Non-volatile memory device for fault tolerant data

Error detection/correction and fault detection/recovery – Pulse or data error handling

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

371 211, 365201, G06F 1200

Patent

active

059548282

DESCRIPTION:

BRIEF SUMMARY
BACKGROUND OF THE INVENTION

1. Field of the Invention
The present invention relates to non-volatile memory devices based on floating gate memory cells; and more particularly to flash EPROM or EEPROM integrated circuits adapted for storing fault tolerant data.
2. Description of Related Art
Non-volatile, integrated circuit memory devices based on floating gate transistors include devices known as electrically programmable read only memory EPROM, electrically erasable and programmable read only memory, EEPROM, and recently so-called flash memory. As the density of the floating gate devices has increased, making them more cost-effective, and as the programming and erasing speed has increased, this type of non-volatile memory has gained significant popularity. However, the process of programming data in a non-volatile memory device based on a floating gate, is still a relatively slow process. The process involves moving charge either into or out of the floating gate of the memory cell, in order to establish a data pattern in the array. Where the floating gate of a given cell is charged up with a population of electrons, the turn on threshold for the memory cell increases above the read gate voltage. Discharging the electrons from the floating gate moves the turn on threshold down below the read gate voltage. Thus, data may be written into the non-volatile memory array by processes which charge and discharge the floating gates.
The mechanisms for charging and discharging the floating gates in these devices include so-called hot electron injection, and so-called Fowler-Nordheim tunneling. Hot electron injection is used for increasing the charge in the floating gate by connecting the gate and the drain to a relatively high voltage, and the source to a relatively low voltage. Hot electrons in the resulting channel current are injected across the thin oxide which separates the floating gate from the channel. This results in an increase in charge in the floating gate. Alternatively, so-called Fowler-Nordheim tunneling can be used to program or erase the cell. The tunneling mechanism operates by establishing a large potential between the gate and the drain, source, or channel. The Fowler-Nordheim tunneling effect results in charge tunneling through the thin oxide which isolates the floating gate. The Fowler-Nordheim tunneling process is relatively slow compared to the hot electron injection process. However, hot electron injection utilizes higher current. Further, hot electron injection cannot be used for discharging the floating gate. Rather, the tunneling mechanism is most often used for the discharging process.
The tunneling and hot electron injection mechanisms used for programming and erasing cells in a floating gate device do not affect each cell in the array identically. Therefore, the programming and erasing functions on modern floating gate devices include erase and program verify algorithms. After a programming or erasing operation, the memory subject of the operation is verified. If any cell fails the verify process, then a re-program or re-erase process is executed. This process is re-tried a large number of times (as many as 1000 times or more in some devices) in order to ensure that all of the data in the array is accurately stored, and to prevent having to discard floating gate devices which would otherwise operate satisfactorily, except for the number of retries required to program or erase the cells.
The program and erase verify procedures involved in these devices are relatively time consuming. Therefore, the use of flash memory or other floating gate memory devices for real time storage applications has been limited. In a real time application, an incoming stream may supply more data than the flash memory device is capable of storing without being overrun. Therefore, real time applications in the past have relied on dynamic RAM, SRAM, or other reliable fast memory techniques. However, these prior art memory techniques are not non-volatile, and data can be lost if there is an interruption in power.


REFERENCES:
patent: 3814922 (1974-06-01), Nibby et al.
patent: 4414665 (1983-11-01), Kimura et al.
patent: 4456995 (1984-06-01), Ryan
patent: 4498151 (1985-02-01), Henry
patent: 4527251 (1985-07-01), Nibby, Jr. et al.
patent: 4736373 (1988-04-01), Schmidt
patent: 4958352 (1990-09-01), Noguchi et al.
patent: 5200959 (1993-04-01), Gross et al.
patent: 5297148 (1994-03-01), Harari, et al.
patent: 5317573 (1994-05-01), Bula et al.
patent: 5361227 (1994-11-01), Tanaka
patent: 5369616 (1994-11-01), Wells et al.
patent: 5416782 (1995-05-01), Wells et al.
patent: 5418752 (1995-05-01), Harari et al.
patent: 5438573 (1995-08-01), Mangan et al.
patent: 5666480 (1997-09-01), Leung et al.
Intel, 28F016SA 16 MBIT (1 MBIT .times.16, 2 MBIT .times.8) Flashfile Memory, 3-6 -3-21, Oct. 1993.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Non-volatile memory device for fault tolerant data does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Non-volatile memory device for fault tolerant data, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Non-volatile memory device for fault tolerant data will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-75996

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.