【发布时间】：2016-05-25 01:01:22
【问题描述】：
有一个使用 MPJ Express 将矩阵和向量相乘的程序。矩阵按行划分。但是在处理时发生了异常。那是我做错了吗？
import java.util.Random;
import mpi.Comm;
import mpi.MPI;
public class Main {
private static final int rootProcessorRank = 0;
private static Comm comunicator;
private static int processorsNumber;
private static int currentProcessorRank;
public static void main(String[] args) {
MPI.Init(args);
comunicator = MPI.COMM_WORLD;
currentProcessorRank = comunicator.Rank();
processorsNumber = comunicator.Size();
if (currentProcessorRank == rootProcessorRank) {
rootProcessorAction();
} else {
notRootProcessorAction();
}
MPI.Finalize();
}
public static void rootProcessorAction() {
int[] matrixVectorSize = new int[] {5};
int[][] matrix = createAndInitMatrix(matrixVectorSize[0]);
int[] vector = createAndInitVector(matrixVectorSize[0]);
for (int i = 1; i < processorsNumber; i++) {
comunicator.Isend(matrixVectorSize, 0, 1, MPI.INT, i, MPI.ANY_TAG);
System.out.println("Proc: " + currentProcessorRank + ", send matrixVectorSize");
comunicator.Isend(vector, 0, vector.length, MPI.INT, i, MPI.ANY_TAG);
System.out.println("Proc: " + currentProcessorRank + ", send vector");
}
int averageRowsPerProcessor = matrix.length / (processorsNumber - 1);
int[] rowsPerProcessor = new int[processorsNumber];
int notDistributedRowsNumber = matrix.length;
for (int i = 1; i < rowsPerProcessor.length; i++) {
if (i == rowsPerProcessor.length - 1) {
rowsPerProcessor[i] = notDistributedRowsNumber;
} else {
rowsPerProcessor[i] = averageRowsPerProcessor;
notDistributedRowsNumber -= averageRowsPerProcessor;
}
}
int offset = 0;
// the processorRows[0] always will be '0'
for (int i = 1; i < rowsPerProcessor.length; i++) {
int[] processorRows = new int[1];
processorRows[0] = rowsPerProcessor[i];
comunicator.Isend(processorRows, 0, 1, MPI.INT, i, MPI.ANY_TAG);
comunicator.Isend(matrix, offset, processorRows[0], MPI.OBJECT, i, MPI.ANY_TAG);
offset += rowsPerProcessor[i];
}
// there will be a code that receive a subRecults from all processes.
}
public static void notRootProcessorAction() {
int[] matrixVectorSize = new int[1];
int[] rowsNumber = new int[1];
int[] vector = null;
int[][] subMatrix = null;
comunicator.Probe(rootProcessorRank, MPI.ANY_SOURCE);
comunicator.Recv(matrixVectorSize, 0, 1, MPI.INT, rootProcessorRank, MPI.ANY_TAG);
System.out.println("Proc: " + currentProcessorRank + ", receive matrixVectorSize");
vector = new int[matrixVectorSize[0]];
comunicator.Probe(rootProcessorRank, MPI.ANY_SOURCE);
comunicator.Recv(vector, 0, vector.length, MPI.INT, rootProcessorRank, MPI.ANY_TAG);
System.out.println("Proc: " + currentProcessorRank + ", receive vector");
comunicator.Probe(rootProcessorRank, MPI.ANY_SOURCE);
comunicator.Recv(rowsNumber, 0, 1, MPI.INT, rootProcessorRank, MPI.ANY_TAG);
System.out.println("Proc: " + currentProcessorRank + ", receive rowsNumber");
subMatrix = new int[rowsNumber[0]][rowsNumber[0]];
comunicator.Probe(rootProcessorRank, MPI.ANY_SOURCE);
comunicator.Recv(subMatrix, 0, subMatrix.length, MPI.OBJECT, rootProcessorRank, MPI.ANY_TAG);
System.out.println("Proc: " + currentProcessorRank + ", receive subMatrix");
int[] result = new int[rowsNumber[0]];
multiplyMatrixVector(subMatrix, vector, result);
comunicator.Send(result, 0, result.length, MPI.INT, rootProcessorRank, MPI.ANY_TAG);
}
private static void multiplyMatrixVector(int[][] matrix, int[] vector, int[] result) {
for (int i = 0; i < matrix.length; i++) {
int summ = 0;
for (int j = 0; j < matrix[i].length; j++) {
summ += matrix[i][j] * vector[j];
}
result[i] = summ;
}
}
private static int[][] createAndInitMatrix(int size) {
int[][] matrix = new int[size][size];
Random random = new Random();
for (int i = 0; i < matrix.length; i++) {
for (int j = 0; j < matrix.length; j++) {
matrix[i][j] = random.nextInt(100);
}
}
return matrix;
}
private static int[] createAndInitVector(int size) {
int[] vector = new int[size];
Random random = new Random();
for (int i = 0; i < vector.length; i++) {
vector[i] = random.nextInt(100);
}
return vector;
}
}
这里有一个例外：
MPJ Express (0.44) 在多核配置中启动 java.lang.reflect.InvocationTargetException 在 sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) 在 sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) 在 sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) 在 java.lang.reflect.Method.invoke(Method.java:606) 在 runtime.starter.MulticoreStarter$1.run(MulticoreStarter.java:281) 在 java.lang.Thread.run(Thread.java:745) 引起：mpi.MPIException： xdev.XDevException：java.lang.NullPointerException 在 mpi.Comm.isend(Comm.java:944) 在 mpi.Comm.Isend(Comm.java:885) 在 Main.main(Main.java:20) 处的 Main.rootProcessorAction(Main.java:35) ... 6 更多原因：xdev.XDevException： java.lang.NullPointerException 在 xdev.smpdev.SMPDevice.isend(SMPDevice.java:104) 在 mpjdev.javampjdev.Comm.isend(Comm.java:1019) 在 mpi.Comm.isend(Comm.java:941) ... 还有 9 个原因： java.lang.NullPointerException 在 xdev.smpdev.SMPDeviceImpl$SendQueue.add(SMPDeviceImpl.java:930) 在 xdev.smpdev.SMPDeviceImpl$SendQueue.add(SMPDeviceImpl.java:909) 在 xdev.smpdev.SMPDeviceImpl.isend(SMPDeviceImpl.java:330) 在 xdev.smpdev.SMPDevice.isend(SMPDevice.java:101) ... 11 更多 xdev.XDevException：java.lang.NullPointerException 在 xdev.smpdev.SMPDevice.recv(SMPDevice.java:162)
【问题讨论】：
-
NULL 指针异常可能通常是由于访问了一些不存在的内存部分...您的源代码中的数据是否连续？
-
你能运行一个简单的 MPJ hello world 吗？
-
其实我用MPI写了一个简单的程序。它正在工作。
标签： java mpi multicore mpj-express