Speed issue with huge C array using 64bit Visual C

Question

I need to read a massive amount of data into a buffer (about 20gig). I have 192gb of very fast DDram available, so no issue with memory size. However, I am finding that the following code runs slower and slower the further it gets into the buffer. The Visual C profiler tells me that 68% of the 12 minute execution time is in the 2 statements inside the loop in myFunc(). I am running win7, 64bit on a very fast dell with 2 cpu's, 6 physical cores each (24 logical cores), and all 24 cores are completely maxed out while running this.

#define TREAM_COUNT 9000
#define ARRAY_SIZE ONE_BILLION

#define offSet(a,b,c,d) ( ((size_t)  ARRAY_SIZE * (a)) + ((size_t) TREAM_COUNT * 800 * (b)) + ((size_t) 800 * (c)) + (d) )

void myFunc(int dogex, int ptxIndex, int xtreamIndex, int carIndex)
{
     short *ptx  =  (short *) calloc(ARRAY_SIZE * 20, sizeof(short));

    #pragma omp parallel for
    for (int bIndex = 0; bIndex < 800; ++bIndex)
          doWork(dogex, ptxIndex, carIndex);
}

 void doWork(int dogex, int ptxIndex, int carIndex)
{

    for (int treamIndex = 0; treamIndex < ONE_BILLION; ++treamIndex)
    {
         short ptxValue     =  ptx[ offSet(dogex, ptxIndex,   treamIndex, carIndex) ];
         short lastPtxValue =  ptx[ offSet(dogex, ptxIndex-1, treamIndex, carIndex) ];

         // ....
    }

}