#define UNSIGNED_LARGE_INT unsigned long long
#define MAX_LOOP_ITER 10
typedef cl_float4 float4;
typedef void (*CPUKernel)(__m128 *, __m128 *, unsigned int);
typedef void (*CPUKernel)(__ibm128 *, __ibm128 *, unsigned int);
class OCLPerfKernelThroughput : public OCLTestImp {
public: