def test_nobroadcast_fp16():
context.set_context(mode=context.GRAPH_MODE, device_target='GPU')
np.random.seed(42)
x1_np = np.random.rand(10, 20).astype(np.float16)
x2_np = np.random.rand(10, 20).astype(np.float16)
output_ms = P.Minimum()(Tensor(x1_np), Tensor(x2_np))
output_np = np.minimum(x1_np, x2_np)
assert np.allclose(output_ms.asnumpy(), output_np)
output_ms = P.Maximum()(Tensor(x1_np), Tensor(x2_np))
output_np = np.maximum(x1_np, x2_np)
assert np.allclose(output_ms.asnumpy(), output_np)
output_ms = P.Greater()(Tensor(x1_np), Tensor(x2_np))
output_np = x1_np > x2_np
assert np.allclose(output_ms.asnumpy(), output_np)
output_ms = P.Less()(Tensor(x1_np), Tensor(x2_np))
output_np = x1_np < x2_np
assert np.allclose(output_ms.asnumpy(), output_np)
output_ms = P.Pow()(Tensor(x1_np), Tensor(x2_np))
output_np = np.power(x1_np, x2_np)
assert np.allclose(output_ms.asnumpy(), output_np)
output_ms = P.RealDiv()(Tensor(x1_np), Tensor(x2_np))
output_np = x1_np / x2_np
assert np.allclose(output_ms.asnumpy(), output_np)
output_ms = P.Mul()(Tensor(x1_np), Tensor(x2_np))
output_np = x1_np * x2_np
assert np.allclose(output_ms.asnumpy(), output_np)
output_ms = P.Sub()(Tensor(x1_np), Tensor(x2_np))
output_np = x1_np - x2_np
assert np.allclose(output_ms.asnumpy(), output_np)
output_ms = P.DivNoNan()(Tensor(x1_np), Tensor(x2_np))
output_np = x1_np / x2_np
assert np.allclose(output_ms.asnumpy(), output_np)
x2_np_zero = np.zeros_like(x2_np)
output_ms = P.DivNoNan()(Tensor(x1_np), Tensor(x2_np_zero))
assert np.allclose(output_ms.asnumpy(), x2_np_zero)
output_ms = P.Mod()(Tensor(x1_np), Tensor(x2_np))
output_np = np.fmod(x1_np, x2_np)
assert np.allclose(output_ms.asnumpy(), output_np)
output_ms = P.FloorMod()(Tensor(x1_np), Tensor(x2_np))
output_np = np.mod(x1_np, x2_np)
assert np.allclose(output_ms.asnumpy(), output_np)
def __init__(self):
super(ModNet, self).__init__()
self.mod = P.Mod()
def __init__(self, strategy1, strategy2):
super().__init__()
self.matmul = P.MatMul().shard(strategy1)
self.mod = P.Mod().shard(strategy2)
