rem cncl in ut & build sh (#52811)

* rem cncl in new test

* rem cncl in build sh

* rem cncl in old test

paddle/scripts/paddle_build.sh

@@ -232,7 +232,6 @@ function cmake_base() {
         -DWITH_PSLIB=${pslib_flag}
         -DWITH_GLOO=${gloo_flag}
         -DWITH_LITE=${WITH_LITE:-OFF}
-        -DWITH_CNCL=${WITH_CNCL:-OFF}
         -DWITH_XPU=${WITH_XPU:-OFF}
         -DWITH_IPU=${WITH_IPU:-OFF}
         -DLITE_GIT_TAG=release/v2.10
@@ -288,7 +287,6 @@ EOF
         -DLITE_GIT_TAG=release/v2.10 \
         -DWITH_XPU=${WITH_XPU:-OFF} \
         -DWITH_IPU=${WITH_IPU:-OFF} \
-        -DWITH_CNCL=${WITH_CNCL:-OFF} \
         -DXPU_SDK_ROOT=${XPU_SDK_ROOT:-""} \
         -DWITH_LITE=${WITH_LITE:-OFF} \
         -DWITH_XPU_BKCL=${WITH_XPU_BKCL:-OFF} \
@@ -2188,7 +2186,7 @@ EOF
             grep -F  -f all_ut_run_by_protobuf3 ut_gpups > ut_run_by_protobuf3_in_gpups
             #get the difference set of ut_gpups and ut_run_by_protobuf3_in_gpups
             grep -F -x -v -f ut_run_by_protobuf3_in_gpups ut_gpups > ut_run_in_gpups
-            
+
             ctest -R ${ut_run_in_gpups} --timeout 120
             pip install protobuf==3.20.2
             ctest -R ${ut_run_by_protobuf3_in_gpups} --timeout 120
@@ -2908,13 +2906,13 @@ EOF
     echo "if you use setup.py to compile,please export envs as following in /paddle ..."
     cat << EOF
     ========================================
-    export CMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE:-Release} WITH_GPU=${WITH_GPU:-OFF} WITH_CUDNN_DSO=${WITH_CUDNN_DSO:-OFF} WITH_TENSORRT=${WITH_TENSORRT:-ON} WITH_ROCM=${WITH_ROCM:-OFF} WITH_CINN=${WITH_CINN:-OFF} WITH_DISTRIBUTE=${distibuted_flag} WITH_MKL=${WITH_MKL:-ON} WITH_AVX=${WITH_AVX:-OFF} CUDA_ARCH_NAME=${CUDA_ARCH_NAME:-All} NEW_RELEASE_PYPI=${NEW_RELEASE_PYPI:-OFF} NEW_RELEASE_ALL=${NEW_RELEASE_ALL:-OFF} NEW_RELEASE_JIT=${NEW_RELEASE_JIT:-OFF} WITH_PYTHON=${WITH_PYTHON:-ON} CUDNN_ROOT=/usr/ WITH_TESTING=${WITH_TESTING:-ON} WITH_COVERAGE=${WITH_COVERAGE:-OFF} WITH_INCREMENTAL_COVERAGE=${WITH_INCREMENTAL_COVERAGE:-OFF} CMAKE_MODULE_PATH=/opt/rocm/hip/cmake CMAKE_EXPORT_COMPILE_COMMANDS=ON WITH_CONTRIB=${WITH_CONTRIB:-ON} WITH_INFERENCE_API_TEST=${WITH_INFERENCE_API_TEST:-ON} INFERENCE_DEMO_INSTALL_DIR=${INFERENCE_DEMO_INSTALL_DIR} PY_VERSION=${PY_VERSION:-3.7} CMAKE_INSTALL_PREFIX=${INSTALL_PREFIX:-/paddle/build} WITH_PSCORE=${pscore_flag} WITH_PSLIB=${pslib_flag} WITH_GLOO=${gloo_flag} LITE_GIT_TAG=release/v2.10 WITH_XPU=${WITH_XPU:-OFF} WITH_IPU=${WITH_IPU:-OFF} WITH_CNCL=${WITH_CNCL:-OFF} XPU_SDK_ROOT=${XPU_SDK_ROOT:-""} WITH_LITE=${WITH_LITE:-OFF} WITH_XPU_BKCL=${WITH_XPU_BKCL:-OFF} WITH_ARM=${WITH_ARM:-OFF} WITH_STRIP=${WITH_STRIP:-ON} ON_INFER=${ON_INFER:-OFF} WITH_HETERPS=${WITH_HETERPS:-OFF} WITH_GPU_GRAPH=${WITH_GPU_GRAPH:-OFF} WITH_FLUID_ONLY=${WITH_FLUID_ONLY:-OFF} CUDA_ARCH_BIN=${CUDA_ARCH_BIN} WITH_RECORD_BUILDTIME=${WITH_RECORD_BUILDTIME:-OFF} WITH_UNITY_BUILD=${WITH_UNITY_BUILD:-OFF} WITH_ONNXRUNTIME=${WITH_ONNXRUNTIME:-OFF} WITH_CUDNN_FRONTEND=${WITH_CUDNN_FRONTEND:-OFF}
+    export CMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE:-Release} WITH_GPU=${WITH_GPU:-OFF} WITH_CUDNN_DSO=${WITH_CUDNN_DSO:-OFF} WITH_TENSORRT=${WITH_TENSORRT:-ON} WITH_ROCM=${WITH_ROCM:-OFF} WITH_CINN=${WITH_CINN:-OFF} WITH_DISTRIBUTE=${distibuted_flag} WITH_MKL=${WITH_MKL:-ON} WITH_AVX=${WITH_AVX:-OFF} CUDA_ARCH_NAME=${CUDA_ARCH_NAME:-All} NEW_RELEASE_PYPI=${NEW_RELEASE_PYPI:-OFF} NEW_RELEASE_ALL=${NEW_RELEASE_ALL:-OFF} NEW_RELEASE_JIT=${NEW_RELEASE_JIT:-OFF} WITH_PYTHON=${WITH_PYTHON:-ON} CUDNN_ROOT=/usr/ WITH_TESTING=${WITH_TESTING:-ON} WITH_COVERAGE=${WITH_COVERAGE:-OFF} WITH_INCREMENTAL_COVERAGE=${WITH_INCREMENTAL_COVERAGE:-OFF} CMAKE_MODULE_PATH=/opt/rocm/hip/cmake CMAKE_EXPORT_COMPILE_COMMANDS=ON WITH_CONTRIB=${WITH_CONTRIB:-ON} WITH_INFERENCE_API_TEST=${WITH_INFERENCE_API_TEST:-ON} INFERENCE_DEMO_INSTALL_DIR=${INFERENCE_DEMO_INSTALL_DIR} PY_VERSION=${PY_VERSION:-3.7} CMAKE_INSTALL_PREFIX=${INSTALL_PREFIX:-/paddle/build} WITH_PSCORE=${pscore_flag} WITH_PSLIB=${pslib_flag} WITH_GLOO=${gloo_flag} LITE_GIT_TAG=release/v2.10 WITH_XPU=${WITH_XPU:-OFF} WITH_IPU=${WITH_IPU:-OFF} XPU_SDK_ROOT=${XPU_SDK_ROOT:-""} WITH_LITE=${WITH_LITE:-OFF} WITH_XPU_BKCL=${WITH_XPU_BKCL:-OFF} WITH_ARM=${WITH_ARM:-OFF} WITH_STRIP=${WITH_STRIP:-ON} ON_INFER=${ON_INFER:-OFF} WITH_HETERPS=${WITH_HETERPS:-OFF} WITH_GPU_GRAPH=${WITH_GPU_GRAPH:-OFF} WITH_FLUID_ONLY=${WITH_FLUID_ONLY:-OFF} CUDA_ARCH_BIN=${CUDA_ARCH_BIN} WITH_RECORD_BUILDTIME=${WITH_RECORD_BUILDTIME:-OFF} WITH_UNITY_BUILD=${WITH_UNITY_BUILD:-OFF} WITH_ONNXRUNTIME=${WITH_ONNXRUNTIME:-OFF} WITH_CUDNN_FRONTEND=${WITH_CUDNN_FRONTEND:-OFF}
     ========================================
 EOF
     echo "if you use cmake to compile,please Configuring cmake in /paddle/build ..."
     cat <<EOF
     ========================================
-    cmake .. -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE:-Release} -DWITH_GPU=${WITH_GPU:-OFF} -DWITH_CUDNN_DSO=${WITH_CUDNN_DSO:-OFF} -DWITH_TENSORRT=${WITH_TENSORRT:-ON} -DWITH_ROCM=${WITH_ROCM:-OFF} -DWITH_CINN=${WITH_CINN:-OFF} -DWITH_DISTRIBUTE=${distibuted_flag} -DWITH_MKL=${WITH_MKL:-ON} -DWITH_AVX=${WITH_AVX:-OFF} -DCUDA_ARCH_NAME=${CUDA_ARCH_NAME:-All} -DNEW_RELEASE_PYPI=${NEW_RELEASE_PYPI:-OFF} -DNEW_RELEASE_ALL=${NEW_RELEASE_ALL:-OFF} -DNEW_RELEASE_JIT=${NEW_RELEASE_JIT:-OFF} -DWITH_PYTHON=${WITH_PYTHON:-ON} -DCUDNN_ROOT=/usr/ -DWITH_TESTING=${WITH_TESTING:-ON} -DWITH_COVERAGE=${WITH_COVERAGE:-OFF} -DWITH_INCREMENTAL_COVERAGE=${WITH_INCREMENTAL_COVERAGE:-OFF} -DCMAKE_MODULE_PATH=/opt/rocm/hip/cmake -DCMAKE_EXPORT_COMPILE_COMMANDS=ON -DWITH_CONTRIB=${WITH_CONTRIB:-ON} -DWITH_INFERENCE_API_TEST=${WITH_INFERENCE_API_TEST:-ON} -DINFERENCE_DEMO_INSTALL_DIR=${INFERENCE_DEMO_INSTALL_DIR} -DPY_VERSION=${PY_VERSION:-3.7} -DCMAKE_INSTALL_PREFIX=${INSTALL_PREFIX:-/paddle/build} -DWITH_PSCORE=${pscore_flag} -DWITH_PSLIB=${pslib_flag} -DWITH_GLOO=${gloo_flag} -DLITE_GIT_TAG=release/v2.10 -DWITH_XPU=${WITH_XPU:-OFF} -DWITH_IPU=${WITH_IPU:-OFF} -DWITH_CNCL=${WITH_CNCL:-OFF} -DXPU_SDK_ROOT=${XPU_SDK_ROOT:-""} -DWITH_LITE=${WITH_LITE:-OFF} -DWITH_XPU_BKCL=${WITH_XPU_BKCL:-OFF} -DWITH_ARM=${WITH_ARM:-OFF} -DWITH_STRIP=${WITH_STRIP:-ON} -DON_INFER=${ON_INFER:-OFF} -DWITH_HETERPS=${WITH_HETERPS:-OFF} -DWITH_GPU_GRAPH=${WITH_GPU_GRAPH:-OFF} -DWITH_FLUID_ONLY=${WITH_FLUID_ONLY:-OFF} -DCUDA_ARCH_BIN=${CUDA_ARCH_BIN} -DWITH_RECORD_BUILDTIME=${WITH_RECORD_BUILDTIME:-OFF} -DWITH_UNITY_BUILD=${WITH_UNITY_BUILD:-OFF} -DWITH_ONNXRUNTIME=${WITH_ONNXRUNTIME:-OFF} -DWITH_CUDNN_FRONTEND=${WITH_CUDNN_FRONTEND:-OFF}
+    cmake .. -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE:-Release} -DWITH_GPU=${WITH_GPU:-OFF} -DWITH_CUDNN_DSO=${WITH_CUDNN_DSO:-OFF} -DWITH_TENSORRT=${WITH_TENSORRT:-ON} -DWITH_ROCM=${WITH_ROCM:-OFF} -DWITH_CINN=${WITH_CINN:-OFF} -DWITH_DISTRIBUTE=${distibuted_flag} -DWITH_MKL=${WITH_MKL:-ON} -DWITH_AVX=${WITH_AVX:-OFF} -DCUDA_ARCH_NAME=${CUDA_ARCH_NAME:-All} -DNEW_RELEASE_PYPI=${NEW_RELEASE_PYPI:-OFF} -DNEW_RELEASE_ALL=${NEW_RELEASE_ALL:-OFF} -DNEW_RELEASE_JIT=${NEW_RELEASE_JIT:-OFF} -DWITH_PYTHON=${WITH_PYTHON:-ON} -DCUDNN_ROOT=/usr/ -DWITH_TESTING=${WITH_TESTING:-ON} -DWITH_COVERAGE=${WITH_COVERAGE:-OFF} -DWITH_INCREMENTAL_COVERAGE=${WITH_INCREMENTAL_COVERAGE:-OFF} -DCMAKE_MODULE_PATH=/opt/rocm/hip/cmake -DCMAKE_EXPORT_COMPILE_COMMANDS=ON -DWITH_CONTRIB=${WITH_CONTRIB:-ON} -DWITH_INFERENCE_API_TEST=${WITH_INFERENCE_API_TEST:-ON} -DINFERENCE_DEMO_INSTALL_DIR=${INFERENCE_DEMO_INSTALL_DIR} -DPY_VERSION=${PY_VERSION:-3.7} -DCMAKE_INSTALL_PREFIX=${INSTALL_PREFIX:-/paddle/build} -DWITH_PSCORE=${pscore_flag} -DWITH_PSLIB=${pslib_flag} -DWITH_GLOO=${gloo_flag} -DLITE_GIT_TAG=release/v2.10 -DWITH_XPU=${WITH_XPU:-OFF} -DWITH_IPU=${WITH_IPU:-OFF} -DXPU_SDK_ROOT=${XPU_SDK_ROOT:-""} -DWITH_LITE=${WITH_LITE:-OFF} -DWITH_XPU_BKCL=${WITH_XPU_BKCL:-OFF} -DWITH_ARM=${WITH_ARM:-OFF} -DWITH_STRIP=${WITH_STRIP:-ON} -DON_INFER=${ON_INFER:-OFF} -DWITH_HETERPS=${WITH_HETERPS:-OFF} -DWITH_GPU_GRAPH=${WITH_GPU_GRAPH:-OFF} -DWITH_FLUID_ONLY=${WITH_FLUID_ONLY:-OFF} -DCUDA_ARCH_BIN=${CUDA_ARCH_BIN} -DWITH_RECORD_BUILDTIME=${WITH_RECORD_BUILDTIME:-OFF} -DWITH_UNITY_BUILD=${WITH_UNITY_BUILD:-OFF} -DWITH_ONNXRUNTIME=${WITH_ONNXRUNTIME:-OFF} -DWITH_CUDNN_FRONTEND=${WITH_CUDNN_FRONTEND:-OFF}
     ========================================
 EOF
     # reset ccache zero stats for collect PR's actual hit rate
@@ -3391,13 +3389,13 @@ function run_setup(){
     echo "if you use setup.py to compile,please export envs as following in /paddle ..."
     cat << EOF
     ========================================
-    export CMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE:-Release} WITH_GPU=${WITH_GPU:-OFF} WITH_CUDNN_DSO=${WITH_CUDNN_DSO:-OFF} WITH_TENSORRT=${WITH_TENSORRT:-ON} WITH_ROCM=${WITH_ROCM:-OFF} WITH_CINN=${WITH_CINN:-OFF} WITH_DISTRIBUTE=${distibuted_flag} WITH_MKL=${WITH_MKL:-ON} WITH_AVX=${WITH_AVX:-OFF} CUDA_ARCH_NAME=${CUDA_ARCH_NAME:-All} NEW_RELEASE_PYPI=${NEW_RELEASE_PYPI:-OFF} NEW_RELEASE_ALL=${NEW_RELEASE_ALL:-OFF} NEW_RELEASE_JIT=${NEW_RELEASE_JIT:-OFF} WITH_PYTHON=${WITH_PYTHON:-ON} CUDNN_ROOT=/usr/ WITH_TESTING=${WITH_TESTING:-ON} WITH_COVERAGE=${WITH_COVERAGE:-OFF} WITH_INCREMENTAL_COVERAGE=${WITH_INCREMENTAL_COVERAGE:-OFF} CMAKE_MODULE_PATH=/opt/rocm/hip/cmake CMAKE_EXPORT_COMPILE_COMMANDS=ON WITH_CONTRIB=${WITH_CONTRIB:-ON} WITH_INFERENCE_API_TEST=${WITH_INFERENCE_API_TEST:-ON} INFERENCE_DEMO_INSTALL_DIR=${INFERENCE_DEMO_INSTALL_DIR} PY_VERSION=${PY_VERSION:-3.7} CMAKE_INSTALL_PREFIX=${INSTALL_PREFIX:-/paddle/build} WITH_PSCORE=${pscore_flag} WITH_PSLIB=${pslib_flag} WITH_GLOO=${gloo_flag} LITE_GIT_TAG=release/v2.10 WITH_XPU=${WITH_XPU:-OFF} WITH_IPU=${WITH_IPU:-OFF} WITH_CNCL=${WITH_CNCL:-OFF} XPU_SDK_ROOT=${XPU_SDK_ROOT:-""} WITH_LITE=${WITH_LITE:-OFF} WITH_XPU_BKCL=${WITH_XPU_BKCL:-OFF} WITH_ARM=${WITH_ARM:-OFF} WITH_STRIP=${WITH_STRIP:-ON} ON_INFER=${ON_INFER:-OFF} WITH_HETERPS=${WITH_HETERPS:-OFF} WITH_GPU_GRAPH=${WITH_GPU_GRAPH:-OFF} WITH_FLUID_ONLY=${WITH_FLUID_ONLY:-OFF} CUDA_ARCH_BIN=${CUDA_ARCH_BIN} WITH_RECORD_BUILDTIME=${WITH_RECORD_BUILDTIME:-OFF} WITH_UNITY_BUILD=${WITH_UNITY_BUILD:-OFF} WITH_ONNXRUNTIME=${WITH_ONNXRUNTIME:-OFF} WITH_CUDNN_FRONTEND=${WITH_CUDNN_FRONTEND:-OFF}
+    export CMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE:-Release} WITH_GPU=${WITH_GPU:-OFF} WITH_CUDNN_DSO=${WITH_CUDNN_DSO:-OFF} WITH_TENSORRT=${WITH_TENSORRT:-ON} WITH_ROCM=${WITH_ROCM:-OFF} WITH_CINN=${WITH_CINN:-OFF} WITH_DISTRIBUTE=${distibuted_flag} WITH_MKL=${WITH_MKL:-ON} WITH_AVX=${WITH_AVX:-OFF} CUDA_ARCH_NAME=${CUDA_ARCH_NAME:-All} NEW_RELEASE_PYPI=${NEW_RELEASE_PYPI:-OFF} NEW_RELEASE_ALL=${NEW_RELEASE_ALL:-OFF} NEW_RELEASE_JIT=${NEW_RELEASE_JIT:-OFF} WITH_PYTHON=${WITH_PYTHON:-ON} CUDNN_ROOT=/usr/ WITH_TESTING=${WITH_TESTING:-ON} WITH_COVERAGE=${WITH_COVERAGE:-OFF} WITH_INCREMENTAL_COVERAGE=${WITH_INCREMENTAL_COVERAGE:-OFF} CMAKE_MODULE_PATH=/opt/rocm/hip/cmake CMAKE_EXPORT_COMPILE_COMMANDS=ON WITH_CONTRIB=${WITH_CONTRIB:-ON} WITH_INFERENCE_API_TEST=${WITH_INFERENCE_API_TEST:-ON} INFERENCE_DEMO_INSTALL_DIR=${INFERENCE_DEMO_INSTALL_DIR} PY_VERSION=${PY_VERSION:-3.7} CMAKE_INSTALL_PREFIX=${INSTALL_PREFIX:-/paddle/build} WITH_PSCORE=${pscore_flag} WITH_PSLIB=${pslib_flag} WITH_GLOO=${gloo_flag} LITE_GIT_TAG=release/v2.10 WITH_XPU=${WITH_XPU:-OFF} WITH_IPU=${WITH_IPU:-OFF} XPU_SDK_ROOT=${XPU_SDK_ROOT:-""} WITH_LITE=${WITH_LITE:-OFF} WITH_XPU_BKCL=${WITH_XPU_BKCL:-OFF} WITH_ARM=${WITH_ARM:-OFF} WITH_STRIP=${WITH_STRIP:-ON} ON_INFER=${ON_INFER:-OFF} WITH_HETERPS=${WITH_HETERPS:-OFF} WITH_GPU_GRAPH=${WITH_GPU_GRAPH:-OFF} WITH_FLUID_ONLY=${WITH_FLUID_ONLY:-OFF} CUDA_ARCH_BIN=${CUDA_ARCH_BIN} WITH_RECORD_BUILDTIME=${WITH_RECORD_BUILDTIME:-OFF} WITH_UNITY_BUILD=${WITH_UNITY_BUILD:-OFF} WITH_ONNXRUNTIME=${WITH_ONNXRUNTIME:-OFF} WITH_CUDNN_FRONTEND=${WITH_CUDNN_FRONTEND:-OFF}
     ========================================
 EOF
     echo "if you use cmake to compile,please Configuring cmake in /paddle/build ..."
     cat <<EOF
     ========================================
-    cmake .. -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE:-Release} -DWITH_GPU=${WITH_GPU:-OFF} -DWITH_CUDNN_DSO=${WITH_CUDNN_DSO:-OFF} -DWITH_TENSORRT=${WITH_TENSORRT:-ON} -DWITH_ROCM=${WITH_ROCM:-OFF} -DWITH_CINN=${WITH_CINN:-OFF} -DWITH_DISTRIBUTE=${distibuted_flag} -DWITH_MKL=${WITH_MKL:-ON} -DWITH_AVX=${WITH_AVX:-OFF} -DCUDA_ARCH_NAME=${CUDA_ARCH_NAME:-All} -DNEW_RELEASE_PYPI=${NEW_RELEASE_PYPI:-OFF} -DNEW_RELEASE_ALL=${NEW_RELEASE_ALL:-OFF} -DNEW_RELEASE_JIT=${NEW_RELEASE_JIT:-OFF} -DWITH_PYTHON=${WITH_PYTHON:-ON} -DCUDNN_ROOT=/usr/ -DWITH_TESTING=${WITH_TESTING:-ON} -DWITH_COVERAGE=${WITH_COVERAGE:-OFF} -DWITH_INCREMENTAL_COVERAGE=${WITH_INCREMENTAL_COVERAGE:-OFF} -DCMAKE_MODULE_PATH=/opt/rocm/hip/cmake -DCMAKE_EXPORT_COMPILE_COMMANDS=ON -DWITH_CONTRIB=${WITH_CONTRIB:-ON} -DWITH_INFERENCE_API_TEST=${WITH_INFERENCE_API_TEST:-ON} -DINFERENCE_DEMO_INSTALL_DIR=${INFERENCE_DEMO_INSTALL_DIR} -DPY_VERSION=${PY_VERSION:-3.7} -DCMAKE_INSTALL_PREFIX=${INSTALL_PREFIX:-/paddle/build} -DWITH_PSCORE=${pscore_flag} -DWITH_PSLIB=${pslib_flag} -DWITH_GLOO=${gloo_flag} -DLITE_GIT_TAG=release/v2.10 -DWITH_XPU=${WITH_XPU:-OFF} -DWITH_IPU=${WITH_IPU:-OFF} -DWITH_CNCL=${WITH_CNCL:-OFF} -DXPU_SDK_ROOT=${XPU_SDK_ROOT:-""} -DWITH_LITE=${WITH_LITE:-OFF} -DWITH_XPU_BKCL=${WITH_XPU_BKCL:-OFF} -DWITH_ARM=${WITH_ARM:-OFF} -DWITH_STRIP=${WITH_STRIP:-ON} -DON_INFER=${ON_INFER:-OFF} -DWITH_HETERPS=${WITH_HETERPS:-OFF} -DWITH_GPU_GRAPH=${WITH_GPU_GRAPH:-OFF} -DWITH_FLUID_ONLY=${WITH_FLUID_ONLY:-OFF} -DCUDA_ARCH_BIN=${CUDA_ARCH_BIN} -DWITH_RECORD_BUILDTIME=${WITH_RECORD_BUILDTIME:-OFF} -DWITH_UNITY_BUILD=${WITH_UNITY_BUILD:-OFF} -DWITH_ONNXRUNTIME=${WITH_ONNXRUNTIME:-OFF} -DWITH_CUDNN_FRONTEND=${WITH_CUDNN_FRONTEND:-OFF}
+    cmake .. -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE:-Release} -DWITH_GPU=${WITH_GPU:-OFF} -DWITH_CUDNN_DSO=${WITH_CUDNN_DSO:-OFF} -DWITH_TENSORRT=${WITH_TENSORRT:-ON} -DWITH_ROCM=${WITH_ROCM:-OFF} -DWITH_CINN=${WITH_CINN:-OFF} -DWITH_DISTRIBUTE=${distibuted_flag} -DWITH_MKL=${WITH_MKL:-ON} -DWITH_AVX=${WITH_AVX:-OFF} -DCUDA_ARCH_NAME=${CUDA_ARCH_NAME:-All} -DNEW_RELEASE_PYPI=${NEW_RELEASE_PYPI:-OFF} -DNEW_RELEASE_ALL=${NEW_RELEASE_ALL:-OFF} -DNEW_RELEASE_JIT=${NEW_RELEASE_JIT:-OFF} -DWITH_PYTHON=${WITH_PYTHON:-ON} -DCUDNN_ROOT=/usr/ -DWITH_TESTING=${WITH_TESTING:-ON} -DWITH_COVERAGE=${WITH_COVERAGE:-OFF} -DWITH_INCREMENTAL_COVERAGE=${WITH_INCREMENTAL_COVERAGE:-OFF} -DCMAKE_MODULE_PATH=/opt/rocm/hip/cmake -DCMAKE_EXPORT_COMPILE_COMMANDS=ON -DWITH_CONTRIB=${WITH_CONTRIB:-ON} -DWITH_INFERENCE_API_TEST=${WITH_INFERENCE_API_TEST:-ON} -DINFERENCE_DEMO_INSTALL_DIR=${INFERENCE_DEMO_INSTALL_DIR} -DPY_VERSION=${PY_VERSION:-3.7} -DCMAKE_INSTALL_PREFIX=${INSTALL_PREFIX:-/paddle/build} -DWITH_PSCORE=${pscore_flag} -DWITH_PSLIB=${pslib_flag} -DWITH_GLOO=${gloo_flag} -DLITE_GIT_TAG=release/v2.10 -DWITH_XPU=${WITH_XPU:-OFF} -DWITH_IPU=${WITH_IPU:-OFF} -DXPU_SDK_ROOT=${XPU_SDK_ROOT:-""} -DWITH_LITE=${WITH_LITE:-OFF} -DWITH_XPU_BKCL=${WITH_XPU_BKCL:-OFF} -DWITH_ARM=${WITH_ARM:-OFF} -DWITH_STRIP=${WITH_STRIP:-ON} -DON_INFER=${ON_INFER:-OFF} -DWITH_HETERPS=${WITH_HETERPS:-OFF} -DWITH_GPU_GRAPH=${WITH_GPU_GRAPH:-OFF} -DWITH_FLUID_ONLY=${WITH_FLUID_ONLY:-OFF} -DCUDA_ARCH_BIN=${CUDA_ARCH_BIN} -DWITH_RECORD_BUILDTIME=${WITH_RECORD_BUILDTIME:-OFF} -DWITH_UNITY_BUILD=${WITH_UNITY_BUILD:-OFF} -DWITH_ONNXRUNTIME=${WITH_ONNXRUNTIME:-OFF} -DWITH_CUDNN_FRONTEND=${WITH_CUDNN_FRONTEND:-OFF}
     ========================================
 EOF
     export CMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE:-Release}
@@ -3432,7 +3430,6 @@ EOF
     export LITE_GIT_TAG=release/v2.10
     export WITH_XPU=${WITH_XPU:-OFF}
     export WITH_IPU=${WITH_IPU:-OFF}
-    export WITH_CNCL=${WITH_CNCL:-OFF}
     export XPU_SDK_ROOT=${XPU_SDK_ROOT:-""}
     export WITH_LITE=${WITH_LITE:-OFF}
     export WITH_XPU_BKCL=${WITH_XPU_BKCL:-OFF}
@@ -3636,13 +3633,13 @@ function run_setup_mac(){
     echo "if you use setup.py to compile,please export envs as following in /paddle ..."
     cat << EOF
     ========================================
-    export CMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE:-Release} WITH_GPU=${WITH_GPU:-OFF} WITH_CUDNN_DSO=${WITH_CUDNN_DSO:-OFF} WITH_TENSORRT=${WITH_TENSORRT:-ON} WITH_ROCM=${WITH_ROCM:-OFF} WITH_CINN=${WITH_CINN:-OFF} WITH_DISTRIBUTE=${distibuted_flag} WITH_MKL=${WITH_MKL:-ON} WITH_AVX=${WITH_AVX:-OFF} CUDA_ARCH_NAME=${CUDA_ARCH_NAME:-All} NEW_RELEASE_PYPI=${NEW_RELEASE_PYPI:-OFF} NEW_RELEASE_ALL=${NEW_RELEASE_ALL:-OFF} NEW_RELEASE_JIT=${NEW_RELEASE_JIT:-OFF} WITH_PYTHON=${WITH_PYTHON:-ON} CUDNN_ROOT=/usr/ WITH_TESTING=${WITH_TESTING:-ON} WITH_COVERAGE=${WITH_COVERAGE:-OFF} WITH_INCREMENTAL_COVERAGE=${WITH_INCREMENTAL_COVERAGE:-OFF} CMAKE_MODULE_PATH=/opt/rocm/hip/cmake CMAKE_EXPORT_COMPILE_COMMANDS=ON WITH_CONTRIB=${WITH_CONTRIB:-ON} WITH_INFERENCE_API_TEST=${WITH_INFERENCE_API_TEST:-ON} INFERENCE_DEMO_INSTALL_DIR=${INFERENCE_DEMO_INSTALL_DIR} PY_VERSION=${PY_VERSION:-3.7} CMAKE_INSTALL_PREFIX=${INSTALL_PREFIX:-/paddle/build} WITH_PSCORE=${pscore_flag} WITH_PSLIB=${pslib_flag} WITH_GLOO=${gloo_flag} LITE_GIT_TAG=release/v2.10 WITH_XPU=${WITH_XPU:-OFF} WITH_IPU=${WITH_IPU:-OFF} WITH_CNCL=${WITH_CNCL:-OFF} XPU_SDK_ROOT=${XPU_SDK_ROOT:-""} WITH_LITE=${WITH_LITE:-OFF} WITH_XPU_BKCL=${WITH_XPU_BKCL:-OFF} WITH_ARM=${WITH_ARM:-OFF} WITH_STRIP=${WITH_STRIP:-ON} ON_INFER=${ON_INFER:-OFF} WITH_HETERPS=${WITH_HETERPS:-OFF} WITH_GPU_GRAPH=${WITH_GPU_GRAPH:-OFF} WITH_FLUID_ONLY=${WITH_FLUID_ONLY:-OFF} CUDA_ARCH_BIN=${CUDA_ARCH_BIN} WITH_RECORD_BUILDTIME=${WITH_RECORD_BUILDTIME:-OFF} WITH_UNITY_BUILD=${WITH_UNITY_BUILD:-OFF} WITH_ONNXRUNTIME=${WITH_ONNXRUNTIME:-OFF} WITH_CUDNN_FRONTEND=${WITH_CUDNN_FRONTEND:-OFF}
+    export CMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE:-Release} WITH_GPU=${WITH_GPU:-OFF} WITH_CUDNN_DSO=${WITH_CUDNN_DSO:-OFF} WITH_TENSORRT=${WITH_TENSORRT:-ON} WITH_ROCM=${WITH_ROCM:-OFF} WITH_CINN=${WITH_CINN:-OFF} WITH_DISTRIBUTE=${distibuted_flag} WITH_MKL=${WITH_MKL:-ON} WITH_AVX=${WITH_AVX:-OFF} CUDA_ARCH_NAME=${CUDA_ARCH_NAME:-All} NEW_RELEASE_PYPI=${NEW_RELEASE_PYPI:-OFF} NEW_RELEASE_ALL=${NEW_RELEASE_ALL:-OFF} NEW_RELEASE_JIT=${NEW_RELEASE_JIT:-OFF} WITH_PYTHON=${WITH_PYTHON:-ON} CUDNN_ROOT=/usr/ WITH_TESTING=${WITH_TESTING:-ON} WITH_COVERAGE=${WITH_COVERAGE:-OFF} WITH_INCREMENTAL_COVERAGE=${WITH_INCREMENTAL_COVERAGE:-OFF} CMAKE_MODULE_PATH=/opt/rocm/hip/cmake CMAKE_EXPORT_COMPILE_COMMANDS=ON WITH_CONTRIB=${WITH_CONTRIB:-ON} WITH_INFERENCE_API_TEST=${WITH_INFERENCE_API_TEST:-ON} INFERENCE_DEMO_INSTALL_DIR=${INFERENCE_DEMO_INSTALL_DIR} PY_VERSION=${PY_VERSION:-3.7} CMAKE_INSTALL_PREFIX=${INSTALL_PREFIX:-/paddle/build} WITH_PSCORE=${pscore_flag} WITH_PSLIB=${pslib_flag} WITH_GLOO=${gloo_flag} LITE_GIT_TAG=release/v2.10 WITH_XPU=${WITH_XPU:-OFF} WITH_IPU=${WITH_IPU:-OFF} XPU_SDK_ROOT=${XPU_SDK_ROOT:-""} WITH_LITE=${WITH_LITE:-OFF} WITH_XPU_BKCL=${WITH_XPU_BKCL:-OFF} WITH_ARM=${WITH_ARM:-OFF} WITH_STRIP=${WITH_STRIP:-ON} ON_INFER=${ON_INFER:-OFF} WITH_HETERPS=${WITH_HETERPS:-OFF} WITH_GPU_GRAPH=${WITH_GPU_GRAPH:-OFF} WITH_FLUID_ONLY=${WITH_FLUID_ONLY:-OFF} CUDA_ARCH_BIN=${CUDA_ARCH_BIN} WITH_RECORD_BUILDTIME=${WITH_RECORD_BUILDTIME:-OFF} WITH_UNITY_BUILD=${WITH_UNITY_BUILD:-OFF} WITH_ONNXRUNTIME=${WITH_ONNXRUNTIME:-OFF} WITH_CUDNN_FRONTEND=${WITH_CUDNN_FRONTEND:-OFF}
     ========================================
 EOF
     echo "if you use cmake to compile,please Configuring cmake in /paddle/build ..."
     cat <<EOF
     ========================================
-    cmake .. -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE:-Release} -DWITH_GPU=${WITH_GPU:-OFF} -DWITH_CUDNN_DSO=${WITH_CUDNN_DSO:-OFF} -DWITH_TENSORRT=${WITH_TENSORRT:-ON} -DWITH_ROCM=${WITH_ROCM:-OFF} -DWITH_CINN=${WITH_CINN:-OFF} -DWITH_DISTRIBUTE=${distibuted_flag} -DWITH_MKL=${WITH_MKL:-ON} -DWITH_AVX=${WITH_AVX:-OFF} -DCUDA_ARCH_NAME=${CUDA_ARCH_NAME:-All} -DNEW_RELEASE_PYPI=${NEW_RELEASE_PYPI:-OFF} -DNEW_RELEASE_ALL=${NEW_RELEASE_ALL:-OFF} -DNEW_RELEASE_JIT=${NEW_RELEASE_JIT:-OFF} -DWITH_PYTHON=${WITH_PYTHON:-ON} -DCUDNN_ROOT=/usr/ -DWITH_TESTING=${WITH_TESTING:-ON} -DWITH_COVERAGE=${WITH_COVERAGE:-OFF} -DWITH_INCREMENTAL_COVERAGE=${WITH_INCREMENTAL_COVERAGE:-OFF} -DCMAKE_MODULE_PATH=/opt/rocm/hip/cmake -DCMAKE_EXPORT_COMPILE_COMMANDS=ON -DWITH_CONTRIB=${WITH_CONTRIB:-ON} -DWITH_INFERENCE_API_TEST=${WITH_INFERENCE_API_TEST:-ON} -DINFERENCE_DEMO_INSTALL_DIR=${INFERENCE_DEMO_INSTALL_DIR} -DPY_VERSION=${PY_VERSION:-3.7} -DCMAKE_INSTALL_PREFIX=${INSTALL_PREFIX:-/paddle/build} -DWITH_PSCORE=${pscore_flag} -DWITH_PSLIB=${pslib_flag} -DWITH_GLOO=${gloo_flag} -DLITE_GIT_TAG=release/v2.10 -DWITH_XPU=${WITH_XPU:-OFF} -DWITH_IPU=${WITH_IPU:-OFF} -DWITH_CNCL=${WITH_CNCL:-OFF} -DXPU_SDK_ROOT=${XPU_SDK_ROOT:-""} -DWITH_LITE=${WITH_LITE:-OFF} -DWITH_XPU_BKCL=${WITH_XPU_BKCL:-OFF} -DWITH_ARM=${WITH_ARM:-OFF} -DWITH_STRIP=${WITH_STRIP:-ON} -DON_INFER=${ON_INFER:-OFF} -DWITH_HETERPS=${WITH_HETERPS:-OFF} -DWITH_GPU_GRAPH=${WITH_GPU_GRAPH:-OFF} -DWITH_FLUID_ONLY=${WITH_FLUID_ONLY:-OFF} -DCUDA_ARCH_BIN=${CUDA_ARCH_BIN} -DWITH_RECORD_BUILDTIME=${WITH_RECORD_BUILDTIME:-OFF} -DWITH_UNITY_BUILD=${WITH_UNITY_BUILD:-OFF} -DWITH_ONNXRUNTIME=${WITH_ONNXRUNTIME:-OFF} -DWITH_CUDNN_FRONTEND=${WITH_CUDNN_FRONTEND:-OFF}
+    cmake .. -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE:-Release} -DWITH_GPU=${WITH_GPU:-OFF} -DWITH_CUDNN_DSO=${WITH_CUDNN_DSO:-OFF} -DWITH_TENSORRT=${WITH_TENSORRT:-ON} -DWITH_ROCM=${WITH_ROCM:-OFF} -DWITH_CINN=${WITH_CINN:-OFF} -DWITH_DISTRIBUTE=${distibuted_flag} -DWITH_MKL=${WITH_MKL:-ON} -DWITH_AVX=${WITH_AVX:-OFF} -DCUDA_ARCH_NAME=${CUDA_ARCH_NAME:-All} -DNEW_RELEASE_PYPI=${NEW_RELEASE_PYPI:-OFF} -DNEW_RELEASE_ALL=${NEW_RELEASE_ALL:-OFF} -DNEW_RELEASE_JIT=${NEW_RELEASE_JIT:-OFF} -DWITH_PYTHON=${WITH_PYTHON:-ON} -DCUDNN_ROOT=/usr/ -DWITH_TESTING=${WITH_TESTING:-ON} -DWITH_COVERAGE=${WITH_COVERAGE:-OFF} -DWITH_INCREMENTAL_COVERAGE=${WITH_INCREMENTAL_COVERAGE:-OFF} -DCMAKE_MODULE_PATH=/opt/rocm/hip/cmake -DCMAKE_EXPORT_COMPILE_COMMANDS=ON -DWITH_CONTRIB=${WITH_CONTRIB:-ON} -DWITH_INFERENCE_API_TEST=${WITH_INFERENCE_API_TEST:-ON} -DINFERENCE_DEMO_INSTALL_DIR=${INFERENCE_DEMO_INSTALL_DIR} -DPY_VERSION=${PY_VERSION:-3.7} -DCMAKE_INSTALL_PREFIX=${INSTALL_PREFIX:-/paddle/build} -DWITH_PSCORE=${pscore_flag} -DWITH_PSLIB=${pslib_flag} -DWITH_GLOO=${gloo_flag} -DLITE_GIT_TAG=release/v2.10 -DWITH_XPU=${WITH_XPU:-OFF} -DWITH_IPU=${WITH_IPU:-OFF} -DXPU_SDK_ROOT=${XPU_SDK_ROOT:-""} -DWITH_LITE=${WITH_LITE:-OFF} -DWITH_XPU_BKCL=${WITH_XPU_BKCL:-OFF} -DWITH_ARM=${WITH_ARM:-OFF} -DWITH_STRIP=${WITH_STRIP:-ON} -DON_INFER=${ON_INFER:-OFF} -DWITH_HETERPS=${WITH_HETERPS:-OFF} -DWITH_GPU_GRAPH=${WITH_GPU_GRAPH:-OFF} -DWITH_FLUID_ONLY=${WITH_FLUID_ONLY:-OFF} -DCUDA_ARCH_BIN=${CUDA_ARCH_BIN} -DWITH_RECORD_BUILDTIME=${WITH_RECORD_BUILDTIME:-OFF} -DWITH_UNITY_BUILD=${WITH_UNITY_BUILD:-OFF} -DWITH_ONNXRUNTIME=${WITH_ONNXRUNTIME:-OFF} -DWITH_CUDNN_FRONTEND=${WITH_CUDNN_FRONTEND:-OFF}
     ========================================
 EOF
     export CMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE:-Release}
@@ -3677,7 +3674,6 @@ EOF
     export LITE_GIT_TAG=release/v2.10
     export WITH_XPU=${WITH_XPU:-OFF}
     export WITH_IPU=${WITH_IPU:-OFF}
-    export WITH_CNCL=${WITH_CNCL:-OFF}
     export XPU_SDK_ROOT=${XPU_SDK_ROOT:-""}
     export WITH_LITE=${WITH_LITE:-OFF}
     export WITH_XPU_BKCL=${WITH_XPU_BKCL:-OFF}

python/paddle/fluid/tests/unittests/test_dist_base.py

@@ -704,7 +704,6 @@ class TestParallelDyGraphRunnerBase:
                 args.update_method == "nccl2"
                 or args.update_method == "bkcl"
                 or args.update_method == "hccl"
-                or args.update_method == "cncl"
             ):
                 strategy = paddle.distributed.parallel.ParallelStrategy()
                 strategy.nranks = nranks
@@ -862,7 +861,6 @@ def runtime_main(test_class):
             "nccl2_reduce_layer",
             "gloo",
             "hccl",
-            "cncl",
         ],
     )
     parser.add_argument('--trainer_id', type=int, required=False, default=0)
@@ -971,7 +969,6 @@ class TestDistBase(unittest.TestCase):
         self._bkcl_mode = False
         self._gloo_mode = False  # now, support gloo backend
         self._hccl_mode = False
-        self._cncl_mode = False
         self._pipeline_mode = False
         self._mp_mode = False
         self._diff_batch = False
@@ -1778,14 +1775,6 @@ class TestDistBase(unittest.TestCase):
                 check_error_log=check_error_log,
                 log_name=log_name,
             )
-        elif self._cncl_mode:
-            tr0_losses, tr1_losses = self._run_cluster_nccl2(
-                model_file,
-                required_envs,
-                update_method='cncl',
-                check_error_log=check_error_log,
-                log_name=log_name,
-            )
         elif self._pipeline_mode:
             tr0_losses, tr1_losses = self._run_pipeline(
                 model_file, required_envs, check_error_log, log_name=log_name

test/cpp/imperative/CMakeLists.txt

@@ -93,8 +93,7 @@ cc_test(
   DEPS tracer layer prepared_operator mul_op)
 if(WITH_NCCL
    OR WITH_RCCL
-   OR WITH_XPU_BKCL
-   OR WITH_CNCL)
+   OR WITH_XPU_BKCL)
   cc_test(
     test_group
     SRCS test_group.cc

test/cpp/imperative/test_group.cc

@@ -77,8 +77,7 @@ void GroupConcatSplit(Place place, size_t size) {
     }
 
     if (std::is_same<Place, platform::CUDAPlace>::value) {
-#if defined(PADDLE_WITH_NCCL) || defined(PADDLE_WITH_RCCL) || \
-    defined(PADDLE_WITH_CNCL)
+#if defined(PADDLE_WITH_NCCL) || defined(PADDLE_WITH_RCCL)
       paddle::memory::Copy(
           place, data, cpu_place, value.data(), sizeof(T) * value.size(), 0);
 #endif