Read threshold estimation systems and methods using deep learning
A controller estimates optimal read threshold values for a memory device using deep learning. The memory device includes multiple pages coupled to select word lines in a memory region. The controller performs multiple read operations on a select type of page for each word line using multiple read threshold sets, obtains fail bit count (FBC) information associated with each read operation, and determines an optimal read threshold set for each word line based on the FBC information. When optimal read threshold sets for the select word lines are different each other, the controller predicts a best read threshold set using the optimal read threshold sets.
1. A memory system comprising:
a memory device including multiple pages coupled to select word lines in a memory region; and
a controller, coupled to the memory device, suitable for:
performing multiple read operations on a select type of page for each word line using multiple read threshold sets;
obtaining fail bit count (FBC) information associated with the multiple read operations, the FBC information including multiple FBC values corresponding to the multiple read threshold sets;
selecting a lowest FBC value among the multiple FBC values;
determining, using a neural network, a read threshold set corresponding to the lowest FBC value as an optimal read threshold set for each word line, wherein the neural network utilizes suboptimal FBC information in addition to the optimal read threshold set to predict the optimal read threshold set; and
when optimal read threshold sets for the select word lines are different each other, predicting, using the neural network, a best read threshold set using the optimal read threshold sets.
2. The memory system of claim 1 , wherein the memory region includes a block or a die.
3. The memory system of claim 1 , wherein the select word lines includes two adjacent word lines.
4. The memory system of claim 1 , wherein the multiple pages include a most significant bit (MSB) page, a center significant bit (CSB) page and a least significant bit (LSB) page.
5. The memory system of claim 4 , wherein the multiple pages is programmed using Gray coding.
6. The memory system of claim 5 , wherein the select type of page includes the LSB page.
7. The memory system of claim 6 , wherein each read threshold set includes a pair of first and second read thresholds.
8. The memory system of claim 1 , wherein the best read threshold set is predicted using an average of the optimal read threshold sets.
9. The memory system of claim 1 , wherein the controller predicts the best read threshold set using the optimal read threshold sets and operating conditions including at least one of endurance of memory device, data retention, read disturbance, age of the memory device, or operating temperature of the memory device.
10. The memory system of claim 1 , wherein the controller transmits a set command to the memory device to select the best read threshold set from among the optimal read threshold sets.
11. A method for operating a memory system, which includes a memory device including multiple pages coupled to select word lines in a memory region, and a controller coupled to the memory device, the method comprising:
performing multiple read operations on a select type of page for each word line using multiple read threshold sets;
obtaining fail bit count (FBC) information associated with the read operations, the FBC information including multiple FBC values corresponding to the multiple read threshold sets;
selecting a lowest FBC value among the multiple FBC values;
determining, using a neural network, a read threshold set corresponding to the lowest FBC value as an optimal read threshold set for each word line based on the FBC information, wherein the neural network utilizes suboptimal FBC information in addition to the optimal read threshold set to predict the optimal read threshold set; and
when optimal read threshold sets for the select word lines are different each other, predicting, using the neural network, a best read threshold set using the optimal read threshold sets.
12. The method of claim 11 , wherein the memory region includes a block or a die.
13. The method of claim 11 , wherein the select word lines includes two adjacent word lines.
14. The method of claim 11 , wherein the multiple pages include a most significant bit (MSB) page, a center significant bit (CSB) page and a least significant bit (LSB) page.
15. The method of claim 14 , wherein the multiple pages is programmed using Gray coding.
16. The method of claim 15 , wherein the select type of page includes the LSB page.
17. The method of claim 16 , wherein each read threshold set includes a pair of first and second read thresholds.
18. The method of claim 11 , wherein the best read threshold set is predicted using an average of the optimal read threshold sets.
19. The method of claim 11 , wherein the predicting of the best read threshold set includes:
predicting the best read threshold set using the optimal read threshold sets and operating conditions including at least one of endurance of the memory device, data retention, read disturbance, age of the memory device, or operating temperature of the memory device.
20. The method of claim 11 , further comprising:
transmitting a set command to the memory device to select the best read threshold set from among the optimal read threshold sets.