small fix sum cuda

2024-05-22 20:59:25 -03:00 · 2024-05-22 20:59:25 -03:00 · 950cde13f7
commit 950cde13f7
parent 718a4c9823
4 changed files with 1 additions and 2 deletions
--- a/build/cuda.cu.o
+++ b/build/cuda.cu.o
--- a/norch/csrc/cuda.cu
+++ b/norch/csrc/cuda.cu
@ -194,7 +194,7 @@ __host__ void sum_tensor_cuda(Tensor* tensor, float* result_data, int axis) {
        }

        cudaDeviceSynchronize();
-
+        
    } else {
        int axis_size = tensor->shape[axis];

--- a/norch/csrc/tensor.cpp
+++ b/norch/csrc/tensor.cpp
@ -211,7 +211,6 @@ extern "C" {

            float* result_data;
            cudaMalloc((void**)&result_data, size * sizeof(float));
-            cudaMemset(result_data, 0, size * sizeof(float));
            sum_tensor_cuda(tensor, result_data, axis);
            
            if (keepdim) {
--- a/norch/libtensor.so
+++ b/norch/libtensor.so