Fix tutorial for Qualcomm AI Engine Direct Backend (#2956) (#3026)

Summary:
We have refactors recently and need to update the tutorial and cmake.

See #2955 for isseues.

Pull Request resolved: #2956

Reviewed By: mcr229, cccclai

Differential Revision: D55947725

Pulled By: kirklandsign

fbshipit-source-id: f23af28b9a8fe071223d8ffa922a6cd4e49efe61
(cherry picked from commit c7fd394)

Author: kirklandsign

backends/qualcomm/CMakeLists.txt

@@ -253,7 +253,7 @@ target_link_libraries(qnn_executorch_backend
     qnn_executorch_header
     qnn_schema
     qnn_manager
-    executorch
+    executorch_no_prim_ops
     qcir_utils
 )
 target_link_libraries(utils

docs/source/build-run-qualcomm-ai-engine-direct-backend.md

@@ -115,6 +115,10 @@ Python APIs on x64 are required to compile models to Qualcomm AI Engine Direct b
 
 ```bash
 cd $EXECUTORCH_ROOT
+# Workaround for fbs files in exir/_serialize
+cp schema/program.fbs exir/_serialize/program.fbs
+cp schema/scalar_type.fbs exir/_serialize/scalar_type.fbs
+
 mkdir build_x86_64
 cd build_x86_64
 cmake .. -DEXECUTORCH_BUILD_QNN=ON -DQNN_SDK_ROOT=${QNN_SDK_ROOT}
@@ -138,8 +142,8 @@ mkdir build_android
 cd build_android
 # build executorch & qnn_executorch_backend
 cmake .. \
-    -DBUCK2=buck2 \
     -DCMAKE_INSTALL_PREFIX=$PWD \
+    -DEXECUTORCH_BUILD_SDK=ON \
     -DEXECUTORCH_BUILD_QNN=ON \
     -DQNN_SDK_ROOT=$QNN_SDK_ROOT \
     -DCMAKE_TOOLCHAIN_FILE=$ANDROID_NDK/build/cmake/android.toolchain.cmake \
@@ -220,6 +224,7 @@ So, we can run `qnn_executor_runner` like
 ```bash
 adb push ./deeplab_v3/dlv3_qnn.pte ${DEVICE_DIR}
 adb push ${EXECUTORCH_ROOT}/build_android/examples/qualcomm/qnn_executor_runner ${DEVICE_DIR}
+adb push ${EXECUTORCH_ROOT}/build_android/lib/libqnn_executorch_backend.so ${DEVICE_DIR}
 adb shell "cd ${DEVICE_DIR} \
            && export LD_LIBRARY_PATH=${DEVICE_DIR} \
            && export ADSP_LIBRARY_PATH=${DEVICE_DIR} \

examples/qualcomm/executor_runner/qnn_executor_runner.cpp

@@ -202,8 +202,10 @@ int main(int argc, char** argv) {
   // be used by a single thread at at time, but it can be reused.
   //
   torch::executor::ETDumpGen etdump_gen = torch::executor::ETDumpGen();
+  // TODO: So far we have issues with etdump_gen during load_method. Enable it
+  // after the issues are fixed.
   Result<Method> method =
-      program->load_method(method_name, &memory_manager, &etdump_gen);
+      program->load_method(method_name, &memory_manager, nullptr);
   ET_CHECK_MSG(
       method.ok(),
       "Loading of method %s failed with status 0x%" PRIx32,