract_inverted_index.bounded | 21 |
| abstract_inverted_index.designs | 44 |
| abstract_inverted_index.immense | 38 |
| abstract_inverted_index.improve | 160 |
| abstract_inverted_index.on-chip | 60 |
| abstract_inverted_index.overall | 178 |
| abstract_inverted_index.present | 97 |
| abstract_inverted_index.results | 146 |
| abstract_inverted_index.sorting | 14, 73, 102, 179 |
| abstract_inverted_index.utilize | 36, 88, 120 |
| abstract_inverted_index.However, | 28 |
| abstract_inverted_index.TopSort, | 98 |
| abstract_inverted_index.directly | 47 |
| abstract_inverted_index.existing | 42 |
| abstract_inverted_index.in-depth | 81 |
| abstract_inverted_index.off-chip | 25, 55 |
| abstract_inverted_index.overhead | 158 |
| abstract_inverted_index.parallel | 117 |
| abstract_inverted_index.required | 59 |
| abstract_inverted_index.resource | 61, 157 |
| abstract_inverted_index.solution | 103 |
| abstract_inverted_index.sorters. | 195 |
| abstract_inverted_index.HBM-based | 106 |
| abstract_inverted_index.available | 24, 54 |
| abstract_inverted_index.bandwidth | 161 |
| abstract_inverted_index.channels, | 175 |
| abstract_inverted_index.channels. | 123 |
| abstract_inverted_index.designers | 33, 78 |
| abstract_inverted_index.emergence | 1 |
| abstract_inverted_index.optimized | 104 |
| abstract_inverted_index.partially | 144 |
| abstract_inverted_index.two-phase | 101 |
| abstract_inverted_index.bandwidth, | 56 |
| abstract_inverted_index.bandwidth. | 27, 39, 91 |
| abstract_inverted_index.increasing | 51 |
| abstract_inverted_index.nontrivial | 31 |
| abstract_inverted_index.challenges, | 95 |
| abstract_inverted_index.effectively | 87 |
| abstract_inverted_index.performance | 12, 74, 180 |
| abstract_inverted_index.HBM-specific | 153 |
| abstract_inverted_index.acceleration | 15 |
| abstract_inverted_index.utilization. | 162 |
| abstract_inverted_index.opportunities | 8 |
| abstract_inverted_index.optimizations | 154 |
| abstract_inverted_index.understanding | 82 |
| abstract_inverted_index.conventionally | 20 |
| abstract_inverted_index.high-bandwidth | 3 |
| abstract_inverted_index.characteristics | 85 |
| abstract_inverted_index.state-of-the-art | 191 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile |