workload_generator/AIOB_simAI_workload_generator.py [249:263]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            self.workload.append(Work_Item(name="moe_grad_norm1", forward_compute_time=default_compute_time,
                                    forward_comm = "NONE", forward_comm_size= 0,
                                    backward_compute_time=default_compute_time, backward_comm="NONE", backward_comm_size=0,
                                    dp_compute_time=default_compute_time, dp_comm="ALLGATHER_DP_EP", dp_comm_size=2*moe_param_count
                                    ))
            self.workload.append(Work_Item(name="moe_grad_norm2", forward_compute_time=default_compute_time,
                                    forward_comm = "NONE", forward_comm_size= 0,
                                    backward_compute_time=default_compute_time, backward_comm="NONE", backward_comm_size=0,
                                    dp_compute_time=default_compute_time, dp_comm="REDUCESCATTER_DP_EP", dp_comm_size=4*moe_param_count
                                    ))
        for _ in range(self.ga_num):
            for layer in layers:
                name = layer.layer_name
                forward_comm = backward_comm = backward_comm_2 = "NONE"
                forward_comm_size = tp_comm_size
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



workload_generator/AIOB_simAI_workload_generator.py [596:610]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            self.workload.append(Work_Item(name="moe_grad_norm1", forward_compute_time=default_compute_time,
                                    forward_comm = "NONE", forward_comm_size= 0,
                                    backward_compute_time=default_compute_time, backward_comm="NONE", backward_comm_size=0,
                                    dp_compute_time=default_compute_time, dp_comm="ALLGATHER_DP_EP", dp_comm_size=2*moe_param_count
                                    ))
            self.workload.append(Work_Item(name="moe_grad_norm2", forward_compute_time=default_compute_time,
                                    forward_comm = "NONE", forward_comm_size= 0,
                                    backward_compute_time=default_compute_time, backward_comm="NONE", backward_comm_size=0,
                                    dp_compute_time=default_compute_time, dp_comm="REDUCESCATTER_DP_EP", dp_comm_size=4*moe_param_count
                                    ))
        for _ in range(self.ga_num):
            for layer in layers:
                name = layer.layer_name
                forward_comm = backward_comm = backward_comm_2 = "NONE"
                forward_comm_size = tp_comm_size
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -