Efficient warp execution in presence of divergence with collaborative context collection Article Swipe

PDF

Farzad Khorasani , Rajiv Gupta , Laxmi N. Bhuyan ·

YOU? · · 2015 · Open Access · · DOI: https://doi.org/10.1145/2830772.2830796

GPU's SIMD architecture is a double-edged sword confronting parallel tasks with control flow divergence. On the one hand, it provides a high performance yet power-efficient platform to accelerate applications via massive parallelism; however, on the other hand, irregularities induce inefficiencies due to the warp's lockstep traversal of all diverging execution paths. In this work, we present a software (compiler) technique named Collaborative Context Collection (CCC) that increases the warp execution efficiency when faced with thread divergence incurred either by different intra-warp task assignment or by intra-warp load imbalance. CCC collects the relevant registers of divergent threads in a warp-specific stack allocated in the fast shared memory, and restores them only when the perfect utilization of warp lanes becomes feasible. We propose code transformations to enable applicability of CCC to variety of program segments with thread divergence. We also introduce optimizations to reduce the cost of CCC and to avoid device occupancy limitation or memory divergence. We have developed a framework that automates application of CCC to CUDA generated intermediate PTX code. We evaluated CCC on real-world applications and multiple scenarios using synthetic programs. CCC improves the warp execution efficiency of real-world benchmarks by up to 56% and achieves an average speedup of 1.69x (maximum 3.08x).

Related Topics

Concepts

Computer science Parallel computing Thread (computing) Speedup Compiler Control flow SIMD Context switch Instruction set Multithreading Execution model CUDA Operating system Programming language

Metadata

Type: article
Language: en
Landing Page: https://doi.org/10.1145/2830772.2830796
PDF: https://dl.acm.org/doi/pdf/10.1145/2830772.2830796
OA Status: gold
Cited By: 34
References: 51
Related Works: 10
OpenAlex ID: https://openalex.org/W2236252626

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W2236252626

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.1145/2830772.2830796

Digital Object Identifier
Title: Efficient warp execution in presence of divergence with collaborative context collection

Work title
Type: article

OpenAlex work type
Language: en

Primary language
Publication year: 2015

Year of publication
Publication date: 2015-12-05

Full publication date if available
Authors: Farzad Khorasani, Rajiv Gupta, Laxmi N. Bhuyan

List of authors in order
Landing page: https://doi.org/10.1145/2830772.2830796

Publisher landing page
PDF URL: https://dl.acm.org/doi/pdf/10.1145/2830772.2830796

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: gold

Open access status per OpenAlex
OA URL: https://dl.acm.org/doi/pdf/10.1145/2830772.2830796

Direct OA link when available
Concepts: Computer science, Parallel computing, Thread (computing), Speedup, Compiler, Control flow, SIMD, Context switch, Instruction set, Multithreading, Execution model, CUDA, Operating system, Programming language

Top concepts (fields/topics) attached by OpenAlex
Cited by: 34

Total citation count in OpenAlex
Citations by year (recent): 2024: 2, 2022: 3, 2021: 2, 2020: 3, 2019: 4

Per-year citation counts (last 5 years)
References (count): 51

Number of works referenced by this work
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W2236252626
doi	https://doi.org/10.1145/2830772.2830796
ids.doi	https://doi.org/10.1145/2830772.2830796
ids.mag	2236252626
ids.openalex	https://openalex.org/W2236252626
fwci	6.01265622
type	article
title	Efficient warp execution in presence of divergence with collaborative context collection
awards[0].id	https://openalex.org/G8002895364
awards[0].funder_id	https://openalex.org/F4320306076
awards[0].display_name
awards[0].funder_award_id	CCF-0905509,CNS-1157377,CCF-1318103,CCF-1524852,CCF-1423108
awards[0].funder_display_name	National Science Foundation
biblio.issue
biblio.volume
biblio.last_page	215
biblio.first_page	204
topics[0].id	https://openalex.org/T10054
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9998999834060669
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1708
topics[0].subfield.display_name	Hardware and Architecture
topics[0].display_name	Parallel Computing and Optimization Techniques
topics[1].id	https://openalex.org/T11181
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9993000030517578
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1705
topics[1].subfield.display_name	Computer Networks and Communications
topics[1].display_name	Advanced Data Storage Technologies
topics[2].id	https://openalex.org/T10715
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/1705
topics[2].subfield.display_name	Computer Networks and Communications
topics[2].display_name	Distributed and Parallel Computing Systems
funders[0].id	https://openalex.org/F4320306076
funders[0].ror	https://ror.org/021nxhr62
funders[0].display_name	National Science Foundation
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.8674681186676025
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C173608175
concepts[1].level	1
concepts[1].score	0.7893720865249634
concepts[1].wikidata	https://www.wikidata.org/wiki/Q232661
concepts[1].display_name	Parallel computing
concepts[2].id	https://openalex.org/C138101251
concepts[2].level	2
concepts[2].score	0.6750968098640442
concepts[2].wikidata	https://www.wikidata.org/wiki/Q213092
concepts[2].display_name	Thread (computing)
concepts[3].id	https://openalex.org/C68339613
concepts[3].level	2
concepts[3].score	0.5920443534851074
concepts[3].wikidata	https://www.wikidata.org/wiki/Q1549489
concepts[3].display_name	Speedup
concepts[4].id	https://openalex.org/C169590947
concepts[4].level	2
concepts[4].score	0.5575736165046692
concepts[4].wikidata	https://www.wikidata.org/wiki/Q47506
concepts[4].display_name	Compiler
concepts[5].id	https://openalex.org/C160191386
concepts[5].level	2
concepts[5].score	0.5255511999130249
concepts[5].wikidata	https://www.wikidata.org/wiki/Q868299
concepts[5].display_name	Control flow
concepts[6].id	https://openalex.org/C150552126
concepts[6].level	2
concepts[6].score	0.4732019603252411
concepts[6].wikidata	https://www.wikidata.org/wiki/Q339387
concepts[6].display_name	SIMD
concepts[7].id	https://openalex.org/C53833338
concepts[7].level	2
concepts[7].score	0.44418448209762573
concepts[7].wikidata	https://www.wikidata.org/wiki/Q1061424
concepts[7].display_name	Context switch
concepts[8].id	https://openalex.org/C202491316
concepts[8].level	2
concepts[8].score	0.4283791184425354
concepts[8].wikidata	https://www.wikidata.org/wiki/Q272683
concepts[8].display_name	Instruction set
concepts[9].id	https://openalex.org/C201410400
concepts[9].level	3
concepts[9].score	0.4264149069786072
concepts[9].wikidata	https://www.wikidata.org/wiki/Q1064412
concepts[9].display_name	Multithreading
concepts[10].id	https://openalex.org/C2776834041
concepts[10].level	2
concepts[10].score	0.4212344288825989
concepts[10].wikidata	https://www.wikidata.org/wiki/Q25346349
concepts[10].display_name	Execution model
concepts[11].id	https://openalex.org/C2778119891
concepts[11].level	2
concepts[11].score	0.4197118282318115
concepts[11].wikidata	https://www.wikidata.org/wiki/Q477690
concepts[11].display_name	CUDA
concepts[12].id	https://openalex.org/C111919701
concepts[12].level	1
concepts[12].score	0.323000431060791
concepts[12].wikidata	https://www.wikidata.org/wiki/Q9135
concepts[12].display_name	Operating system
concepts[13].id	https://openalex.org/C199360897
concepts[13].level	1
concepts[13].score	0.3218782842159271
concepts[13].wikidata	https://www.wikidata.org/wiki/Q9143
concepts[13].display_name	Programming language
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.8674681186676025
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/parallel-computing
keywords[1].score	0.7893720865249634
keywords[1].display_name	Parallel computing
keywords[2].id	https://openalex.org/keywords/thread
keywords[2].score	0.6750968098640442
keywords[2].display_name	Thread (computing)
keywords[3].id	https://openalex.org/keywords/speedup
keywords[3].score	0.5920443534851074
keywords[3].display_name	Speedup
keywords[4].id	https://openalex.org/keywords/compiler
keywords[4].score	0.5575736165046692
keywords[4].display_name	Compiler
keywords[5].id	https://openalex.org/keywords/control-flow
keywords[5].score	0.5255511999130249
keywords[5].display_name	Control flow
keywords[6].id	https://openalex.org/keywords/simd
keywords[6].score	0.4732019603252411
keywords[6].display_name	SIMD
keywords[7].id	https://openalex.org/keywords/context-switch
keywords[7].score	0.44418448209762573
keywords[7].display_name	Context switch
keywords[8].id	https://openalex.org/keywords/instruction-set
keywords[8].score	0.4283791184425354
keywords[8].display_name	Instruction set
keywords[9].id	https://openalex.org/keywords/multithreading
keywords[9].score	0.4264149069786072
keywords[9].display_name	Multithreading
keywords[10].id	https://openalex.org/keywords/execution-model
keywords[10].score	0.4212344288825989
keywords[10].display_name	Execution model
keywords[11].id	https://openalex.org/keywords/cuda
keywords[11].score	0.4197118282318115
keywords[11].display_name	CUDA
keywords[12].id	https://openalex.org/keywords/operating-system
keywords[12].score	0.323000431060791
keywords[12].display_name	Operating system
keywords[13].id	https://openalex.org/keywords/programming-language
keywords[13].score	0.3218782842159271
keywords[13].display_name	Programming language
language	en
locations[0].id	doi:10.1145/2830772.2830796
locations[0].is_oa	True
locations[0].source
locations[0].license	cc-by
locations[0].pdf_url	https://dl.acm.org/doi/pdf/10.1145/2830772.2830796
locations[0].version	publishedVersion
locations[0].raw_type	proceedings-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	Proceedings of the 48th International Symposium on Microarchitecture
locations[0].landing_page_url	https://doi.org/10.1145/2830772.2830796
indexed_in	crossref
authorships[0].author.id	https://openalex.org/A5036836220
authorships[0].author.orcid
authorships[0].author.display_name	Farzad Khorasani
authorships[0].countries	US
authorships[0].affiliations[0].institution_ids	https://openalex.org/I103635307
authorships[0].affiliations[0].raw_affiliation_string	University of California, Riverside, CA
authorships[0].institutions[0].id	https://openalex.org/I103635307
authorships[0].institutions[0].ror	https://ror.org/03nawhv43
authorships[0].institutions[0].type	education
authorships[0].institutions[0].lineage	https://openalex.org/I103635307
authorships[0].institutions[0].country_code	US
authorships[0].institutions[0].display_name	University of California, Riverside
authorships[0].author_position	first
authorships[0].raw_author_name	Farzad Khorasani
authorships[0].is_corresponding	False
authorships[0].raw_affiliation_strings	University of California, Riverside, CA
authorships[1].author.id	https://openalex.org/A5100699251
authorships[1].author.orcid	https://orcid.org/0000-0002-9348-3974
authorships[1].author.display_name	Rajiv Gupta
authorships[1].countries	US
authorships[1].affiliations[0].institution_ids	https://openalex.org/I103635307
authorships[1].affiliations[0].raw_affiliation_string	University of California, Riverside, CA
authorships[1].institutions[0].id	https://openalex.org/I103635307
authorships[1].institutions[0].ror	https://ror.org/03nawhv43
authorships[1].institutions[0].type	education
authorships[1].institutions[0].lineage	https://openalex.org/I103635307
authorships[1].institutions[0].country_code	US
authorships[1].institutions[0].display_name	University of California, Riverside
authorships[1].author_position	middle
authorships[1].raw_author_name	Rajiv Gupta
authorships[1].is_corresponding	False
authorships[1].raw_affiliation_strings	University of California, Riverside, CA
authorships[2].author.id	https://openalex.org/A5048949780
authorships[2].author.orcid	https://orcid.org/0000-0002-8759-0458
authorships[2].author.display_name	Laxmi N. Bhuyan
authorships[2].countries	US
authorships[2].affiliations[0].institution_ids	https://openalex.org/I103635307
authorships[2].affiliations[0].raw_affiliation_string	University of California, Riverside, CA
authorships[2].institutions[0].id	https://openalex.org/I103635307
authorships[2].institutions[0].ror	https://ror.org/03nawhv43
authorships[2].institutions[0].type	education
authorships[2].institutions[0].lineage	https://openalex.org/I103635307
authorships[2].institutions[0].country_code	US
authorships[2].institutions[0].display_name	University of California, Riverside
authorships[2].author_position	last
authorships[2].raw_author_name	Laxmi N. Bhuyan
authorships[2].is_corresponding	False
authorships[2].raw_affiliation_strings	University of California, Riverside, CA
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/10.1145/2830772.2830796
open_access.oa_status	gold
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Efficient warp execution in presence of divergence with collaborative context collection
has_fulltext	True
is_retracted	False
updated_date	2025-11-06T03:46:38.306776
primary_topic.id	https://openalex.org/T10054
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9998999834060669
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1708
primary_topic.subfield.display_name	Hardware and Architecture
primary_topic.display_name	Parallel Computing and Optimization Techniques
related_works	https://openalex.org/W1995705225, https://openalex.org/W4248655967, https://openalex.org/W2138520521, https://openalex.org/W2184902834, https://openalex.org/W2110105483, https://openalex.org/W2107831078, https://openalex.org/W4248145683, https://openalex.org/W1672168401, https://openalex.org/W2100579514, https://openalex.org/W2156983793
cited_by_count	34
counts_by_year[0].year	2024
counts_by_year[0].cited_by_count	2
counts_by_year[1].year	2022
counts_by_year[1].cited_by_count	3
counts_by_year[2].year	2021
counts_by_year[2].cited_by_count	2
counts_by_year[3].year	2020
counts_by_year[3].cited_by_count	3
counts_by_year[4].year	2019
counts_by_year[4].cited_by_count	4
counts_by_year[5].year	2018
counts_by_year[5].cited_by_count	8
counts_by_year[6].year	2017
counts_by_year[6].cited_by_count	9
counts_by_year[7].year	2016
counts_by_year[7].cited_by_count	3
locations_count	1
best_oa_location.id	doi:10.1145/2830772.2830796
best_oa_location.is_oa	True
best_oa_location.source
best_oa_location.license	cc-by
best_oa_location.pdf_url	https://dl.acm.org/doi/pdf/10.1145/2830772.2830796
best_oa_location.version	publishedVersion
best_oa_location.raw_type	proceedings-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	Proceedings of the 48th International Symposium on Microarchitecture
best_oa_location.landing_page_url	https://doi.org/10.1145/2830772.2830796
primary_location.id	doi:10.1145/2830772.2830796
primary_location.is_oa	True
primary_location.source
primary_location.license	cc-by
primary_location.pdf_url	https://dl.acm.org/doi/pdf/10.1145/2830772.2830796
primary_location.version	publishedVersion
primary_location.raw_type	proceedings-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	Proceedings of the 48th International Symposium on Microarchitecture
primary_location.landing_page_url	https://doi.org/10.1145/2830772.2830796
publication_date	2015-12-05
publication_year	2015
referenced_works	https://openalex.org/W2169880332, https://openalex.org/W2156831150, https://openalex.org/W1971997351, https://openalex.org/W2155568054, https://openalex.org/W3146509083, https://openalex.org/W1973538724, https://openalex.org/W2167675119, https://openalex.org/W2151686327, https://openalex.org/W2013247896, https://openalex.org/W2016706026, https://openalex.org/W2156180003, https://openalex.org/W1504291959, https://openalex.org/W4300125772, https://openalex.org/W2067313328, https://openalex.org/W27773700, https://openalex.org/W981516807, https://openalex.org/W2432978112, https://openalex.org/W2094945791, https://openalex.org/W2146591355, https://openalex.org/W2090584832, https://openalex.org/W1978155891, https://openalex.org/W2168921806, https://openalex.org/W2125979435, https://openalex.org/W2098505406, https://openalex.org/W2135947393, https://openalex.org/W2132598270, https://openalex.org/W2171399035, https://openalex.org/W1985291160, https://openalex.org/W2012630996, https://openalex.org/W4236883517, https://openalex.org/W2061313045, https://openalex.org/W2043420024, https://openalex.org/W1965061255, https://openalex.org/W1994316441, https://openalex.org/W2295329047, https://openalex.org/W6640247899, https://openalex.org/W2144061463, https://openalex.org/W1970815868, https://openalex.org/W2492496105, https://openalex.org/W2123440268, https://openalex.org/W1994688997, https://openalex.org/W3013490664, https://openalex.org/W2090495704, https://openalex.org/W2148443481, https://openalex.org/W2075739954, https://openalex.org/W164384110, https://openalex.org/W2748306984, https://openalex.org/W142653777, https://openalex.org/W3006582303, https://openalex.org/W579519726, https://openalex.org/W1919570435
referenced_works_count	51
abstract_inverted_index.a	4, 20, 56, 97, 158
abstract_inverted_index.In	51
abstract_inverted_index.On	14
abstract_inverted_index.We	119, 136, 155, 171
abstract_inverted_index.an	198
abstract_inverted_index.by	78, 84, 192
abstract_inverted_index.in	96, 101
abstract_inverted_index.is	3
abstract_inverted_index.it	18
abstract_inverted_index.of	46, 93, 114, 126, 130, 144, 163, 189, 201
abstract_inverted_index.on	33, 174
abstract_inverted_index.or	83, 152
abstract_inverted_index.to	26, 41, 123, 128, 140, 147, 165, 194
abstract_inverted_index.up	193
abstract_inverted_index.we	54
abstract_inverted_index.56%	195
abstract_inverted_index.CCC	88, 127, 145, 164, 173, 183
abstract_inverted_index.PTX	169
abstract_inverted_index.all	47
abstract_inverted_index.and	106, 146, 177, 196
abstract_inverted_index.due	40
abstract_inverted_index.one	16
abstract_inverted_index.the	15, 34, 42, 67, 90, 102, 111, 142, 185
abstract_inverted_index.via	29
abstract_inverted_index.yet	23
abstract_inverted_index.CUDA	166
abstract_inverted_index.SIMD	1
abstract_inverted_index.also	137
abstract_inverted_index.code	121
abstract_inverted_index.cost	143
abstract_inverted_index.fast	103
abstract_inverted_index.flow	12
abstract_inverted_index.have	156
abstract_inverted_index.high	21
abstract_inverted_index.load	86
abstract_inverted_index.only	109
abstract_inverted_index.task	81
abstract_inverted_index.that	65, 160
abstract_inverted_index.them	108
abstract_inverted_index.this	52
abstract_inverted_index.warp	68, 115, 186
abstract_inverted_index.when	71, 110
abstract_inverted_index.with	10, 73, 133
abstract_inverted_index.(CCC)	64
abstract_inverted_index.1.69x	202
abstract_inverted_index.GPU's	0
abstract_inverted_index.avoid	148
abstract_inverted_index.code.	170
abstract_inverted_index.faced	72
abstract_inverted_index.hand,	17, 36
abstract_inverted_index.lanes	116
abstract_inverted_index.named	60
abstract_inverted_index.other	35
abstract_inverted_index.stack	99
abstract_inverted_index.sword	6
abstract_inverted_index.tasks	9
abstract_inverted_index.using	180
abstract_inverted_index.work,	53
abstract_inverted_index.device	149
abstract_inverted_index.either	77
abstract_inverted_index.enable	124
abstract_inverted_index.induce	38
abstract_inverted_index.memory	153
abstract_inverted_index.paths.	50
abstract_inverted_index.reduce	141
abstract_inverted_index.shared	104
abstract_inverted_index.thread	74, 134
abstract_inverted_index.warp's	43
abstract_inverted_index.3.08x).	204
abstract_inverted_index.Context	62
abstract_inverted_index.average	199
abstract_inverted_index.becomes	117
abstract_inverted_index.control	11
abstract_inverted_index.massive	30
abstract_inverted_index.memory,	105
abstract_inverted_index.perfect	112
abstract_inverted_index.present	55
abstract_inverted_index.program	131
abstract_inverted_index.propose	120
abstract_inverted_index.speedup	200
abstract_inverted_index.threads	95
abstract_inverted_index.variety	129
abstract_inverted_index.(maximum	203
abstract_inverted_index.achieves	197
abstract_inverted_index.collects	89
abstract_inverted_index.however,	32
abstract_inverted_index.improves	184
abstract_inverted_index.incurred	76
abstract_inverted_index.lockstep	44
abstract_inverted_index.multiple	178
abstract_inverted_index.parallel	8
abstract_inverted_index.platform	25
abstract_inverted_index.provides	19
abstract_inverted_index.relevant	91
abstract_inverted_index.restores	107
abstract_inverted_index.segments	132
abstract_inverted_index.software	57
abstract_inverted_index.allocated	100
abstract_inverted_index.automates	161
abstract_inverted_index.developed	157
abstract_inverted_index.different	79
abstract_inverted_index.divergent	94
abstract_inverted_index.diverging	48
abstract_inverted_index.evaluated	172
abstract_inverted_index.execution	49, 69, 187
abstract_inverted_index.feasible.	118
abstract_inverted_index.framework	159
abstract_inverted_index.generated	167
abstract_inverted_index.increases	66
abstract_inverted_index.introduce	138
abstract_inverted_index.occupancy	150
abstract_inverted_index.programs.	182
abstract_inverted_index.registers	92
abstract_inverted_index.scenarios	179
abstract_inverted_index.synthetic	181
abstract_inverted_index.technique	59
abstract_inverted_index.traversal	45
abstract_inverted_index.(compiler)	58
abstract_inverted_index.Collection	63
abstract_inverted_index.accelerate	27
abstract_inverted_index.assignment	82
abstract_inverted_index.benchmarks	191
abstract_inverted_index.divergence	75
abstract_inverted_index.efficiency	70, 188
abstract_inverted_index.imbalance.	87
abstract_inverted_index.intra-warp	80, 85
abstract_inverted_index.limitation	151
abstract_inverted_index.real-world	175, 190
abstract_inverted_index.application	162
abstract_inverted_index.confronting	7
abstract_inverted_index.divergence.	13, 135, 154
abstract_inverted_index.performance	22
abstract_inverted_index.utilization	113
abstract_inverted_index.applications	28, 176
abstract_inverted_index.architecture	2
abstract_inverted_index.double-edged	5
abstract_inverted_index.intermediate	168
abstract_inverted_index.parallelism;	31
abstract_inverted_index.Collaborative	61
abstract_inverted_index.applicability	125
abstract_inverted_index.optimizations	139
abstract_inverted_index.warp-specific	98
abstract_inverted_index.inefficiencies	39
abstract_inverted_index.irregularities	37
abstract_inverted_index.power-efficient	24
abstract_inverted_index.transformations	122
cited_by_percentile_year.max	99
cited_by_percentile_year.min	93
countries_distinct_count	1
institutions_distinct_count	3
citation_normalized_percentile.value	0.97312717
citation_normalized_percentile.is_in_top_1_percent	False
citation_normalized_percentile.is_in_top_10_percent	True