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];
 }

shaders/A2Task1Sequential.comp

@@ -16,6 +16,11 @@ layout(push_constant) uniform PushStruct {
 
 layout(binding = 0) buffer inoutBufer { uint v[]; };
 
-void main() {
-    // TODO: Kernel implementation
+void main() {    
+    uint gIDx = gl_GlobalInvocationID.x;
+    if (gIDx >= p.size) {
+        return;
+    }
+
+    v[gIDx] = v[gIDx] + v[gIDx + p.offset];
 }

shaders/A2Task2Naive.comp

@@ -19,5 +19,4 @@ layout(binding = 0) buffer inBuffer { uint v[]; };
 layout(binding = 1) buffer outBufer { uint g_v[]; };
 
 void main() {
-    // TODO: Kernel implementation
 }