////////////////////////////////////////////////////////////////////////////
// This function is executed at library load time.
// Initilize HBW arena by making a dummy allocation/free at library load
// time. Until HBW initialization is complete, we must not call any
// allocation routines with HBW as kind.
////////////////////////////////////////////////////////////////////////////
void __attribute__ ((constructor)) autohbw_load(void)
{
// First set the default memory type this library allocates. This can
// be overridden by env variable
// Note: 'memkind_hbw_preferred' will allow falling back to DDR but
// 'memkind_hbw will not'
// Note: If HBM is not installed on a system, memkind_hbw_preferred call
// woudl fail. Therefore, we need to check for availability first.
//
int ret = 0;
if (memkind_check_available(MEMKIND_HBW) == 0) {
ret = memkind_get_kind_by_name("memkind_hbw_preferred", &HBW_Type);
}
else {
printf("WARN: *** No HBM found in system. Will use default (DDR) "
"OR user specifid type ***\n");
ret = memkind_get_kind_by_name("memkind_default", &HBW_Type);
}
assert(!ret && "FATAL: Could not find default memory type\n");
// Read any env variables. This has to be done first because DbgLevel
// is set using env variables and debug printing is used below
//
setEnvValues(); // read any env variables
DBG(1) printf("INFO: autohbw.so loaded!\n");
// dummy HBW call to initialize HBW arena
//
void *pp = memkind_malloc(HBW_Type, 16);
//
if (pp) {
// We have successfully initilized HBW arena
//
DBG(2) printf("\t-HBW int call succeeded\n");
memkind_free(0, pp);
MemkindInitDone = TRUE; // enable HBW allocation
}
else {
errPrn("\t-HBW init call FAILED. Is required memory type present on your system?\n");
assert(0 && "HBW/memkind initialization faild");
}
}
int
main(int argc, char **argv)
{
int quantum, checktick();
int BytesPerWord;
int k;
ssize_t j;
STREAM_TYPE scalar;
double t, times[4][NTIMES];
#ifdef ENABLE_DYNAMIC_ALLOC
int err = 0;
memkind_t kind;
char err_msg[ERR_MSG_SIZE];
if (argc > 1 && (strncmp("--help", argv[1], strlen("--help")) == 0 ||
strncmp("-h", argv[1], strlen("-h")) == 0)) {
printf("Usage: %s [memkind_default | memkind_hbw | memkind_hbw_hugetlb | \n"
" memkind_hbw_preferred | memkind_hbw_preferred_hugetlb | \n"
" memkind_hbw_gbtlb | memkind_hbw_preferred_gbtlb | memkind_gbtlb | \n"
" memkind_hbw_interleave | memkind_interleave]\n",
argv[0]);
return 0;
}
#endif
/* --- SETUP --- determine precision and check timing --- */
printf(HLINE);
printf("STREAM version $Revision: 5.10 $\n");
#ifdef ENABLE_DYNAMIC_ALLOC
printf("Variant that uses the memkind library for dynamic memory allocation.\n");
#endif
printf(HLINE);
BytesPerWord = sizeof(STREAM_TYPE);
printf("This system uses %d bytes per array element.\n",
BytesPerWord);
printf(HLINE);
#ifdef N
printf("***** WARNING: ******\n");
printf(" It appears that you set the preprocessor variable N when compiling this code.\n");
printf(" This version of the code uses the preprocesor variable STREAM_ARRAY_SIZE to control the array size\n");
printf(" Reverting to default value of STREAM_ARRAY_SIZE=%llu\n",(unsigned long long) STREAM_ARRAY_SIZE);
printf("***** WARNING: ******\n");
#endif
printf("Array size = %llu (elements), Offset = %d (elements)\n" , (unsigned long long) STREAM_ARRAY_SIZE, OFFSET);
printf("Memory per array = %.1f MiB (= %.1f GiB).\n",
BytesPerWord * ( (double) STREAM_ARRAY_SIZE / 1024.0/1024.0),
BytesPerWord * ( (double) STREAM_ARRAY_SIZE / 1024.0/1024.0/1024.0));
printf("Total memory required = %.1f MiB (= %.1f GiB).\n",
(3.0 * BytesPerWord) * ( (double) STREAM_ARRAY_SIZE / 1024.0/1024.),
(3.0 * BytesPerWord) * ( (double) STREAM_ARRAY_SIZE / 1024.0/1024./1024.));
printf("Each kernel will be executed %d times.\n", NTIMES);
printf(" The *best* time for each kernel (excluding the first iteration)\n");
printf(" will be used to compute the reported bandwidth.\n");
#ifdef _OPENMP
printf(HLINE);
#pragma omp parallel
{
#pragma omp master
{
k = omp_get_num_threads();
printf ("Number of Threads requested = %i\n",k);
}
}
#endif
#ifdef _OPENMP
k = 0;
#pragma omp parallel
#pragma omp atomic
k++;
printf ("Number of Threads counted = %i\n",k);
#endif
#ifdef ENABLE_DYNAMIC_ALLOC
if (argc > 1) {
err = memkind_get_kind_by_name(argv[1], &kind);
}
else {
err = memkind_get_kind_by_name("memkind_default", &kind);
}
if (err) {
memkind_error_message(err, err_msg, ERR_MSG_SIZE);
fprintf(stderr, "ERROR: %s\n", err_msg);
return -1;
}
err = memkind_posix_memalign(kind, (void **)&a, 2097152, BytesPerWord * (STREAM_ARRAY_SIZE + OFFSET));
if (err) {
fprintf(stderr, "ERROR: Unable to allocate stream array a\n");
return -err;
}
err = memkind_posix_memalign(kind, (void **)&b, 2097152, BytesPerWord * (STREAM_ARRAY_SIZE + OFFSET));
if (err) {
fprintf(stderr, "ERROR: Unable to allocate stream array b\n");
return -err;
}
err = memkind_posix_memalign(kind, (void **)&c, 2097152, BytesPerWord * (STREAM_ARRAY_SIZE + OFFSET));
if (err) {
fprintf(stderr, "ERROR: Unable to allocate stream array c\n");
return -err;
}
#endif
/* Get initial value for system clock. */
#pragma omp parallel for
for (j=0; j<STREAM_ARRAY_SIZE; j++) {
a[j] = 1.0;
b[j] = 2.0;
c[j] = 0.0;
}
printf(HLINE);
if ( (quantum = checktick()) >= 1)
printf("Your clock granularity/precision appears to be "
"%d microseconds.\n", quantum);
else {
printf("Your clock granularity appears to be "
"less than one microsecond.\n");
quantum = 1;
}
t = mysecond();
#pragma omp parallel for
for (j = 0; j < STREAM_ARRAY_SIZE; j++)
a[j] = 2.0E0 * a[j];
t = 1.0E6 * (mysecond() - t);
printf("Each test below will take on the order"
" of %d microseconds.\n", (int) t );
printf(" (= %d clock ticks)\n", (int) (t/quantum) );
printf("Increase the size of the arrays if this shows that\n");
printf("you are not getting at least 20 clock ticks per test.\n");
printf(HLINE);
printf("WARNING -- The above is only a rough guideline.\n");
printf("For best results, please be sure you know the\n");
printf("precision of your system timer.\n");
printf(HLINE);
/* --- MAIN LOOP --- repeat test cases NTIMES times --- */
scalar = 3.0;
for (k=0; k<NTIMES; k++)
{
times[0][k] = mysecond();
#ifdef TUNED
tuned_STREAM_Copy();
#else
#pragma omp parallel for
for (j=0; j<STREAM_ARRAY_SIZE; j++)
c[j] = a[j];
#endif
times[0][k] = mysecond() - times[0][k];
times[1][k] = mysecond();
#ifdef TUNED
tuned_STREAM_Scale(scalar);
#else
#pragma omp parallel for
for (j=0; j<STREAM_ARRAY_SIZE; j++)
b[j] = scalar*c[j];
#endif
times[1][k] = mysecond() - times[1][k];
times[2][k] = mysecond();
#ifdef TUNED
tuned_STREAM_Add();
#else
#pragma omp parallel for
for (j=0; j<STREAM_ARRAY_SIZE; j++)
c[j] = a[j]+b[j];
#endif
times[2][k] = mysecond() - times[2][k];
times[3][k] = mysecond();
#ifdef TUNED
tuned_STREAM_Triad(scalar);
#else
#pragma omp parallel for
for (j=0; j<STREAM_ARRAY_SIZE; j++)
a[j] = b[j]+scalar*c[j];
#endif
times[3][k] = mysecond() - times[3][k];
}
/* --- SUMMARY --- */
for (k=1; k<NTIMES; k++) /* note -- skip first iteration */
{
for (j=0; j<4; j++)
{
avgtime[j] = avgtime[j] + times[j][k];
mintime[j] = MIN(mintime[j], times[j][k]);
maxtime[j] = MAX(maxtime[j], times[j][k]);
}
}
printf("Function Best Rate MB/s Avg time Min time Max time\n");
for (j=0; j<4; j++) {
avgtime[j] = avgtime[j]/(double)(NTIMES-1);
printf("%s%12.1f %11.6f %11.6f %11.6f\n", label[j],
1.0E-06 * bytes[j]/mintime[j],
avgtime[j],
mintime[j],
maxtime[j]);
}
printf(HLINE);
/* --- Check Results --- */
checkSTREAMresults();
printf(HLINE);
#ifdef ENABLE_DYNAMIC_ALLOC
memkind_free(kind, c);
memkind_free(kind, b);
memkind_free(kind, a);
#endif
return 0;
}
