Method and apparatus for programming analog neural memory in a deep learning artificial neural network
Numerous embodiments of programming systems and methods for use with a vector-by-matrix multiplication (VMM) array in an artificial neural network are disclosed. Selected cells thereby can be programmed with extreme precision to hold one of N different values.
1. A method of programming a selected memory cell in a vector-by-matrix multiplication array comprising rows and columns of flash memory cells, the method comprising:
programming a plurality of flash memory cells in the array;
partially erasing the plurality of flash memory cells in the array;
performing a first program operation on a selected cell within the plurality of flash memory cells, wherein a first level of electric charge is stored on a floating gate of the selected cell;
performing a second program operation on the selected cell wherein an additional level of electric charge is stored on the floating gate of the selected cell; and
repeating the second program operation until a desired level of electric charge is stored on the selected cell or until the second program operation is performed a maximum number of times.
2. The method of claim 1 , wherein a verify step is performed after each second program operation, and the repeating step occurs if the verify step yields a first result and the repeating step does not occur if the verify step yields a second result.
3. The method of claim 1 , further comprising a hard program step for un-used memory cells.
4. The method of claim 1 , wherein the first program operation and the second program operation utilize pulse modulation.
5. The method of claim 1 , wherein the first program operation and the second program operation utilize program current modulation.
6. The method of claim 1 , wherein the first program operation and the second program operation utilize pulse modulation for a selected memory cell and constant program pulse for another selected memory cell.
7. The method of claim 1 , wherein the first program operation and the second program operation utilize high voltage level modulation.
8. The method of claim 2 , wherein the verify step comprises comparing a current drawn by the selected cell with a current drawn by a reference matrix.
9. The method of claim 1 , wherein the memory cell is a split gate memory cell.
10. The method of claim 1 , wherein the memory cell is a stacked gate memory cell.
11. The method of claim 1 , wherein the reference matrix comprises a shared control gate and a shared erase gate.
12. The method of claim 1 , wherein the reference matrix comprises a shared control gate and a separate erase gate for each reference cell.
13. The method of claim 1 , wherein the reference current is combined from a plurality of constant currents, increment currents, and difference currents from a reference matrix.