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

fix pow, div, log operations

Browse source
This commit is contained in:
lucasdelimanogueira 2024-05-06 10:18:12 -03:00
parent ca4a0f0dbc
commit 065c6a0f29
15 changed files with 160 additions and 51 deletions
Download patch file Download diff file Expand all files Collapse all files

51
norch/csrc/tensor.cpp
View file

@ -411,6 +411,57 @@ extern "C" {
}
}
Tensor* tensor_div_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);
exit(1);
}
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);
}
char* device = (char*)malloc(strlen(tensor1->device) + 1);
if (device != NULL) {
strcpy(device, tensor1->device);
} else {
fprintf(stderr, "Memory allocation failed\n");
exit(-1);
}
int ndim = tensor1->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++) {
if (tensor1->shape[i] != tensor2->shape[i]) {
fprintf(stderr, "Tensors must have the same shape %d and %d at index %d for subtraction\n", tensor1->shape[i], tensor2->shape[i], i);
exit(1);
}
shape[i] = tensor1->shape[i];
}
if (strcmp(tensor1->device, "cuda") == 0) {
float* result_data;
cudaMalloc((void **)&result_data, tensor1->size * sizeof(float));
tensor_div_tensor_cuda(tensor1, tensor2, result_data);
return create_tensor(result_data, shape, ndim, device);
}
else {
float* result_data = (float*)malloc(tensor1->size * sizeof(float));
if (result_data == NULL) {
fprintf(stderr, "Memory allocation failed\n");
exit(1);
}
tensor_div_tensor_cpu(tensor1, tensor2, result_data);
return create_tensor(result_data, shape, ndim, device);
}
}
Tensor* matmul_tensor(Tensor* tensor1, Tensor* tensor2) {
//MxN @ NxP = MxP
// Check if tensors have compatible shapes for matrix multiplication