static void bernoulli_generate(int n, double p, int* r) {
int seed = 17 + caffe_rng_rand() % 4096;
#ifdef _OPENMP
int nthr = omp_get_max_threads();
int threshold = nthr * caffe::cpu::OpenMpManager::getProcessorSpeedMHz() / 3;
bool run_parallel =
(Caffe::mode() != Caffe::GPU) &&
(omp_in_parallel() == 0) &&
(n >= threshold);
if (!run_parallel) nthr = 1;
# pragma omp parallel num_threads(nthr)
{
const int ithr = omp_get_thread_num();
const int avg_amount = (n + nthr - 1) / nthr;
const int my_offset = ithr * avg_amount;
const int my_amount = std::min(my_offset + avg_amount, n) - my_offset;
#else
{
const int my_amount = n;
const int my_offset = 0;
#endif
VSLStreamStatePtr stream;
vslNewStream(&stream, VSL_BRNG_MCG31, seed);
vslSkipAheadStream(stream, my_offset);
viRngBernoulli(VSL_RNG_METHOD_BERNOULLI_ICDF, stream, my_amount,
r + my_offset, p);
vslDeleteStream(&stream);
}
}
JNIEXPORT jint JNICALL Java_edu_berkeley_bid_VSL_viRngBernoulli
(JNIEnv * env, jobject calling_obj, jint method, jobject j_stream, jint n, jintArray j_r, jdouble a) {
VSLStreamStatePtr stream = getStream(env, calling_obj, j_stream);
jint * r = (*env)->GetPrimitiveArrayCritical(env, j_r, JNI_FALSE);
jint retval = viRngBernoulli(method, stream, n, r, a);
(*env)->ReleasePrimitiveArrayCritical(env, j_r, r, 0);
return retval;
}
void DropoutLayer<Dtype>::Forward_cpu(const vector<Blob<Dtype>*>& bottom,
vector<Blob<Dtype>*>* top) {
const Dtype* bottom_data = bottom[0]->cpu_data();
Dtype* top_data = (*top)[0]->mutable_cpu_data();
int* mask = reinterpret_cast<int*>(rand_vec_->mutable_cpu_data());
const int count = bottom[0]->count();
if (Caffe::phase() == Caffe::TRAIN) {
// Create random numbers
#if 0
viRngBernoulli(VSL_RNG_METHOD_BERNOULLI_ICDF, Caffe::vsl_stream(),
count, mask, 1. - threshold_);
for (int i = 0; i < count; ++i) {
top_data[i] = bottom_data[i] * mask[i] * scale_;
}
#else
NOT_IMPLEMENTED;
#endif
} else {
memcpy(top_data, bottom_data, bottom[0]->count() * sizeof(Dtype));
}
}
