diff --git a/build/cuda.cu.o b/build/cuda.cu.o
index 8bbf51d..004bd90 100644
Binary files a/build/cuda.cu.o and b/build/cuda.cu.o differ
diff --git a/build/libtensor.so b/build/libtensor.so
index 8dc7cf6..9c8edfd 100755
Binary files a/build/libtensor.so and b/build/libtensor.so differ
diff --git a/build/tensor.o b/build/tensor.o
index 13c474d..9a67429 100644
Binary files a/build/tensor.o and b/build/tensor.o differ
diff --git a/norch/csrc/cuda.cu b/norch/csrc/cuda.cu
index c24e48a..c757724 100644
--- a/norch/csrc/cuda.cu
+++ b/norch/csrc/cuda.cu
@@ -90,6 +90,8 @@ __global__ void sum_tensor_cuda_kernel(float* data, float* result_data) {
 
 __host__ void sum_tensor_cuda(Tensor* tensor, float* result_data) {
 
+    cudaMemcpy(result_data, tensor->data, tensor->size * sizeof(float), cudaMemcpyHostToDevice);
+
     int number_of_blocks = (int)ceil(tensor->size / THREADS_PER_BLOCK);
     sum_tensor_cuda_kernel<<<number_of_blocks, THREADS_PER_BLOCK>>>(tensor->data, result_data);
     sum_tensor_cuda_kernel<<<1, THREADS_PER_BLOCK>>>(result_data, result_data);
diff --git a/norch/csrc/tensor.cpp b/norch/csrc/tensor.cpp
index 22391ee..c361161 100644
--- a/norch/csrc/tensor.cpp
+++ b/norch/csrc/tensor.cpp
@@ -10,7 +10,7 @@
 extern "C" {
 
     Tensor* create_tensor(float* data, int* shape, int ndim, char* device) {
-
+        
         printf("Creating tensor\n");
         Tensor* tensor = (Tensor*)malloc(sizeof(Tensor));
         if (tensor == NULL) {
@@ -172,7 +172,6 @@ extern "C" {
 
             float* result_data;
             cudaMalloc((void**)&result_data, tensor->size * sizeof(float));
-            result_data[0] = 0;
             sum_tensor_cuda(tensor, result_data);
             return create_tensor(result_data, shape, ndim, device);
         } 
diff --git a/test.py b/test.py
index 8cff585..7efccf6 100644
--- a/test.py
+++ b/test.py
@@ -27,33 +27,35 @@ if __name__ == "__main__":
 
     #d = b-c
 
-    a = norch.Tensor([[1, 2], [1, 2], [1, 2]], requires_grad=True)#.to("cuda")
+    """a = norch.Tensor([[1, 2], [1, 2], [1, 2]], requires_grad=True)#.to("cuda")
     b = norch.Tensor([[1, 400, 3], [1, 2, 3]], requires_grad=True)
 
     c = (a@b).reshape([9])
     d = c.sum()
     d.backward()
 
-    print(a.grad)
+    print(a.grad)"""
     
     """#print(a)
-    N = 1000
-    a = Tensor([[random.uniform(0, 1) for _ in range(N)] for _ in range(N)])
-    b = Tensor([[random.uniform(0, 1) for _ in range(N)] for _ in range(N)])
+    """
+    N = 10
+    a = norch.Tensor([[1 for _ in range(N)] for _ in range(N)])
+    #b = norch.Tensor([[random.uniform(0, 1) for _ in range(N)] for _ in range(N)])
     #b = Tensor([[1, 2, 3], [1, 2, 3], [1, 2, 3]])
     #a = Tensor([[[[1, 2, 3], [1, 2, 3], [1, 2, 3], [1, 2, 3]], [[1, 2, 3], [1, 2, 3], [1, 2, 3], [1, 2, 3]], [[1, 2, 3], [1, 2, 3], [1, 2, 3], [1, 2, 3]], [[1, 2, 3], [1, 2, 3], [1, 2, 3], [1, 2, 3]]]])
     #b = Tensor([[[[1, 2, 3], [1, 2, 3], [1, 2, 3], [1, 2, 3]], [[1, 2, 3], [1, 2, 3], [1, 2, 3], [1, 2, 3]], [[1, 2, 3], [1, 2, 3], [1, 2, 3], [1, 2, 3]], [[1, 2, 3], [1, 2, 3], [1, 2, 3], [1, 2, 3]]]])
     ini = time.time()
-    c = a + b
+    c = a.sum()
 
     print("\n#####2######")
     
     fim = time.time()
 
     print(fim-ini)
-
+    print(c)
     print("\n\n")
 
+    """
     
     a = [[random.uniform(0, 1) for _ in range(N)] for _ in range(N)]
     b = [[random.uniform(0, 1) for _ in range(N)] for _ in range(N)]