doc: refine diagram of software architecture in toplevel README.md

Author: zhouwg

README.md

@@ -247,50 +247,70 @@ Instructions for adding support for new models: [HOWTO-add-model.md](docs/develo
 
 ## Software architecture
 
+
 ```mermaid
 block-beta
 columns 1
 
 block:llamacpp
-   llamacpp["llama_cpp"]
-   style llamacpp fill:#3c3,color:#000,stroke:#000
+    llamacpp["llama_cpp"]
+    style llamacpp fill:#3c3,color:#000,stroke:#000
 end
 
-block:ggml
-   ggml["GGML"]
-   style ggml     fill:#3c3,color:#000,stroke:#000
-
-   ggml_cpu["ggml-cpu"]
-   ggml_metal["ggml-metal"]
-   ggml_sycl["ggml-sycl"]
-   ggml_cuda["ggml-cuda"]
-   ggml_hip["ggml-hip"]
-   ggml_vulkan["ggml-vulkan"]
-   ggml_cann["ggml-cann"]
-   ggml_opencl["ggml-opencl"]
-   ggml_qnn["ggml-qnn"]
-   ggml_nnpa["ggml-nnpa"]
-   ggml_ane["ggml-ane"]
-
-   style ggml_cpu       fill:#888,color:#000,stroke:#000
-   style ggml_metal     fill:#888,color:#000,stroke:#000
-   style ggml_sycl      fill:#888,color:#000,stroke:#000
-   style ggml_cuda      fill:#888,color:#000,stroke:#000
-   style ggml_hip       fill:#888,color:#000,stroke:#000
-   style ggml_vulkan    fill:#888,color:#000,stroke:#000
-   style ggml_cann      fill:#888,color:#000,stroke:#000
-
-   style ggml_opencl    fill:#cc3,color:#000,stroke:#000
-   style ggml_qnn       fill:#cc3,color:#000,stroke:#000
-   style ggml_ane       fill:#fff,color:#000,stroke:#f00,stroke-width:2,stroke-dasharray:5
-   style ggml_nnpa      fill:#cc3,color:#000,stroke:#000
+block:ggml_backend
+    ggml_backend["GGML backend subsystem"]
+    style ggml_backend fill:#3c3,color:#000,stroke:#000
+
+    block:ggmlbackends
+        ggml_cpu["ggml-cpu"]
+        ggml_metal["ggml-metal"]
+        ggml_sycl["ggml-sycl"]
+        ggml_cuda["ggml-cuda"]
+        ggml_hip["ggml-hip"]
+        ggml_vulkan["ggml-vulkan"]
+        ggml_cann["ggml-cann"]
+        ggml_opencl["ggml-opencl"]
+        ggml_qnn["ggml-qnn"]
+        ggml_nnpa["ggml-nnpa"]
+        ggml_ane["ggml-ane"]
+
+        style ggml_cpu      fill:#888,color:#000,stroke:#000
+        style ggml_metal    fill:#888,color:#000,stroke:#000
+        style ggml_sycl     fill:#888,color:#000,stroke:#000
+        style ggml_cuda     fill:#888,color:#000,stroke:#000
+        style ggml_hip      fill:#888,color:#000,stroke:#000
+        style ggml_vulkan   fill:#888,color:#000,stroke:#000
+        style ggml_cann     fill:#888,color:#000,stroke:#000
+
+        style ggml_opencl   fill:#cc3,color:#000,stroke:#000
+        style ggml_qnn       fill:#cc3,color:#000,stroke:#000
+        style ggml_ane       fill:#fff,color:#000,stroke:#f00,stroke-width:2,stroke-dasharray:5
+        style ggml_nnpa      fill:#cc3,color:#000,stroke:#000
+    end
 end
 
 block:ggml_pal
-   ggml_pal["GGML Platform Abstraction Layer"]
-   style ggml_pal       fill:#c33,color:#000,stroke:#000
+    ggml_pal["Platform Abstraction Layer"]
+    style ggml_pal fill:#c33,color:#000,stroke:#000
+end
+
+block:ggml_backendsubsystem
+    ggml_backendsubsystem["GGML backend subsystem"]
+    style ggml_backendsubsystem fill:#3c3,color:#000,stroke:#000
 end
 
+block:group1:2
+    columns 2
+    block:ggml_tensor
+        ggml_tensor["GGML tensor"]
+        style ggml_tensor fill:#3c3,color:#000,stroke:#000
+    end
+
+    block:ggml_cgraph
+        ggml_cgraph["GGML cgraph"]
+        style ggml_cgraph  fill:#3c3,color:#000,stroke:#000
+    end
+end
 
 block:OS
     Windows