线程安全并行.c#

我是法国人，所以首先为我的英语道歉。

我在visual studio上有一个错误(索引超出范围)，我只有一个并行的问题。For not with classic For .

我想一个线程想访问我的数组[I]，另一个线程也想…

这是一个计算Kmeans聚类的代码，用于在文档之间建立链接(具有余弦相似度)。

更多信息:

• indexoutorange on similarityMeasure[i]=.....

• 我有一台2处理器的计算机(12logical)

• with classic for, cpu使用率为9-14%，一次迭代时间=9min.

• 平行。对于，cpu使用率为70-90% =p，一次迭代时间=~1min30

• 有时在产生错误之前工作更长时间

我的功能是:

    private static int FindClosestClusterCenter(List<Centroid> clustercenter, DocumentVector obj)
{
    float[] similarityMeasure = new float[clustercenter.Count()];
    float[] copy = similarityMeasure;
    object sync = new Object();
  Parallel.For(0, clustercenter.Count(), (i) =>      //for(int i = 0; i < clustercenter.Count(); i++)  Parallel.For(0, clustercenter.Count(), (i) =>  //
       {
                similarityMeasure[i] = SimilarityMatrics.FindCosineSimilarity(clustercenter[i].GroupedDocument[0].VectorSpace, obj.VectorSpace);
       });
    int index = 0;
    float maxValue = similarityMeasure[0];
    for (int i = 0; i < similarityMeasure.Count(); i++)
    {
        if (similarityMeasure[i] > maxValue)
        {
            maxValue = similarityMeasure[i];
            index = i;
        }
    }
    return index;
}

我的函数在这里调用:

do
            {
                prevClusterCenter = centroidCollection;
                DateTime starttime = DateTime.Now;
                  foreach (DocumentVector obj in documentCollection)//Parallel.ForEach(documentCollection, parallelOptions, obj =>//foreach (DocumentVector obj in documentCollection)
                   {
                       int ind = FindClosestClusterCenter(centroidCollection, obj);
                       resultSet[ind].GroupedDocument.Add(obj);
                   }
                TimeSpan tempsecoule = DateTime.Now.Subtract(starttime);
                Console.WriteLine(tempsecoule);
                //Console.ReadKey();
                InitializeClusterCentroid(out centroidCollection, centroidCollection.Count());
                centroidCollection = CalculMeanPoints(resultSet);
                stoppingCriteria = CheckStoppingCriteria(prevClusterCenter, centroidCollection);
                if (!stoppingCriteria)
                {
                    //initialisation du resultat pour la prochaine itération
                    InitializeClusterCentroid(out resultSet, centroidCollection.Count);
                }
            } while (stoppingCriteria == false);
            _counter = counter;
            return resultSet;

FindCosSimilarity:

 public static float FindCosineSimilarity(float[] vecA, float[] vecB)
        {
            var dotProduct = DotProduct(vecA, vecB);
            var magnitudeOfA = Magnitude(vecA);
            var magnitudeOfB = Magnitude(vecB);
            float result = dotProduct / (float)Math.Pow((magnitudeOfA * magnitudeOfB),2);
            //when 0 is divided by 0 it shows result NaN so return 0 in such case.
            if (float.IsNaN(result))
                return 0;
            else
                return (float)result;
        }

CalculMeansPoint:

 private static List<Centroid> CalculMeanPoints(List<Centroid> _clust)
        {
            for (int i = 0; i < _clust.Count(); i++)
            {
                if (_clust[i].GroupedDocument.Count() > 0)
                {
                    for (int j = 0; j < _clust[i].GroupedDocument[0].VectorSpace.Count(); j++)
                    {
                        float total = 0;
                        foreach (DocumentVector vspace in _clust[i].GroupedDocument)
                        {
                            total += vspace.VectorSpace[j];
                        }
                        _clust[i].GroupedDocument[0].VectorSpace[j] = total / _clust[i].GroupedDocument.Count();
                    }
                }
            }
            return _clust;
        }

similarityMeasure = clustercenter
      .AsParallel().AsOrdered()
      .Select(c=> SimilarityMatrics.FindCosineSimilarity(c.GroupedDocument[0].VectorSpace, obj.VectorSpace))
      .ToArray();