Forward error correction mechanism for peripheral component interconnect-express (PCI-e)
Aspects of the embodiments are directed to systems, methods, and devices that can activate forward error correction (FEC) based on the channel loss of a channel. The channel's loss can be characterized as a high loss channel if the channel loss exceeds a predetermined threshold value. For channels with high loss and for those that operate at high data rates (e.g., data rates commensurate with PCIe Gen 4 or Gen 5), FEC can be activated so that the channels can achieve higher data rates.
1. An apparatus comprising:
means to identify, by a port, an indication of a channel loss of a channel;
means to identify, by the port, an indication of whether a receiver associated with the port desires forward error correction (FEC) for the channel;
means to identify, by the port based on the indication of the channel loss and the indication of whether the receiver desires FEC, whether latency associated with the FEC is above an acceptability threshold; and
means to identify, by the port based on whether the latency is above the acceptability threshold, whether to advertise a Gen 4 or Gen 5 peripheral component interconnect-express (PCI-e) data rate.
2. The apparatus of claim 1 , whether the channel latency is related to a distance between two components within the channel.
3. The apparatus of claim 2 , wherein one of the components of the two components is a retimer.
4. The apparatus of claim 1 , wherein the indication of the channel loss is a bit that indicates that the channel loss above 30 decibels (dB).
5. The apparatus of claim 1 , wherein error correction code is transmitted with data blocks at predetermined intervals.
6. The apparatus of claim 5 , wherein error correction code is embedded into every nth data block.
7. The apparatus of claim 5 , wherein error correction code is transmitted after every nth data block as separate symbols than the nth data block.
8. The apparatus of claim 1 , further comprising means to correct, by the port, bit flips of ordered sets during L0 and the transition between ordered sets and data blocks based on redundancy.
9. A method comprising:
identifying, by a port, an indication of a channel loss of a channel;
determining that the channel loss of the channel is higher than a predetermined threshold value;
determining that the channel is to operate at a high data rate; and
activating forward error correction (FEC) for the channel based on the determination that the channel loss is above a predetermined threshold and the determination that the channel is to operate at a high data rate.
10. The method of claim 9 , further comprising:
identifying that a latency associated with the FEC is above a threshold latency value; and
advertising, by the port based on whether the latency is above the threshold latency value, a Gen 4 or Gen 5 peripheral component interconnect-express (PCI-e) data rate.
11. The method of claim 10 , wherein the channel latency is related to a distance between two components within the channel.
12. The method of claim 9 , wherein the predetermined threshold value for channel loss is 30 decibels (dB).
13. The method of claim 9 , further comprising transmitting one or more error correcting code bits embedded with a data block transmitted at predetermined intervals.
14. The method of claim 9 , further comprising transmitting one or more error correcting code bits after every nth data block as a separate symbol from the nth data block.
15. One or more non-transitory computer-readable media comprising instructions to cause an apparatus, upon execution of the instructions by one or more processors of the apparatus, to:
identify, by a port, an indication of a channel loss of a channel;
identify, by the port, an indication of whether a receiver associated with the port desires forward error correction (FEC) for the channel;
identify, by the port based on the indication of the channel loss and the indication of whether the receiver desires FEC, whether latency associated with the FEC is above an acceptability threshold; and
identify, by the port based on whether the latency is above the acceptability threshold, whether to advertise a Gen 4 or Gen 5 peripheral component interconnect-express (PCI-e) data rate.
16. The one or more non-transitory computer-readable media of claim 15 , wherein the channel latency is related to a distance between two components within the channel.
17. The one or more non-transitory computer-readable media of claim 15 , wherein one of the components of the two components is a retimer.
18. The one or more non-transitory computer-readable media of claim 15 , wherein the indication of the channel loss is a bit that indicates whether the channel loss is less than 30 decibels (dB) or between 30 and 35 dB.
19. The one or more non-transitory computer-readable media of claim 15 and/or some other example herein, wherein the instructions are further to correct, by the port, bit flips of ordered sets during L0 and the transition between ordered sets and data blocks based on redundancy.
20. An apparatus comprising:
a channel that includes a plurality of components; and
a port associated with the channel, the port to:
identify an indication of a channel loss of a channel;
determine that the channel loss of the channel is higher than a predetermined threshold value;
determine that the channel is to operate at a high data rate; and
activate forward error correction (FEC) for the channel based on the determination that the channel loss is above a predetermined threshold and the determination that the channel is to operate at a high data rate.
21. The apparatus of claim 20 , the port to:
identify that a latency associated with the FEC is above a threshold latency value; and
advertise, by the port based on whether the latency is above the threshold latency value, a Gen 4 or Gen 5 peripheral component interconnect-express (PCI-e) data rate.