CC := nvcc -m64 -std=c++17 -ccbin g++-12 -Xcompiler -m64,-std=c++17
OBJ_DIR := bin
$(shell mkdir -p $(OBJ_DIR))
MODELS_DIR := models
OUT_DIR := out
SRC_DIR := .
#CFLAGS := -O0 -Werror=all-warnings -g -G
#CFLAGS := $(CFLAGS) -pg
#CFLAGS := $(CFLAGS) -Xptxas=-w
#CFLAGS := $(CFLAGS) -Xcompiler -Wall,-O0,-g,-Werror,-Werror=implicit-fallthrough=0,-Wextra,-rdynamic
CFLAGS := -O4 -Xcompiler -O4
EXEC := $(OBJ_DIR)/ViolaJones
DATA := ../data/X_train.bin ../data/X_test.bin ../data/y_train.bin ../data/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 start reset clean mrproper debug check

all: $(EXEC) $(DATA)

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

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

$(EXEC): $(OBJ)
	@echo Linking objects files to $@
	@$(CC) $(CFLAGS) $^ -o $@

$(DATA):
	@bash ../download_data.sh ..

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

profile: start
	@gprof $(EXEC) gmon.out | gprof2dot | dot -Tpng -o output.png
#@gprof $(EXEC) gmon.out > analysis.txt

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

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

cudacheck: $(EXEC) $(DATA)
	@cuda-memcheck --destroy-on-device-error kernel --tool memcheck --leak-check full --report-api-errors all $(EXEC)
#@cuda-memcheck --destroy-on-device-error kernel --tool racecheck --racecheck-report all $(EXEC)
#@cuda-memcheck --destroy-on-device-error kernel --tool initcheck --track-unused-memory yes $(EXEC)
#@cuda-memcheck --destroy-on-device-error kernel --tool synccheck $(EXEC)
#@compute-sanitizer --destroy-on-device-error kernel --tool memcheck --leak-check full --report-api-errors all --track-stream-ordered-races 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)

r2: $(EXEC) $(DATA)
	@r2 $(EXEC)

reset:
	@echo Deleting generated states and models
	@rm -rf $(OUT_DIR)/* $(MODELS_DIR)/* | true

clean:
	@rm $(EXEC)

mrproper:
	@rm -r $(OBJ_DIR)