@@ -7,6 +7,12 @@ $(error $(CONFIG_FILE) not found. See $(CONFIG_FILE).example.)
 endif
 include $(CONFIG_FILE)
 
+ifeq ($(CPU_ONLY),1)
+	USE_CUDA := 0
+endif
+ifeq ($(USE_ACL),1)
+	USE_CUDA := 0
+endif
 BUILD_DIR_LINK := $(BUILD_DIR)
 ifeq ($(RELEASE_BUILD_DIR),)
 	RELEASE_BUILD_DIR := .$(BUILD_DIR)_release
@@ -172,13 +178,13 @@ endif
 CUDA_LIB_DIR += $(CUDA_DIR)/lib
 
 INCLUDE_DIRS += $(BUILD_INCLUDE_DIR) ./src ./include
-ifneq ($(CPU_ONLY), 1)
+ifeq ($(USE_CUDA), 1)
 	INCLUDE_DIRS += $(CUDA_INCLUDE_DIR)
 	LIBRARY_DIRS += $(CUDA_LIB_DIR)
 	LIBRARIES := cudart cublas curand
 endif
 
-LIBRARIES += glog gflags protobuf boost_system boost_filesystem m hdf5_hl hdf5
+LIBRARIES += glog gflags protobuf boost_system boost_filesystem m 
 
 # handle IO dependencies
 USE_LEVELDB ?= 1
@@ -271,7 +277,7 @@ endif
 # libstdc++ for NVCC compatibility on OS X >= 10.9 with CUDA < 7.0
 ifeq ($(OSX), 1)
 	CXX := /usr/bin/clang++
-	ifneq ($(CPU_ONLY), 1)
+	ifeq ($(USE_CUDA), 1)
 		CUDA_VERSION := $(shell $(CUDA_DIR)/bin/nvcc -V | grep -o 'release [0-9.]*' | tr -d '[a-z ]')
 		ifeq ($(shell echo | awk '{exit $(CUDA_VERSION) < 7.0;}'), 1)
 			CXXFLAGS += -stdlib=libstdc++
@@ -296,6 +302,10 @@ ifeq ($(OSX), 1)
 	ORIGIN := @loader_path
 	VERSIONFLAGS += -Wl,-install_name,@rpath/$(DYNAMIC_VERSIONED_NAME_SHORT) -Wl,-rpath,$(ORIGIN)/../../build/lib
 else
+	ifeq (${USE_OPENMP}, 1)
+		CXXFLAGS += -fopenmp
+		LINKFLAGS += -fopenmp
+	endif
 	ORIGIN := \$$ORIGIN
 endif
 
@@ -334,6 +344,27 @@ ifeq ($(USE_NCCL), 1)
 	COMMON_FLAGS += -DUSE_NCCL
 endif
 
+# ACL acceleration configuration
+ifeq ($(USE_ACL), 1)
+        LIBRARY_DIRS += $(ACL_LIBS_DIR)
+	LIBRARIES += $(ACL_LIBS)
+	INCLUDE_DIRS +=$(ACL_INCS)
+	COMMON_FLAGS += -DUSE_ACL -std=c++11
+endif
+
+#USE_PROFILING -- get profiling informations, is controled by LOGACL
+#LAYER_PERF_STAT -- haitao's net profiling information
+ifeq ($(USE_PROFILING), 1)
+	COMMON_FLAGS += -DUSE_PROFILING -DLAYER_PERF_STAT
+endif
+#HDF5
+ifeq ($(USE_HDF5), 1)
+        LIBRARY_DIRS += $(HDF5_LIBRARY_DIRS)
+	LIBRARIES += $(HDF5_LIBRARIES)
+	INCLUDE_DIRS +=$(HDF5_INCLUDE_DIRS)
+	COMMON_FLAGS += -DUSE_HDF5
+endif
+
 # configure IO libraries
 ifeq ($(USE_OPENCV), 1)
 	COMMON_FLAGS += -DUSE_OPENCV
@@ -358,14 +389,24 @@ ifeq ($(CPU_ONLY), 1)
 	COMMON_FLAGS += -DCPU_ONLY
 endif
 
+ifeq ($(USE_ACL), 1)
+	OBJS := $(PROTO_OBJS) $(CXX_OBJS)
+	TEST_OBJS := $(TEST_CXX_OBJS)
+	TEST_BINS := $(TEST_CXX_BINS)
+	ALL_WARNS := $(ALL_CXX_WARNS)
+	TEST_FILTER := --gtest_filter="-*GPU*"
+	COMMON_FLAGS += -DCPU_ONLY
+endif
+
 # Python layer support
 ifeq ($(WITH_PYTHON_LAYER), 1)
 	COMMON_FLAGS += -DWITH_PYTHON_LAYER
 	LIBRARIES += $(PYTHON_LIBRARIES)
 endif
 
 # BLAS configuration (default = ATLAS)
-BLAS ?= atlas
+#BLAS ?= atlas
+BLAS ?= open
 ifeq ($(BLAS), mkl)
 	# MKL
 	LIBRARIES += mkl_rt
 
@@ -0,0 +1,140 @@
+## Refer to http://caffe.berkeleyvision.org/installation.html
+# Contributions simplifying and improving our build system are welcome!
+
+# cuDNN acceleration switch (uncomment to build with cuDNN).
+# USE_CUDNN := 1
+
+# CPU-only switch (uncomment to build without GPU support).
+CPU_ONLY := 1
+
+USE_PROFILING := 0
+
+USE_ACL :=1
+ACL_ROOT :=/home/firefly/ComputeLibrary
+ACL_INCS :=$(ACL_ROOT)/include 
+ACL_INCS +=$(ACL_ROOT)
+ACL_LIBS_DIR :=$(ACL_ROOT)/build
+ACL_LIBS_DIR +=$(ACL_ROOT)/build/arm_compute
+ACL_LIBS :=arm_compute OpenCL
+
+# uncomment to disable IO dependencies and corresponding data layers
+# USE_OPENCV := 0
+# USE_LEVELDB := 0
+# USE_LMDB := 0
+
+# uncomment to allow MDB_NOLOCK when reading LMDB files (only if necessary)
+#	You should not set this flag if you will be reading LMDBs with any
+#	possibility of simultaneous read and write
+# ALLOW_LMDB_NOLOCK := 1
+
+# Uncomment if you're using OpenCV 3
+# OPENCV_VERSION := 3
+
+# To customize your choice of compiler, uncomment and set the following.
+# N.B. the default for Linux is g++ and the default for OSX is clang++
+# CUSTOM_CXX := g++
+#CUSTOM_CXX := aarch64-linux-gnu-g++
+#os :=linux 
+#arch :=arm64-v8a
+
+# CUDA directory contains bin/ and lib/ directories that we need.
+CUDA_DIR := /usr/local/cuda
+# On Ubuntu 14.04, if cuda tools are installed via
+# "sudo apt-get install nvidia-cuda-toolkit" then use this instead:
+# CUDA_DIR := /usr
+
+# CUDA architecture setting: going with all of them.
+# For CUDA < 6.0, comment the *_50 through *_61 lines for compatibility.
+# For CUDA < 8.0, comment the *_60 and *_61 lines for compatibility.
+CUDA_ARCH := -gencode arch=compute_20,code=sm_20 \
+		-gencode arch=compute_20,code=sm_21 \
+		-gencode arch=compute_30,code=sm_30 \
+		-gencode arch=compute_35,code=sm_35 \
+		-gencode arch=compute_50,code=sm_50 \
+		-gencode arch=compute_52,code=sm_52 \
+		-gencode arch=compute_60,code=sm_60 \
+		-gencode arch=compute_61,code=sm_61 \
+		-gencode arch=compute_61,code=compute_61
+
+# BLAS choice:
+# atlas for ATLAS (default)
+# mkl for MKL
+# open for OpenBlas
+#BLAS := atlas
+BLAS := open
+# Custom (MKL/ATLAS/OpenBLAS) include and lib directories.
+# Leave commented to accept the defaults for your choice of BLAS
+# (which should work)!
+# BLAS_INCLUDE := /path/to/your/blas
+# BLAS_LIB := /path/to/your/blas
+
+# Homebrew puts openblas in a directory that is not on the standard search path
+# BLAS_INCLUDE := $(shell brew --prefix openblas)/include
+# BLAS_LIB := $(shell brew --prefix openblas)/lib
+
+# This is required only if you will compile the matlab interface.
+# MATLAB directory should contain the mex binary in /bin.
+# MATLAB_DIR := /usr/local
+# MATLAB_DIR := /Applications/MATLAB_R2012b.app
+
+# NOTE: this is required only if you will compile the python interface.
+# We need to be able to find Python.h and numpy/arrayobject.h.
+PYTHON_INCLUDE := /usr/include/python2.7 \
+		/usr/lib/python2.7/dist-packages/numpy/core/include
+# Anaconda Python distribution is quite popular. Include path:
+# Verify anaconda location, sometimes it's in root.
+# ANACONDA_HOME := $(HOME)/anaconda
+# PYTHON_INCLUDE := $(ANACONDA_HOME)/include \
+		# $(ANACONDA_HOME)/include/python2.7 \
+		# $(ANACONDA_HOME)/lib/python2.7/site-packages/numpy/core/include
+
+# Uncomment to use Python 3 (default is Python 2)
+# PYTHON_LIBRARIES := boost_python3 python3.5m
+# PYTHON_INCLUDE := /usr/include/python3.5m \
+#                 /usr/lib/python3.5/dist-packages/numpy/core/include
+
+# We need to be able to find libpythonX.X.so or .dylib.
+PYTHON_LIB := /usr/lib
+# PYTHON_LIB := $(ANACONDA_HOME)/lib
+
+# Homebrew installs numpy in a non standard path (keg only)
+# PYTHON_INCLUDE += $(dir $(shell python -c 'import numpy.core; print(numpy.core.__file__)'))/include
+# PYTHON_LIB += $(shell brew --prefix numpy)/lib
+
+# Uncomment to support layers written in Python (will link against Python libs)
+# WITH_PYTHON_LAYER := 1
+
+# Whatever else you find you need goes here.
+INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include
+LIBRARY_DIRS := $(PYTHON_LIB) /usr/local/lib /usr/lib
+
+# If Homebrew is installed at a non standard location (for example your home directory) and you use it for general dependencies
+# INCLUDE_DIRS += $(shell brew --prefix)/include
+# LIBRARY_DIRS += $(shell brew --prefix)/lib
+
+# NCCL acceleration switch (uncomment to build with NCCL)
+# https://github.com/NVIDIA/nccl (last tested version: v1.2.3-1+cuda8.0)
+# USE_NCCL := 1
+
+# Uncomment to use `pkg-config` to specify OpenCV library paths.
+# (Usually not necessary -- OpenCV libraries are normally installed in one of the above $LIBRARY_DIRS.)
+# USE_PKG_CONFIG := 1
+
+# N.B. both build and distribute dirs are cleared on `make clean`
+BUILD_DIR := build
+DISTRIBUTE_DIR := distribute
+
+#HDF5
+USE_HDF5 := 1
+HDF5_INCLUDE_DIRS := /usr/include/hdf5/serial
+HDF5_LIBRARY_DIRS := /usr/lib/aarch64-linux-gnu/hdf5/serial
+HDF5_LIBRARIES :=hdf5_hl hdf5
+
+# Uncomment for debugging. Does not work on OSX due to https://github.com/BVLC/caffe/issues/171
+# DEBUG := 1
+
+# The ID of the GPU that 'make runtest' will use to run unit tests.
+TEST_GPUID := 0
+
+# enable pretty build (comment to see full commands)
+Q ?= @
@@ -1,3 +1,14 @@
+# CaffeOnACL
+[![License](https://img.shields.io/badge/license-BSD-blue.svg)](LICENSE)
+
+CaffeOnACL is a project to use ARM Compute Library (NEON+GPU) to speed up caffe and provide utilities to debug, profile and tune application performance.
+
+Check out the documents for the details like
+- [release notes](https://github.com/OAID/caffeOnACL/tree/master/docs/caffeOnACL_release_notes_0_2_0.docx)
+- [user guide](https://github.com/OAID/caffeOnACL/tree/master/docs/caffeOnACL_user_guide_0_2_0.docx)
+
+
+
 # Caffe
 
 [![Build Status](https://travis-ci.org/BVLC/caffe.svg?branch=master)](https://travis-ci.org/BVLC/caffe)
 
@@ -66,6 +66,21 @@ if(USE_LEVELDB)
   list(APPEND Caffe_DEFINITIONS PUBLIC -DUSE_LEVELDB)
 endif()
 
+# ---[ ACL
+if(USE_ACL)
+  find_package(ACL REQUIRED)
+  list(APPEND Caffe_INCLUDE_DIRS PUBLIC ${ACL_INCLUDE})
+  list(APPEND Caffe_INCLUDE_DIRS PUBLIC ${ACL_INCLUDE}/include)
+  set(__list ${ACL_LIBRARIES})
+  separate_arguments(__list)
+    list(REMOVE_DUPLICATES __list)
+    foreach(i ${__list})
+        list(APPEND Caffe_LINKER_LIBS PUBLIC ${i})
+    endforeach()
+  list(APPEND Caffe_COMPILE_OPTIONS PRIVATE -std=c++11)
+  list(APPEND Caffe_DEFINITIONS PUBLIC -DUSE_ACL)
+endif()
+
 # ---[ Snappy
 if(USE_LEVELDB)
   find_package(Snappy REQUIRED)
 
@@ -0,0 +1,37 @@
+set(ACL_INC_PATHS
+    /usr/include
+    /usr/local/include
+    /usr/local/acl
+    $ENV{ACL_DIR}/include
+    )
+
+set(ACL_LIB_PATHS
+    /lib
+    /lib64
+    /usr/lib
+    /usr/lib64
+    /usr/local/lib
+    /usr/local/lib64
+    /usr/local/acl/lib
+    /usr/local/acl/lib64
+    $ENV{ACL_DIR}/lib
+    )
+
+find_path(ACL_INCLUDE NAMES arm_compute PATHS ${ACL_INC_PATHS})
+find_library(ACL_LIBRARIES NAMES arm_compute-static PATHS ${ACL_LIB_PATHS})
+find_library(ACL_CORE_LIBRARIES NAMES arm_compute_core-static PATHS ${ACL_LIB_PATHS})
+SET(ACL_LIBRARIES "${ACL_CORE_LIBRARIES} ${ACL_LIBRARIES}")
+
+if(ACL_INCS)
+  SET(ACL_INCLUDE "${ACL_INCS}")
+  SET(ACL_LIBRARIES "${ACL_LIBS}")
+  SET(ACL_FOUND 1)
+else  ()
+  include(FindPackageHandleStandardArgs)
+  find_package_handle_standard_args(ACL DEFAULT_MSG ACL_INCLUDE ACL_LIBRARIES)
+endif ()
+
+if (ACL_FOUND)
+  message(STATUS "Found ACL    (include: ${ACL_INCLUDE}, library: ${ACL_LIBRARIES})")
+  mark_as_advanced(ACL_INCLUDE ACL_LIBRARIES)
+endif ()