Framework for balancing robustness and latency during collection of statistics from soft reads

Patent metadata

Field	Value
Publication number	US-9645763-B2
Application number	US-201414181893-A
Country	US
Kind code	B2
Filing date	Feb 17, 2014
Priority date	Jan 13, 2014
Publication date	May 9, 2017
Grant date	May 9, 2017

Abstract

An apparatus includes a plurality of memory devices and a controller. The controller is coupled to the plurality of memory devices and configured to store data in the plurality of memory devices using units of super-blocks. Each super-block comprises a block from each of the plurality of memory devices and the controller balances time efficiency and robustness during collection of statistics from soft reads of each super-block.

First claim

The invention claimed is:

1. An apparatus comprising:
a memory comprising a plurality of memory devices; and
a controller coupled to the memory and configured to process a plurality of read/write operations to/from the memory, store data in the plurality of memory devices using units of super-blocks, and generate a number of unique weight statistics in a single read operation by reading a number of dies within a super-block with dissimilar read reference voltages, wherein each super-block comprises a block from a die of each of the plurality of memory devices, and the number of unique weight statistics are represented by 3-tuple vectors of weights.

2. The apparatus according to claim 1 , wherein the controller is further configured to balance time efficiency and robustness during collection of statistics from soft reads of each super-block by setting a number of parameters of an adaptive tracking routine.

3. The apparatus according to claim 2 , wherein the parameters comprise a first parameter defining a number of dies in a group and a second parameter defining a number of groups.

4. The apparatus according to claim 3 , wherein the adaptive tracking routine is configured to average a number of page weights collected from within each group.

5. The apparatus according to claim 1 , wherein the controller is further configured to perform one or more of:
averaging page weights on a component weight basis; and
choosing pages across the dies of each super-block such that the pages are distributed to average out page-to-page variation.

6. The apparatus according to claim 1 , wherein the controller is further configured to split the number of dies in each super-block into two sets and collect page weights for upper pages from one of the two sets and page weights for lower pages from the other of the two sets.

7. The apparatus according to claim 6 , wherein:
across all lower page reads, MSB related voltages are set to default or previously tracked read reference voltages;
across all upper page reads, LSB related voltages are set to default or previously tracked read reference voltages; and
averaging and interleaving are applied within each set.

8. The apparatus according to claim 1 , wherein the memory and the controller are part of a solid state drive (SSD).

9. A method of collecting statistics from soft reads of a flash memory comprising:
storing data in a plurality of flash memory devices using units of super-blocks, wherein each super-block comprises a block from a die of each of the plurality of flash memory devices; and
generating a number of unique weight statistics in a single read operation by reading a number of the dies within a super-block with dissimilar read reference voltages, wherein the number of unique weight statistics are represented by 3-tuple vectors of weights.

10. The method according to claim 9 , further comprising:
splitting the number of dies in each super-block into two sets to collect page weights for upper and lower pages.

11. The method according to claim 10 , wherein:
across all lower page reads, MSB related voltages are set to default or previously tracked read reference voltages;
across all upper page reads, LSB related voltages are set to default or previously tracked read reference voltages; and
averaging and interleaving are applied within each set.

12. The method according to claim 9 , further comprising:
choosing pages across the dies of each super-block such that the pages are distributed to average out page-to-page variation.

13. The method according to claim 9 , further comprising:
balancing time efficiency and robustness during collection of statistics from soft reads of each super-block by setting a number of parameters of an adaptive tracking routine.

14. The method according to claim 13 , wherein the parameters comprise a first parameter defining a number of dies in a group and a second parameter defining a number of groups in each super-block.

15. The method according to claim 14 , wherein the adaptive tracking routine is configured to average a number of page weights collected from within a group.

16. An apparatus comprising:
an interface configured to process a plurality of read/write operations to/from a memory comprising a plurality of memory devices; and
a control circuit configured to store data in the plurality of memory devices using units of super-blocks, balance time efficiency and robustness during collection of statistics from soft reads of each super-block, and generate a number of unique weight statistics in a single read operation by reading a number of dies within a super-block with dissimilar read reference voltages, wherein each super-block comprises a block from a die of each of the plurality of memory devices, and the number of unique weight statistics are represented by 3-tuple vectors of weights.

17. The apparatus according to claim 16 , wherein the control circuit is further configured to split the number of dies in each super-block into two sets and collect page weights for upper pages from one of the two sets and page weights for lower pages from the other of the two sets.

18. The apparatus according to claim 16 , wherein the interface and the control circuit are part of a solid state drive (SSD) controller.

Assignees

• Seagate Technology Llc

Inventors

• Sankaranarayanan Sundararajan
• Haratsch Erich F

Classifications

• G06F3/0653 Primary

  Monitoring storage devices or systems · CPC title

• G06F3/0679

  Non-volatile semiconductor memory device, e.g. flash memory, one time programmable memory [OTP] · CPC title

• G06F3/0688

  Non-volatile semiconductor memory arrays · CPC title

• G06F3/0611 Primary

  in relation to response time · CPC title

• G06F3/0655

  Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices · CPC title