- android - 多次调用 OnPrimaryClipChangedListener
- android - 无法更新 RecyclerView 中的 TextView 字段
- android.database.CursorIndexOutOfBoundsException : Index 0 requested, 光标大小为 0
- android - 使用 AppCompat 时,我们是否需要明确指定其 UI 组件(Spinner、EditText)颜色
我是这样做的:
void calculateClusterCentroIDs(int numCoords, int numObjs, int numClusters, float * dataSetMatrix, int * clusterAssignmentCurrent, float *clustersCentroID) {
int * clusterMemberCount = (int *) calloc (numClusters,sizeof(int));
#pragma omp parallel
{
int ** localClusterMemberCount;
int * activeCluster;
#pragma omp single
{
localClusterMemberCount = (int **) malloc (omp_get_num_threads() * sizeof(int *));
//localClusterMemberCount[0] = (int *) calloc (omp_get_num_threads()*numClusters,sizeof(int));
for (int i = 0; i < omp_get_num_threads(); ++i) {
localClusterMemberCount[i] = calloc (numClusters,sizeof(int));
//localClusterMemberCount[i] = localClusterMemberCount[i-1] + numClusters;
}
activeCluster = (int *) calloc (omp_get_num_threads(),sizeof(int));
}
// sum all points
// for every point
for (int i = 0; i < numObjs; ++i) {
// which cluster is it in?
activeCluster[omp_get_thread_num()] = clusterAssignmentCurrent[i];
// update count of members in that cluster
++localClusterMemberCount[omp_get_thread_num()][activeCluster[omp_get_thread_num()]];
// sum point coordinates for finding centroid
for (int j = 0; j < numCoords; ++j)
#pragma omp atomic
clustersCentroID[activeCluster[omp_get_thread_num()]*numCoords + j] += dataSetMatrix[i*numCoords + j];
}
// now divide each coordinate sum by number of members to find mean/centroid
// for each cluster
for (int i = 0; i < numClusters; ++i) {
if (localClusterMemberCount[omp_get_thread_num()][i] != 0)
// for each numCoordsension
for (int j = 0; j < numCoords; ++j)
#pragma omp atomic
clustersCentroID[i*numCoords + j] /= localClusterMemberCount[omp_get_thread_num()][i]; /// XXXX will divide by zero here for any empty clusters!
}
// free memory
#pragma omp single
{
free (localClusterMemberCount[0]);
free (localClusterMemberCount);
free (activeCluster);
}
}
free(clusterMemberCount);
但我收到错误:Segment violation ('core' generated)
所以我做错了,我认为错误是在 mallocing 指针上,因为我已经尝试了顺序代码,它是工作正常。我也尝试过并行代码但没有 mallocs(使用带有原子的全局变量)并且也工作正常。只有当我尝试创建私有(private)指针并对其进行 malloc 时,才会出现该错误。
知道如何解决吗?
最佳答案
段错误的两个原因:
localClusterMemberCount
应该是在并行区域外声明的共享变量,由单个线程在并行区域内初始化。否则,每个线程都有自己的变量副本,并且对于除了已经通过单个
部分的线程之外的所有线程,它都指向内存的随机位置。代码几乎没有其他问题。请参阅下面带有 ***
标记的我自己的评论:
void calculateClusterCentroIDs(int numCoords, int numObjs, int numClusters, float * dataSetMatrix, int * clusterAssignmentCurrent, float *clustersCentroID) {
int * clusterMemberCount = (int *) calloc (numClusters,sizeof(int));
/* ***
* This has to be a shared variable that each thread can access
* If declared inside the parallel region, it will be a thread-local variable
* which is left un-initialized for all but one thread. Further attempts to access
* that variable will lead to segfaults
*/
int ** localClusterMemberCount;
#pragma omp parallel shared(localClusterMemberCount,clusterMemberCount)
{
// *** Make activeCluster a thread-local variable rather than a shared array (shared array will result in false sharing)
int activeCluster;
#pragma omp single
{
localClusterMemberCount = (int **) malloc (omp_get_num_threads() * sizeof(int *));
//localClusterMemberCount[0] = (int *) calloc (omp_get_num_threads()*numClusters,sizeof(int));
for (int i = 0; i < omp_get_num_threads(); ++i) {
localClusterMemberCount[i] = calloc (numClusters,sizeof(int));
//localClusterMemberCount[i] = localClusterMemberCount[i-1] + numClusters;
}
}
// sum all points
// for every point
for (int i = 0; i < numObjs; ++i) {
// which cluster is it in?
activeCluster = clusterAssignmentCurrent[i];
// update count of members in that cluster
++localClusterMemberCount[omp_get_thread_num()][activeCluster];
// sum point coordinates for finding centroid
// *** This may be slower in parallel because of the atomic operation
for (int j = 0; j < numCoords; ++j)
#pragma omp atomic
clustersCentroID[activeCluster*numCoords + j] += dataSetMatrix[i*numCoords + j];
}
/* ***
* Missing: one reduction step
* The global cluster member count needs to be updated
* one option is below :
*/
#pragma omp critical
for (int i=0; i < numClusters; ++i) clusterMemberCount+=localClusterMemberCount[omp_get_thread_num()];
#pragma omp barrier // wait here before moving on
// *** The code below was wrong; to compute the average, coordinates should be divided by the global count
// *** Sucessive divisions by local count will fail. Like, 1/(4+6) is not the same as (1/4)/6
// now divide each coordinate sum by number of members to find mean/centroid
// for each cluster
#pragma omp for
for (int i = 0; i < numClusters; ++i) {
if (clusterMemberCount != 0)
// for each numCoordsension
#pragma omp simd //not sure this will help, the compiler may already vectorize that
for (int j = 0; j < numCoords; ++j)
clustersCentroID[i*numCoords + j] /= clusterMemberCount[i]; /// XXXX will divide by zero here for any empty clusters!
// *** ^^ atomic is not needed
// *** only one thread will access each value of clusterCentroID
}
#pragma omp barrier
/* ***
* A barrier is needed otherwise the first thread arriving there will start to free the memory
* Other threads may still be in the previous loop attempting to access localClusterMemberCount
* If the pointer has been freed already, this will result in a segfault
*
* With the corrected code, the implicit barrier at the end of the distributed
* for loop would be sufficient. With your initial code, an explicit barrier
* would have been needed.
*/
// free memory
#pragma omp single
{
// *** Need to free all pointers and not only the first one
for (int i = 0; i < omp_get_num_threads(); ++i) free (localClusterMemberCount[i]);
free (localClusterMemberCount);
}
}
free(clusterMemberCount);
关于c - 如何在 OpenMP 并行区域内声明和 malloc 指针? (错误 : Segment violation ('core' generated)),我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/53412033/
我刚接触 C 语言几周,所以对它还很陌生。 我见过这样的事情 * (variable-name) = -* (variable-name) 在讲义中,但它到底会做什么?它会否定所指向的值吗? 最佳答案
我有一个指向内存地址的void 指针。然后,我做 int 指针 = void 指针 float 指针 = void 指针 然后,取消引用它们以获取值。 { int x = 25; vo
我正在与计算机控制的泵进行一些串行端口通信,我用来通信的 createfile 函数需要将 com 端口名称解析为 wchar_t 指针。 我也在使用 QT 创建一个表单并获取 com 端口名称作为
#include "stdio.h" #include "malloc.h" int main() { char*x=(char*)malloc(1024); *(x+2)=3; --
#include #include main() { int an_int; void *void_pointer = &an_int; double *double_ptr = void
对于每个时间步长,我都有一个二维矩阵 a[ix][iz],ix 从 0 到 nx-1 和 iz 从 0 到 nz-1。 为了组装所有时间步长的矩阵,我定义了一个长度为 nx*nz*nt 的 3D 指针
我有一个函数,它接受一个指向 char ** 的指针并用字符串填充它(我猜是一个字符串数组)。 *list_of_strings* 在函数内部分配内存。 char * *list_of_strings
我试图了解当涉及到字符和字符串时,内存分配是如何工作的。 我知道声明的数组的名称就像指向数组第一个元素的指针,但该数组将驻留在内存的堆栈中。 另一方面,当我们想要使用内存堆时,我们使用 malloc,
我有一个 C 语言的 .DLL 文件。该 DLL 中所有函数所需的主要结构具有以下形式。 typedef struct { char *snsAccessID; char *
我得到了以下数组: let arr = [ { children: [ { children: [], current: tru
#include int main(void) { int i; int *ptr = (int *) malloc(5 * sizeof(int)); for (i=0;
我正在编写一个程序,它接受一个三位数整数并将其分成两个整数。 224 将变为 220 和 4。 114 将变为 110 和 4。 基本上,您可以使用模数来完成。我写了我认为应该工作的东西,编译器一直说
好吧,我对 C++ 很陌生,我确定这个问题已经在某个地方得到了回答,而且也很简单,但我似乎找不到答案.... 我有一个自定义数组类,我将其用作练习来尝试了解其工作原理,其定义如下: 标题: class
1) this 指针与其他指针有何不同?据我了解,指针指向堆中的内存。如果有指向它们的指针,这是否意味着对象总是在堆中构造? 2)我们可以在 move 构造函数或 move 赋值中窃取this指针吗?
这个问题在这里已经有了答案: 关闭 11 年前。 Possible Duplicate: C : pointer to struct in the struct definition 在我的初学者类
我有两个指向指针的结构指针 typedef struct Square { ... ... }Square; Square **s1; //Representing 2D array of say,
变量在内存中是如何定位的?我有这个代码 int w=1; int x=1; int y=1; int z=1; int main(int argc, char** argv) { printf
#include #include main() { char *q[]={"black","white","red"}; printf("%s",*q+3); getch()
我在“C”类中有以下函数 class C { template void Func1(int x); template void Func2(int x); }; template void
我在64位linux下使用c++,编译器(g++)也是64位的。当我打印某个变量的地址时,例如一个整数,它应该打印一个 64 位整数,但实际上它打印了一个 48 位整数。 int i; cout <<
我是一名优秀的程序员,十分优秀!