diff --git a/src/conv_kernels.cu b/src/conv_kernels.cu
index d244300..7bde8b0 100644
--- a/src/conv_kernels.cu
+++ b/src/conv_kernels.cu
@@ -202,6 +202,8 @@ void conv2d_variant3(const float* input, const float* kernel, float* output,
 // - Degree of overlap visible on the NSYS timeline (copies concurrent with kernels).
 // - Any change in kernel performance (avoid starving compute with too many small chunks).
 //
+// NOTE: const float* input, const float* kernel are host pointers in this task
+//
 // =============================================================================
 
 
diff --git a/src/main.cu b/src/main.cu
index 0a4f6c1..97cbb54 100644
--- a/src/main.cu
+++ b/src/main.cu
@@ -157,7 +157,7 @@ int main(int argc, char** argv) {
             conv2d_variant3(device_input, device_kernel, device_output, 
                             batch_size, height, width, kernel_size, stream);
         } else if (impl_name == "variant4") {
-            conv2d_variant4(device_input, device_kernel, device_output, 
+            conv2d_variant4(host_images.data(), host_kernel.data(), device_output, 
                             batch_size, height, width, kernel_size, stream);
         } else {
             std::fprintf(stderr, "Unknown implementation: %s\n", impl_name.c_str());