Artificial intelligence augmented iterative product decoding
A method for product decoding within a data storage system includes receiving data to be decoded within a first decoder; performing a plurality of decoding iterations to decode the data utilizing a first decoder and a second decoder; and outputting fully decoded data based on the performance of the plurality of decoding iterations. Each of the plurality of decoding iterations includes (i) decoding the data with the first decoder operating at a first decoder operational mode to generate once decoded data; (ii) sending the once decoded data from the first decoder to the second decoder; (iii) receiving error information from the first decoder with an artificial intelligence system; (iv) selecting a second decoder operational mode based at least in part on the error information that is received by the artificial intelligence system; and (v) decoding the once decoded data with the second decoder operating at the second decoder operational mode to generate twice decoded data; and outputting fully decoded data based on the performance of the plurality of decoding iterations.
1. A method for product decoding within a data storage system, the method comprising:
receiving data to be decoded within a first decoder;
performing a plurality of decoding iterations to decode the data utilizing a first decoder and a second decoder, each of the plurality of decoding iterations including:
(i) decoding the data with the first decoder operating at a first decoder operational mode to generate once decoded data;
(ii) sending the once decoded data from the first decoder to the second decoder;
(iii) receiving error information from the first decoder with an artificial intelligence system;
(iv) selecting a second decoder operational mode based at least in part on the error information that is received by the artificial intelligence system; and
(v) decoding the once decoded data with the second decoder operating at the second decoder operational mode to generate twice decoded data; and
outputting fully decoded data based on the performance of the plurality of decoding iterations.
2. The method of claim 1 wherein the step of selecting includes the second decoder operational mode being based at least in part on side information from the first decoder and the error information that is received by the artificial intelligence system.
3. The method of claim 1 wherein the step of decoding the data with the first decoder includes the first decoder operational mode being updated for each of the plurality of decoding iterations.
4. The method of claim 1 further comprising running the artificial intelligence system to feed a correction block and a symbol classifier to determine the first decoder operational mode for the first decoder and the second decoder operational mode for the second decoder.
5. The method of claim 1 wherein for each of the plurality of decoding iterations, the method further comprises receiving second error information from the second decoder with the artificial intelligence system; and wherein the step of selecting includes selecting the second decoder operational mode based at least in part on the error information that is received from the first decoder and the second error information that is received from the second decoder by the artificial intelligence system.
6. The method of claim 1 further comprising processing the data with a detector prior to decoding the data with the first decoder.
7. The method of claim 6 further comprising generating channel reliability information with a channel reliability estimator based on output from the detector; and receiving the channel reliability information with the artificial intelligence system to supplement the error information that is received by the artificial intelligence system.
8. The method of claim 1 wherein the step of receiving error information includes the artificial intelligence system being a joint deep neural network.
9. The method of claim 8 further comprising adding an extra layer to the joint deep neural network for each subsequent decoding iteration.
10. The method of claim 1 wherein for each of the plurality of decoding iterations, the method further comprises assigning one of “Error”, “Erasure” and “Correct” with the first decoder for a state of the once decoded data.
11. The method of claim 10 wherein for each of the plurality of decoding iterations, the method further comprises assigning an accuracy to the decoding of one accurate erasure information, false erasure information, unlabeled error and correctly labeled good data.
12. The method of claim 1 wherein the step of decoding the data with the first decoder includes the first decoder being a C1 decoder; and wherein the step of sending the once decoded data from the first decoder to the second decoder includes the second decoder being a C2 decoder.
13. A data storage system comprising:
a product decoding system including:
a first decoder that is configured to receive data, the first decoder being further configured to operate at a first decoder operational mode to decode the data to generate once decoded data;
a second decoder that is configured to receive the once decoded data, the second decoder being further configured to operate at a second decoder operational mode to decode the once decoded data to generate twice decoded data; and
an artificial intelligence system that is configured to receive error information from the first decoder;
wherein the product decoding system is configured to perform a plurality of decoding iterations to decode the data;
wherein the second decoder operational mode is selected based at least in part on the error information that is received by the artificial intelligence system; and
wherein the product decoding system is configured to output fully decoded data based on the performance of the plurality of decoding iterations.
14. The data storage system of claim 13 wherein the second decoder operational mode is selected based at least in part on side information from the first decoder and the error information that is received by the artificial intelligence system.
15. The data storage system of claim 13 wherein the first decoder operational mode is updated for each of the plurality of decoding iterations.
16. The data storage system of claim 13 wherein the artificial intelligence system feeds a correction block and a symbol classifier to determine the first decoder operational mode for the first decoder and the second decoder operational mode for the second decoder.
17. The data storage system of claim 13 wherein the artificial intelligence system is further configured to receive second error information from the second decoder; and wherein the second decoder operational mode is selected based at least in part on the error information that is received from the first decoder and the second error information that is received from the second decoder by the artificial intelligence system.
18. The data storage system of claim 13 further comprising a detector that is configured to process the data before the data is decoded with the first decoder.
19. The data storage system of claim 13 wherein the artificial intelligence system is a joint deep neural network.
20. The data storage system of claim 13 wherein the first decoder is a C1 decoder; and wherein the second decoder is a C2 decoder.