File content as of revision 0:fba50ae123e6:

#include "mbed.h"
#include "cmsis_os.h"

Serial debug(USBTX, USBRX);

typedef struct
{
    double      *a;
    double      *b;
    double     sum;
    int     veclen;
} DOTDATA;

#define NUMTHRDS 4
#define VECLEN 200
DOTDATA dotstr;
osMutexId stdio_mutex;
osMutexDef(stdio_mutex);



void dotprod(void const *arg)
{
    osThreadId id;
    int i, start, end, len ;
    long offset;
    double mysum, *x, *y;
    offset = (long)arg;

    len = dotstr.veclen;
    start = offset*len;
    end   = start + len;
    x = dotstr.a;
    y = dotstr.b;

    mysum = 0;
    for (i=start; i<end ; i++)
    {
        mysum += (x[i] * y[i]);
    }

    osMutexWait(stdio_mutex, osWaitForever);
    dotstr.sum += mysum;
    printf("Thread %ld did %d to %d:  mysum=%f global sum=%f\n",offset,start,end,mysum,dotstr.sum);
    osMutexRelease(stdio_mutex);

    id = osThreadGetId();
    osThreadTerminate(id);
}


void t0(void const *argument) {dotprod(argument);}
osThreadDef(t0, osPriorityNormal, DEFAULT_STACK_SIZE);

void t1(void const *argument) {dotprod(argument);}
osThreadDef(t1, osPriorityNormal, DEFAULT_STACK_SIZE);

void t2(void const *argument) {dotprod(argument);}
osThreadDef(t2, osPriorityNormal, DEFAULT_STACK_SIZE);

void t3(void const *argument) {dotprod(argument);}
osThreadDef(t3, osPriorityNormal, DEFAULT_STACK_SIZE);

int main() {
    debug.baud(57600);

    long i;
    double *a, *b;
    //void *status;

    /* Assign storage and initialize values */

    a = (double*) malloc (NUMTHRDS*VECLEN*sizeof(double));
    b = (double*) malloc (NUMTHRDS*VECLEN*sizeof(double));

    for (i=0; i<VECLEN*NUMTHRDS; i++) {
      a[i]=1;
      b[i]=a[i];
      }

    dotstr.veclen = VECLEN;
    dotstr.a = a;
    dotstr.b = b;
    dotstr.sum=0;

    stdio_mutex = osMutexCreate(osMutex(stdio_mutex));

    for(i=0;i<NUMTHRDS;i++)
    {
        if(i==0) osThreadCreate(osThread(t0), (void *)i);
        if(i==1) osThreadCreate(osThread(t1), (void *)i);
        if(i==2) osThreadCreate(osThread(t2), (void *)i);
        if(i==3) osThreadCreate(osThread(t3), (void *)i);
    }

    printf ("Sum =  %f \n", dotstr.sum);
    free (a);
    free (b);
}