CC := nvcc -m64 -t=0 -std=c++17 -Xcompiler -m64,-std=c++17
OBJ_DIR := bin
MODELS_DIR := models
OUT_DIR := out
SRC_DIR := .
DATA_PATH := ../data
#CFLAGS := -O0 -g -G -Xptxas=-w -Xcompiler -O0,-rdynamic,-g
#CFLAGS := -O0 -g -G -pg -Xptxas=-w -Xcompiler -O0,-rdynamic,-g
CFLAGS := -dlto -O2 -Xcompiler -O2
#CFLAGS := -dlto -O2 -g -Xcompiler -O2,-g,-ggdb
CFLAGS := $(CFLAGS) -MMD -MP -Werror=all-warnings -Xcompiler -Wall,-Werror,-Werror=implicit-fallthrough=0,-Wextra
EXEC := $(OBJ_DIR)/ViolaJones
DATA := $(DATA_PATH)/X_train.bin $(DATA_PATH)/X_test.bin $(DATA_PATH)/y_train.bin $(DATA_PATH)/y_test.bin
SRC := $(shell find $(SRC_DIR) -name '*.cpp' -o -name '*.cu')
OBJ_EXT := o
ifeq ($(OS), Windows_NT)
	EXEC := $(EXEC).exe
	OBJ_EXT := obj
endif
OBJ := $(SRC:$(SRC_DIR)/%.cpp=$(OBJ_DIR)/%.$(OBJ_EXT))
OBJ := $(OBJ:$(SRC_DIR)/%.cu=$(OBJ_DIR)/%.$(OBJ_EXT))

.PHONY: all
all: $(EXEC)

$(OBJ_DIR):
	@mkdir -v $@

# Compiling host code
$(OBJ_DIR)/%.$(OBJ_EXT): $(SRC_DIR)/%.cpp | $(OBJ_DIR) check-nvcc-works
	@echo Compiling $<
	@$(CC) $(CFLAGS) -c $< -o $@

# Compiling gpu code
$(OBJ_DIR)/%.$(OBJ_EXT): $(SRC_DIR)/%.cu | $(OBJ_DIR) check-nvcc-works
	@echo Compiling $<
	@$(CC) $(CFLAGS) -c $< -o $@

# FIXME When using the docker image, Make check prequisites even when the target already exists
#$(EXEC): $(OBJ) | check-nvcc-works
$(EXEC): $(OBJ)
	@echo Linking objects files to $@
	@$(CC) $(CFLAGS) $^ -o $@

$(DATA):
	@echo 'Missing $(DATA) files, use downloader first' && exit 1

.PHONY: start
start: $(EXEC) $(DATA)
	@./$(EXEC)

.PHONY: debug
debug: $(EXEC) $(DATA)
	#@cuda-gdb -q $(EXEC)
	@gdb -q --tui $(EXEC)

.PHONY: profile
profile: start | check-gprof-works check-gprof2dot-works check-dot-works
	@gprof $(EXEC) gmon.out | gprof2dot | dot -T png -o output.png

.PHONY: check
check: $(EXEC) $(DATA) | check-valgrind-works
	@valgrind -q -s --leak-check=full --show-leak-kinds=all $(EXEC)

.PHONY: cudacheck
cudacheck: $(EXEC) $(DATA) | check-computer-sanitizer-works
	@compute-sanitizer --destroy-on-device-error kernel --tool memcheck --leak-check full --report-api-errors all --track-stream-ordered-races all --target-processes all $(EXEC)
	#@compute-sanitizer --destroy-on-device-error kernel --tool racecheck --racecheck-detect-level info --racecheck-report all $(EXEC)
	#@compute-sanitizer --destroy-on-device-error kernel --tool initcheck --track-unused-memory yes $(EXEC)
	#@compute-sanitizer --destroy-on-device-error kernel --tool synccheck $(EXEC)

.PHONY: log
log: $(DATA) reset
	@echo 'Building GPU'
	@sed -i 's/GPU_BOOSTED false/GPU_BOOSTED true/' config.hpp
	@make -s -j "$(shell nproc)"
	@echo 'Logging GPU'
	@make -s start > log_gpu
	@echo 'Building CPU'
	@sed -i 's/GPU_BOOSTED true/GPU_BOOSTED false/' config.hpp
	@make -s -j "$(shell nproc)"
	@echo 'Logging CPU'
	@make -s start > log_cpu
	@sed -i 's/GPU_BOOSTED false/GPU_BOOSTED true/' config.hpp
	@echo 'Cleaning up'
	@make -s reset

.PHONY: reset
reset:
	@echo 'Deleting generated states and models'
	@rm -frv $(OUT_DIR)/* $(MODELS_DIR)/*
#@ln -sv /mnt/pierre_stuffs/ViolaJones/cpp/models .
#@ln -sv /mnt/pierre_stuffs/ViolaJones/cpp/out .

.PHONY: clean
clean:
	@rm -fv $(EXEC) log_gpu log_cpu

.PHONY: mrproper
mrproper: clean
	@rm -rfv $(OBJ_DIR) gmon.out

.PHONY: help
help:
	@echo "Available targets:"
	@echo "\tall: alias for start, (default target)"
	@echo "\tstart: Start the ViolaJones algorithm, require data beforehand downloaded by the downloader."
	@echo "\tdebug: Debug the ViolaJones algorithm, require data beforehand downloaded by the downloader."
	@echo "\tprofile: Profile the ViolaJones algorithm functions timestamps, require data beforehand downloaded by the downloader."
	@echo "\treset: Will delete any saved models and processed data made by ViolaJones."
	@echo "\tmrproper: Will remove cpp binary files. Will execute reset target beforehand."

.PHONY: check-nvcc-works
check-nvcc-works:
	@nvcc --version >/dev/null 2>&1 || (echo 'Please install NVIDIA Cuda compiler.' && exit 1)

.PHONY: check-gprof-works
check-gprof-works:
	@gprof --version >/dev/null 2>&1 || (echo 'Please install GNU gprof.' && exit 1)

.PHONY: check-gprof2dot-works
check-gprof2dot-works:
	@gprof2dot --help >/dev/null 2>&1 || (echo 'Please install gprof2dot.' && exit 1)

.PHONY: check-dot-works
check-dot-works:
	@dot --version >/dev/null 2>&1 || (echo 'Please install dot from graphviz.' && exit 1)

.PHONY: check-valgrind-works
check-valgrind-works:
	@valgrind --version >/dev/null 2>&1 || (echo 'Please install valgrind.' && exit 1)

.PHONY: check-computer-sanitizer-works
check-computer-sanitizer-works:
	@computer-sanitizer --version >/dev/null 2>&1 || (echo 'Please install Compute Sanitizer from Cuda toolkit.' && exit 1)

-include $(OBJ:.o=.d)