test_cuda.py 文件源码

def test_broadcast_coalesced(self):
        numel = 5
        num_bytes = numel * 8
        tensors = [
            torch.randn(numel).long().cuda(),
            torch.randn(numel).cuda(),
            torch.randn(numel).long().cuda(),
            torch.randn(numel).long().cuda(),
            torch.randn(numel * 2).int().cuda(),  # int is 2x shorter
            torch.randn(numel).cuda(),
        ]

        b_tensors = [comm.broadcast(t, (0, 1)) for t in tensors]
        for (_, bt), t in zip(b_tensors, tensors):
            self.assertEqual(bt.get_device(), 1)
            self.assertEqual(bt, t)
            self.assertIsInstance(bt, type(t))

        bc_tensors = comm.broadcast_coalesced(tensors, (0, 1), buffer_size=num_bytes * 5 // 2)
        bc_tensors_t = list(zip(*bc_tensors))
        self.assertEqual(b_tensors, bc_tensors_t)
        for (_, bt), (_, bct) in zip(b_tensors, bc_tensors_t):
            self.assertEqual(bt.get_device(), bct.get_device())
            self.assertIsInstance(bct, type(bt))