diff --git a/S1/ICVXKH/example_cudacode.py b/S1/ICVXKH/example_cudacode.py
index 3232300efee7e8feeb1170f2ea03d12b1295c238..4e61f119eec293c443cea69cfd129e6d66e0b2ff 100644
--- a/S1/ICVXKH/example_cudacode.py
+++ b/S1/ICVXKH/example_cudacode.py
@@ -17,7 +17,7 @@ __global__ void relu_kernel(const float* x, float* y, int size) {
 torch::Tensor relu_cuda(torch::Tensor x) {
     auto size = x.numel();
     auto y = torch::empty_like(x);
-    const int block_size = 256;
+    const int block_size = 128;
     int num_blocks = (size + block_size - 1) / block_size;
     relu_kernel<<<num_blocks, block_size>>>(x.data_ptr<float>(), y.data_ptr<float>(), size);
     return y;