Greentea LibDNN benchmarks

greentea/Makefile.config

@@ -1,30 +1,52 @@
 ## Refer to http://caffe.berkeleyvision.org/installation.html
 # Contributions simplifying and improving our build system are welcome!
 
+# 32 bit / 64 bit indexing
+# USE_INDEX_64 := 1
+
 # GreenTea (ViennaCL/OpenCL) backend switch
 
 # Enable the CUDA backend
-USE_CUDA := 0
+USE_CUDA := 1
 
 # Enable the OpenCL/Greentea backend
 USE_GREENTEA := 1
+USE_LIBDNN := 1
 
 # Folder of the ViennaCL header-only library
 VIENNACL_DIR = ../ViennaCL
 
-# Either set clBLAS to 1 or it will use ViennaclBLAS.
-# CLBLAS should be faster, especially on AMD cards.
-USE_CLBLAS := 0
+# Override BLAS, use clBLAS insead of ViennaclBLAS.
+# USE_CLBLAS := 1
+
+# Override BLAS, use ISAAC instead of ViennaclBLAS.
+# USE_ISAAC := 1
 
 # cuDNN acceleration switch (uncomment to build with cuDNN).
 # USE_CUDNN := 1
 
 # CPU-only switch (uncomment to build without GPU support).
 # CPU_ONLY := 1
 
+# uncomment to disable IO dependencies and corresponding data layers
+# USE_OPENCV := 0
+# USE_LEVELDB := 0
+# USE_LMDB := 0
+
+# Uncomment for FFT
+# USE_FFT := 1
+
+# 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 := /usr/local/gcc/4.9.2/bin/g++
+# CUSTOM_CXX := g++
 
 # CUDA directory contains bin/ and lib/ directories that we need.
 CUDA_DIR := /usr/local/cuda
@@ -52,6 +74,10 @@ BLAS := open
 # 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
@@ -68,17 +94,30 @@ PYTHON_INCLUDE := /usr/include/python2.7 \
 		# $(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
+
 # 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

greentea/run_forcegradinput.sh

@@ -2,8 +2,8 @@
 
 rm output_forceGradInput.log
 
-./caffe/build/tools/caffe time --model=../caffe/proto_forceGradInput/conv1.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_forceGradInput.log 2>&1
-./caffe/build/tools/caffe time --model=../caffe/proto_forceGradInput/conv2.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_forceGradInput.log 2>&1
-./caffe/build/tools/caffe time --model=../caffe/proto_forceGradInput/conv3.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_forceGradInput.log 2>&1
-./caffe/build/tools/caffe time --model=../caffe/proto_forceGradInput/conv4.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_forceGradInput.log 2>&1
-./caffe/build/tools/caffe time --model=../caffe/proto_forceGradInput/conv5.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_forceGradInput.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/proto_forceGradInput/conv1.prototxt --iterations=10 --gpu 1 --logtostderr=1 >>output_forceGradInput.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/proto_forceGradInput/conv2.prototxt --iterations=10 --gpu 1 --logtostderr=1 >>output_forceGradInput.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/proto_forceGradInput/conv3.prototxt --iterations=10 --gpu 1 --logtostderr=1 >>output_forceGradInput.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/proto_forceGradInput/conv4.prototxt --iterations=10 --gpu 1 --logtostderr=1 >>output_forceGradInput.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/proto_forceGradInput/conv5.prototxt --iterations=10 --gpu 1 --logtostderr=1 >>output_forceGradInput.log 2>&1

greentea/run_forcegradinput_cuda.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+
+rm output_forceGradInput.log
+
+./caffe/build/tools/caffe time --model=../caffe/proto_forceGradInput/conv1.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_forceGradInput.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/proto_forceGradInput/conv2.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_forceGradInput.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/proto_forceGradInput/conv3.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_forceGradInput.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/proto_forceGradInput/conv4.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_forceGradInput.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/proto_forceGradInput/conv5.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_forceGradInput.log 2>&1

greentea/run_imagenet.sh

@@ -1,7 +1,8 @@
 #!/bin/bash
 rm output_*.log
-./caffe/build/tools/caffe time --model=../caffe/imagenet_winners/alexnet.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_alexnet.log 2>&1
-./caffe/build/tools/caffe time --model=../caffe/imagenet_winners/overfeat.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_overfeat.log 2>&1
-./caffe/build/tools/caffe time --model=../caffe/imagenet_winners/vgg_a.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_vgg_a.log 2>&1
-./caffe/build/tools/caffe time --model=./imagenet_winners/googlenet.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_googlenet.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/imagenet_winners/alexnet.prototxt --iterations=10 --gpu 1 --logtostderr=1 >>output_alexnet.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/imagenet_winners/overfeat.prototxt --iterations=10 --gpu 1 --logtostderr=1 >>output_overfeat.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/imagenet_winners/vgg_a.prototxt --iterations=10 --gpu 1 --logtostderr=1 >>output_vgg_a.log 2>&1
+./caffe/build/tools/caffe time --model=./imagenet_winners/googlenet.prototxt --iterations=10 --gpu 1 --logtostderr=1 >>output_googlenet.log 2>&1
+
 

greentea/run_imagenet_cuda.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+rm output_*.log
+./caffe/build/tools/caffe time --model=../caffe/imagenet_winners/alexnet.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_alexnet.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/imagenet_winners/overfeat.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_overfeat.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/imagenet_winners/vgg_a.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_vgg_a.log 2>&1
+./caffe/build/tools/caffe time --model=./imagenet_winners/googlenet.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_googlenet.log 2>&1
+
+

greentea/run_nogradinput.sh

@@ -1,8 +1,9 @@
 #!/bin/bash
 rm output_noGradInput.log
-./caffe/build/tools/caffe time --model=../caffe/proto_noGradInput/conv1.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_noGradInput.log 2>&1
-./caffe/build/tools/caffe time --model=../caffe/proto_noGradInput/conv2.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_noGradInput.log 2>&1
-./caffe/build/tools/caffe time --model=../caffe/proto_noGradInput/conv3.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_noGradInput.log 2>&1
-./caffe/build/tools/caffe time --model=../caffe/proto_noGradInput/conv4.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_noGradInput.log 2>&1
-./caffe/build/tools/caffe time --model=../caffe/proto_noGradInput/conv5.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_noGradInput.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/proto_noGradInput/conv1.prototxt --iterations=10 --gpu 1 --logtostderr=1 >>output_noGradInput.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/proto_noGradInput/conv2.prototxt --iterations=10 --gpu 1 --logtostderr=1 >>output_noGradInput.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/proto_noGradInput/conv3.prototxt --iterations=10 --gpu 1 --logtostderr=1 >>output_noGradInput.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/proto_noGradInput/conv4.prototxt --iterations=10 --gpu 1 --logtostderr=1 >>output_noGradInput.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/proto_noGradInput/conv5.prototxt --iterations=10 --gpu 1 --logtostderr=1 >>output_noGradInput.log 2>&1
+
 

greentea/run_nogradinput_cuda.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+rm output_noGradInput.log
+./caffe/build/tools/caffe time --model=../caffe/proto_noGradInput/conv1.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_noGradInput.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/proto_noGradInput/conv2.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_noGradInput.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/proto_noGradInput/conv3.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_noGradInput.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/proto_noGradInput/conv4.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_noGradInput.log 2>&1
+./caffe/build/tools/caffe time --model=../caffe/proto_noGradInput/conv5.prototxt --iterations=10 --gpu 0 --logtostderr=1 >>output_noGradInput.log 2>&1
+
+