fd32b990ac
- support for PyTorch 1.7 and TensorRT 7.2 - limit sample audio file length
73 lines
2.6 KiB
Makefile
73 lines
2.6 KiB
Makefile
# Copyright (c) 2020, NVIDIA CORPORATION. All rights reserved.
|
|
|
|
# Redistribution and use in source and binary forms, with or without
|
|
# modification, are permitted provided that the following conditions are met:
|
|
# * Redistributions of source code must retain the above copyright
|
|
# notice, this list of conditions and the following disclaimer.
|
|
# * Redistributions in binary form must reproduce the above copyright
|
|
# notice, this list of conditions and the following disclaimer in the
|
|
# documentation and/or other materials provided with the distribution.
|
|
# * Neither the name of the NVIDIA CORPORATION nor the
|
|
# names of its contributors may be used to endorse or promote products
|
|
# derived from this software without specific prior written permission.
|
|
|
|
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
|
|
# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
|
|
# WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
|
# DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
|
|
# DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
|
|
# (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
|
|
# LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
|
|
# ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
|
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
|
# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
|
|
ARCH = "sm_70" # Volta
|
|
# ARCH = "sm_75" # Turing
|
|
# ARCH = "sm_80" # Ampere
|
|
|
|
CUDA_PATH =/usr/local/cuda
|
|
|
|
CUDA_INC_PATH = $(CUDA_PATH)/include
|
|
CUDA_COM_PATH = $(CUDA_PATH)/samples/common/inc
|
|
|
|
GCC = g++
|
|
NVCC = $(CUDA_PATH)/bin/nvcc
|
|
# CCFLAGS = -g -std=c++11 -DNDEBUG
|
|
CCFLAGS = -w -std=c++11 -DNDEBUG
|
|
# CCFLAGS+= -DDEBUG_ME
|
|
INCLUDES := -I$(CUDA_COM_PATH) -I$(CUDA_INC_PATH) -I/usr/include # cuda 11
|
|
# INCLUDES := -I../../../../cub -I$(CUDA_COM_PATH) -I$(CUDA_INC_PATH) -I/usr/include # cuda 10
|
|
|
|
CUDA_LIB_PATH = $(CUDA_PATH)/lib64
|
|
LDFLAGS := -L$(CUDA_LIB_PATH)
|
|
LDFLAGS += -lnvinfer -lcudart
|
|
|
|
LDFLAGS += -Wl,-rpath=$(CUDA_LIB_PATH)
|
|
|
|
SO = RepeatPlugin.so
|
|
OBJ = $(shell find . -name '*.o')
|
|
DEP = $(OBJ:.o=.d)
|
|
|
|
all: $(SO) $(CUDA_BIN)
|
|
|
|
RepeatPlugin.so: RepeatPlugin.o
|
|
|
|
-include $(DEP)
|
|
|
|
clean:
|
|
rm -rf $(SO) $(CUDA_BIN) $(OBJ) $(DEP)
|
|
|
|
%.o: %.cpp
|
|
$(GCC) $(CCFLAGS) -fPIC -MD -MP $(INCLUDES) -o $@ -c $<
|
|
|
|
%.o: %.cu
|
|
$(NVCC) $(CCFLAGS) -M -MT $@ $(INCLUDES) -o $(@:.o=.d) $<
|
|
$(NVCC) $(CCFLAGS) $(INCLUDES) -Xcompiler -fPIC -arch=$(ARCH) -o $@ -c $<
|
|
|
|
$(SO):
|
|
$(GCC) $(CCFLAGS) -shared -o $@ $+ $(LDFLAGS)
|
|
|
|
test: all
|
|
python3 test_repeat_plugin.py
|