aparler/PyNorch
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

sigmoid kernel avoid overflow

Browse source
This commit is contained in:
lucasdelimanogueira 2024-05-22 13:24:01 -03:00
parent 0972a0873f
commit cebf890165
18 changed files with 126 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

37
norch/csrc/tensor.cpp
View file

@ -1290,6 +1290,43 @@ extern "C" {
}
}
Tensor* sigmoid_tensor(Tensor* tensor) {
char* device = (char*)malloc(strlen(tensor->device) + 1);
if (device != NULL) {
strcpy(device, tensor->device);
} else {
fprintf(stderr, "Memory allocation failed\n");
exit(-1);
}
int ndim = tensor->ndim;
int* shape = (int*)malloc(ndim * sizeof(int));
if (shape == NULL) {
fprintf(stderr, "Memory allocation failed\n");
exit(1);
}
for (int i = 0; i < ndim; i++) {
shape[i] = tensor->shape[i];
}
if (strcmp(tensor->device, "cuda") == 0) {
float* result_data;
cudaMalloc((void **)&result_data, tensor->size * sizeof(float));
sigmoid_tensor_cuda(tensor, result_data);
return create_tensor(result_data, shape, ndim, device);
}
else {
float* result_data = (float*)malloc(tensor->size * sizeof(float));
if (result_data == NULL) {
fprintf(stderr, "Memory allocation failed\n");
exit(1);
}
sigmoid_tensor_cpu(tensor, result_data);
return create_tensor(result_data, shape, ndim, device);
}
}
Tensor* transpose_tensor(Tensor* tensor) {
char* device = (char*)malloc(strlen(tensor->device) + 1);
if (device != NULL) {