[OpenMP] Make bug49334.cpp more reproducible

[tianshilei1992]

Summary

bug49334.cpp cannot detect data race in libomptarget efficiently. It
is reported that with N = 256 and BS = 16, the data race can be reproduced
more steadily. The next coming pathces will fix it so this patch is expected to
fail now.

[jdoerfert]

LG

openmp/libomptarget/test/offloading/bug49334.cpp

public:
   }
 
   float *GetBlock(int i, int j) const {
     assert(i < nBlocksPerCol && j < nBlocksPerRow && "Accessing outside block");
     return Blocks[i][j].get();
   }
 };
 
-constexpr const int BS = 256;
-constexpr const int N = 1024;
+constexpr const int BS = 16;
+constexpr const int N = 256;
 
 int BlockMatMul_TargetNowait(BlockMatrix &A, BlockMatrix &B, BlockMatrix &C) {
 #pragma omp parallel
 #pragma omp master
   for (int i = 0; i < N / BS; ++i)
     for (int j = 0; j < N / BS; ++j) {
       float *BlockC = C.GetBlock(i, j);
       for (int k = 0; k < N / BS; ++k) {