Hi,
I think the runtime support here (https://github.com/apache/incubator-tvm/pull/3554) is for uop and instructions sync via PCIe. However, if we want to run a full network (e.g., Resnet), we're still missing layer-wise synchronization/device_copy if two adjacent layers are resident in different devices.  For example, in the above figure, we have to auto-insert a *device_copy* op between maxpool and conv2d. --- [Visit Topic](https://discuss.tvm.ai/t/rfc-vta-support-for-cloud-devices-opencl-compatible/6676/22) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/e42b1966b3e313c63d9bc539f9d5a2b7bc6c880565d9e0e928256312d758e328).
