CUDA-From-Correctness-To-Performance-Code/Makefile at master · interestingLSY/CUDA-From-Correctness-To-Performance-Code · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
CC = nvcc
CXXFLAGS = -O3

DEPS = gemm_cpu_naive.h gemm_cpu_simd.h gemm_gpu_1thread.h gemm_gpu_mult_thread.h gemm_gpu_mult_block.h gemm_gpu_mult_block_no_restrict.h gemm_gpu_mult_block_no_restrict_reg.h gemm_gpu_tiling.h
OBJS = gemm_cpu_naive.o gemm_cpu_simd.o gemm_test.o gemm_gpu_1thread.o gemm_gpu_mult_thread.o gemm_gpu_mult_block.o gemm_gpu_mult_block_no_restrict.o gemm_gpu_mult_block_no_restrict_reg.o gemm_gpu_tiling.o

.PHONY: all clean

all: gemm_test

%.o: %.cc $(DEPS)	# for .cc files
	$(CC) -c $(CXXFLAGS) $< -o $@

%.o: %.cu $(DEPS)	# for .cu files
	$(CC) -c $(CXXFLAGS) $< -o $@

gemm_test: $(OBJS)
	$(CC) $(CXXFLAGS) $^ -o gemm_test

clean:
	rm -f *.o gemm_test