Qualcomm AI Engine Direct - LE support

Summary:
- enable linux embedded support for toolchain:
  aarch64-oe-linux-gcc9.3, aarch64-oe-linux-gcc11.2 (SXR1230P, QCS9100)
- update document a bit

Author: haowhsu-quic

.ci/scripts/build-qnn-sdk.sh

@@ -18,7 +18,7 @@ build_qnn_backend() {
   export EXECUTORCH_ROOT="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")/../.." && pwd)"
 
   parallelism=$(( $(nproc) - 1 ))
-  bash backends/qualcomm/scripts/build.sh --skip_aarch64 --job_number ${parallelism} --release
+  bash backends/qualcomm/scripts/build.sh --skip_la --job_number ${parallelism} --release
 }
 
 set_up_aot() {

backends/qualcomm/README.md

@@ -27,6 +27,7 @@ Please check `generate_qnn_executorch_compiler_spec()` in
 - SXR1230P
 - SXR2230P
 - SXR2330P
+- QCS9100
 
 ### Adding more supported Chipset
 Currently, users cannot add additional chipset models because the chipset ID is not accessible to community users. If you have specific chipset models you wish to add, please contact one of the authors in the `Code Reviews` section at the bottom of this page.

backends/qualcomm/debugger/README.md

@@ -54,6 +54,7 @@ adb = SimpleADB(
     device_id=args.device,
     host_id=args.host,
     soc_model=args.model,
+    target=args.target,
 )
 binaries_trace = generate_optrace(
     args, adb, f"{args.artifact}/{pte_filename}.pte", example_input

backends/qualcomm/scripts/build.sh

@@ -17,8 +17,10 @@ fi
 usage() {
   echo "Usage: Build the aarch64 version of executor runner or the python interface of Qnn Manager"
   echo "First, you need to set the environment variable for QNN_SDK_ROOT"
-  echo ", and if you want to build the aarch64 version of executor runner"
+  echo ", and if you want to build the android version of executor runner"
   echo ", you need to export ANDROID_NDK_ROOT=/path/to/android_ndkXX"
+  echo "(or export TOOLCHAIN_ROOT_HOST=/path/to/sysroots/xx_host, "
+  echo "TOOLCHAIN_ROOT_TARGET=/path/to/sysroots/xx_target for linux embedded with --le)"
   echo "e.g.: executorch$ ./backends/qualcomm/scripts/build.sh --skip_x86_64"
   exit 1
 }
@@ -28,8 +30,10 @@ usage() {
 
 BUILD_X86_64="true"
 CMAKE_X86_64="build-x86"
-BUILD_AARCH64="true"
-CMAKE_AARCH64="build-android"
+BUILD_ANDROID="true"
+CMAKE_ANDROID="build-android"
+BUILD_OE_LINUX="false"
+CMAKE_OE_LINUX="build-oe-linux"
 CLEAN="true"
 BUILD_TYPE="RelWithDebInfo"
 BUILD_JOB_NUMBER="16"
@@ -42,7 +46,7 @@ if [ -z BUCK2 ]; then
   BUCK2="buck2"
 fi
 
-long_options=skip_x86_64,skip_aarch64,no_clean,release,job_number:
+long_options=skip_x86_64,skip_la,skip_le,le,no_clean,release,job_number:
 
 parsed_args=$(getopt -a --options '' --longoptions $long_options --name "$0" -- "$@")
 eval set -- "$parsed_args"
@@ -51,7 +55,9 @@ eval set -- "$parsed_args"
 while true ; do
     case "$1" in
         --skip_x86_64) BUILD_X86_64="false"; shift;;
-        --skip_aarch64) BUILD_AARCH64="false"; shift;;
+        --skip_la) BUILD_ANDROID="false"; shift;;
+        --skip_le) BUILD_OE_LINUX="false"; shift;;
+        --le) BUILD_ANDROID="false"; BUILD_OE_LINUX="true"; shift;;
         --no_clean) CLEAN="false"; shift;;
         --release) BUILD_TYPE="Release"; shift;;
         --job_number) BUILD_JOB_NUMBER="$2"; shift 2;;
@@ -61,13 +67,13 @@ done
 
 PRJ_ROOT="$( cd "$(dirname "$0")/../../.." ; pwd -P)"
 
-if [ "$BUILD_AARCH64" = true ]; then
+if [ "$BUILD_ANDROID" = true ]; then
     if [[ -z ${ANDROID_NDK_ROOT} ]]; then
         echo "Please export ANDROID_NDK_ROOT=/path/to/android_ndkXX"
         exit -1
     fi
 
-    BUILD_ROOT=$PRJ_ROOT/$CMAKE_AARCH64
+    BUILD_ROOT=$PRJ_ROOT/$CMAKE_ANDROID
     if [ "$CLEAN" = true ]; then
         rm -rf $BUILD_ROOT && mkdir $BUILD_ROOT
     else
@@ -134,6 +140,72 @@ if [ "$BUILD_AARCH64" = true ]; then
     cmake --build $LLAMA_EXAMPLE_ROOT -j$BUILD_JOB_NUMBER
 fi
 
+if [ "$BUILD_OE_LINUX" = true ]; then
+    if [[ -z ${TOOLCHAIN_ROOT_HOST} ]]; then
+        echo "Please export e.g. TOOLCHAIN_ROOT_HOST=/path/to/sysroots/x86_64-qtisdk-linux"
+        exit -1
+    fi
+    if [[ -z ${TOOLCHAIN_ROOT_TARGET} ]]; then
+        echo "Please export e.g. TOOLCHAIN_ROOT_TARGET=/path/to/sysroots/armv8a-oe-linux"
+        exit -1
+    fi
+
+    BUILD_ROOT=$PRJ_ROOT/$CMAKE_OE_LINUX
+    if [ "$CLEAN" = true ]; then
+        rm -rf $BUILD_ROOT && mkdir $BUILD_ROOT
+    else
+        # Force rebuild flatccrt for the correct platform
+        cd $BUILD_ROOT/third-party/flatcc && make clean
+    fi
+
+    TOOLCHAN_PREFIX=$TOOLCHAIN_ROOT_HOST/usr/bin/aarch64-oe-linux/aarch64-oe-linux-
+    cd $BUILD_ROOT
+    cmake .. \
+        -DCMAKE_INSTALL_PREFIX=$BUILD_ROOT \
+        -DCMAKE_BUILD_TYPE=$BUILD_TYPE \
+        -DCMAKE_C_COMPILER=${TOOLCHAN_PREFIX}gcc \
+        -DCMAKE_CXX_COMPILER=${TOOLCHAN_PREFIX}g++ \
+        -DCMAKE_SYSROOT=$TOOLCHAIN_ROOT_TARGET \
+        -DCMAKE_SYSTEM_NAME=Linux \
+        -DCMAKE_SYSTEM_PROCESSOR=aarch64 \
+        -DCMAKE_FIND_ROOT_PATH_MODE_PROGRAM=NEVER \
+        -DEXECUTORCH_BUILD_CPUINFO=OFF \
+        -DEXECUTORCH_BUILD_QNN=ON \
+        -DEXECUTORCH_BUILD_DEVTOOLS=ON \
+        -DEXECUTORCH_BUILD_EXTENSION_LLM=ON \
+        -DEXECUTORCH_BUILD_EXTENSION_LLM_RUNNER=ON \
+        -DEXECUTORCH_BUILD_EXTENSION_MODULE=ON \
+        -DEXECUTORCH_BUILD_EXTENSION_DATA_LOADER=ON \
+        -DEXECUTORCH_BUILD_EXTENSION_FLAT_TENSOR=ON \
+        -DEXECUTORCH_BUILD_EXTENSION_TENSOR=ON \
+        -DEXECUTORCH_ENABLE_EVENT_TRACER=ON \
+        -DQNN_SDK_ROOT=$QNN_SDK_ROOT \
+        -DEXECUTORCH_BUILD_KERNELS_QUANTIZED=ON \
+        -DPYTHON_EXECUTABLE=$PYTHON_EXECUTABLE \
+        -B$BUILD_ROOT
+
+    cmake --build $BUILD_ROOT -j$BUILD_JOB_NUMBER --target install
+
+    EXAMPLE_ROOT=examples/qualcomm
+    CMAKE_PREFIX_PATH="${BUILD_ROOT};${BUILD_ROOT}/third-party/gflags;"
+
+    cmake $PRJ_ROOT/$EXAMPLE_ROOT \
+        -DCMAKE_BUILD_TYPE=$BUILD_TYPE \
+        -DCMAKE_PREFIX_PATH=$CMAKE_PREFIX_PATH \
+        -DCMAKE_C_COMPILER=${TOOLCHAN_PREFIX}gcc \
+        -DCMAKE_CXX_COMPILER=${TOOLCHAN_PREFIX}g++ \
+        -DCMAKE_SYSROOT=$TOOLCHAIN_ROOT_TARGET \
+        -DCMAKE_SYSTEM_NAME=Linux \
+        -DCMAKE_SYSTEM_PROCESSOR=aarch64 \
+        -DEXECUTORCH_BUILD_KERNELS_QUANTIZED=ON \
+        -DCMAKE_FIND_ROOT_PATH_MODE_PROGRAM=NEVER \
+        -DCMAKE_FIND_ROOT_PATH_MODE_PACKAGE=BOTH \
+        -DPYTHON_EXECUTABLE=$PYTHON_EXECUTABLE \
+        -B$EXAMPLE_ROOT
+
+    cmake --build $EXAMPLE_ROOT -j$BUILD_JOB_NUMBER
+fi
+
 if [ "$BUILD_X86_64" = true ]; then
     BUILD_ROOT=$PRJ_ROOT/$CMAKE_X86_64
     if [ "$CLEAN" = true ]; then

backends/qualcomm/serialization/qc_compiler_spec.fbs

@@ -43,6 +43,7 @@ enum QcomChipset: int {
   SXR1230P = 45,
   SXR2230P = 53,
   SXR2330P = 75,
+  QCS9100 = 77,
 }
 
 /// Indicate the information of the specified SoC.

backends/qualcomm/serialization/qc_schema.py

@@ -49,6 +49,7 @@ class QcomChipset(IntEnum):
     SXR1230P = 45  # v73
     SXR2230P = 53  # v69
     SXR2330P = 75  # v79
+    QCS9100 = 77  # v73
 
 
 @dataclass
@@ -69,6 +70,7 @@ class SocInfo:
     QcomChipset.SXR1230P: SocInfo(QcomChipset.SXR1230P, HtpInfo(HtpArch.V73, 2)),
     QcomChipset.SXR2230P: SocInfo(QcomChipset.SXR2230P, HtpInfo(HtpArch.V69, 8)),
     QcomChipset.SXR2330P: SocInfo(QcomChipset.SXR2330P, HtpInfo(HtpArch.V79, 8)),
+    QcomChipset.QCS9100: SocInfo(QcomChipset.QCS9100, HtpInfo(HtpArch.V73, 8)),
 }