Compatibility enhancement and performance measurement for socket interface with PCIe interconnections View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-12

AUTHORS

Cheol Shim, Rupali Shinde, Min Choi

ABSTRACT

Today the key technology of high-performance computing systems is the emergence of interconnect technology that makes multiple computers into one computer cluster. This technique is a general method in which each constituent node processes its own operation and communicates with different nodes. Therefore, a high-performance network has been required. InfiniBand and Gigabit Ethernet technologies are typical examples of high-performance network. As an alternative to those technologies the development of interconnection technology using PCI Express (Peripheral Component Interconnect Express), officially abbreviated as PCIe or PCI-e, is a high-speed serial computer expansion bus standard, which has characteristics of high speed, low power, and high protocol efficiency is actively under development. In a high-performance network, the TCP/IP protocol consumes CPU resources and memory bandwidth by nature, which is a bottleneck. In this paper, we implement the PCIe based interconnection network system with low latency, low power, RDMA, and other characteristics. We utilize Socket API which is mainly used in the user-level application program rather than the existing MPI and PGAS model interfaces. The implemented PCIe interconnection network system was measured with the metrics as the bandwidth using the Iperf Benchmark which uses the Socket API. The bandwidth at 4 Mbyte of transmission data size was measured to be 1084 Mbyte/s bandwidth based on PCIe, which is about 96 times higher than that of 11.2 Mbyte/s bandwidth based on Ethernet. More... »

PAGES

10

Identifiers

URI

http://scigraph.springernature.com/pub.10.1186/s13673-019-0170-0

DOI

http://dx.doi.org/10.1186/s13673-019-0170-0

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1112739281


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/2008/1005", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Communications Technologies", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/10", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Technology", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Chungbuk National University", 
          "id": "https://www.grid.ac/institutes/grid.254229.a", 
          "name": [
            "Department of Information and Communication Engineering, Chungbuk National University, 28644, Cheongju, South Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Shim", 
        "givenName": "Cheol", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Chungbuk National University", 
          "id": "https://www.grid.ac/institutes/grid.254229.a", 
          "name": [
            "Department of Information and Communication Engineering, Chungbuk National University, 28644, Cheongju, South Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Shinde", 
        "givenName": "Rupali", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Chungbuk National University", 
          "id": "https://www.grid.ac/institutes/grid.254229.a", 
          "name": [
            "Department of Information and Communication Engineering, Chungbuk National University, 28644, Cheongju, South Korea"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Choi", 
        "givenName": "Min", 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/j.future.2012.06.009", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1011568152"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.5573/ieie.2015.52.8.074", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1019067614"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/2903150.2903168", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052476399"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1049/ip-cdt:19990246", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1056845150"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/40.671404", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061168352"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3745/jips.01.0013", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1084440442"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/s13673-017-0115-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091668072", 
          "https://doi.org/10.1186/s13673-017-0115-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/conect.2003.1231473", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093725694"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/ipdps.2006.1639560", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093751896"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/clustr.2005.347027", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094961548"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/autest.2007.4374248", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095133561"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.7840/kics.2017.42.11.2122", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1100246220"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-12", 
    "datePublishedReg": "2019-12-01", 
    "description": "Today the key technology of high-performance computing systems is the emergence of interconnect technology that makes multiple computers into one computer cluster. This technique is a general method in which each constituent node processes its own operation and communicates with different nodes. Therefore, a high-performance network has been required. InfiniBand and Gigabit Ethernet technologies are typical examples of high-performance network. As an alternative to those technologies the development of interconnection technology using PCI Express (Peripheral Component Interconnect Express), officially abbreviated as PCIe or PCI-e, is a high-speed serial computer expansion bus standard, which has characteristics of high speed, low power, and high protocol efficiency is actively under development. In a high-performance network, the TCP/IP protocol consumes CPU resources and memory bandwidth by nature, which is a bottleneck. In this paper, we implement the PCIe based interconnection network system with low latency, low power, RDMA, and other characteristics. We utilize Socket API which is mainly used in the user-level application program rather than the existing MPI and PGAS model interfaces. The implemented PCIe interconnection network system was measured with the metrics as the bandwidth using the Iperf Benchmark which uses the Socket API. The bandwidth at 4 Mbyte of transmission data size was measured to be 1084 Mbyte/s bandwidth based on PCIe, which is about 96 times higher than that of 11.2 Mbyte/s bandwidth based on Ethernet.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1186/s13673-019-0170-0", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1136381", 
        "issn": [
          "2192-1962", 
          "2192-1962"
        ], 
        "name": "Human-centric Computing and Information Sciences", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "9"
      }
    ], 
    "name": "Compatibility enhancement and performance measurement for socket interface with PCIe interconnections", 
    "pagination": "10", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "d5db2a7a1bf65960eb6b32821545e5b5bfdbb46d3d3af3332ad3af083a290f25"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1186/s13673-019-0170-0"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1112739281"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1186/s13673-019-0170-0", 
      "https://app.dimensions.ai/details/publication/pub.1112739281"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T11:46", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000358_0000000358/records_127459_00000011.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://link.springer.com/10.1186%2Fs13673-019-0170-0"
  }
]
 

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.10.1186/s13673-019-0170-0'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1186/s13673-019-0170-0'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1186/s13673-019-0170-0'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1186/s13673-019-0170-0'


 

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

108 TRIPLES      21 PREDICATES      39 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1186/s13673-019-0170-0 schema:about anzsrc-for:10
2 anzsrc-for:1005
3 schema:author N5a9c3e35d70d47aca9a9d76a9fe18bc6
4 schema:citation sg:pub.10.1186/s13673-017-0115-4
5 https://doi.org/10.1016/j.future.2012.06.009
6 https://doi.org/10.1049/ip-cdt:19990246
7 https://doi.org/10.1109/40.671404
8 https://doi.org/10.1109/autest.2007.4374248
9 https://doi.org/10.1109/clustr.2005.347027
10 https://doi.org/10.1109/conect.2003.1231473
11 https://doi.org/10.1109/ipdps.2006.1639560
12 https://doi.org/10.1145/2903150.2903168
13 https://doi.org/10.3745/jips.01.0013
14 https://doi.org/10.5573/ieie.2015.52.8.074
15 https://doi.org/10.7840/kics.2017.42.11.2122
16 schema:datePublished 2019-12
17 schema:datePublishedReg 2019-12-01
18 schema:description Today the key technology of high-performance computing systems is the emergence of interconnect technology that makes multiple computers into one computer cluster. This technique is a general method in which each constituent node processes its own operation and communicates with different nodes. Therefore, a high-performance network has been required. InfiniBand and Gigabit Ethernet technologies are typical examples of high-performance network. As an alternative to those technologies the development of interconnection technology using PCI Express (Peripheral Component Interconnect Express), officially abbreviated as PCIe or PCI-e, is a high-speed serial computer expansion bus standard, which has characteristics of high speed, low power, and high protocol efficiency is actively under development. In a high-performance network, the TCP/IP protocol consumes CPU resources and memory bandwidth by nature, which is a bottleneck. In this paper, we implement the PCIe based interconnection network system with low latency, low power, RDMA, and other characteristics. We utilize Socket API which is mainly used in the user-level application program rather than the existing MPI and PGAS model interfaces. The implemented PCIe interconnection network system was measured with the metrics as the bandwidth using the Iperf Benchmark which uses the Socket API. The bandwidth at 4 Mbyte of transmission data size was measured to be 1084 Mbyte/s bandwidth based on PCIe, which is about 96 times higher than that of 11.2 Mbyte/s bandwidth based on Ethernet.
19 schema:genre research_article
20 schema:inLanguage en
21 schema:isAccessibleForFree false
22 schema:isPartOf N3e6680f11e7d4039858143522b314544
23 Nd9a35c2ff8fd421da0a24a3d350aa1fe
24 sg:journal.1136381
25 schema:name Compatibility enhancement and performance measurement for socket interface with PCIe interconnections
26 schema:pagination 10
27 schema:productId N51a64bb8a17a4a9da186e0dcf27496c7
28 N89d406d2a29a47fa99e85ffdb6a3c4df
29 Nf74e6def429044c5b799ed5fb559db02
30 schema:sameAs https://app.dimensions.ai/details/publication/pub.1112739281
31 https://doi.org/10.1186/s13673-019-0170-0
32 schema:sdDatePublished 2019-04-11T11:46
33 schema:sdLicense https://scigraph.springernature.com/explorer/license/
34 schema:sdPublisher Neb0cbc49fa9f4a299b9c6bb7c7a733f0
35 schema:url https://link.springer.com/10.1186%2Fs13673-019-0170-0
36 sgo:license sg:explorer/license/
37 sgo:sdDataset articles
38 rdf:type schema:ScholarlyArticle
39 N3e6680f11e7d4039858143522b314544 schema:volumeNumber 9
40 rdf:type schema:PublicationVolume
41 N410f0c009e2249d3852ab309e1416d31 schema:affiliation https://www.grid.ac/institutes/grid.254229.a
42 schema:familyName Choi
43 schema:givenName Min
44 rdf:type schema:Person
45 N4db1f3d9ad004d9d99e51daa10a80353 schema:affiliation https://www.grid.ac/institutes/grid.254229.a
46 schema:familyName Shinde
47 schema:givenName Rupali
48 rdf:type schema:Person
49 N51a64bb8a17a4a9da186e0dcf27496c7 schema:name readcube_id
50 schema:value d5db2a7a1bf65960eb6b32821545e5b5bfdbb46d3d3af3332ad3af083a290f25
51 rdf:type schema:PropertyValue
52 N525d95f051fb4239a7dd4a96c13fd096 schema:affiliation https://www.grid.ac/institutes/grid.254229.a
53 schema:familyName Shim
54 schema:givenName Cheol
55 rdf:type schema:Person
56 N5a9c3e35d70d47aca9a9d76a9fe18bc6 rdf:first N525d95f051fb4239a7dd4a96c13fd096
57 rdf:rest Nec37321f1a324727ab519b5fc4c7580a
58 N89d406d2a29a47fa99e85ffdb6a3c4df schema:name dimensions_id
59 schema:value pub.1112739281
60 rdf:type schema:PropertyValue
61 Nd9a35c2ff8fd421da0a24a3d350aa1fe schema:issueNumber 1
62 rdf:type schema:PublicationIssue
63 Neb0cbc49fa9f4a299b9c6bb7c7a733f0 schema:name Springer Nature - SN SciGraph project
64 rdf:type schema:Organization
65 Nec37321f1a324727ab519b5fc4c7580a rdf:first N4db1f3d9ad004d9d99e51daa10a80353
66 rdf:rest Nf5006811a874417cbd7318dfa23391f1
67 Nf5006811a874417cbd7318dfa23391f1 rdf:first N410f0c009e2249d3852ab309e1416d31
68 rdf:rest rdf:nil
69 Nf74e6def429044c5b799ed5fb559db02 schema:name doi
70 schema:value 10.1186/s13673-019-0170-0
71 rdf:type schema:PropertyValue
72 anzsrc-for:10 schema:inDefinedTermSet anzsrc-for:
73 schema:name Technology
74 rdf:type schema:DefinedTerm
75 anzsrc-for:1005 schema:inDefinedTermSet anzsrc-for:
76 schema:name Communications Technologies
77 rdf:type schema:DefinedTerm
78 sg:journal.1136381 schema:issn 2192-1962
79 schema:name Human-centric Computing and Information Sciences
80 rdf:type schema:Periodical
81 sg:pub.10.1186/s13673-017-0115-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091668072
82 https://doi.org/10.1186/s13673-017-0115-4
83 rdf:type schema:CreativeWork
84 https://doi.org/10.1016/j.future.2012.06.009 schema:sameAs https://app.dimensions.ai/details/publication/pub.1011568152
85 rdf:type schema:CreativeWork
86 https://doi.org/10.1049/ip-cdt:19990246 schema:sameAs https://app.dimensions.ai/details/publication/pub.1056845150
87 rdf:type schema:CreativeWork
88 https://doi.org/10.1109/40.671404 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061168352
89 rdf:type schema:CreativeWork
90 https://doi.org/10.1109/autest.2007.4374248 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095133561
91 rdf:type schema:CreativeWork
92 https://doi.org/10.1109/clustr.2005.347027 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094961548
93 rdf:type schema:CreativeWork
94 https://doi.org/10.1109/conect.2003.1231473 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093725694
95 rdf:type schema:CreativeWork
96 https://doi.org/10.1109/ipdps.2006.1639560 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093751896
97 rdf:type schema:CreativeWork
98 https://doi.org/10.1145/2903150.2903168 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052476399
99 rdf:type schema:CreativeWork
100 https://doi.org/10.3745/jips.01.0013 schema:sameAs https://app.dimensions.ai/details/publication/pub.1084440442
101 rdf:type schema:CreativeWork
102 https://doi.org/10.5573/ieie.2015.52.8.074 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019067614
103 rdf:type schema:CreativeWork
104 https://doi.org/10.7840/kics.2017.42.11.2122 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100246220
105 rdf:type schema:CreativeWork
106 https://www.grid.ac/institutes/grid.254229.a schema:alternateName Chungbuk National University
107 schema:name Department of Information and Communication Engineering, Chungbuk National University, 28644, Cheongju, South Korea
108 rdf:type schema:Organization
 




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


...