Methods of Managing Completion Space - 1.3 English

UltraScale+ Devices Integrated Block for PCI Express Product Guide (PG213)

Document ID
PG213
Release Date
2023-10-19
Version
1.3 English

A user application can choose one of five methods to manage receive-buffer completion space, as listed in Table C-4. For convenience, this discussion refers to these methods as LIMIT_FC, PACKET_FC, RCB_FC, and DATA_FC. Each method has advantages and disadvantages that you need to consider when developing the user application.

Table 1. Managing Receive Completion Space Methods
Method Description Advantage Disadvantage
LIMIT_FC Limit the total number of outstanding NP Requests Simplest method to implement in user logic Much Completion capacity goes unused
PACKET_FC Track the number of outstanding CplH and CplD credits; allocate and deallocate on a per-packet basis Relatively simple user logic; finer allocation granularity means less wasted capacity than LIMIT_FC As with LIMIT_FC, credits for an NP are still tied up until the request is completely satisfied
RCB_FC Track the number of outstanding CplH and CplD credits; allocate and deallocate on a per-RCB basis Ties up credits for less time than PACKET_FC More complex user logic than LIMIT_FC or PACKET_FC
DATA_FC Track the number of outstanding CplH and CplD credits; allocate and deallocate on a per-RCB basis Lowest amount of wasted capacity More complex user logic than LIMIT_FC, PACKET_FC, and RCB_FC