[ET-VK] Optimizing buffer to int8 quantized packing op to improve width packed performance.

Pull Request resolved: #12388

This diff simplifies looping in int8 quantized packing operation for width pack tensor, to improve performance.

Differential Revision: [D78143041](https://our.internmc.facebook.com/intern/diff/D78143041/)
ghstack-source-id: 295655468

Author: trivedivivek

backends/vulkan/runtime/graph/ops/glsl/nchw_to_bitw8_image_nobitw8buffer.glsl

@@ -57,12 +57,24 @@ ivec4 read_texel(ivec4 tidx) {
 
   ivec4 out_tex = ivec4(0);
 
-  [[unroll]] for (int i = 0; i < 4; ++i) {
-    if (tidx[packed_dim] + i < sizes[packed_dim]) {
-      const int in_texel = nchw_in[buf_indices[i] >> 2];
-      int extracted_val = (in_texel >> (8 * (buf_indices[i] & 3))) & mask;
-      extracted_val = extend_sign(extracted_val);
-      out_tex[i] = extracted_val;
+  if (packed_dim == 0) {
+    int buf_index = buf_indices[0];
+    [[unroll]] for (int i = 0; i < 4; ++i, ++buf_index) {
+      if (tidx[packed_dim] + i < sizes[packed_dim]) {
+        const int in_texel = nchw_in[buf_index >> 2];
+        int extracted_val = (in_texel >> (8 * (buf_index & 3))) & mask;
+        extracted_val = extend_sign(extracted_val);
+        out_tex[i] = extracted_val;
+      }
+    }
+  } else {
+    [[unroll]] for (int i = 0; i < 4; ++i) {
+      if (tidx[packed_dim] + i < sizes[packed_dim]) {
+        const int in_texel = nchw_in[buf_indices[i] >> 2];
+        int extracted_val = (in_texel >> (8 * (buf_indices[i] & 3))) & mask;
+        extracted_val = extend_sign(extracted_val);
+        out_tex[i] = extracted_val;
+      }
     }
   }