1 Ocak 2016 Dergi makalesi Açık Erişim

Yilmaz, Buse; Aktemur, Baris; Garzaran, Maria J.; Kamin, Sam; Kirac, Furkan

JSON

{
  "conceptrecid": "57992", 
  "created": "2021-03-16T00:25:25.335369+00:00", 
  "doi": "10.1145/2851500", 
  "files": [
    {
      "bucket": "73a98c00-36ff-43bd-bc18-a8f513a57cac", 
      "checksum": "md5:dfd6259d90e6c44da88df64c8d0bec99", 
      "key": "bib-d5ddedc8-307b-4679-a156-6a19e570fae0.txt", 
      "links": {
        "self": "https://aperta.ulakbim.gov.tr/api/files/73a98c00-36ff-43bd-bc18-a8f513a57cac/bib-d5ddedc8-307b-4679-a156-6a19e570fae0.txt"
      }, 
      "size": 206, 
      "type": "txt"
    }
  ], 
  "id": 57993, 
  "links": {
    "badge": "https://aperta.ulakbim.gov.tr/badge/doi/10.1145/2851500.svg", 
    "bucket": "https://aperta.ulakbim.gov.tr/api/files/73a98c00-36ff-43bd-bc18-a8f513a57cac", 
    "doi": "https://doi.org/10.1145/2851500", 
    "html": "https://aperta.ulakbim.gov.tr/record/57993", 
    "latest": "https://aperta.ulakbim.gov.tr/api/records/57993", 
    "latest_html": "https://aperta.ulakbim.gov.tr/record/57993"
  }, 
  "metadata": {
    "access_right": "open", 
    "access_right_category": "success", 
    "communities": [
      {
        "id": "tubitak-destekli-proje-yayinlari"
      }
    ], 
    "creators": [
      {
        "affiliation": "Ozyegin Univ, TR-34794 Istanbul, Turkey", 
        "name": "Yilmaz, Buse"
      }, 
      {
        "affiliation": "Ozyegin Univ, TR-34794 Istanbul, Turkey", 
        "name": "Aktemur, Baris"
      }, 
      {
        "name": "Garzaran, Maria J."
      }, 
      {
        "name": "Kamin, Sam"
      }, 
      {
        "affiliation": "Ozyegin Univ, TR-34794 Istanbul, Turkey", 
        "name": "Kirac, Furkan"
      }
    ], 
    "description": "Runtime specialization is used for optimizing programs based on partial information available only at runtime. In this paper we apply autotuning on runtime specialization of Sparse Matrix-Vector Multiplication to predict a best specialization method among several. In 91% to 96% of the predictions, either the best or the second-best method is chosen. Predictions achieve average speedups that are very close to the speedups achievable when only the best methods are used. By using an efficient code generator and a carefully designed set of matrix features, we show the runtime costs can be amortized to bring performance benefits for many real-world cases.", 
    "doi": "10.1145/2851500", 
    "has_grant": false, 
    "journal": {
      "issue": "1", 
      "title": "ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION", 
      "volume": "13"
    }, 
    "license": {
      "id": "cc-by"
    }, 
    "publication_date": "2016-01-01", 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "57993"
          }, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "57992"
          }
        }
      ]
    }, 
    "resource_type": {
      "subtype": "article", 
      "title": "Dergi makalesi", 
      "type": "publication"
    }, 
    "title": "Autotuning Runtime Specialization for Sparse Matrix-Vector Multiplication"
  }, 
  "owners": [
    1
  ], 
  "revision": 1, 
  "stats": {
    "downloads": 9.0, 
    "unique_downloads": 9.0, 
    "unique_views": 29.0, 
    "version_downloads": 9.0, 
    "version_unique_downloads": 9.0, 
    "version_unique_views": 29.0, 
    "version_views": 33.0, 
    "version_volume": 1854.0, 
    "views": 33.0, 
    "volume": 1854.0
  }, 
  "updated": "2021-03-16T00:25:25.380161+00:00"
}