[refactor] move tests to tests/, add pytest functions and main() entrypoints

- Moved src/tests/ → tests/
- Added test_* functions with assertions to script-style test files
- Added main() to each so IDEs offer it as a separate run target from pytest
- Fixed cupy_test.py: remove spurious x_gpu += x_cpu, fix duplicate xlabel

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

tests/cupy_test.py

@@ -0,0 +1,107 @@
+import time
+
+import numpy as np
+import cupy as cp
+
+from matplotlib import pyplot as plt
+
+def warmup_cupy():
+	a = cp.random.random((10,10))
+	b = cp.random.random((10,10))
+	_ = cp.dot(a, b)
+
+def calc_cpu(a: np.array, b: np.array):
+	return np.dot(a, b)
+
+def calc_gpu(a: np.array, b: np.array):
+	return cp.dot(a, b)
+
+def perf_test_2():
+	### Numpy and CPU
+	print("Creation")
+	s = time.time()
+	x_cpu = np.ones((1000, 1000, 1000))
+	e = time.time()
+	time_cpu = e - s
+	s = time.time()
+	x_gpu = cp.ones((1000, 1000, 1000))
+	cp.cuda.Stream.null.synchronize()
+	e = time.time()
+	time_gpu = e - s
+	print(f"Speedup: {time_cpu/time_gpu}")
+
+	### Numpy and CPU
+	print("Multiply with constant")
+	s = time.time()
+	x_cpu *= 5
+	e = time.time()
+	time_cpu = e - s
+	s = time.time()
+	x_gpu *= 5
+	cp.cuda.Stream.null.synchronize()
+	e = time.time()
+	time_gpu = e - s
+	print(f"Speedup: {time_cpu/time_gpu}")
+
+	### Numpy and CPU
+	print("Multiply with constant, Square, Square")
+	s = time.time()
+	x_cpu *= 5
+	x_cpu *= x_cpu
+	x_cpu += x_cpu
+	e = time.time()
+	time_cpu = e - s
+	s = time.time()
+	x_gpu *= 5
+	x_gpu *= x_gpu
+	x_gpu += x_gpu
+	cp.cuda.Stream.null.synchronize()
+	e = time.time()
+	time_gpu = e - s
+	print(f"Speedup: {time_cpu/time_gpu}")
+
+def perf_test_1():
+	n_values = []
+	np_times = []
+	cp_times = []
+	ratio_times = []
+
+	for N in range(100, 5100, 100):
+		a_np = np.random.rand(1024, N)
+		b_np = np.random.rand(N, 1024)
+
+		a_cp = cp.asarray(a_np)
+		b_cp = cp.asarray(b_np)
+
+		start_time = time.time()
+		c_np = calc_cpu(a_np, b_np)
+		end_time = time.time()
+		numpy_time = end_time - start_time
+
+		start_time = time.time()
+		c_cp = calc_gpu(a_cp, b_cp)
+		c_np = cp.asnumpy(c_cp)
+		end_time = time.time()
+		cupy_time = end_time - start_time
+
+		n_values.append(N)
+		np_times.append(numpy_time)
+		cp_times.append(cupy_time)
+		ratio_times.append(numpy_time/cupy_time)
+
+	plt.plot(n_values, np_times, label='numpy time')
+	plt.plot(n_values, cp_times, label='cupy time')
+	plt.plot(n_values, ratio_times, label='numpy/cupy time')
+	plt.xlabel("Matrix size [N]")
+	plt.ylabel("Time [s]")
+	plt.title("Performance numpy vs cupy")
+	plt.grid()
+	plt.legend()
+	plt.show()
+
+def main():
+	warmup_cupy()
+	perf_test_2()
+
+if __name__ == "__main__":
+	main()