Method and system for improving boot process of a memory using enhanced DFE training technique
Various example embodiments are directed to techniques for a booting process of a memory device using a Decision Feedback Equalizer (DFE) training technique. A method may include predicting one or more DFE tap values based on a plurality of configuration parameters of the memory device, determining an accuracy level of the predicted one or more DFE tap values based on a signal processed using the predicted one or more DFE tap values, and in response to the accuracy level of the predicted one or more DFE tap values being above an accuracy threshold value, setting a value of a prediction flag as TRUE, validating a plurality of eye margins of the signal processed using the predicted DFE tap values, storing the predicted DFE tap values based on results of the validation, and performing a subsequent boot process of the memory device using the predicted DFE tap values.
1 . A method for booting a memory device using a Decision Feedback Equalizer (DFE) training technique, the method comprising:
predicting one or more DFE tap values based on a plurality of configuration parameters of the memory device;
determining an accuracy level of the predicted one or more DFE tap values based on a signal processed using the predicted one or more DFE tap values and the signal processed using a set of comparative DFE tap values obtained from a trained machine learning (ML) model; and
in response to the accuracy level of the predicted one or more DFE tap values being above an accuracy threshold value,
setting a value of a prediction flag as TRUE,
validating a plurality of eye margins of the signal processed using the predicted one or more DFE tap values,
storing the predicted one or more DFE tap values based on results of the validation, and
performing a subsequent boot process of the memory device using the predicted one or more DFE tap values.
2 . The method as claimed in claim 1 , wherein the plurality of configuration parameters comprises one or more of:
alternating current (AC) parameters, direct current (DC) parameters, total number of Dual In-line Memory Modules (DIMMs) in the memory device, size of the DIMMs, or any combinations thereof.
3 . The method as claimed in claim 1 , wherein the validating the plurality of eye margins further comprises:
determining whether the plurality of eye margins is within an eye margin threshold range.
4 . The method as claimed in claim 3 , wherein in response to the plurality of eye margins not being within the eye margin threshold range, the method further comprises:
setting the value of the prediction flag as FALSE.
5 . The method as claimed in claim 1 , wherein the memory device is a Double Data Rate (DDR) 5 Dynamic Random Access Memory (DRAM).
6 . A system for booting a memory device using a Decision Feedback Equalizer (DFE) training technique, comprising:
processing circuitry configured to:
predict one or more DFE tap values based on a plurality of configuration parameters of the memory device;
determine an accuracy level of the predicted one or more DFE tap values based on a signal processed using the predicted one or more DFE tap values and the signal processed using a set of comparative DFE tap values obtained from a trained machine learning (ML) model; and
in response to the accuracy level being above an accuracy threshold value,
set a value of a prediction flag as TRUE,
validate a plurality of eye margins of the signal processed using the predicted one or more DFE tap values,
store the predicted one or more DFE tap values based on results of the validation, and
perform a subsequent boot process of the memory device using the predicted one or more DFE tap values.
7 . The system as claimed in claim 6 , wherein the plurality of configuration parameters comprises one or more of:
alternating current (AC) parameters, direct current (DC) parameters, total number of Dual In-line Memory Modules (DIMMs) in the memory device, and a size of the DIMMs.
8 . The system as claimed in claim 6 , wherein in response to the accuracy level being above the accuracy threshold value, the processing circuitry is further configured to:
determine whether the plurality of eye margins is within an eye margin threshold range.
9 . The system as claimed in claim 8 , wherein in response to the plurality of eye margins not being within the eye margin threshold range, the processing circuitry is further configured to:
set the value of the prediction flag as FALSE.
10 . The system as claimed in claim 6 , wherein the memory device is a Double Data Rate (DDR) 5 Dynamic Random Access Memory (DRAM).