Can user-level protocols take advantage of multi-CPU NICs?

User-level protocols and their implementations on programmable network interface cards (NICs) have been alleviating the communication bottleneck for high speed interconnects. Most of the user-level protocols developed so far have been based on single-CPU NICs. One of the more popular current generation Gigabit Ethernet NICs includes two CPUs, though. This raises an open challenge whether performance of user-level protocols can be improved by taking advantage of a multi-CPU NIC. In this paper, we anal the intrinsic issues associated with such a challenge and explore different parallelization and pipelining schemes to enhance the performance of our earlier developed EMP protocol for single-CPU Alteon NICs. Performance evaluation results indicate that parallelizing the receive path of the protocol can deliver 964 Mbps of bandwidth, close to the maximum achievable on Gigabit Ethernet. This scheme also delivers up to 8% improvement in latency for a range of message sizes. Parallelizing the send path leads to 17% improvement in bidirectional bandwidth.