Abstract
A static random access memory (SRAM) has one or more arrays of memory cells, each array of memory cells activated in columns by a wordline. The activated column of memory cells asserts output data onto a plurality of bitlines coupled to output drivers. The SRAM includes a wordline controller generating a variable pulse width wordline which may be reduced sufficient to introduce memory read errors. Each of a high error rate, medium error rate, low error rate, and error-free rate is associated with a pulse width value generated by the wordline controller. A power consumption tradeoff exists between the wordline pulse width and consumed SRAM power. The wordline controller is thereby able to associate a wordline pulse width to an associated error rate for performing tasks which are insensitive to a high error rate or a medium error rate, which are specific to certain neural network training and inference using various NN data types.
Claims
1. A memory device comprising: a wordline controller configured to activate a wordline, the wordline controller causing a pulse width of the activated wordline to be associated with at least two data retrieval error rates; at least one memory array arranged as a sequence of columns of data, each column of data activated by a wordline, the activated wordline causing data to be asserted to bitlines coupled to an input/output driver; the wordline controller comprising a driver converting an address into an activated wordline associated with a column of data in the memory array, the activated wordline held active for an associated pulse width of a data error rate; the column of data in the memory array transferred through the bitlines to an output of the memory device, the controller selecting the width pulse for one of the at least two data retrieval error rates.
2. The memory device of claim 1 where the at least one memory array comprises a top memory cell array and a bottom memory cell array.
3. The memory device of claim 1 where the at least one memory array is configured to provide a high value address in a location which has a greater distance from the wordline controller than a low value address.
4. The memory device of claim 1 where the at least one memory array is configured to have a wordline length which is shorter for a most significant bit (MSB) than a least significant bit (LSB) for a column of data.
5. The memory device of claim 1 where the bitlines provide multiples of 8 bits of data.
6. The memory device of claim 1 where the bitlines provide 32 bits of data arranged as four eight bit bytes which are individually selectable as output data.
7. The memory device of claim 1 where the at least two error rates include error rates of approximately 10% MSB errors, approximately 1% MSB errors, approximately 0.1% MSB errors, and less than 0.00034% MSB errors.
8. The memory device of claim 7 where for a given error rate and a given address, an MSB error rate is less than a corresponding LSB error rate.
9. The memory device of claim 1 where the at least two error rates are a high error rate of 2% to 15% MSB error rate, a medium error rate of 0.5% to 2% MSB error rate, a low error rate of 0.005% to 0.5%, and an error free rate of less than 0.00034% error rate.
10. A memory array comprising: a top memory cell array accessed by activating a wordline which causes the top memory cell array to output data onto one or more bitlines; a bottom memory cell array accessed by activating a wordline which causes bottom memory cell array to output data onto one or more bitlines; a wordline controller configured to examine output data from the one or more bitlines, the wordline controller modifying a wordline pulse width until at least one of four error states occurs: a high error rate where an MSB of a memory cell has an error rate in the range of 2% to 15%, or approximately 10%; a moderate error rate where an MSB of a memory cell has an error rate in the range of .5% to 2%, or approximately 1%; a low error rate where an MSB of a memory cell has an error rate in the range of 0.005% to 0.5%, or approximately 0.1% an error-free error rate where an MSB of a memory cell has an error rate less than 0.00034%.
11. The memory device of claim 10 where the at least one memory array is configured to provide a high value address a greater distance from the wordline controller than a low value address.
12. The memory device of claim 10 where the at least one memory array is configured to have a wordline length which is shorter for a most significant bit (MSB) than a least significant bit (LSB) for a column of data.
13. The memory device of claim 10 where the bitlines provide multiples of 8 bits of data.
14. The memory device of claim 10 where the bitlines provide 32 bits of data arranged as four eight bit bytes which are individually selectable as output data.
15. The memory device of claim 10 where the at least two error rates include error rates of approximately 10% MSB errors, approximately 1% MSB errors, approximately 0.1% MSB errors, and less than 0.00034% MSB errors.
16. The memory device of claim 15 where for a given error rate and a given address, an MSB error rate is less than a corresponding LSB error rate.
17. The memory device of claim 10 where the at least two error rates are a high error rate of 2% to 15% MSB error rate, a medium error rate of 0.5% to 2% MSB error rate, a low error rate of 0.005% to 0.5%, and an error free rate of less than 0.00034% error rate.
Description
BRIEF DESCRIPTION OF THE DRAWINGS
[0017] FIG. 1A is a plan view of a memory cell array with IO, control, and drivers, showing a longest wordline path.
[0018] FIG. 1B is a plan view of a memory cell array with IO, control, and drivers, showing a shortest wordline path.
[0019] FIG. 2 is a plot for a wordline waveform for a low address and short length with a wordline waveform for a high address and long length.
[0020] FIG. 3 is a plot of wordline delay vs address which includes a bitline delay associated with bit position for each memory address.
[0021] FIG. 4 provides examples for four error rates which may be associated with wordline active width and example applications for the associated error rates.
[0022] FIG. 5 is a schematic diagram example for a wordline width controller having four selectable wordline widths.
[0023] FIG. 6 are waveform plots for the four selectable wordline widths of FIG. 5.
[0024] FIG. 7 is a flowchart for calibration of wordline delay with associated wordline pulse widths to associated error rates.
DETAILED DESCRIPTION OF THE INVENTION
[0025] In the present application, like reference numbers refer to like structures. References to “approximately” a nominal value are understood to be in the range of ⅕th of the nominal value to 5x the nominal value. References to “on the order of” a nominal value are understood to be in the range of ⅒th of the nominal value to 10x the nominal value. Other values such as 200ps wordline delay over address ranges and 20ps wordline delay over data bits are for example use only, and depend on the address and data size of the memory, as well as physical layout.
[0026] FIG. 1A shows an example memory cell array 102 in an example a chip layout, where top memory cell array 130A and bottom memory cell array 138A comprise arrays of SRAM memory cells. Each memory cell is arranged by sequential address in sequential columns, and each address corresponds to a column which is activated by a wordline driven by control 136A. A column of memory cells activated by a particular wordline drives a plurality of bitlines, which deliver associated output data from the column of memory cells to top I/O drivers 132A and bottom I/O drivers 140A, which deliver data shown as 8 bit bytes to multiplexer 114 which may provide the output data in selectable bytes as data output 116. The wordlines are driven by a controller 136A.
[0027] FIG. 1A shows an example longest wordline path for a high address such as 0xFFFF, and FIG. 1B shows an example shortest wordline path for a low address such as 0x0000. In the longest wordline path example of FIG. 1A, controller output 104A drives wordline 108A to the high address memory column furthest from the controller output 104A, with wordline 106A transferring the memory column enable signal to a corresponding column of memory cells, the outputs of which are taken as an example 32 bits (four bytes) as two bytes from each of the top and bottom memory arrays. The top memory array cells drive bitlines 110A and the bottom memory array cells drive bitlines 110B. The data bits for a column are arranged with the MSB closest to the innermost control lines and the LSB closest to the outermost control lines having comparatively longer wordline paths. Accordingly, the MSB has an incrementally shorter bitline path than an LSB for any given memory address. FIG. 1B shows a shortest path wordline example for a low value address, where controller output 104B drives comparatively short wordline 108B to column wordline 106B to a respective column of low value address memory cells. The outputs of the memory cells are transferred via bitlines 110B and 112B to top I/O drivers 132B bottom I/O drivers 140B, which drive the example 32 bit output mux 114 for byte selection 120, as was also shown in FIG. 1A.
[0028] FIG. 2 shows a plot of wordline waveform signal integrity as delivered to a low value address memory cell, where wordline 210 with shortest wordline path length to the memory cell array has comparatively fast risetimes 220 and a pulse width 203 from turn on 202 to turn off 204. Waveform 212 shows an example wordline plot received by a distant memory cell associated with a high address value, and longest wordline path length, where the slew rate 222 is reduced from the RC time constant and drive current to the wordline, resulting in reduced activation duration 207 from turn on 206 to turn off 208. The reduced activation time 207 for a remote (high address value) memory cell column compared to a nearby (low address value) memory cell with comparatively longer activation time 203 means that the selection of the wordline pulse width (activation duration) for the memory would be governed by worst case pulse width 207 for error-free operation, and pulse width 203 would be correspondingly greater, while causing unnecessary incremental power consumption but little other benefit.
[0029] FIG. 3 shows a plot 304 of an example wordline delay time 314 vs accessed memory address 316 from a low address to a high address. Plot 304 is trapezoidal to show also the variation in access time associated with a MSB 306 compared to LSB 308 for each given memory address, corresponding to the MLB/LSB bitline paths of FIGS. 1A and 1B. The line 304 passing through LSB point 308 may represent the wordline delays for the LSB of the address range, where the lower wordline delays of the line passing through points 302, 306, and 310 may represent the wordline delays for the MSB of the address range, with the other intermediate data bits being linearly arranged vertically according to bit significance. Note from the layout of FIGS. 1A and 1B that for a 32 bit word, the “MSB” and LSB” bits are arranged as two 16 bit values with b0 and b16 as “LSB” and b15 and b31 as “MSB” by position. In an alternative arrangement, the data bits are arranged by wordline length, such that the wordline column of [b31:b0] is physically arranged as [b31 b15 b30 b14 b29 b13 b28 b12 b27 b11 b26 b10 b25 b9 b24 b8 b23 b7 b22 b6 b21 b5 b20 b4 b19 b3 b18 b2 b17 b1 b16 b0], with b31 from upper array and b15 from lower array with shortest wordline path distances, and b16 from upper array and b0 from lower array having longest wordline path distances from source to IO, as shown in FIGS. 1A and 1B.
[0030] FIG. 4 shows four example cases for error rates, case 1 being a high error rate such as 10% MSB error rate for training neural network data with a large dataset, case 2 being a moderate MSB bit error rate, such as forming neural network inferences from an audio data stream or noisy image data, case 3 being a low MSB bit error rate, or alternatively a bit error rate where the MSB has no bit errors and where only LSB errors are acceptable (such as training on the standard National Institute for Standards ImageNet dataset available at NIST.gov), and case 4 where virtually no errors are tolerable on any bits, such as a six sigma error rate of less than 0.00034%.
[0031] FIG. 5 shows an example wordline width controller with associated waveforms shown in FIG. 6. A system clock 506 and memory request 504 may generate a Mem_Clk 508 signal from the assertion of a memory request 504, and MEM_CLK 508 presets D flip flop 526 to assert wordline _out 530. The Mem_Clk 508 signal also is fed to AND gates 514, 516, 518, 520, each of which is individually enabled by delay select lines DLY1, DLY2, DLY3, DLY4, only one of which is asserted at a time, resulting in a variable length reset signal 524 which clears DFF 526 output to 0, de-asserting Wordline _Out 530. The assertion of DLY1 has the shortest delay and results in the shortest Wordline_Out activation time, and DLY2 assertion enables 516 and results in an incrementally greater delay associated with the two inverters at the input of AND gate 516. DLY3 enables 518 and provides an incrementally greater delay by the combined Delay 1 510 (with inverted output) and gate delay to input of AND gate 518, and DLY4 provides the longest delay associated with Delay2 512 plus three inverters driving AND gate 520. Accordingly, DLY4 may be associated with error-free wordline pulse width, DLY3 may be associated with low error rate pulse width, DLY2 with medium error rate pulse width, and DLY1 with a high error rate pulse width, according to the reduced wordline pulse width (activation time) associated with each, as shown in Wordline _Out waveforms and associated DLY values 618, 620, 622, and 624, respectively, resulting in wordline pulse width (activation duration) 602, 604, 608, and 610, respectively.
[0032] FIG. 7 shows an example wordline error rate and pulse width association flowchart. The wordline pulse width may be set to a maximum pulse width such as DLY4 initially 704, and loop steps 705, 706, 708, and 714 result in the reading N times of a word in step 705 compared to a reference value stored in a controller register, followed by estimating an error rate 706, determining if the error rate for a given DLY value is below than a threshold value 708, and decreasing the wordline pulse width 714 if so (such as by changing from DLY4 to DLY3 or DLY3 to DLY2, etc.), until the DLY[3:0] value associated with lowest pulse width which satisfies a particular error rate is achieved, at which time the pulse width may be optionally incremented by one DLY step for a safety margin to ensure an error rate which is no greater than the desired one, and the DLY value associated with a particular error rate is saved in step 712 for future reference. In this manner, each of the error rates such as the examples of FIG. 4 has an associated DLY value which may be used for the associated data types of FIG. 4.
[0033] In another example of the invention, the error rates for a particular DLY value may increase with address value, since a fixed DLY value is associated with a particular data type. In this example, data associated with a lower error rate may be stored in low addresses and data associated with high error rates may be stored in high addresses. Similarly, it is preferable to arrange memory cells to have a shortest path for the MSB and incrementally longer paths for LSB in certain neural network applications, where LSB errors cause fewer inference errors than MSB errors.
[0034] The present examples are provided for illustrative purposes only, and are not intended to limit the invention to only the embodiments shown.
