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

sub broadcasted cpu autograd

Browse source
This commit is contained in:
lucasdelimanogueira 2024-05-16 17:03:09 -03:00
parent 27a866d721
commit ddf04363d1
12 changed files with 190 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

37
norch/csrc/tensor.cpp
View file

@ -259,6 +259,43 @@ extern "C" {
}
}
Tensor* sub_broadcasted_tensor(Tensor* tensor1, Tensor* tensor2) {
if (strcmp(tensor1->device, tensor2->device) != 0) {
fprintf(stderr, "Tensors must be on the same device: %s and %s\n", tensor1->device, tensor2->device);
exit(1);
}
int max_ndim = tensor1->ndim > tensor2->ndim ? tensor1->ndim : tensor2->ndim;
// Determine the broadcasted shape
int* broadcasted_shape = (int*)malloc(max_ndim * sizeof(int));
if (broadcasted_shape == NULL) {
fprintf(stderr, "Memory allocation failed\n");
exit(1);
}
for (int i = 0; i < max_ndim; i++) {
int dim1 = i < tensor1->ndim ? tensor1->shape[tensor1->ndim - 1 - i] : 1;
int dim2 = i < tensor2->ndim ? tensor2->shape[tensor2->ndim - 1 - i] : 1;
if (dim1 != dim2 && dim1 != 1 && dim2 != 1) {
fprintf(stderr, "Shapes are not compatible for broadcasting\n");
exit(1);
}
broadcasted_shape[max_ndim - 1 - i] = dim1 > dim2 ? dim1 : dim2;
}
// Allocate memory for result tensor
float* result_data = (float*)malloc(tensor1->size * sizeof(float));
if (result_data == NULL) {
fprintf(stderr, "Memory allocation failed\n");
exit(1);
}
sub_broadcasted_tensor_cpu(tensor1, tensor2, result_data, broadcasted_shape);
return create_tensor(result_data, broadcasted_shape, max_ndim, tensor1->device);
}
Tensor* elementwise_mul_tensor(Tensor* tensor1, Tensor* tensor2) {
if (tensor1->ndim != tensor2->ndim) {
fprintf(stderr, "Tensors must have the same number of dimensions %d and %d for element-wise multiplication\n", tensor1->ndim, tensor2->ndim);