With assumption that all Mellanox ConnectX-3 Pro EN features are covered by Mellanox ConnectX-3 Pro VPI, I'm interested on Mellanox ConnectX-3 Pro EN vs Intel XL710 comparison on http://www.mellanox.com/related-docs/whitepapers/CB_Intel_XL710.pdf. I'm focusing on the different of Overlay Networks on page 2 where states that Intel XL710 only do VXLAN offloading only on transmit (Tx). If I refer to "ethtool -k" result on https://www.spinics.net/lists/netdev/msg363599.html for ConnectX-3 Pro EN and Figure 11 on https://www.intel.com/content/dam/www/public/us/en/documents/technology-briefs/xl710-ethernet-controller-vxlan-technical-brief.pdf (page 15) for Intel XL710, I cannot see any different related to Receive (Rx) VXLAN offloading. I'm looking the status or configuration capture which show that different. Is ConnectX-3 Pro (VPI and/or EN) really have receive VXLAN offloading capability?
In order to validate receive VXLAN offload, you can configure the system by using 'ethtool' and settingg rx-checksumming and GRO on receive side, run the traffic and observe that receive packet size is bigger than MTU using wireshark/tcpdump on receiver side.