get slow but correct results for intermediate

shaders/A2Task1Interleaved.comp

@@ -12,10 +12,12 @@ layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 layout(push_constant) uniform PushStruct {
     uint size;
     uint stride;
-} p;
+}p;
 
 layout(binding = 0) buffer inoutBufer {uint v[];};
 
 void main() {
-    // TODO: Kernel implementation
+    uint idx = gl_GlobalInvocationID.x;
+    
+    v[idx] += v[idx + p.stride];
 }