To share or not to share vector registers? View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2022-04-28

AUTHORS

Johannes Pietrzyk, Alexander Krause, Dirk Habich, Wolfgang Lehner

ABSTRACT

Query execution techniques in database systems constantly adapt to novel hardware features to achieve high query performance, in particular for analytical queries. In recent years, vectorization based on the Single Instruction Multiple Data parallel paradigm has been established as a state-of-the-art approach to increase single-query performance. However, since concurrent analytical queries running in parallel often access the same columns and perform a same set of vectorized operations, data accesses and computations among different queries may be executed redundantly. Various techniques have already been proposed to avoid such redundancy, ranging from concurrent scans via the construction of materialized views to applying multiple query optimization techniques. Continuing this line of research, we investigate the opportunity of sharing vector registers for concurrently running queries in analytical scenarios in this paper. In particular, our novel sharing approach relies on processing data elements of different queries together within a single vector register. As we are going to show, sharing vector registers to optimize the execution of concurrent analytical queries can be very beneficial in single-threaded as well as multi-thread environments. Therefore, we demonstrate the feasibility and applicability of such a novel work sharing strategy and thus open up a wide spectrum of future research opportunities. More... »

PAGES

1-22

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s00778-022-00744-2

DOI

http://dx.doi.org/10.1007/s00778-022-00744-2

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1147471106


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0806", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information Systems", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Database Systems Group, Technische Universit\u00e4t Dresden, Dresden, Germany", 
          "id": "http://www.grid.ac/institutes/grid.4488.0", 
          "name": [
            "Database Systems Group, Technische Universit\u00e4t Dresden, Dresden, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Pietrzyk", 
        "givenName": "Johannes", 
        "id": "sg:person.011726731635.60", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011726731635.60"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Database Systems Group, Technische Universit\u00e4t Dresden, Dresden, Germany", 
          "id": "http://www.grid.ac/institutes/grid.4488.0", 
          "name": [
            "Database Systems Group, Technische Universit\u00e4t Dresden, Dresden, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Krause", 
        "givenName": "Alexander", 
        "id": "sg:person.014117253235.76", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014117253235.76"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Database Systems Group, Technische Universit\u00e4t Dresden, Dresden, Germany", 
          "id": "http://www.grid.ac/institutes/grid.4488.0", 
          "name": [
            "Database Systems Group, Technische Universit\u00e4t Dresden, Dresden, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Habich", 
        "givenName": "Dirk", 
        "id": "sg:person.014130236343.21", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014130236343.21"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Database Systems Group, Technische Universit\u00e4t Dresden, Dresden, Germany", 
          "id": "http://www.grid.ac/institutes/grid.4488.0", 
          "name": [
            "Database Systems Group, Technische Universit\u00e4t Dresden, Dresden, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Lehner", 
        "givenName": "Wolfgang", 
        "id": "sg:person.014174244741.81", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014174244741.81"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/s00778-019-00547-y", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1118035511", 
          "https://doi.org/10.1007/s00778-019-00547-y"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2022-04-28", 
    "datePublishedReg": "2022-04-28", 
    "description": "Query execution techniques in database systems constantly adapt to novel hardware features to achieve high query performance, in particular for analytical queries. In recent years, vectorization based on the Single Instruction Multiple Data parallel paradigm has been established as a state-of-the-art approach to increase single-query performance. However, since concurrent analytical queries running in parallel often access the same columns and perform a same set of vectorized operations, data accesses and computations among different queries may be executed redundantly. Various techniques have already been proposed to avoid such redundancy, ranging from concurrent scans via the construction of materialized views to applying multiple query optimization techniques. Continuing this line of research, we investigate the opportunity of sharing vector registers for concurrently running queries in analytical scenarios in this paper. In particular, our novel sharing approach relies on processing data elements of different queries together within a single vector register. As we are going to show, sharing vector registers to optimize the execution of concurrent analytical queries can be very beneficial in single-threaded as well as multi-thread environments. Therefore, we demonstrate the feasibility and applicability of such a novel work sharing strategy and thus open up a wide spectrum of future research opportunities.", 
    "genre": "article", 
    "id": "sg:pub.10.1007/s00778-022-00744-2", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1044889", 
        "issn": [
          "1066-8888", 
          "0949-877X"
        ], 
        "name": "The VLDB Journal", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }
    ], 
    "keywords": [
      "analytical queries", 
      "vector registers", 
      "different queries", 
      "multiple query optimization techniques", 
      "query execution techniques", 
      "query optimization techniques", 
      "data parallel paradigm", 
      "multi-threaded environment", 
      "high query performance", 
      "materialized views", 
      "query performance", 
      "database systems", 
      "hardware features", 
      "vectorized operations", 
      "parallel paradigm", 
      "art approaches", 
      "queries", 
      "sharing approach", 
      "execution techniques", 
      "concurrent scans", 
      "data elements", 
      "sharing strategy", 
      "such redundancy", 
      "optimization techniques", 
      "future research opportunities", 
      "analytical scenarios", 
      "research opportunities", 
      "recent years", 
      "line of research", 
      "vectorization", 
      "same set", 
      "execution", 
      "redundancy", 
      "performance", 
      "computation", 
      "technique", 
      "scenarios", 
      "paradigm", 
      "set", 
      "environment", 
      "operation", 
      "system", 
      "features", 
      "opportunities", 
      "applicability", 
      "feasibility", 
      "wide spectrum", 
      "parallel", 
      "data", 
      "view", 
      "construction", 
      "research", 
      "Register", 
      "strategies", 
      "same column", 
      "state", 
      "elements", 
      "scans", 
      "lines", 
      "years", 
      "spectra", 
      "column", 
      "approach", 
      "paper"
    ], 
    "name": "To share or not to share vector registers?", 
    "pagination": "1-22", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1147471106"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s00778-022-00744-2"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s00778-022-00744-2", 
      "https://app.dimensions.ai/details/publication/pub.1147471106"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-06-01T22:25", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220601/entities/gbq_results/article/article_935.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1007/s00778-022-00744-2"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/s00778-022-00744-2'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s00778-022-00744-2'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00778-022-00744-2'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00778-022-00744-2'


 

This table displays all metadata directly associated to this object as RDF triples.

141 TRIPLES      22 PREDICATES      88 URIs      79 LITERALS      4 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s00778-022-00744-2 schema:about anzsrc-for:08
2 anzsrc-for:0806
3 schema:author Ne425812a51544c029974fcc9eb0c0fc0
4 schema:citation sg:pub.10.1007/s00778-019-00547-y
5 schema:datePublished 2022-04-28
6 schema:datePublishedReg 2022-04-28
7 schema:description Query execution techniques in database systems constantly adapt to novel hardware features to achieve high query performance, in particular for analytical queries. In recent years, vectorization based on the Single Instruction Multiple Data parallel paradigm has been established as a state-of-the-art approach to increase single-query performance. However, since concurrent analytical queries running in parallel often access the same columns and perform a same set of vectorized operations, data accesses and computations among different queries may be executed redundantly. Various techniques have already been proposed to avoid such redundancy, ranging from concurrent scans via the construction of materialized views to applying multiple query optimization techniques. Continuing this line of research, we investigate the opportunity of sharing vector registers for concurrently running queries in analytical scenarios in this paper. In particular, our novel sharing approach relies on processing data elements of different queries together within a single vector register. As we are going to show, sharing vector registers to optimize the execution of concurrent analytical queries can be very beneficial in single-threaded as well as multi-thread environments. Therefore, we demonstrate the feasibility and applicability of such a novel work sharing strategy and thus open up a wide spectrum of future research opportunities.
8 schema:genre article
9 schema:inLanguage en
10 schema:isAccessibleForFree false
11 schema:isPartOf sg:journal.1044889
12 schema:keywords Register
13 analytical queries
14 analytical scenarios
15 applicability
16 approach
17 art approaches
18 column
19 computation
20 concurrent scans
21 construction
22 data
23 data elements
24 data parallel paradigm
25 database systems
26 different queries
27 elements
28 environment
29 execution
30 execution techniques
31 feasibility
32 features
33 future research opportunities
34 hardware features
35 high query performance
36 line of research
37 lines
38 materialized views
39 multi-threaded environment
40 multiple query optimization techniques
41 operation
42 opportunities
43 optimization techniques
44 paper
45 paradigm
46 parallel
47 parallel paradigm
48 performance
49 queries
50 query execution techniques
51 query optimization techniques
52 query performance
53 recent years
54 redundancy
55 research
56 research opportunities
57 same column
58 same set
59 scans
60 scenarios
61 set
62 sharing approach
63 sharing strategy
64 spectra
65 state
66 strategies
67 such redundancy
68 system
69 technique
70 vector registers
71 vectorization
72 vectorized operations
73 view
74 wide spectrum
75 years
76 schema:name To share or not to share vector registers?
77 schema:pagination 1-22
78 schema:productId N54b2cd958d384aed9f82907839b34696
79 Nb814dea20b644d93986346751229c84a
80 schema:sameAs https://app.dimensions.ai/details/publication/pub.1147471106
81 https://doi.org/10.1007/s00778-022-00744-2
82 schema:sdDatePublished 2022-06-01T22:25
83 schema:sdLicense https://scigraph.springernature.com/explorer/license/
84 schema:sdPublisher N442e2bbb97564bf4aad0ad4125a980b3
85 schema:url https://doi.org/10.1007/s00778-022-00744-2
86 sgo:license sg:explorer/license/
87 sgo:sdDataset articles
88 rdf:type schema:ScholarlyArticle
89 N442e2bbb97564bf4aad0ad4125a980b3 schema:name Springer Nature - SN SciGraph project
90 rdf:type schema:Organization
91 N54b2cd958d384aed9f82907839b34696 schema:name doi
92 schema:value 10.1007/s00778-022-00744-2
93 rdf:type schema:PropertyValue
94 N8e572c7cf18f461aa3e4adedab31df27 rdf:first sg:person.014117253235.76
95 rdf:rest Na89cab7ca6fa42bbba25aa088708cb82
96 Na5bd2a29032e4a9994cf13ccee6e1b9f rdf:first sg:person.014174244741.81
97 rdf:rest rdf:nil
98 Na89cab7ca6fa42bbba25aa088708cb82 rdf:first sg:person.014130236343.21
99 rdf:rest Na5bd2a29032e4a9994cf13ccee6e1b9f
100 Nb814dea20b644d93986346751229c84a schema:name dimensions_id
101 schema:value pub.1147471106
102 rdf:type schema:PropertyValue
103 Ne425812a51544c029974fcc9eb0c0fc0 rdf:first sg:person.011726731635.60
104 rdf:rest N8e572c7cf18f461aa3e4adedab31df27
105 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
106 schema:name Information and Computing Sciences
107 rdf:type schema:DefinedTerm
108 anzsrc-for:0806 schema:inDefinedTermSet anzsrc-for:
109 schema:name Information Systems
110 rdf:type schema:DefinedTerm
111 sg:journal.1044889 schema:issn 0949-877X
112 1066-8888
113 schema:name The VLDB Journal
114 schema:publisher Springer Nature
115 rdf:type schema:Periodical
116 sg:person.011726731635.60 schema:affiliation grid-institutes:grid.4488.0
117 schema:familyName Pietrzyk
118 schema:givenName Johannes
119 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011726731635.60
120 rdf:type schema:Person
121 sg:person.014117253235.76 schema:affiliation grid-institutes:grid.4488.0
122 schema:familyName Krause
123 schema:givenName Alexander
124 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014117253235.76
125 rdf:type schema:Person
126 sg:person.014130236343.21 schema:affiliation grid-institutes:grid.4488.0
127 schema:familyName Habich
128 schema:givenName Dirk
129 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014130236343.21
130 rdf:type schema:Person
131 sg:person.014174244741.81 schema:affiliation grid-institutes:grid.4488.0
132 schema:familyName Lehner
133 schema:givenName Wolfgang
134 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014174244741.81
135 rdf:type schema:Person
136 sg:pub.10.1007/s00778-019-00547-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1118035511
137 https://doi.org/10.1007/s00778-019-00547-y
138 rdf:type schema:CreativeWork
139 grid-institutes:grid.4488.0 schema:alternateName Database Systems Group, Technische Universität Dresden, Dresden, Germany
140 schema:name Database Systems Group, Technische Universität Dresden, Dresden, Germany
141 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...