| | |
|---|
| | | GPU=0 |
|---|
| | | CUDNN=0 |
|---|
| | | CUDNN_HALF=0 |
|---|
| | | OPENCV=0 |
|---|
| | | DEBUG=0 |
|---|
| | | AVX=0 |
|---|
| | | OPENMP=0 |
|---|
| | | LIBSO=0 |
|---|
| | | |
|---|
| | | # set GPU=1 and CUDNN=1 to speedup on GPU |
|---|
| | | # set CUDNN_HALF=1 to further speedup 3 x times (Mixed-precision using Tensor Cores) on GPU Tesla V100, Titan V, DGX-2 |
|---|
| | | # set AVX=1 and OPENMP=1 to speedup on CPU (if error occurs then set AVX=0) |
|---|
| | | |
|---|
| | | DEBUG=0 |
|---|
| | | |
|---|
| | | ARCH= -gencode arch=compute_30,code=sm_30 \ |
|---|
| | | -gencode arch=compute_35,code=sm_35 \ |
|---|
| | | -gencode arch=compute_50,code=[sm_50,compute_50] \ |
|---|
| | |
|---|
| | | # GP100/Tesla P100 DGX-1 |
|---|
| | | # ARCH= -gencode arch=compute_60,code=sm_60 |
|---|
| | | |
|---|
| | | # For Jetson Tx1 uncomment: |
|---|
| | | # ARCH= -gencode arch=compute_51,code=[sm_51,compute_51] |
|---|
| | | # For Jetson TX1, Tegra X1, DRIVE CX, DRIVE PX - uncomment: |
|---|
| | | # ARCH= -gencode arch=compute_53,code=[sm_53,compute_53] |
|---|
| | | |
|---|
| | | # For Jetson Tx2 or Drive-PX2 uncomment: |
|---|
| | | # ARCH= -gencode arch=compute_62,code=[sm_62,compute_62] |
|---|
| | |
|---|
| | | ifeq ($(DEBUG), 1) |
|---|
| | | OPTS= -O0 -g |
|---|
| | | else |
|---|
| | | CFLAGS+= -ffp-contract=fast -mavx |
|---|
| | | ifeq ($(AVX), 1) |
|---|
| | | CFLAGS+= -ffp-contract=fast -mavx -mavx2 -msse3 -msse4.1 -msse4.2 -msse4a |
|---|
| | | endif |
|---|
| | | endif |
|---|
| | | |
|---|
| | | CFLAGS+=$(OPTS) |
|---|
| | |
|---|
| | | endif |
|---|
| | | endif |
|---|
| | | |
|---|
| | | ifeq ($(CUDNN_HALF), 1) |
|---|
| | | COMMON+= -DCUDNN_HALF |
|---|
| | | CFLAGS+= -DCUDNN_HALF |
|---|
| | | ARCH+= -gencode arch=compute_70,code=[sm_70,compute_70] |
|---|
| | | endif |
|---|
| | | |
|---|
| | | OBJ=http_stream.o gemm.o utils.o cuda.o convolutional_layer.o list.o image.o activations.o im2col.o col2im.o blas.o crop_layer.o dropout_layer.o maxpool_layer.o softmax_layer.o data.o matrix.o network.o connected_layer.o cost_layer.o parser.o option_list.o darknet.o detection_layer.o captcha.o route_layer.o writing.o box.o nightmare.o normalization_layer.o avgpool_layer.o coco.o dice.o yolo.o detector.o layer.o compare.o classifier.o local_layer.o swag.o shortcut_layer.o activation_layer.o rnn_layer.o gru_layer.o rnn.o rnn_vid.o crnn_layer.o demo.o tag.o cifar.o go.o batchnorm_layer.o art.o region_layer.o reorg_layer.o reorg_old_layer.o super.o voxel.o tree.o yolo_layer.o upsample_layer.o |
|---|
| | | ifeq ($(GPU), 1) |
|---|
| | | LDFLAGS+= -lstdc++ |
|---|
