SparGD: A Sparse GEMM Accelerator with Dynamic Dataflow Article Swipe
Bo Wang
,
Sheng Ma
,
Shengbai Luo
,
Lizhou Wu
,
Jianmin Zhang
,
Chunyuan Zhang
,
Tiejun Li
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.1145/3634703
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.1145/3634703
Deep learning has become a highly popular research field, and previously deep learning algorithms ran primarily on CPUs and GPUs. However, with the rapid development of deep learning, it was discovered that existing processors could not meet the specific large-scale computing requirements of deep learning, and custom deep learning accelerators have become popular. The majority of the primary workloads in deep learning are general matrix-matrix multiplications (GEMMs), and emerging GEMMs are highly sparse and irregular. The TPU and SIGMA are typical GEMM accelerators in recent years, but the TPU does not support sparsity, and both the TPU and SIGMA have insufficient utilization rates of the Processing Element (PE). We design and implement SparGD, a sparse GEMM accelerator with dynamic dataflow. SparGD has specific PE structures, flexible distribution networks and reduction networks, and a simple dataflow switching module. When running sparse and irregular GEMMs, SparGD can maintain high PE utilization while utilizing sparsity, and can switch to the optimal dataflow according to the computing environment. For sparse, irregular GEMMs, our experimental results show that SparGD outperforms systolic arrays by 30 times and SIGMA by 3.6 times.
Related Topics
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1145/3634703
- https://dl.acm.org/doi/pdf/10.1145/3634703
- OA Status
- hybrid
- Cited By
- 6
- References
- 34
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4389046642
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4389046642Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1145/3634703Digital Object Identifier
- Title
-
SparGD: A Sparse GEMM Accelerator with Dynamic DataflowWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-11-27Full publication date if available
- Authors
-
Bo Wang, Sheng Ma, Shengbai Luo, Lizhou Wu, Jianmin Zhang, Chunyuan Zhang, Tiejun LiList of authors in order
- Landing page
-
https://doi.org/10.1145/3634703Publisher landing page
- PDF URL
-
https://dl.acm.org/doi/pdf/10.1145/3634703Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
hybridOpen access status per OpenAlex
- OA URL
-
https://dl.acm.org/doi/pdf/10.1145/3634703Direct OA link when available
- Concepts
-
Dataflow, Computer science, Parallel computing, Computational science, Computer architectureTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
6Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 5, 2024: 1Per-year citation counts (last 5 years)
- References (count)
-
34Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4389046642 |
|---|---|
| doi | https://doi.org/10.1145/3634703 |
| ids.doi | https://doi.org/10.1145/3634703 |
| ids.openalex | https://openalex.org/W4389046642 |
| fwci | 0.47593601 |
| type | article |
| title | SparGD: A Sparse GEMM Accelerator with Dynamic Dataflow |
| awards[0].id | https://openalex.org/G8613193636 |
| awards[0].funder_id | https://openalex.org/F4320321001 |
| awards[0].display_name | |
| awards[0].funder_award_id | 62172430 |
| awards[0].funder_display_name | National Natural Science Foundation of China |
| biblio.issue | 2 |
| biblio.volume | 29 |
| biblio.last_page | 32 |
| biblio.first_page | 1 |
| topics[0].id | https://openalex.org/T11044 |
| topics[0].field.id | https://openalex.org/fields/31 |
| topics[0].field.display_name | Physics and Astronomy |
| topics[0].score | 0.9991000294685364 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/3106 |
| topics[0].subfield.display_name | Nuclear and High Energy Physics |
| topics[0].display_name | Particle Detector Development and Performance |
| 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 | 0.9984999895095825 |
| 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/T11181 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9973000288009644 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1705 |
| topics[2].subfield.display_name | Computer Networks and Communications |
| topics[2].display_name | Advanced Data Storage Technologies |
| funders[0].id | https://openalex.org/F4320321001 |
| funders[0].ror | https://ror.org/01h0zpd94 |
| funders[0].display_name | National Natural Science Foundation of China |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C96324660 |
| concepts[0].level | 2 |
| concepts[0].score | 0.9341293573379517 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q205446 |
| concepts[0].display_name | Dataflow |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.910722017288208 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C173608175 |
| concepts[2].level | 1 |
| concepts[2].score | 0.716931939125061 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q232661 |
| concepts[2].display_name | Parallel computing |
| concepts[3].id | https://openalex.org/C459310 |
| concepts[3].level | 1 |
| concepts[3].score | 0.3980615735054016 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q117801 |
| concepts[3].display_name | Computational science |
| concepts[4].id | https://openalex.org/C118524514 |
| concepts[4].level | 1 |
| concepts[4].score | 0.34330087900161743 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q173212 |
| concepts[4].display_name | Computer architecture |
| keywords[0].id | https://openalex.org/keywords/dataflow |
| keywords[0].score | 0.9341293573379517 |
| keywords[0].display_name | Dataflow |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.910722017288208 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/parallel-computing |
| keywords[2].score | 0.716931939125061 |
| keywords[2].display_name | Parallel computing |
| keywords[3].id | https://openalex.org/keywords/computational-science |
| keywords[3].score | 0.3980615735054016 |
| keywords[3].display_name | Computational science |
| keywords[4].id | https://openalex.org/keywords/computer-architecture |
| keywords[4].score | 0.34330087900161743 |
| keywords[4].display_name | Computer architecture |
| language | en |
| locations[0].id | doi:10.1145/3634703 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S105046310 |
| locations[0].source.issn | 1084-4309, 1557-7309 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 1084-4309 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | ACM Transactions on Design Automation of Electronic Systems |
| locations[0].source.host_organization | https://openalex.org/P4310319798 |
| locations[0].source.host_organization_name | Association for Computing Machinery |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310319798 |
| locations[0].source.host_organization_lineage_names | Association for Computing Machinery |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://dl.acm.org/doi/pdf/10.1145/3634703 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | ACM Transactions on Design Automation of Electronic Systems |
| locations[0].landing_page_url | https://doi.org/10.1145/3634703 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5111365385 |
| authorships[0].author.orcid | https://orcid.org/0009-0004-9441-0509 |
| authorships[0].author.display_name | Bo Wang |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I170215575 |
| authorships[0].affiliations[0].raw_affiliation_string | School of Computer, National University of Defense Technology, China |
| authorships[0].institutions[0].id | https://openalex.org/I170215575 |
| authorships[0].institutions[0].ror | https://ror.org/05d2yfz11 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I170215575 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | National University of Defense Technology |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Bo Wang |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | School of Computer, National University of Defense Technology, China |
| authorships[1].author.id | https://openalex.org/A5100760813 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-1710-4060 |
| authorships[1].author.display_name | Sheng Ma |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I170215575 |
| authorships[1].affiliations[0].raw_affiliation_string | School of Computer, National University of Defense Technology, China |
| authorships[1].institutions[0].id | https://openalex.org/I170215575 |
| authorships[1].institutions[0].ror | https://ror.org/05d2yfz11 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I170215575 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | National University of Defense Technology |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Sheng Ma |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | School of Computer, National University of Defense Technology, China |
| authorships[2].author.id | https://openalex.org/A5102638449 |
| authorships[2].author.orcid | https://orcid.org/0009-0007-5551-2897 |
| authorships[2].author.display_name | Shengbai Luo |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I170215575 |
| authorships[2].affiliations[0].raw_affiliation_string | School of Computer, National University of Defense Technology, China |
| authorships[2].institutions[0].id | https://openalex.org/I170215575 |
| authorships[2].institutions[0].ror | https://ror.org/05d2yfz11 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I170215575 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | National University of Defense Technology |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Shengbai Luo |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | School of Computer, National University of Defense Technology, China |
| authorships[3].author.id | https://openalex.org/A5009217361 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-4439-7436 |
| authorships[3].author.display_name | Lizhou Wu |
| authorships[3].countries | CN |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I170215575 |
| authorships[3].affiliations[0].raw_affiliation_string | School of Computer, National University of Defense Technology, China |
| authorships[3].institutions[0].id | https://openalex.org/I170215575 |
| authorships[3].institutions[0].ror | https://ror.org/05d2yfz11 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I170215575 |
| authorships[3].institutions[0].country_code | CN |
| authorships[3].institutions[0].display_name | National University of Defense Technology |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Lizhou Wu |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | School of Computer, National University of Defense Technology, China |
| authorships[4].author.id | https://openalex.org/A5111365403 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-1008-4805 |
| authorships[4].author.display_name | Jianmin Zhang |
| authorships[4].countries | CN |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I170215575 |
| authorships[4].affiliations[0].raw_affiliation_string | School of Computer, National University of Defense Technology, China |
| authorships[4].institutions[0].id | https://openalex.org/I170215575 |
| authorships[4].institutions[0].ror | https://ror.org/05d2yfz11 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I170215575 |
| authorships[4].institutions[0].country_code | CN |
| authorships[4].institutions[0].display_name | National University of Defense Technology |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Jianmin Zhang |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | School of Computer, National University of Defense Technology, China |
| authorships[5].author.id | https://openalex.org/A5100710936 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-0944-2708 |
| authorships[5].author.display_name | Chunyuan Zhang |
| authorships[5].countries | CN |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I170215575 |
| authorships[5].affiliations[0].raw_affiliation_string | School of Computer, National University of Defense Technology, China |
| authorships[5].institutions[0].id | https://openalex.org/I170215575 |
| authorships[5].institutions[0].ror | https://ror.org/05d2yfz11 |
| authorships[5].institutions[0].type | education |
| authorships[5].institutions[0].lineage | https://openalex.org/I170215575 |
| authorships[5].institutions[0].country_code | CN |
| authorships[5].institutions[0].display_name | National University of Defense Technology |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Chunyuan Zhang |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | School of Computer, National University of Defense Technology, China |
| authorships[6].author.id | https://openalex.org/A5101633853 |
| authorships[6].author.orcid | https://orcid.org/0000-0003-1509-1761 |
| authorships[6].author.display_name | Tiejun Li |
| authorships[6].countries | CN |
| authorships[6].affiliations[0].institution_ids | https://openalex.org/I170215575 |
| authorships[6].affiliations[0].raw_affiliation_string | School of Computer, National University of Defense Technology, China |
| authorships[6].institutions[0].id | https://openalex.org/I170215575 |
| authorships[6].institutions[0].ror | https://ror.org/05d2yfz11 |
| authorships[6].institutions[0].type | education |
| authorships[6].institutions[0].lineage | https://openalex.org/I170215575 |
| authorships[6].institutions[0].country_code | CN |
| authorships[6].institutions[0].display_name | National University of Defense Technology |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Tiejun Li |
| authorships[6].is_corresponding | False |
| authorships[6].raw_affiliation_strings | School of Computer, National University of Defense Technology, China |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://dl.acm.org/doi/pdf/10.1145/3634703 |
| open_access.oa_status | hybrid |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | SparGD: A Sparse GEMM Accelerator with Dynamic Dataflow |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T11044 |
| primary_topic.field.id | https://openalex.org/fields/31 |
| primary_topic.field.display_name | Physics and Astronomy |
| primary_topic.score | 0.9991000294685364 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/3106 |
| primary_topic.subfield.display_name | Nuclear and High Energy Physics |
| primary_topic.display_name | Particle Detector Development and Performance |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2748952813, https://openalex.org/W2293118914, https://openalex.org/W2998381397, https://openalex.org/W4236419692, https://openalex.org/W3167919718, https://openalex.org/W4251718783, https://openalex.org/W2171015181, https://openalex.org/W4239447582, https://openalex.org/W1998888015 |
| cited_by_count | 6 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 5 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 1 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1145/3634703 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S105046310 |
| best_oa_location.source.issn | 1084-4309, 1557-7309 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | 1084-4309 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | ACM Transactions on Design Automation of Electronic Systems |
| best_oa_location.source.host_organization | https://openalex.org/P4310319798 |
| best_oa_location.source.host_organization_name | Association for Computing Machinery |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310319798 |
| best_oa_location.source.host_organization_lineage_names | Association for Computing Machinery |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://dl.acm.org/doi/pdf/10.1145/3634703 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | ACM Transactions on Design Automation of Electronic Systems |
| best_oa_location.landing_page_url | https://doi.org/10.1145/3634703 |
| primary_location.id | doi:10.1145/3634703 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S105046310 |
| primary_location.source.issn | 1084-4309, 1557-7309 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 1084-4309 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | ACM Transactions on Design Automation of Electronic Systems |
| primary_location.source.host_organization | https://openalex.org/P4310319798 |
| primary_location.source.host_organization_name | Association for Computing Machinery |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310319798 |
| primary_location.source.host_organization_lineage_names | Association for Computing Machinery |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://dl.acm.org/doi/pdf/10.1145/3634703 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | ACM Transactions on Design Automation of Electronic Systems |
| primary_location.landing_page_url | https://doi.org/10.1145/3634703 |
| publication_date | 2023-11-27 |
| publication_year | 2023 |
| referenced_works | https://openalex.org/W3158146252, https://openalex.org/W2516141709, https://openalex.org/W2289252105, https://openalex.org/W2945146780, https://openalex.org/W3187481008, https://openalex.org/W3213528054, https://openalex.org/W2979439447, https://openalex.org/W2962949934, https://openalex.org/W2285660444, https://openalex.org/W2979310060, https://openalex.org/W1999085092, https://openalex.org/W2606722458, https://openalex.org/W2618530766, https://openalex.org/W4244024631, https://openalex.org/W2953915593, https://openalex.org/W4225287131, https://openalex.org/W2910096450, https://openalex.org/W3019166713, https://openalex.org/W4236868170, https://openalex.org/W4360831848, https://openalex.org/W4221072574, https://openalex.org/W3159727696, https://openalex.org/W3134012069, https://openalex.org/W4381050415, https://openalex.org/W3184376546, https://openalex.org/W3217357178, https://openalex.org/W3005724337, https://openalex.org/W2963577671, https://openalex.org/W4285789112, https://openalex.org/W4245223843, https://openalex.org/W2183057791, https://openalex.org/W4245659846, https://openalex.org/W4232808712, https://openalex.org/W4230315356 |
| referenced_works_count | 34 |
| abstract_inverted_index.a | 4, 113, 132 |
| abstract_inverted_index.30 | 178 |
| abstract_inverted_index.PE | 123, 147 |
| abstract_inverted_index.We | 108 |
| abstract_inverted_index.by | 177, 182 |
| abstract_inverted_index.in | 59, 83 |
| abstract_inverted_index.it | 28 |
| abstract_inverted_index.of | 25, 42, 55, 103 |
| abstract_inverted_index.on | 16 |
| abstract_inverted_index.to | 155, 160 |
| abstract_inverted_index.3.6 | 183 |
| abstract_inverted_index.For | 164 |
| abstract_inverted_index.TPU | 76, 88, 96 |
| abstract_inverted_index.The | 53, 75 |
| abstract_inverted_index.and | 9, 18, 45, 67, 73, 77, 93, 97, 110, 128, 131, 140, 152, 180 |
| abstract_inverted_index.are | 62, 70, 79 |
| abstract_inverted_index.but | 86 |
| abstract_inverted_index.can | 144, 153 |
| abstract_inverted_index.has | 2, 121 |
| abstract_inverted_index.not | 35, 90 |
| abstract_inverted_index.our | 168 |
| abstract_inverted_index.ran | 14 |
| abstract_inverted_index.the | 22, 37, 56, 87, 95, 104, 156, 161 |
| abstract_inverted_index.was | 29 |
| abstract_inverted_index.CPUs | 17 |
| abstract_inverted_index.Deep | 0 |
| abstract_inverted_index.GEMM | 81, 115 |
| abstract_inverted_index.When | 137 |
| abstract_inverted_index.both | 94 |
| abstract_inverted_index.deep | 11, 26, 43, 47, 60 |
| abstract_inverted_index.does | 89 |
| abstract_inverted_index.have | 50, 99 |
| abstract_inverted_index.high | 146 |
| abstract_inverted_index.meet | 36 |
| abstract_inverted_index.show | 171 |
| abstract_inverted_index.that | 31, 172 |
| abstract_inverted_index.with | 21, 117 |
| abstract_inverted_index.(PE). | 107 |
| abstract_inverted_index.GEMMs | 69 |
| abstract_inverted_index.GPUs. | 19 |
| abstract_inverted_index.SIGMA | 78, 98, 181 |
| abstract_inverted_index.could | 34 |
| abstract_inverted_index.rapid | 23 |
| abstract_inverted_index.rates | 102 |
| abstract_inverted_index.times | 179 |
| abstract_inverted_index.while | 149 |
| abstract_inverted_index.GEMMs, | 142, 167 |
| abstract_inverted_index.SparGD | 120, 143, 173 |
| abstract_inverted_index.arrays | 176 |
| abstract_inverted_index.become | 3, 51 |
| abstract_inverted_index.custom | 46 |
| abstract_inverted_index.design | 109 |
| abstract_inverted_index.field, | 8 |
| abstract_inverted_index.highly | 5, 71 |
| abstract_inverted_index.recent | 84 |
| abstract_inverted_index.simple | 133 |
| abstract_inverted_index.sparse | 72, 114, 139 |
| abstract_inverted_index.switch | 154 |
| abstract_inverted_index.times. | 184 |
| abstract_inverted_index.years, | 85 |
| abstract_inverted_index.Element | 106 |
| abstract_inverted_index.SparGD, | 112 |
| abstract_inverted_index.dynamic | 118 |
| abstract_inverted_index.general | 63 |
| abstract_inverted_index.module. | 136 |
| abstract_inverted_index.optimal | 157 |
| abstract_inverted_index.popular | 6 |
| abstract_inverted_index.primary | 57 |
| abstract_inverted_index.results | 170 |
| abstract_inverted_index.running | 138 |
| abstract_inverted_index.sparse, | 165 |
| abstract_inverted_index.support | 91 |
| abstract_inverted_index.typical | 80 |
| abstract_inverted_index.(GEMMs), | 66 |
| abstract_inverted_index.However, | 20 |
| abstract_inverted_index.dataflow | 134, 158 |
| abstract_inverted_index.emerging | 68 |
| abstract_inverted_index.existing | 32 |
| abstract_inverted_index.flexible | 125 |
| abstract_inverted_index.learning | 1, 12, 48, 61 |
| abstract_inverted_index.maintain | 145 |
| abstract_inverted_index.majority | 54 |
| abstract_inverted_index.networks | 127 |
| abstract_inverted_index.popular. | 52 |
| abstract_inverted_index.research | 7 |
| abstract_inverted_index.specific | 38, 122 |
| abstract_inverted_index.systolic | 175 |
| abstract_inverted_index.according | 159 |
| abstract_inverted_index.computing | 40, 162 |
| abstract_inverted_index.dataflow. | 119 |
| abstract_inverted_index.implement | 111 |
| abstract_inverted_index.irregular | 141, 166 |
| abstract_inverted_index.learning, | 27, 44 |
| abstract_inverted_index.networks, | 130 |
| abstract_inverted_index.primarily | 15 |
| abstract_inverted_index.reduction | 129 |
| abstract_inverted_index.sparsity, | 92, 151 |
| abstract_inverted_index.switching | 135 |
| abstract_inverted_index.utilizing | 150 |
| abstract_inverted_index.workloads | 58 |
| abstract_inverted_index.Processing | 105 |
| abstract_inverted_index.algorithms | 13 |
| abstract_inverted_index.discovered | 30 |
| abstract_inverted_index.irregular. | 74 |
| abstract_inverted_index.previously | 10 |
| abstract_inverted_index.processors | 33 |
| abstract_inverted_index.accelerator | 116 |
| abstract_inverted_index.development | 24 |
| abstract_inverted_index.large-scale | 39 |
| abstract_inverted_index.outperforms | 174 |
| abstract_inverted_index.structures, | 124 |
| abstract_inverted_index.utilization | 101, 148 |
| abstract_inverted_index.accelerators | 49, 82 |
| abstract_inverted_index.distribution | 126 |
| abstract_inverted_index.environment. | 163 |
| abstract_inverted_index.experimental | 169 |
| abstract_inverted_index.insufficient | 100 |
| abstract_inverted_index.requirements | 41 |
| abstract_inverted_index.matrix-matrix | 64 |
| abstract_inverted_index.multiplications | 65 |
| cited_by_percentile_year.max | 98 |
| cited_by_percentile_year.min | 90 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 7 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/9 |
| sustainable_development_goals[0].score | 0.5099999904632568 |
| sustainable_development_goals[0].display_name | Industry, innovation and infrastructure |
| citation_normalized_percentile.value | 0.93552317 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |