add -mattr=+neon for all arm cpu target (#1612)

apps/benchmark/README.md

@@ -63,8 +63,11 @@ python3 -m tvm.exec.rpc_tracker
   python3 arm_cpu_imagenet_bench.py --device mate10pro --rpc-key mate10pro  
   ```
 
-  If your device has a same SoC of the above device, you can reuse these parameters
-  (e.g. use `llvm -device=arm_cpu -mode=rk3399 -target=aarch64-linux-gnu` as target).
-  Otherwise, you need to tune for your own device, please follow this 
-  [tutorial](https://docs.tvm.ai/tutorials/autotvm/tune_nnvm_arm.html).
+  If your device has a same or similar SoC of the above devices, you can reuse these parameters.
+  For example, if your SoC is similar to rasp3b, use
+  ```bash
+  python3 arm_cpu_imagenet_bench.py --device rasp3b --rpc-key your_custom_key
+  ```
+  For other devices, to get the best performance, it is recommended that you tune your network by yourself. 
+  Please follow this [tutorial](https://docs.tvm.ai/tutorials/autotvm/tune_nnvm_arm.html).
 

python/tvm/target.py

@@ -427,14 +427,14 @@ def arm_cpu(model='unknown', options=None):
     from . import autotvm
 
     trans_table = {
-        "pixel2":    ["-model=snapdragon835", "-target=arm64-linux-android"],
-        "mate10":    ["-model=kirin970", "-target=arm64-linux-android"],
-        "mate10pro": ["-model=kirin970", "-target=arm64-linux-android"],
-        "p20":       ["-model=kirin970", "-target=arm64-linux-android"],
-        "p20pro":    ["-model=kirin970", "-target=arm64-linux-android"],
-        "rasp3b":    ["-model=bcm2837", "-target=armv7l-linux-gnueabihf"],
-        "rk3399":    ["-model=rk3399", "-target=aarch64-linux-gnu"],
-        "pynq":      ["-model=pynq", "-target=armv7a-linux-eabi"],
+        "pixel2":    ["-model=snapdragon835", "-target=arm64-linux-android -mattr=+neon"],
+        "mate10":    ["-model=kirin970", "-target=arm64-linux-android -mattr=+neon"],
+        "mate10pro": ["-model=kirin970", "-target=arm64-linux-android -mattr=+neon"],
+        "p20":       ["-model=kirin970", "-target=arm64-linux-android -mattr=+neon"],
+        "p20pro":    ["-model=kirin970", "-target=arm64-linux-android -mattr=+neon"],
+        "rasp3b":    ["-model=bcm2837", "-target=armv7l-linux-gnueabihf -mattr=+neon"],
+        "rk3399":    ["-model=rk3399", "-target=aarch64-linux-gnu -mattr=+neon"],
+        "pynq":      ["-model=pynq", "-target=armv7a-linux-eabi -mattr=+neon"],
     }
     pre_defined_opt = trans_table.get(model, ["-model=%s" % model])
 

tutorials/nnvm/deploy_model_on_rasp.py

@@ -154,7 +154,7 @@ if local_demo:
 else:
     target = tvm.target.arm_cpu('rasp3b')
     # The above line is a simple form of
-    # target = tvm.target.create('llvm -devcie=arm_cpu -target=armv7l-linux-gnueabihf')
+    # target = tvm.target.create('llvm -devcie=arm_cpu -model=bcm2837 -target=armv7l-linux-gnueabihf -mattr=+neon')
 
 with nnvm.compiler.build_config(opt_level=2, add_pass=['AlterOpLayout']):
     graph, lib, params = nnvm.compiler.build(