US20030076725A1 - System and method for power saving memory refresh for dynamic random access memory devices after an extended interval - Google Patents
System and method for power saving memory refresh for dynamic random access memory devices after an extended interval Download PDFInfo
- Publication number
- US20030076725A1 US20030076725A1 US10/002,707 US270701A US2003076725A1 US 20030076725 A1 US20030076725 A1 US 20030076725A1 US 270701 A US270701 A US 270701A US 2003076725 A1 US2003076725 A1 US 2003076725A1
- Authority
- US
- United States
- Prior art keywords
- refresh
- row
- dram
- address signal
- row addressing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000015654 memory Effects 0.000 title claims description 344
- 238000000034 method Methods 0.000 title claims description 31
- 230000003111 delayed effect Effects 0.000 claims description 28
- 230000004044 response Effects 0.000 claims description 15
- 230000000977 initiatory effect Effects 0.000 claims description 11
- 239000004020 conductor Substances 0.000 claims description 8
- 238000010586 diagram Methods 0.000 description 13
- 239000003990 capacitor Substances 0.000 description 10
- 239000000463 material Substances 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 238000003491 array Methods 0.000 description 4
- 230000001934 delay Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000003213 activating effect Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 229910000078 germane Inorganic materials 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000020169 heat generation Effects 0.000 description 1
- 239000011810 insulating material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 239000002923 metal particle Substances 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002918 waste heat Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C11/00—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor
- G11C11/21—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using electric elements
- G11C11/34—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using electric elements using semiconductor devices
- G11C11/40—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using electric elements using semiconductor devices using transistors
- G11C11/401—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using electric elements using semiconductor devices using transistors forming cells needing refreshing or charge regeneration, i.e. dynamic cells
- G11C11/406—Management or control of the refreshing or charge-regeneration cycles
Definitions
- the present invention is directed to dynamic random access memory (DRAM) devices, and, more particularly, to a system and method for saving power while refreshing DRAM devices such as programmable conductor DRAM (PCDRAM) devices which only need to be refreshed after an extended interval.
- DRAM dynamic random access memory
- PCDRAM programmable conductor DRAM
- DRAM dynamic random access memory
- DRAM devices are fairly inexpensive because a DRAM memory cell needs relatively few components to store a data bit as compared with other types of memory cells.
- a large system memory can be implemented using DRAM devices for a relatively low cost.
- DRAM devices have the disadvantage that their memory cells must be continually refreshed because of the inherently transitory nature of their storage technology.
- a DRAM memory cell consists of a transistor/capacitor pair. High and low voltages stored in the capacitor represent logical one and zero data bits, respectively.
- one plate of the capacitor is connected to the drain of the transistor, and the other plate is connected to ground.
- a data bit is written to the cell by enabling the gate of the transistor and applying a voltage corresponding to the data bit to be written to the transistor's source. The enabled transistor conducts the voltage to the capacitor, charging the capacitor and storing the data bit. When the transistor is disabled, the data bit remains stored. Re-enabling the transistor reconnects the capacitor to the source of the transistor, and the stored voltage representing the data bit can be read at the source.
- sense amplifier The use of a sense amplifier is well known in the art to detect whether a stored voltage is high or low, and drive it toward the appropriate binary voltage parameter of the digital device. Fortunately, reading each cell using a sense amplifier not only reads the bit stored in the cell, but also simultaneously refreshes the voltage stored in that cell. The use of sense amplifiers to read and refresh DRAM memory cells is well known in the art. In the interest of brevity, the details of their operation will not be recounted here.
- Constantly refreshing DRAM memory cells presents two problems. First, refreshing memory cells slows the useful function of the memory. Memory cells are presented in arrays of rows and columns, often thousands of rows deep and thousands of columns wide. Even though entire rows of an array are refreshed at a time, it still requires thousands of refresh operations to refresh every row in the array. Moreover, these memory arrays cannot be accessed during a refresh cycle. Unless the memory array is equipped with a dual accessing mechanism, a row cache device, or similar means, the array can be neither read from nor written to during a refresh cycle without interrupting or destroying the cycle. If the central processing unit or other controller initiates a memory read or write operation during a refresh cycle, the processor or controller will have to wait for completion of that refresh cycle. This waiting slows processing throughput.
- FIGS. 1 and 1A A simplified view of a typical, conventional DRAM memory array is depicted in FIGS. 1 and 1A. Both show part of a 256 Mb array 110 which stores data in two conventional DRAM memory banks 112 and 114 .
- Each memory bank 112 and 114 for example, has 8,192 rows of memory cells, for a total of 16,384 rows.
- the figures are simplified most notably in the sense that they omit components such as column address multiplexers, column address latches, and column decoders.
- reading from or writing to a memory bank requires both a row and a column address to identify the specific memory location where the data is or will be stored. Both row and column addressing circuits are needed to read from and write data to the memory banks.
- refreshing a memory bank is typically performed by reading and thereby refreshing an entire row at a time across each memory bank, and column addresses are irrelevant.
- the invention described in this application is directed to a system and method for refreshing a memory array, thus column addressing is not germane. Further discussion of column addressing means has been omitted for the sake of simplicity.
- a memory array can be refreshed in either a burst refresh mode or a distributed refresh mode.
- a burst refresh mode every row of a memory array is sequentially refreshed in rapid succession. Then, after every passage of a predetermined interval, every row of the memory array again is refreshed in rapid succession.
- the maximum duration of the predetermined interval is the span of time after which the data stored in the DRAM array begins to degrade less the time required to sequentially refresh every row in the array. This standard interval is necessarily brief considering the rapid refreshing needs of a conventional DRAM device.
- FIG. 1 depicts a system memory which employs burst refresh.
- a refresh controller 120 generates a refresh signal after the passage of the predetermined interval. Incremented by each pulse of a refresh clock 122 , a refresh counter 124 sequences through a series of 14-bit binary numbers. The 14-bit binary number equates to one of 2 14 or 16,384 numbers, one of which uniquely corresponds to the address of each row of one of the two memory banks 112 and 114 .
- Each row in the memory banks 112 and 114 is accessed through a network of addressing circuitry 160 which includes a row address multiplexer 130 , row address latch A 150 , row address latch B 152 , and row decoders 132 - 142 .
- the row address is directed by the row multiplexer 130 to row address latch A 150 or row address latch B 152 , respectively. From the appropriate row address latch 150 or 152 , five bits of the 14-bit address uniquely identify one of the 2 5 or sixteen row decoders 132 - 142 associated with each memory bank.
- the remaining nine bits of the address uniquely correspond to one of the 2 9 or 512 rows addressed by each row decoder 132 - 142 . Only a few of the sixteen row decoders needed for each memory bank 112 and 114 are shown in the figures for the sake of visual clarity.
- Using a distributed refresh mode one row of the memory array is refreshed, then, after passage of a predetermined interval, the next row of the array is refreshed. This process is repeated until every row in the memory array is refreshed.
- the predetermined interval between the refreshing of each row is far shorter than the predetermined interval between refresh cycles in a burst refresh context.
- the maximum duration of the predetermined interval between row refreshes is the span of time after which the data stored in the DRAM array begins to degrade, less the time required to sequentially refresh every row in the array, divided by the number of rows in the array. In other words, all other variables being equal, the predetermined interval in the distributed refresh mode would be equal to the predetermined interval in the burst refresh mode divided by the number of rows in the memory array.
- the predetermined interval between row refreshes in a distributed refresh would be 1/8,192 as long as the predetermined interval between array refreshes in a burst refresh.
- FIG. 1A depicts a system memory which employs distributed refresh.
- the refresh cycle in a distributed refresh mode is largely similar to the refresh cycle in a burst refresh mode, as reflected by how similar FIG. 1A is to FIG. 1.
- the essential difference in a memory system employing distributed refresh is that there is not a single signal from the refresh controller 120 which initiates a refresh of the entire memory array. Instead, after each passage of the much shortened predetermined interval, the refresh controller 120 generates a refresh signal that causes one row of either memory bank A 112 or memory bank B 114 to be refreshed.
- the refresh controller 120 instead of enabling a rapid count of the refresh counter 124 through its entire sequence, pulses the refresh counter 124 causing its count to be incremented by one.
- This row address is passed to the addressing circuitry 160 which reads and thereby refreshes one row of the array in an identical manner as to how each row of the memory array is refreshed in a burst refresh. Then, after the passage of another much shortened predetermined interval, the refresh controller 120 emits another refresh signal which increments the refresh counter 124 , which, in turn, causes the next row in the memory array to be read and refreshed. This process repeats continually.
- PCDRAM programmable conductor dynamic random access memory
- FIG. 2A One known form of PCDRAM memory cell 200 , as depicted in FIG. 2A, uses a conducting layer 202 , which may be comprised of silver, applied to an insulating layer 204 , which may be comprised of glass. The conducting layer 202 and insulating layer 204 are perpendicularly disposed in a frame of insulating material 206 .
- Conducting plates 208 and 210 are disposed on outermost surfaces of the conducting layer 202 and insulating layer 204 , respectively. Tautologically, the conducting layer 202 conducts, whereas the insulating layer 204 does not conduct. When a low voltage is applied across the conducting plates 208 and 210 , the voltage will not be conducted because it will be blocked by the insulating layer 204 . Therefore, the memory cell is 200 not conductive in its initial state.
- FIG. 2B depicts the same memory cell 200 after a relatively high voltage has been applied.
- the relatively high positive voltage forces dendrils 212 of the material from the conducting layer 202 through the insulating layer 204 toward the conducting plate 210 disposed on the insulating layer 204 .
- Formation of the dendrils 212 of material from the conducting layer 202 through the insulating layer 204 is caused by the charged metal particles being attracted and repelled by fields of differing or similar charge, respectively. This phenomenon is known, and will not be described further here in the interest of brevity.
- the cell 200 becomes conductive.
- the cell 200 will now conduct when even low voltages are applied, thus, this cell effectively now stores a logical one which later can be read by the system associated with the memory cell 200 .
- the memory cell 200 can also be reprogrammed to store a logical zero.
- a relatively high voltage of reverse polarity i.e., with the positive voltage applied to the conducting plate 210 , reverses the migration of the dendrils 212 of material from the conducting layer.
- the dendrils 212 of material from the conducting layer 202 passing through the insulating layer 204 are forced back toward the conducting layer 202 and out of the insulating layer 204 by the same natural attraction and repulsion of charges which originally caused the cell to be programmed.
- This relatively high voltage of reverse polarity causes the memory cell 200 to become nonconductive once more. When a lesser voltage is applied, the memory cell 200 will no longer conduct. Thus, and the cell now effectively stores a logical zero.
- higher voltages of opposite sense can be used to program and reprogram these cells to conduct or not conduct, storing logical ones or zeroes, respectively.
- the PCDRAM memory cell 200 described is far less volatile than a conventional DRAM memory cell. Without being refreshed, a conventional DRAM cell only can maintain its logical bit for microseconds, while the PCDRAM memory cell 200 potentially can maintain its logical bit for days. Eventually, natural diffusion of the material from the conducting layer 202 into and out of the insulating layer 204 resulting from ordinary atomic motion will corrupt the data stored. Nonetheless, PCDRAM devices need only be refreshed after an extended interval, thus, less power is needed to refresh these devices than is needed for the frequent refreshing required by conventional DRAM devices.
- refresh signal delay means an array comprised of less volatile DRAM devices, which only need to be refreshed after an extended interval, can be refreshed less frequently, consuming less power, while still using conventional DRAM refreshing control circuitry.
- the delay means delays externally generated refresh signals supplied to accommodate the refresh rate required by conventional DRAM memory devices but, in response, generates far less frequent delayed refresh signals. This reduces the frequency with which the less volatile DRAM devices will be refreshed, and powers off supporting addressing circuitry when it is not needed. Therefore, the delay means allows computing systems designed to use conventional DRAM devices to work with DRAM devices which only need to be refreshed after an extended interval and reduces the amount power wasted through unnecessarily frequent refresh cycles.
- FIG. 1 is a simplified block diagram of a section of a conventional DRAM memory array that may be adapted to use the invention in a burst refresh mode.
- FIG. 1A is a simplified block diagram of a section of a conventional DRAM memory array that may be adapted to use the invention in a distributed refresh mode.
- FIG. 2A is a cross-sectional view of a known programmable conductor DRAM (PCDRAM) memory cell in its initial state before the application of a voltage that can be used to write to the cell that may be used with the invention.
- PCDRAM programmable conductor DRAM
- FIG. 2B is a cross-sectional view of the PCDRAM cell depicted in FIG. 2A after a high voltage has been applied to the cell to write a logical one to the cell.
- FIG. 2C is a cross-sectional view of the PCDRAM cell depicted in FIG. 2B after a high voltage of polarity opposite to that applied to cause the state depicted in FIG. 2B has been applied to the cell to write a logical zero to the cell.
- FIG. 3 is a symbolic block diagram generally representing the functioning of embodiments of the present invention.
- FIG. 4 is a block diagram of the same section of a DRAM memory array depicted in FIG. 1 replacing the conventional DRAM devices with DRAM devices which only need to be refreshed after an extended interval and adapted with a first embodiment of the invention to reduce the power needed to refresh the memory array using a burst refresh mode.
- FIG. 4A is a block diagram of the same section of a DRAM memory array depicted in FIG. 1 replacing the conventional DRAM devices with DRAM devices which only need to be refreshed after an extended interval and adapted with a first embodiment of the invention to reduce the power needed to refresh the memory array using a distributed refresh mode.
- FIG. 5 is a timing diagram of the first embodiment of the invention to reflect the reduction in state changes made possible by the first embodiment of the invention.
- FIG. 6 is a block diagram of the same section of a DRAM memory array depicted in FIG. 4 further adapted with a second embodiment of the invention to save additional power in refreshing the memory array using a burst refresh mode.
- FIG. 6A is a block diagram of the same section of a DRAM memory array depicted in FIG. 4 further adapted with a second embodiment of the invention to save additional power in refreshing the memory array using a distributed refresh mode.
- FIG. 7 is a timing diagram of the second embodiment of the invention to reflect the reduction in state changes made possible by the second embodiment of the invention.
- FIG. 8 is a block diagram of a computer system using a memory array employing DRAM devices which only need to be refreshed after an extended interval and a power saving memory device of an embodiment of the invention.
- FIG. 3 represents the basic operation of embodiments of the present invention.
- External control devices designed to work with conventional DRAM devices will generate frequent conventional refresh signals. These conventional refresh signals 310 will be generated at a frequency f which corresponds to the rapidity with which conventional DRAM devices must be refreshed.
- Control systems designed to work with DRAM devices that only need to be refreshed after an extended interval generate delayed refresh signals 320 far less often at a frequency f′.
- conventional DRAM devices might need to be refreshed thousands of times per second, whereas DRAM devices such as PCDRAM cells may only need to be refreshed once per day. In this example, therefore, frequency f′ could be many orders of magnitude smaller than frequency f.
- the present invention uses delay means 330 operable to receive the conventional refresh signals 310 and, at appropriately delayed intervals, generate the less frequent delayed refresh signals 320 .
- external devices designed to work with conventional DRAM devices may be used with DRAM devices which only need to be refreshed after an extended interval, without wasting power on unnecessarily frequent refresh cycles.
- FIG. 4 depicts a memory array 410 very similar to the memory array 110 described in FIG. 1. Identical components shown in FIG. 4 have been provided with the same reference numeral, and explanation of their function and operation will not be repeated in the interest of brevity. The differences between the memory array 110 shown in FIG. 1 and the memory array 410 shown in FIG. 4 are twofold. First, the memory array 410 depicted in FIG. 4 has been adapted to use DRAM memory banks which only need to be refreshed after an extended interval 412 and 414 .
- a delay counter 420 has been added to the memory array 410 .
- the memory array 410 shown in FIG. 4 employs burst refresh, as does memory array 110 in FIG. 1.
- the delay counter 420 shown in FIG. 4 is a bit up counter which extends the interval between refresh cycles being conducted in the memory banks 412 and 414 , and powers off supporting circuitry when it is not needed.
- the delay counter 420 extends the interval between refresh cycles by intercepting and counting the refresh signals being generated by the refresh controller 120 , the refresh controller 120 being responsive to externally applied refresh signals.
- the delay counter 420 generates a delayed refresh signal to initiate a refresh cycle only after having counted a large, predetermined number of refresh signals from the refresh controller 120 . In effect, the overflow signal of the delay counter 420 becomes the actual refresh signal for the memory array 410 .
- FIG. 5 shows how the delay counter 420 receives refresh signals from the refresh controller 120 and periodically generates a delayed refresh signal to trigger a refresh cycle.
- the refresh controller 120 generates a refresh signal as often as is needed to refresh conventional DRAM memory banks 112 and 114 with which the conventional external circuitry (not shown) was designed to operate. In a conventional DRAM array, each pulse of the refresh controller 120 would trigger a refresh cycle for the entire memory array 410 .
- the refresh controller 120 issues a refresh signal at intervals t 1 through t 10 , the refresh counter 124 and the addressing circuitry 160 , including the row multiplexer 130 , row address latches 150 and 152 , and row decoders 132 - 142 , remain powered off and no refresh cycle is conducted until t 3 . Instead, for each refresh signal generated by the refresh controller 120 , the delay counter 420 is incremented. The delayed refresh signal will be generated only when a desired number of refresh signals generated by the refresh controller 120 have been counted and skipped.
- the delay counter 420 reaches its overflow count and the delay counter 420 overflow signal goes high.
- the overflow signal from the delay counter 420 turns on the refresh counter 124 and the rest of the addressing circuitry 160 , including the row multiplexer 130 , row address latches 150 and 152 , and row decoders 132 - 142 .
- the refresh counter 124 cycles through all 2 14 or 16,384 row addresses in the memory array 410 . Each address is passed to the row address multiplexer 130 which, in turn, directs the generated address to one of two row address latches 150 and 152 .
- the row address latches 150 and 152 supply the row address to one of sixteen row address decoders 132 - 142 associated with each memory bank 410 and 412 .
- the overflow bit of the refresh counter 124 goes high as depicted at t 4 of FIG. 5. This overflow bit is fed back to the delay counter 420 and resets it. At this point, the delay counter 420 once again begins counting the refresh signals generated by the refresh controller 120 , initiating a refresh cycle only after the delay counter 420 again reaches its overflow count.
- a suitably large delay counter 420 could be used so that the delay counter 420 would only overflow as often as needed to refresh the memory banks 412 and 414 only after an extended interval.
- the addressing circuitry 160 including the row multiplexer 130 , the row address latches 150 and 152 , and the row decoders 132 - 142 , all can be left powered off except as needed. Unneeded refresh signals generated by the refresh controller 120 , as shown at t 1 , t 2 , t 5 , and t 8 in FIG. 5, can be ignored, and the addressing circuitry left powered off. Power need not be supplied to the addressing circuitry 160 until the delay counter 420 reaches overflow and indicates the addressing circuitry 160 needs to be powered on, as shown at t 3 and again at t 9 . The addressing circuitry 160 can be powered off at the conclusion of each of the refresh cycles, as shown at t 4 and t 10 in FIG. 5.
- the addressing circuitry 160 still will be needed to perform memory read or write operations, as signaled by the external address signal 126 as shown at t 6 . However, because the refresh counter 124 is not needed for a memory read or write operation, the refresh counter 124 can still be left powered off at these times.
- the addressing circuitry 160 will be powered on by the delay counter 420 or the external address signal 126 . If the power sourced by the overflow signal of the delay counter 420 or external address signal 126 is not sufficient to power the addressing circuitry 160 , the overflow signal of the delay counter 420 or the external address signal 126 can be used to enable a transistor having sufficient power-handling capability to power these circuits. Use of a transistor or other device which can supply more power, switched by the output of another circuit, is well known in the art and will not be described here further for the sake of brevity.
- FIG. 4A depicts a similar memory array 410 A adapted to use the first embodiment of the invention in a distributed refresh mode.
- the refresh counter 124 is pulsed by the delay counter 420 instead of the refresh clock 122 .
- each refresh signal issued by the refresh controller 120 causes one single row of the memory banks 412 and 414 to be refreshed at a time instead of all the rows being refreshed in a single sequence.
- the delay counter 420 will count a large, predetermined number of these signals before initiating the refresh sequence for the next row in the memory array.
- the interval between refresh sequences initiated by the delay counter 420 will be 1/8,192 as long as the interval between refresh sequences initiated by the delay counter 420 for the memory array 410 .
- the refresh counter 124 is not powered on and off by the delay counter 420 . Using distributed refresh, the refresh counter 124 must constantly maintains its row count. Third, in the memory array 410 A, an overflow output of the refresh counter 124 is not needed.
- the first embodiment of the invention provides three significant advantages.
- the embodiment of FIG. 4 allows the use of conventional refreshing circuitry only by adding the delay counter 420 to control the enabling of the addressing circuitry 160 .
- Third, power consumed by the addressing circuitry 160 is reduced because these devices would be powered off when not in use.
- a second embodiment of the invention shown in FIG. 6 shows how additional power can be saved by selectively powering on only parts of the addressing circuitry 660 during a refresh cycle.
- the first embodiment of the invention when either the delay counter 420 reaches overflow, all of the addressing circuitry 160 is powered on, regardless of which row of which memory bank 412 or 414 is to be accessed. In other words, whenever the memory banks 412 or 414 are accessed, thirty-five different devices are powered on, including the row address multiplexer 130 , two row address latches 150 and 152 , and thirty-two row decoders 132 - 142 .
- the memory array 410 stores just one bit of what presumably is at least an eight-bit word, then at least eight times as many devices would be powered on each time the memory is accessed for a read, write, or refresh operation, even though only one row can be read from, written to, or refreshed at one time.
- This second embodiment uses five additional control devices to control addressing of the memory array during refresh cycles, only three of which are powered on at one time when using a burst refresh mode. These additional devices allow for only six supporting devices to be activated at a time during a refresh cycle instead of thirty-five. This saves the wasteful powering and heat generation of twenty-nine superfluous devices. For a memory array eight bits in width, forty-eight devices would only need to be powered on at one time instead of two-hundred and eighty.
- FIG. 6 depicts a memory array 610 very similar to the memory array 410 described in FIG. 4.
- PCDRAM memory banks which only need to be refreshed after an extended interval 412 and 414 still are being used, and to take advantage of their lower volatility, a delay counter 420 again is employed to extend the interval between refresh cycles.
- Five devices are added to the memory array 610 shown in FIG. 6: a bank segment bit up counter 670 , two row bit up counters 680 and 682 , and two row decoder selectors 690 and 692 . The purpose of these devices is to selectively power on only the row decoder 132 - 142 that is needed at any one point of a refresh cycle.
- These row decoders 132 - 142 constitute thirty-two of the thirty-five devices or 90% of the addressing circuitry 160 (FIGS. 1 and 4) conventionally used to sequentially address a memory array during a refresh cycle.
- the sample memory array 610 again includes two memory banks 412 and 414 , each of which comprises, for example, 8,196 rows of memory cells. Associated with each of the memory banks 412 and 414 are sixteen row decoders 132 - 142 . Each row decoder addresses 512 rows of a memory bank. To sequentially access each of the row decoders 132 - 142 , a four-bit counter is needed to sequentially generate a code for each of the 2 4 or sixteen counters. This embodiment of the invention includes two four-bit row bit up counters 680 and 682 , one to generate the address of each of the sixteen row decoders 132 - 142 for each memory bank 412 and 414 .
- each of the two counters 680 and 682 is a four-bit demultiplexer which serves as a row decoder selector 690 and 692 .
- these row decoder selectors will activate one bit of a sixteen-bit wide output as is well known in the art.
- row bit up counter A 680 and row decoder selector A 690 , and row bit up counter B 682 and row bit up decoder B 692 can selectively and sequentially power on each of the sixteen bit row decoders 132 - 142 for each of their respective memory banks 412 and 414 , one row at a time.
- FIG. 7 shows how the delay counter 420 receives refresh signals from the refresh controller 120 , periodically triggers a refresh cycle, and governs the selective powering on of the addressing circuitry 660 .
- FIG. 7 details a shorter interval of time to highlight the sequential powering on of the individual row decoders 132 - 142 during a refresh cycle.
- the refresh signals generated by the refresh controller 120 are not shown; it will be appreciated that the refresh controller 120 necessarily continues to generate refresh signals, but depiction of its signal has been eliminated from this figure for the sake of simplicity.
- the delay counter 420 has counted the large, predetermined number of refresh signals generated by the refresh controller 120 to warrant initiating a refresh sequence for the DRAM memory banks which only need to be refreshed after an extended interval 412 and 414 .
- the overflow signal of the delay counter 420 goes high and powers on the refresh counter 124 , the row address multiplexer 130 , and the row address latches 150 and 152 .
- the overflow signal generated by the delay counter 420 does not power on each of the row decoders 132 - 142 . Instead, this overflow signal powers on row bit up counter A 680 , row decoder selector A 690 , and the bank segment bit up counter 670 .
- row decoder selector A With row bit up counter A 680 powered on in its initial state, it supplies a count of four zeroes to row decoder selector A 690 . Row decoder selector A therefore activates row decoder A 0 132 . Because it is active, row decoder A 0 132 is able to sequentially address each of the 2 9 or 512 rows that it addresses in memory bank A 412 . These row addresses are supplied to row decoder A 0 132 by row address latch A 150 , which has received that address from the row address multiplexer 130 . The row address multiplexer 130 has generated this address by decoding the count provided to it by the refresh counter 124 .
- the bank segment bit up counter 670 is a nine-bit counter that will reach overflow after counting 2 9 or 512 pulses of the refresh clock 122 .
- the overflow of the bank segment bit up counter 670 is connected to both the row bit up counters 680 and 682 .
- the overflow signal from the bank segment bit up counter 670 can increment row bit up counters 680 and 682 after every 512 pulses of the refresh clock 122 have enabled the refreshing of each of the 512 rows in the memory bank segment addressed by each of the row decoders 132 - 142 .
- the same refresh clock 122 pulses the bank segment bit up counter 670 and the refresh counter 124 .
- the nine-bit count maintained by the bank segment bit up counter 670 and the nine least significant bits of the count maintained by the refresh counter 124 will be synchronized. Because they are synchronized, with the completion of each nine-bit count, the bank segment bit up counter 670 will overflow to increment the appropriate row bit up counter 680 and 682 , in turn enabling the appropriate row decoder selector 690 and 692 to activate the appropriate row decoder 132 - 142 , while the refresh counter 124 continues to count the rows it refreshes throughout the memory array 610 .
- the bank segment bit up counter 670 has sequenced through its entire nine-bit sequence and generates an overflow signal.
- This overflow signal increments row bit up counter A 680 .
- row decoder selector A 690 generates a different sixteen-bit code which powers off row decoder A 0 132 and powers on row decoder A 1 134 .
- the refresh counter 124 sequences through the nine least significant bits of its count for the second time. This time, however, the nine least significant bits of the count generated by refresh counter 124 are applied through row decoder A 1 134 and serve to address and refresh the next 512 rows of memory bank A 412 .
- row decoder A 1 134 is then powered off while the next row decoder A 2 (not shown in FIG. 6) is powered on, while all the other row decoders 132 - 142 remain powered off.
- row bit up counter A 680 reaches overflow. As shown in FIG. 7, this overflow signal powers on row decoder selector B 682 and its associated row decoder selector 692 .
- a simple latch could be used to preserve the high overflow signal generated by row bit up counter A 680 to maintain power to row bit up counter B 682 and its associated row decoder selector B 692 while powering off row bit up counter A 680 and row decoder selector A 690 .
- row bit up counter B 682 when it is powered on at t 4 , row bit up counter B 682 supplies a count of four zeroes to row decoder selector B 692 .
- Row decoder selector B 692 activates row decoder B 0 138 .
- Row decoder B 0 138 then sequentially addresses each of the 512 rows of memory bank A 412 that it serves. These row addresses are supplied to row decoder B 0 138 by row address latch B 152 , which has received that address from the row address multiplexer 130 .
- the row address multiplexer 130 has generated this address by decoding the count provided to it by the refresh counter 124 .
- the bank segment bit up counter 670 has sequenced through its nine-bit count and reached overflow.
- This overflow signal causes row bit up counter B 682 to increment, in turn causing row decoder selector B 692 to power off row decoder B 0 138 and activate row decoder B 1 140 .
- the repeated overflow of the bank segment bit up counter 670 activates one at a time the sixteen address decoders 138 - 142 associated with memory bank B 414 , while each addresses the 512 rows it serves in associated memory bank B 414 .
- each row decoder 132 - 142 has addressed and refreshed all 512 rows it serves, the refresh counter 124 reaches overflow, and the refresh cycle is complete.
- Overflow of the refresh counter 124 powers off the addressing circuitry 660 and the refresh counter 124 .
- One difference in the second embodiment is that fewer devices in the addressing circuitry 660 will be turned off upon overflow of the refresh counter 124 .
- FIG. 6A depicts a similar memory array 610 A adapted to use the first embodiment of the invention in a distributed refresh mode.
- the refresh counter 124 is pulsed by the delay counter 420 instead of the refresh clock 122 .
- the refresh counter 124 , the row segment bit up counter 670 , and row bit up counter A 680 and row bit up counter B 682 are not powered on and off by the delay counter 420 .
- the refresh counter 124 and the bank segment bit up counter 670 must constantly maintain their row counts.
- row bit up counter A 680 or row bit up counter B 682 whichever is currently active, must remain powered on to maintain its count of which of the row decoders 132 - 142 should be activated when the next row is refreshed.
- the overflow output of row bit up counter A 680 can be used to power on row bit up counter B 682
- the overflow output of row bit up counter B 682 can be used to power on row bit up counter A 680 so that the one not being used does not need to be powered on at all times.
- both row bit up counters 680 and 682 could be left powered on at all times. Accordingly, using distributed refresh mode, three or four additional devices will need to be powered on at all times.
- an overflow output of the refresh counter 124 is not needed.
- the invention also could be embodied in other forms.
- One example not shown in the figures could be a hybrid form using a series of distributed refresh signals generated by the refresh controller to perform, in essence, a slow burst refresh of the array after the passage of an extended interval.
- the refresh controller would be programmed to generate row refresh signals after the passage of a suitable interval for a conventional DRAM array.
- the delay counter would intercept, count, and ignore a number of these distributed refresh signals until the passage of an extended interval by when the less volatile memory devices would have to be refreshed.
- the number of refresh signals from the refresh controller to be ignored would be determined by the duration of the extended interval divided by the duration between refresh signals generated by the refresh controller for a conventional DRAM memory array.
- the delay counter would pass the refresh signals from the refresh controller through to the refresh counter. This could be handled by connecting the overflow signal from the delay counter and the refresh signal from the refresh controller to an AND gate, the output of which would become the input pulse to the refresh controller. After counting a number of refresh signals corresponding to the extended interval causing the delay counter's overflow signal to go high, the refresh signals would cause a high output from the AND gate which, in turn, would pulse the refresh counter. The rows of the less volatile memory array would then be refreshed sequentially as pulsed by the row refresh signals from the refresh controller. In other words, the memory array would be refreshed in one slow, sequential burst in rhythm to the row refresh signals from the refresh controller after the passage of an extended interval. Once all the rows were refreshed, the delay counter would reset, and proceed to ignore another long sequence of row refresh commands from the refresh controller until the less volatile memory array once again needed to be refreshed.
- FIG. 8 is a block diagram of a computer system 810 that includes a processor 812 for performing various computing functions by executing software to perform specific calculations or tasks.
- the processor 812 is coupled to a processor bus 814 that normally includes an address bus, a control bus, and a data bus (not separately shown).
- the computer system 810 includes a system memory 816 , which could be the memory array 410 of FIG. 4 or the memory array 610 of FIG. 6, both of which use DRAM devices which only need to be refreshed after an extended interval, such as PCDRAM devices, and supporting circuitry which enables the power savings previously described.
- the system memory 816 is coupled to the processor bus 814 by a system controller 820 or similar device, which is also coupled to an expansion bus 822 , such as a Peripheral Component Interface (“PCI”) bus.
- a bus 726 coupling the system controller 820 to the system memory 816 also normally includes an address bus, a control bus, and a data bus (not separately shown), although other architectures can be used.
- the data bus of the system memory 816 may be coupled to the data bus of the processor bus 814 , or the system memory 816 may be implemented by a packetized memory (not shown), which normally does not include a separate address bus and control bus.
- the computer system 810 also includes one or more input devices 834 , such as a keyboard or a mouse, coupled to the processor 812 through the expansion bus 822 , the system controller 820 , and the processor bus 814 . Also typically coupled to the expansion bus 822 are one or more output devices 836 , such as a printer or a video terminal.
- One or more data storage devices 838 are also typically coupled to the expansion bus 822 to allow the processor 812 to store data or retrieve data from internal or external storage media (not shown). Examples of typical storage devices 838 include hard and floppy disks, tape cassettes, and compact disk read-only memories (CD-ROMs).
- the processor 812 is also typically coupled to cache memory 840 through the processor bus 814 .
- PCDRAM devices unlike conventional DRAM devices 112 and 114 , PCDRAM devices also must be signaled as to when they are being refreshed as opposed to merely being read. The reason for this, as was previously described, is one of the inherent differences between conventional DRAM devices and PCDRAM devices.
- a conventional DRAM memory cell reading a memory cell through an associated sense amplifier simultaneously and automatically refreshes that cell. Accordingly, presented with a row address, a conventional DRAM device will read the cells in that row, and, coincidentally, refresh the cells in that row.
- a PCDRAM device cannot be refreshed simply by reading it.
- a higher voltage than carried by read signals in the device must be applied to cause the formation or reformation of dendrils 212 (FIG. 2B).
- the memory banks 412 and 414 must be signaled that this is not an ordinary read signal, but that the addresses in that row must be read and refreshed with the application of a higher voltage, as previously described.
- PCDRAM devices themselves can be powered off when not being accessed. PCDRAM devices store their data bits by undergoing a physical transformation as previously described. Thus, they can be turned off when not in use.
- memory bank A 412 and memory bank B 414 could be powered on and off by the same delay counter 420 overflow signal that powered on the addressing circuitry 160 .
- memory bank A 412 could be powered on by the same delay counter 420 overflow signal that powers on row bit up decoder A 680 and row decoder selector A 690 , and powered off by the same row bit up counter A 680 overflow signal that powers off row bit up decoder A 680 and row decoder selector A 690 .
- memory bank B 414 could be powered on by the same row bit up counter A 680 overflow signal that powers on row bit up decoder B 682 and row decoder selector B 692 , and powered off by the same refresh counter 124 overflow signal that powers off row bit up decoder B 682 and row decoder selector B 692 .
- the first embodiment of the invention saves power by extending the time between refresh cycles to exploit less volatile DRAM devices which need to be refreshed only after an extended interval.
- the first embodiment accomplishes this predominantly through the use of a delay counter which delays the refresh signals generated by a conventional refresh controller designed for conventional DRAM memory devices, and generates refresh signals much less frequently.
- the second embodiment of the invention further saves power during each refresh cycle by sequentially activating only the row decoders needed to address the rows currently being refreshed rather than powering on all the row decoders at once.
Landscapes
- Engineering & Computer Science (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Computer Hardware Design (AREA)
- Dram (AREA)
Abstract
Description
- The present invention is directed to dynamic random access memory (DRAM) devices, and, more particularly, to a system and method for saving power while refreshing DRAM devices such as programmable conductor DRAM (PCDRAM) devices which only need to be refreshed after an extended interval.
- Most computers and other digital systems have a system memory which often consists of dynamic random access memory (“DRAM”) devices. DRAM devices are fairly inexpensive because a DRAM memory cell needs relatively few components to store a data bit as compared with other types of memory cells. Thus, a large system memory can be implemented using DRAM devices for a relatively low cost. However, DRAM devices have the disadvantage that their memory cells must be continually refreshed because of the inherently transitory nature of their storage technology.
- Generally a DRAM memory cell consists of a transistor/capacitor pair. High and low voltages stored in the capacitor represent logical one and zero data bits, respectively. In a basic DRAM memory cell, one plate of the capacitor is connected to the drain of the transistor, and the other plate is connected to ground. A data bit is written to the cell by enabling the gate of the transistor and applying a voltage corresponding to the data bit to be written to the transistor's source. The enabled transistor conducts the voltage to the capacitor, charging the capacitor and storing the data bit. When the transistor is disabled, the data bit remains stored. Re-enabling the transistor reconnects the capacitor to the source of the transistor, and the stored voltage representing the data bit can be read at the source.
- The foregoing is a simplified view, ignoring two considerations presented by the physical nature of the capacitor used in the memory cell. First, a capacitor can hold a voltage only briefly. The smaller the capacitor, the shorter is the duration for which the voltage can be stored. In a DRAM memory device containing thousands of memory cells on a single piece of a semiconductor wafer, these capacitors are infinitesimal, and can only reliably maintain a voltage for microseconds. Consequently, these memory cells must be refreshed thousands of times per second. Second, because these stored voltages dissipate so rapidly, reading the voltage after just a short interval requires a sense amplifier. The use of a sense amplifier is well known in the art to detect whether a stored voltage is high or low, and drive it toward the appropriate binary voltage parameter of the digital device. Fortunately, reading each cell using a sense amplifier not only reads the bit stored in the cell, but also simultaneously refreshes the voltage stored in that cell. The use of sense amplifiers to read and refresh DRAM memory cells is well known in the art. In the interest of brevity, the details of their operation will not be recounted here.
- Constantly refreshing DRAM memory cells presents two problems. First, refreshing memory cells slows the useful function of the memory. Memory cells are presented in arrays of rows and columns, often thousands of rows deep and thousands of columns wide. Even though entire rows of an array are refreshed at a time, it still requires thousands of refresh operations to refresh every row in the array. Moreover, these memory arrays cannot be accessed during a refresh cycle. Unless the memory array is equipped with a dual accessing mechanism, a row cache device, or similar means, the array can be neither read from nor written to during a refresh cycle without interrupting or destroying the cycle. If the central processing unit or other controller initiates a memory read or write operation during a refresh cycle, the processor or controller will have to wait for completion of that refresh cycle. This waiting slows processing throughput.
- Second, and even more problematic than processing delays, is the power consumed in the continual, rapid refreshing of these memory cells. Thousands of times per second, the gate of each transistor in each memory cell across the entire DRAM array must be activated to refresh the array. Resistance of the conductors through the memory array to address each and every transistor, in each and every row, in each and every column, consumes considerable power. More power is consumed by transistors used in the sense amplifiers which read and refresh the memory cells in respective columns. Still further, supporting circuitry needed to access the rows of memory cells, such as a refresh counter, row multiplexers, row decoders, and address latches, uses even more power.
- A simplified view of a typical, conventional DRAM memory array is depicted in FIGS. 1 and 1A. Both show part of a 256
Mb array 110 which stores data in two conventionalDRAM memory banks memory bank - A memory array can be refreshed in either a burst refresh mode or a distributed refresh mode. Using a burst refresh mode, every row of a memory array is sequentially refreshed in rapid succession. Then, after every passage of a predetermined interval, every row of the memory array again is refreshed in rapid succession. The maximum duration of the predetermined interval is the span of time after which the data stored in the DRAM array begins to degrade less the time required to sequentially refresh every row in the array. This standard interval is necessarily brief considering the rapid refreshing needs of a conventional DRAM device.
- FIG. 1 depicts a system memory which employs burst refresh. A
refresh controller 120 generates a refresh signal after the passage of the predetermined interval. Incremented by each pulse of arefresh clock 122, arefresh counter 124 sequences through a series of 14-bit binary numbers. The 14-bit binary number equates to one of 214 or 16,384 numbers, one of which uniquely corresponds to the address of each row of one of the twomemory banks - Each row in the
memory banks circuitry 160 which includes arow address multiplexer 130, rowaddress latch A 150, rowaddress latch B 152, and row decoders 132-142. Depending upon whether the row address generated by therefresh counter 124 refers to a row inmemory bank A 112 ormemory bank B 114, the row address is directed by therow multiplexer 130 to rowaddress latch A 150 or rowaddress latch B 152, respectively. From the appropriaterow address latch memory bank - After supplying the address of a row to the
appropriate memory bank memory bank refresh counter 124 has sequenced through all 16,384 row addresses, the refresh cycle is over. Therefresh counter 124 and the addressingcircuitry 160 sit idle, consuming power, awaiting the next refresh signal from therefresh controller 120 or the nextexternal address signal 126. - Using a distributed refresh mode, one row of the memory array is refreshed, then, after passage of a predetermined interval, the next row of the array is refreshed. This process is repeated until every row in the memory array is refreshed. The predetermined interval between the refreshing of each row is far shorter than the predetermined interval between refresh cycles in a burst refresh context. The maximum duration of the predetermined interval between row refreshes is the span of time after which the data stored in the DRAM array begins to degrade, less the time required to sequentially refresh every row in the array, divided by the number of rows in the array. In other words, all other variables being equal, the predetermined interval in the distributed refresh mode would be equal to the predetermined interval in the burst refresh mode divided by the number of rows in the memory array. For example, assuming that the span of time after which the data stored in the DRAM array begins to degrade and the total time to refresh the rows themselves is equal to that for the DRAM array refreshed in a burst refresh mode, and there are 8,192 rows in the array, the predetermined interval between row refreshes in a distributed refresh would be 1/8,192 as long as the predetermined interval between array refreshes in a burst refresh.
- FIG. 1A depicts a system memory which employs distributed refresh. The refresh cycle in a distributed refresh mode is largely similar to the refresh cycle in a burst refresh mode, as reflected by how similar FIG. 1A is to FIG. 1. The essential difference in a memory system employing distributed refresh is that there is not a single signal from the
refresh controller 120 which initiates a refresh of the entire memory array. Instead, after each passage of the much shortened predetermined interval, therefresh controller 120 generates a refresh signal that causes one row of eithermemory bank A 112 ormemory bank B 114 to be refreshed. Therefresh controller 120, instead of enabling a rapid count of therefresh counter 124 through its entire sequence, pulses therefresh counter 124 causing its count to be incremented by one. This row address is passed to the addressingcircuitry 160 which reads and thereby refreshes one row of the array in an identical manner as to how each row of the memory array is refreshed in a burst refresh. Then, after the passage of another much shortened predetermined interval, therefresh controller 120 emits another refresh signal which increments therefresh counter 124, which, in turn, causes the next row in the memory array to be read and refreshed. This process repeats continually. - Regardless of which mode of refresh is employed, merely the number of devices needed to refresh the array suggests that significant power is consumed in refreshing the array. Moreover, in an actual system memory, power would have to be supplied to eight times as many memory cells and decoders for every byte of data stored. For example, to store 256 MB of data, eight parallel 256 Mb arrays are needed, each of which has its own two banks of memory cells, sixteen row decoders, two row address latches, and a row address multiplexer. The aggregate amount of power used to refresh the cells throughout an entire system memory becomes relatively immense.
- The power expended in these refresh cycles is a significant problem. Most significantly, excessive power consumption quickly exhausts battery power in increasingly popular portable computing devices. The consumption of this power also generates a great deal of heat. For all the power expended in refreshing these DRAM memory cells, an additional—and substantial—quantity of power is expended by cooling fans in eliminating the waste heat produced during these refresh cycles.
- Much of the power wasted in refreshing DRAM memory could be saved by using less volatile DRAM devices. Instead of having to be refreshed thousands of times per second, after the passage of only a brief interval, less volatile DRAM devices only need to be refreshed after the passage of an extended interval. For one example, programmable conductor dynamic random access memory (PCDRAM) devices need to be refreshed far less frequently than conventional DRAM devices. One known form of
PCDRAM memory cell 200, as depicted in FIG. 2A, uses aconducting layer 202, which may be comprised of silver, applied to an insulatinglayer 204, which may be comprised of glass. Theconducting layer 202 and insulatinglayer 204 are perpendicularly disposed in a frame of insulatingmaterial 206. Conductingplates conducting layer 202 and insulatinglayer 204, respectively. Tautologically, theconducting layer 202 conducts, whereas the insulatinglayer 204 does not conduct. When a low voltage is applied across the conductingplates layer 204. Therefore, the memory cell is 200 not conductive in its initial state. - However, applying a relatively high voltage across the conducting
plates cell 200. FIG. 2B depicts thesame memory cell 200 after a relatively high voltage has been applied. The relatively high positive voltage forces dendrils 212 of the material from theconducting layer 202 through the insulatinglayer 204 toward the conductingplate 210 disposed on the insulatinglayer 204. Formation of thedendrils 212 of material from theconducting layer 202 through the insulatinglayer 204 is caused by the charged metal particles being attracted and repelled by fields of differing or similar charge, respectively. This phenomenon is known, and will not be described further here in the interest of brevity. - Because the voltage has driven
dendrils 212 of material from theconducting layer 202 through the insulatinglayer 204 to contact the conductingplate 210 on the opposite surface of the insulatinglayer 204, thecell 200 becomes conductive. Thecell 200 will now conduct when even low voltages are applied, thus, this cell effectively now stores a logical one which later can be read by the system associated with thememory cell 200. - The
memory cell 200 can also be reprogrammed to store a logical zero. As shown in FIG. 2C, after application of a relatively high voltage of reverse polarity, i.e., with the positive voltage applied to the conductingplate 210, reverses the migration of thedendrils 212 of material from the conducting layer. Thedendrils 212 of material from theconducting layer 202 passing through the insulatinglayer 204 are forced back toward theconducting layer 202 and out of the insulatinglayer 204 by the same natural attraction and repulsion of charges which originally caused the cell to be programmed. This relatively high voltage of reverse polarity causes thememory cell 200 to become nonconductive once more. When a lesser voltage is applied, thememory cell 200 will no longer conduct. Thus, and the cell now effectively stores a logical zero. In sum, higher voltages of opposite sense can be used to program and reprogram these cells to conduct or not conduct, storing logical ones or zeroes, respectively. - The
PCDRAM memory cell 200 described is far less volatile than a conventional DRAM memory cell. Without being refreshed, a conventional DRAM cell only can maintain its logical bit for microseconds, while thePCDRAM memory cell 200 potentially can maintain its logical bit for days. Eventually, natural diffusion of the material from theconducting layer 202 into and out of the insulatinglayer 204 resulting from ordinary atomic motion will corrupt the data stored. Nonetheless, PCDRAM devices need only be refreshed after an extended interval, thus, less power is needed to refresh these devices than is needed for the frequent refreshing required by conventional DRAM devices. - The problem remains that systems designed to work with conventional DRAM arrays are very common and standardized. One might substitute an array of PCDRAM memory cells in place of an array of conventional DRAM cells. However, power still would be wasted because control systems designed to work with conventional DRAM cells would refresh the PCDRAM cells at a rate consistent with the refresh rate requirements of conventional DRAM cells. The PCDRAM memory cells would be refreshed at a rate that is significantly higher than is required, wasting power.
- The need to redesign circuitry interfacing with the DRAM devices to take advantage of the power savings possible with PCDRAM devices may, at least initially, limit the usefulness of and market demand for PCDRAM devices. What is needed is a way to allow circuitry developed to refresh conventional DRAMs to work with PCDRAMs without wasting power. It is to this need that the present invention is directed.
- Through the addition of refresh signal delay means, an array comprised of less volatile DRAM devices, which only need to be refreshed after an extended interval, can be refreshed less frequently, consuming less power, while still using conventional DRAM refreshing control circuitry. The delay means delays externally generated refresh signals supplied to accommodate the refresh rate required by conventional DRAM memory devices but, in response, generates far less frequent delayed refresh signals. This reduces the frequency with which the less volatile DRAM devices will be refreshed, and powers off supporting addressing circuitry when it is not needed. Therefore, the delay means allows computing systems designed to use conventional DRAM devices to work with DRAM devices which only need to be refreshed after an extended interval and reduces the amount power wasted through unnecessarily frequent refresh cycles.
- FIG. 1 is a simplified block diagram of a section of a conventional DRAM memory array that may be adapted to use the invention in a burst refresh mode.
- FIG. 1A is a simplified block diagram of a section of a conventional DRAM memory array that may be adapted to use the invention in a distributed refresh mode.
- FIG. 2A is a cross-sectional view of a known programmable conductor DRAM (PCDRAM) memory cell in its initial state before the application of a voltage that can be used to write to the cell that may be used with the invention.
- FIG. 2B is a cross-sectional view of the PCDRAM cell depicted in FIG. 2A after a high voltage has been applied to the cell to write a logical one to the cell.
- FIG. 2C is a cross-sectional view of the PCDRAM cell depicted in FIG. 2B after a high voltage of polarity opposite to that applied to cause the state depicted in FIG. 2B has been applied to the cell to write a logical zero to the cell.
- FIG. 3 is a symbolic block diagram generally representing the functioning of embodiments of the present invention.
- FIG. 4 is a block diagram of the same section of a DRAM memory array depicted in FIG. 1 replacing the conventional DRAM devices with DRAM devices which only need to be refreshed after an extended interval and adapted with a first embodiment of the invention to reduce the power needed to refresh the memory array using a burst refresh mode.
- FIG. 4A is a block diagram of the same section of a DRAM memory array depicted in FIG. 1 replacing the conventional DRAM devices with DRAM devices which only need to be refreshed after an extended interval and adapted with a first embodiment of the invention to reduce the power needed to refresh the memory array using a distributed refresh mode.
- FIG. 5 is a timing diagram of the first embodiment of the invention to reflect the reduction in state changes made possible by the first embodiment of the invention.
- FIG. 6 is a block diagram of the same section of a DRAM memory array depicted in FIG. 4 further adapted with a second embodiment of the invention to save additional power in refreshing the memory array using a burst refresh mode.
- FIG. 6A is a block diagram of the same section of a DRAM memory array depicted in FIG. 4 further adapted with a second embodiment of the invention to save additional power in refreshing the memory array using a distributed refresh mode.
- FIG. 7 is a timing diagram of the second embodiment of the invention to reflect the reduction in state changes made possible by the second embodiment of the invention.
- FIG. 8 is a block diagram of a computer system using a memory array employing DRAM devices which only need to be refreshed after an extended interval and a power saving memory device of an embodiment of the invention.
- FIG. 3 represents the basic operation of embodiments of the present invention. External control devices designed to work with conventional DRAM devices will generate frequent conventional refresh signals. These conventional refresh signals310 will be generated at a frequency f which corresponds to the rapidity with which conventional DRAM devices must be refreshed. Control systems designed to work with DRAM devices that only need to be refreshed after an extended interval generate delayed refresh signals 320 far less often at a frequency f′. As described, conventional DRAM devices might need to be refreshed thousands of times per second, whereas DRAM devices such as PCDRAM cells may only need to be refreshed once per day. In this example, therefore, frequency f′ could be many orders of magnitude smaller than frequency f. The present invention uses delay means 330 operable to receive the conventional refresh signals 310 and, at appropriately delayed intervals, generate the less frequent delayed refresh signals 320. Thus, with the present invention, external devices designed to work with conventional DRAM devices may be used with DRAM devices which only need to be refreshed after an extended interval, without wasting power on unnecessarily frequent refresh cycles.
- FIG. 4 depicts a
memory array 410 very similar to thememory array 110 described in FIG. 1. Identical components shown in FIG. 4 have been provided with the same reference numeral, and explanation of their function and operation will not be repeated in the interest of brevity. The differences between thememory array 110 shown in FIG. 1 and thememory array 410 shown in FIG. 4 are twofold. First, thememory array 410 depicted in FIG. 4 has been adapted to use DRAM memory banks which only need to be refreshed after anextended interval extended interval delay counter 420 has been added to thememory array 410. Thememory array 410 shown in FIG. 4 employs burst refresh, as doesmemory array 110 in FIG. 1. - The
delay counter 420 shown in FIG. 4 is a bit up counter which extends the interval between refresh cycles being conducted in thememory banks delay counter 420 extends the interval between refresh cycles by intercepting and counting the refresh signals being generated by therefresh controller 120, therefresh controller 120 being responsive to externally applied refresh signals. Thedelay counter 420 generates a delayed refresh signal to initiate a refresh cycle only after having counted a large, predetermined number of refresh signals from therefresh controller 120. In effect, the overflow signal of thedelay counter 420 becomes the actual refresh signal for thememory array 410. - FIG. 5 shows how the
delay counter 420 receives refresh signals from therefresh controller 120 and periodically generates a delayed refresh signal to trigger a refresh cycle. Therefresh controller 120 generates a refresh signal as often as is needed to refresh conventionalDRAM memory banks refresh controller 120 would trigger a refresh cycle for theentire memory array 410. However, even though therefresh controller 120 issues a refresh signal at intervals t1 through t10, therefresh counter 124 and the addressingcircuitry 160, including therow multiplexer 130, row address latches 150 and 152, and row decoders 132-142, remain powered off and no refresh cycle is conducted until t3. Instead, for each refresh signal generated by therefresh controller 120, thedelay counter 420 is incremented. The delayed refresh signal will be generated only when a desired number of refresh signals generated by therefresh controller 120 have been counted and skipped. - At t3 the
delay counter 420 reaches its overflow count and thedelay counter 420 overflow signal goes high. As shown in FIG. 5, the overflow signal from thedelay counter 420 turns on therefresh counter 124 and the rest of the addressingcircuitry 160, including therow multiplexer 130, row address latches 150 and 152, and row decoders 132-142. Therefresh counter 124 cycles through all 214 or 16,384 row addresses in thememory array 410. Each address is passed to therow address multiplexer 130 which, in turn, directs the generated address to one of two row address latches 150 and 152. The row address latches 150 and 152 supply the row address to one of sixteen row address decoders 132-142 associated with eachmemory bank - At the conclusion of the refresh cycle, the overflow bit of the
refresh counter 124 goes high as depicted at t4 of FIG. 5. This overflow bit is fed back to thedelay counter 420 and resets it. At this point, thedelay counter 420 once again begins counting the refresh signals generated by therefresh controller 120, initiating a refresh cycle only after thedelay counter 420 again reaches its overflow count. A suitablylarge delay counter 420 could be used so that thedelay counter 420 would only overflow as often as needed to refresh thememory banks - The cells in the
memory banks circuitry 160, including therow multiplexer 130, the row address latches 150 and 152, and the row decoders 132-142, all can be left powered off except as needed. Unneeded refresh signals generated by therefresh controller 120, as shown at t1, t2, t5, and t8 in FIG. 5, can be ignored, and the addressing circuitry left powered off. Power need not be supplied to the addressingcircuitry 160 until thedelay counter 420 reaches overflow and indicates the addressingcircuitry 160 needs to be powered on, as shown at t3 and again at t9. The addressingcircuitry 160 can be powered off at the conclusion of each of the refresh cycles, as shown at t4 and t10 in FIG. 5. - The addressing
circuitry 160 still will be needed to perform memory read or write operations, as signaled by theexternal address signal 126 as shown at t6. However, because therefresh counter 124 is not needed for a memory read or write operation, therefresh counter 124 can still be left powered off at these times. - The addressing
circuitry 160 will be powered on by thedelay counter 420 or theexternal address signal 126. If the power sourced by the overflow signal of thedelay counter 420 orexternal address signal 126 is not sufficient to power the addressingcircuitry 160, the overflow signal of thedelay counter 420 or theexternal address signal 126 can be used to enable a transistor having sufficient power-handling capability to power these circuits. Use of a transistor or other device which can supply more power, switched by the output of another circuit, is well known in the art and will not be described here further for the sake of brevity. - FIG. 4A depicts a
similar memory array 410A adapted to use the first embodiment of the invention in a distributed refresh mode. There are only three differences between thememory array 410A depicted in FIG. 4A andmemory array 410 depicted in FIG. 4. First, therefresh counter 124 is pulsed by thedelay counter 420 instead of therefresh clock 122. As previously described, when using a distributed refresh mode, each refresh signal issued by therefresh controller 120 causes one single row of thememory banks delay counter 420 will count a large, predetermined number of these signals before initiating the refresh sequence for the next row in the memory array. Also as previously described, because one refresh sequence will be initiated for each of the 8,192 rows in thememory array 410A, the interval between refresh sequences initiated by thedelay counter 420 will be 1/8,192 as long as the interval between refresh sequences initiated by thedelay counter 420 for thememory array 410. Second, in thememory array 410A therefresh counter 124 is not powered on and off by thedelay counter 420. Using distributed refresh, therefresh counter 124 must constantly maintains its row count. Third, in thememory array 410A, an overflow output of therefresh counter 124 is not needed. - No separate timing diagram is included for the embodiment of the invention depicted in FIG. 4A. As will be appreciated in light of the foregoing discussion, the main differences between the timing of operations between the burst and distributed refresh mode embodiments are that the
refresh counter 124 always remains on and there is no need for arefresh counter 124 overflow signal. Thus, the plots of these signals in FIG. 5 can be ignored. Just as with the burst mode embodiment, when thedelay counter 420 reaches overflow, the addressing circuitry is powered on and the next row in the memory array is refreshed. - In sum, the first embodiment of the invention provides three significant advantages. First, none of the circuitry designed to work with conventional DRAM devices, including the
refresh controller 120,refresh clock 122,refresh counter 124, row decoders 132-142, row address latches 150 and 152, androw multiplexer 130 or any external circuitry directing therefresh controller 120, must be redesigned or even altered. The embodiment of FIG. 4 allows the use of conventional refreshing circuitry only by adding thedelay counter 420 to control the enabling of the addressingcircuitry 160. Second, power consumption is reduced within thememory storage banks circuitry 160 is reduced because these devices would be powered off when not in use. - A second embodiment of the invention shown in FIG. 6 shows how additional power can be saved by selectively powering on only parts of the addressing
circuitry 660 during a refresh cycle. In the first embodiment of the invention, when either thedelay counter 420 reaches overflow, all of the addressingcircuitry 160 is powered on, regardless of which row of whichmemory bank memory banks row address multiplexer 130, two row address latches 150 and 152, and thirty-two row decoders 132-142. Further, considering that thememory array 410 stores just one bit of what presumably is at least an eight-bit word, then at least eight times as many devices would be powered on each time the memory is accessed for a read, write, or refresh operation, even though only one row can be read from, written to, or refreshed at one time. - This second embodiment uses five additional control devices to control addressing of the memory array during refresh cycles, only three of which are powered on at one time when using a burst refresh mode. These additional devices allow for only six supporting devices to be activated at a time during a refresh cycle instead of thirty-five. This saves the wasteful powering and heat generation of twenty-nine superfluous devices. For a memory array eight bits in width, forty-eight devices would only need to be powered on at one time instead of two-hundred and eighty.
- FIG. 6 depicts a
memory array 610 very similar to thememory array 410 described in FIG. 4. PCDRAM memory banks which only need to be refreshed after anextended interval delay counter 420 again is employed to extend the interval between refresh cycles. Five devices are added to thememory array 610 shown in FIG. 6: a bank segment bit upcounter 670, two row bit upcounters row decoder selectors - The
sample memory array 610 again includes twomemory banks memory banks counters memory bank counters row decoder selector counters counter A 680 and rowdecoder selector A 690, and row bit upcounter B 682 and row bit updecoder B 692, can selectively and sequentially power on each of the sixteen bit row decoders 132-142 for each of theirrespective memory banks - FIG. 7 shows how the
delay counter 420 receives refresh signals from therefresh controller 120, periodically triggers a refresh cycle, and governs the selective powering on of the addressingcircuitry 660. As compared to FIG. 5, which described the operation of the first embodiment of this invention, FIG. 7 details a shorter interval of time to highlight the sequential powering on of the individual row decoders 132-142 during a refresh cycle. Unlike FIG. 5, in FIG. 7 the refresh signals generated by therefresh controller 120 are not shown; it will be appreciated that therefresh controller 120 necessarily continues to generate refresh signals, but depiction of its signal has been eliminated from this figure for the sake of simplicity. - At t1, the
delay counter 420 has counted the large, predetermined number of refresh signals generated by therefresh controller 120 to warrant initiating a refresh sequence for the DRAM memory banks which only need to be refreshed after anextended interval delay counter 420 goes high and powers on therefresh counter 124, therow address multiplexer 130, and the row address latches 150 and 152. However, in contrast to the first embodiment of this invention, the overflow signal generated by thedelay counter 420 does not power on each of the row decoders 132-142. Instead, this overflow signal powers on row bit up counter A 680, rowdecoder selector A 690, and the bank segment bit upcounter 670. With row bit up counter A 680 powered on in its initial state, it supplies a count of four zeroes to rowdecoder selector A 690. Row decoder selector A therefore activatesrow decoder A 0 132. Because it is active,row decoder A 0 132 is able to sequentially address each of the 29 or 512 rows that it addresses inmemory bank A 412. These row addresses are supplied to rowdecoder A 0 132 by rowaddress latch A 150, which has received that address from therow address multiplexer 130. Therow address multiplexer 130 has generated this address by decoding the count provided to it by therefresh counter 124. - In this example, the bank segment bit up
counter 670 is a nine-bit counter that will reach overflow after counting 29 or 512 pulses of therefresh clock 122. The overflow of the bank segment bit upcounter 670 is connected to both the row bit upcounters counters refresh clock 122 have enabled the refreshing of each of the 512 rows in the memory bank segment addressed by each of the row decoders 132-142. Thesame refresh clock 122 pulses the bank segment bit upcounter 670 and therefresh counter 124. Thus, the nine-bit count maintained by the bank segment bit upcounter 670 and the nine least significant bits of the count maintained by therefresh counter 124 will be synchronized. Because they are synchronized, with the completion of each nine-bit count, the bank segment bit up counter 670 will overflow to increment the appropriate row bit upcounter row decoder selector refresh counter 124 continues to count the rows it refreshes throughout thememory array 610. - At time t2 the bank segment bit up
counter 670 has sequenced through its entire nine-bit sequence and generates an overflow signal. This overflow signal increments row bit upcounter A 680. In turn, rowdecoder selector A 690 generates a different sixteen-bit code which powers offrow decoder A 0 132 and powers onrow decoder A 1 134. As the bank segment bit up counter 670 again sequences through its nine-bit count, therefresh counter 124 sequences through the nine least significant bits of its count for the second time. This time, however, the nine least significant bits of the count generated byrefresh counter 124 are applied throughrow decoder A 1 134 and serve to address and refresh the next 512 rows ofmemory bank A 412. - At t3, when the bank segment bit up
counter 670 reaches overflow for the second time,row decoder A 1 134 is then powered off while the next row decoder A2 (not shown in FIG. 6) is powered on, while all the other row decoders 132-142 remain powered off. This sequence continues until t4, when the bank segment bit upcounter 670 has reached overflow for the sixteenth time. At t4, having counted sixteen overflows of the bank segment bit upcounter 670, row bit up counter A 680 reaches overflow. As shown in FIG. 7, this overflow signal powers on rowdecoder selector B 682 and its associatedrow decoder selector 692. A simple latch, whose use is well known in the art, could be used to preserve the high overflow signal generated by row bit upcounter A 680 to maintain power to row bit upcounter B 682 and its associated rowdecoder selector B 692 while powering off row bit upcounter A 680 and rowdecoder selector A 690. - As was the case with row bit up counter A680, when it is powered on at t4, row bit up
counter B 682 supplies a count of four zeroes to rowdecoder selector B 692. Rowdecoder selector B 692 activatesrow decoder B 0 138.Row decoder B 0 138 then sequentially addresses each of the 512 rows ofmemory bank A 412 that it serves. These row addresses are supplied to rowdecoder B 0 138 by rowaddress latch B 152, which has received that address from therow address multiplexer 130. Therow address multiplexer 130 has generated this address by decoding the count provided to it by therefresh counter 124. - At t5 the bank segment bit up
counter 670 has sequenced through its nine-bit count and reached overflow. This overflow signal causes row bit upcounter B 682 to increment, in turn causing rowdecoder selector B 692 to power offrow decoder B 0 138 and activaterow decoder B 1 140. Thus, as with the sixteen row decoders 132-136 associated withmemory bank A 412, the repeated overflow of the bank segment bit upcounter 670 activates one at a time the sixteen address decoders 138-142 associated withmemory bank B 414, while each addresses the 512 rows it serves in associatedmemory bank B 414. - At t6 all sixteen row decoders 132-142 for both
memory banks refresh counter 124 reaches overflow, and the refresh cycle is complete. Overflow of therefresh counter 124, as in the first embodiment, powers off the addressingcircuitry 660 and therefresh counter 124. One difference in the second embodiment is that fewer devices in the addressingcircuitry 660 will be turned off upon overflow of therefresh counter 124. This is because only a few devices needed to refresh the last 512 rows ofmemory bank B 414 still will be powered on at the end of the refresh cycle, including therow address multiplexer 130, rowaddress latch A 150, rowaddress latch B 152, row bit upcounter B 682, rowdecoder selector B 692, androw decoder B 15 142. These, too, will be powered off upon overflow of therefresh counter 124. - At t7, when an
external address signal 126 is received, all the addressingcircuitry 660 is powered up. In this embodiment, all of the circuitry is powered up so that each of thememory banks external address signal 126 having to wait for the sequential activation of row decoders 132-142 which would slow system processing throughput. The memory access initiated by receipt of theexternal address signal 126 is completed at t8, and all of the addressingcircuitry 660 is powered off. - FIG. 6A depicts a
similar memory array 610A adapted to use the first embodiment of the invention in a distributed refresh mode. There are only three differences between thememory array 610A depicted in FIG. 6A andmemory array 610 depicted in FIG. 6. First, as with the first embodiment of the invention adapted to use distributed refresh, therefresh counter 124 is pulsed by thedelay counter 420 instead of therefresh clock 122. Second, in thememory array 610A, therefresh counter 124, the row segment bit upcounter 670, and row bit upcounter A 680 and row bit upcounter B 682 are not powered on and off by thedelay counter 420. Using distributed refresh, therefresh counter 124 and the bank segment bit up counter 670 must constantly maintain their row counts. Similarly, at least one of either row bit up counter A 680 or row bit upcounter B 682, whichever is currently active, must remain powered on to maintain its count of which of the row decoders 132-142 should be activated when the next row is refreshed. Using latches (not shown), the overflow output of row bit up counter A 680 can be used to power on row bit upcounter B 682, and the overflow output of row bit upcounter B 682 can be used to power on row bit up counter A 680 so that the one not being used does not need to be powered on at all times. Alternatively, for design simplicity, both row bit upcounters memory array 410A, an overflow output of therefresh counter 124 is not needed. - No separate timing diagram is included for the embodiment of the invention depicted in FIG. 6A. As will be appreciated in light of the foregoing discussion, the main differences between the timing of operations between the burst and distributed refresh mode embodiments are that the
refresh counter 124, the bank segment bit upcounter 670, and at least one of the row bit upcounters delay counter 420 reaches overflow, the addressingcircuitry 660 will be powered on, one row will be refreshed, and then the addressing circuitry will be powered off until thenext delay counter 420 overflow. Just as with the burst mode embodiment, when either of the row bit upcounters - Certainly, the invention also could be embodied in other forms. One example not shown in the figures could be a hybrid form using a series of distributed refresh signals generated by the refresh controller to perform, in essence, a slow burst refresh of the array after the passage of an extended interval. The refresh controller would be programmed to generate row refresh signals after the passage of a suitable interval for a conventional DRAM array. The delay counter would intercept, count, and ignore a number of these distributed refresh signals until the passage of an extended interval by when the less volatile memory devices would have to be refreshed. As with other embodiments, the number of refresh signals from the refresh controller to be ignored would be determined by the duration of the extended interval divided by the duration between refresh signals generated by the refresh controller for a conventional DRAM memory array.
- After the extended interval had passed, the delay counter would pass the refresh signals from the refresh controller through to the refresh counter. This could be handled by connecting the overflow signal from the delay counter and the refresh signal from the refresh controller to an AND gate, the output of which would become the input pulse to the refresh controller. After counting a number of refresh signals corresponding to the extended interval causing the delay counter's overflow signal to go high, the refresh signals would cause a high output from the AND gate which, in turn, would pulse the refresh counter. The rows of the less volatile memory array would then be refreshed sequentially as pulsed by the row refresh signals from the refresh controller. In other words, the memory array would be refreshed in one slow, sequential burst in rhythm to the row refresh signals from the refresh controller after the passage of an extended interval. Once all the rows were refreshed, the delay counter would reset, and proceed to ignore another long sequence of row refresh commands from the refresh controller until the less volatile memory array once again needed to be refreshed.
- This is just one potential additional embodiment. Other embodiments of the invention also conceivably might be created to exploit the power savings afforded by the use of a delay apparatus to avoid unnecessary refresh cycles.
- Embodiments of the invention can be incorporated into a computer system by one skilled in the art. FIG. 8 is a block diagram of a
computer system 810 that includes aprocessor 812 for performing various computing functions by executing software to perform specific calculations or tasks. Theprocessor 812 is coupled to aprocessor bus 814 that normally includes an address bus, a control bus, and a data bus (not separately shown). In addition, thecomputer system 810 includes asystem memory 816, which could be thememory array 410 of FIG. 4 or thememory array 610 of FIG. 6, both of which use DRAM devices which only need to be refreshed after an extended interval, such as PCDRAM devices, and supporting circuitry which enables the power savings previously described. Thesystem memory 816 is coupled to theprocessor bus 814 by asystem controller 820 or similar device, which is also coupled to anexpansion bus 822, such as a Peripheral Component Interface (“PCI”) bus. A bus 726 coupling thesystem controller 820 to thesystem memory 816 also normally includes an address bus, a control bus, and a data bus (not separately shown), although other architectures can be used. For example, the data bus of thesystem memory 816 may be coupled to the data bus of theprocessor bus 814, or thesystem memory 816 may be implemented by a packetized memory (not shown), which normally does not include a separate address bus and control bus. - The
computer system 810 also includes one ormore input devices 834, such as a keyboard or a mouse, coupled to theprocessor 812 through theexpansion bus 822, thesystem controller 820, and theprocessor bus 814. Also typically coupled to theexpansion bus 822 are one ormore output devices 836, such as a printer or a video terminal. One or moredata storage devices 838 are also typically coupled to theexpansion bus 822 to allow theprocessor 812 to store data or retrieve data from internal or external storage media (not shown). Examples oftypical storage devices 838 include hard and floppy disks, tape cassettes, and compact disk read-only memories (CD-ROMs). Theprocessor 812 is also typically coupled tocache memory 840 through theprocessor bus 814. - It should be noted that, unlike
conventional DRAM devices memory banks - One also should note that PCDRAM devices themselves can be powered off when not being accessed. PCDRAM devices store their data bits by undergoing a physical transformation as previously described. Thus, they can be turned off when not in use. In the first embodiment of the invention,
memory bank A 412 andmemory bank B 414 could be powered on and off by thesame delay counter 420 overflow signal that powered on the addressingcircuitry 160. In the second embodiment of the invention,memory bank A 412 could be powered on by thesame delay counter 420 overflow signal that powers on row bit updecoder A 680 and rowdecoder selector A 690, and powered off by the same row bit up counter A 680 overflow signal that powers off row bit updecoder A 680 and rowdecoder selector A 690. Similarly,memory bank B 414 could be powered on by the same row bit up counter A 680 overflow signal that powers on row bit updecoder B 682 and rowdecoder selector B 692, and powered off by thesame refresh counter 124 overflow signal that powers off row bit updecoder B 682 and rowdecoder selector B 692. - In sum, the first embodiment of the invention saves power by extending the time between refresh cycles to exploit less volatile DRAM devices which need to be refreshed only after an extended interval. The first embodiment accomplishes this predominantly through the use of a delay counter which delays the refresh signals generated by a conventional refresh controller designed for conventional DRAM memory devices, and generates refresh signals much less frequently. The second embodiment of the invention further saves power during each refresh cycle by sequentially activating only the row decoders needed to address the rows currently being refreshed rather than powering on all the row decoders at once.
- It is to be understood that, even though various embodiments and advantages of the present invention have been set forth in the foregoing description, the above disclosure is illustrative only. Changes may be made in detail, and yet remain within the broad principles of the invention.
Claims (143)
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/002,707 US6560155B1 (en) | 2001-10-24 | 2001-10-24 | System and method for power saving memory refresh for dynamic random access memory devices after an extended interval |
US10/418,945 US6930944B2 (en) | 2001-10-24 | 2003-04-18 | System and method for power saving memory refresh for dynamic random access memory devices after an extended interval |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/002,707 US6560155B1 (en) | 2001-10-24 | 2001-10-24 | System and method for power saving memory refresh for dynamic random access memory devices after an extended interval |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/418,945 Continuation US6930944B2 (en) | 2001-10-24 | 2003-04-18 | System and method for power saving memory refresh for dynamic random access memory devices after an extended interval |
Publications (2)
Publication Number | Publication Date |
---|---|
US20030076725A1 true US20030076725A1 (en) | 2003-04-24 |
US6560155B1 US6560155B1 (en) | 2003-05-06 |
Family
ID=21702081
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/002,707 Expired - Lifetime US6560155B1 (en) | 2001-10-24 | 2001-10-24 | System and method for power saving memory refresh for dynamic random access memory devices after an extended interval |
US10/418,945 Expired - Lifetime US6930944B2 (en) | 2001-10-24 | 2003-04-18 | System and method for power saving memory refresh for dynamic random access memory devices after an extended interval |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/418,945 Expired - Lifetime US6930944B2 (en) | 2001-10-24 | 2003-04-18 | System and method for power saving memory refresh for dynamic random access memory devices after an extended interval |
Country Status (1)
Country | Link |
---|---|
US (2) | US6560155B1 (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2932006A1 (en) * | 2008-06-03 | 2009-12-04 | E2V Semiconductors | Integrated circuit for use on electronic chip of electronic matrix image sensor, has logic authorization circuits associated to corresponding groups for authorizing or preventing activation of lines by decoders based on content of cells |
US11373695B2 (en) * | 2019-12-18 | 2022-06-28 | Micron Technology, Inc. | Memory accessing with auto-precharge |
US20230042731A1 (en) * | 2021-08-06 | 2023-02-09 | Winbond Electronics Corp. | Semiconductor memory device |
US12022666B2 (en) | 2018-08-13 | 2024-06-25 | Micron Technology, Inc. | Memory cell stack and via formation for a memory device |
US12087358B2 (en) | 2018-08-13 | 2024-09-10 | Micron Technology, Inc. | Access line grain modulation in a memory device |
Families Citing this family (33)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2820874B1 (en) * | 2001-02-13 | 2003-05-30 | St Microelectronics Sa | METHOD FOR THE RANDOM AND QUICK ACCESS MANAGEMENT OF A DRAM MEMORY |
US6646902B2 (en) * | 2001-08-30 | 2003-11-11 | Micron Technology, Inc. | Method of retaining memory state in a programmable conductor RAM |
US6560155B1 (en) * | 2001-10-24 | 2003-05-06 | Micron Technology, Inc. | System and method for power saving memory refresh for dynamic random access memory devices after an extended interval |
EP1408510A3 (en) * | 2002-05-17 | 2005-05-18 | Matsushita Electric Industrial Co., Ltd. | Memory control apparatus, method and program |
JP4246971B2 (en) * | 2002-07-15 | 2009-04-02 | 富士通マイクロエレクトロニクス株式会社 | Semiconductor memory |
KR100543914B1 (en) * | 2003-04-30 | 2006-01-23 | 주식회사 하이닉스반도체 | Semiconductor memory device for reducing peak current during refreshing operation |
US6961277B2 (en) * | 2003-07-08 | 2005-11-01 | Micron Technology, Inc. | Method of refreshing a PCRAM memory device |
KR100596443B1 (en) * | 2004-04-27 | 2006-07-05 | 주식회사 하이닉스반도체 | Refresh control circuit and method for multi-bank structure dram |
US7099221B2 (en) * | 2004-05-06 | 2006-08-29 | Micron Technology, Inc. | Memory controller method and system compensating for memory cell data losses |
US20060010339A1 (en) * | 2004-06-24 | 2006-01-12 | Klein Dean A | Memory system and method having selective ECC during low power refresh |
US7340668B2 (en) * | 2004-06-25 | 2008-03-04 | Micron Technology, Inc. | Low power cost-effective ECC memory system and method |
US7116602B2 (en) * | 2004-07-15 | 2006-10-03 | Micron Technology, Inc. | Method and system for controlling refresh to avoid memory cell data losses |
US6965537B1 (en) * | 2004-08-31 | 2005-11-15 | Micron Technology, Inc. | Memory system and method using ECC to achieve low power refresh |
KR100564633B1 (en) * | 2004-09-25 | 2006-03-28 | 삼성전자주식회사 | Semiconductor memory device having improved operation performance and access control method of the same |
US7356642B2 (en) * | 2004-11-12 | 2008-04-08 | International Business Machines Corporation | Deferring refreshes during calibrations in memory systems |
JP4282612B2 (en) * | 2005-01-19 | 2009-06-24 | エルピーダメモリ株式会社 | Memory device and refresh method thereof |
US7177208B2 (en) * | 2005-03-11 | 2007-02-13 | Micron Technology, Inc. | Circuit and method for operating a delay-lock loop in a power saving manner |
US7158434B2 (en) * | 2005-04-29 | 2007-01-02 | Infineon Technologies, Ag | Self-refresh circuit with optimized power consumption |
US7366047B2 (en) * | 2005-11-09 | 2008-04-29 | Infineon Technologies Ag | Method and apparatus for reducing standby current in a dynamic random access memory during self refresh |
US20070279975A1 (en) * | 2006-06-06 | 2007-12-06 | Hudgens Stephen J | Refreshing a phase change memory |
US7599208B2 (en) * | 2006-07-27 | 2009-10-06 | Hynix Semiconductor Inc. | Nonvolatile ferroelectric memory device and refresh method thereof |
US7505349B2 (en) * | 2006-09-07 | 2009-03-17 | Honeywell International Inc. | Refresh sequence control for multiple memory elements |
US7894289B2 (en) | 2006-10-11 | 2011-02-22 | Micron Technology, Inc. | Memory system and method using partial ECC to achieve low power refresh and fast access to data |
US7900120B2 (en) * | 2006-10-18 | 2011-03-01 | Micron Technology, Inc. | Memory system and method using ECC with flag bit to identify modified data |
US8042022B2 (en) | 2007-03-08 | 2011-10-18 | Micron Technology, Inc. | Method, system, and apparatus for distributed decoding during prolonged refresh |
CN103197753A (en) * | 2013-03-25 | 2013-07-10 | 西安华芯半导体有限公司 | Power saving method of DRAM (Dynamic Random Access Memory) |
US8982654B2 (en) * | 2013-07-05 | 2015-03-17 | Qualcomm Incorporated | DRAM sub-array level refresh |
US9939865B2 (en) | 2014-06-13 | 2018-04-10 | Seagate Technology Llc | Selective storage resource powering for data transfer management |
US9721640B2 (en) | 2015-12-09 | 2017-08-01 | Intel Corporation | Performance of additional refresh operations during self-refresh mode |
US10467172B2 (en) | 2016-06-01 | 2019-11-05 | Seagate Technology Llc | Interconnect for shared control electronics |
US10297307B1 (en) * | 2017-12-29 | 2019-05-21 | Micron Technology, Inc. | Methods for independent memory bank maintenance and memory devices and systems employing the same |
US11568913B2 (en) * | 2020-02-05 | 2023-01-31 | Micron Technology, Inc. | Voltage adjustment based on pending refresh operations |
US12093546B2 (en) | 2021-03-02 | 2024-09-17 | Seagate Technology Llc | Operating multiple storage devices using NVM interface |
Family Cites Families (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0778991B2 (en) * | 1988-07-26 | 1995-08-23 | 株式会社東芝 | Semiconductor memory |
US6392948B1 (en) * | 1996-08-29 | 2002-05-21 | Micron Technology, Inc. | Semiconductor device with self refresh test mode |
US5991851A (en) * | 1997-05-02 | 1999-11-23 | Enhanced Memory Systems, Inc. | Enhanced signal processing random access memory device utilizing a DRAM memory array integrated with an associated SRAM cache and internal refresh control |
US5999481A (en) * | 1997-08-22 | 1999-12-07 | Micron Technology, Inc. | Method and apparatus for controlling the operation of an integrated circuit responsive to out-of-synchronism control signals |
US6724654B1 (en) * | 2000-08-14 | 2004-04-20 | Micron Technology, Inc. | Pulsed write techniques for magneto-resistive memories |
US6646902B2 (en) * | 2001-08-30 | 2003-11-11 | Micron Technology, Inc. | Method of retaining memory state in a programmable conductor RAM |
US6560155B1 (en) * | 2001-10-24 | 2003-05-06 | Micron Technology, Inc. | System and method for power saving memory refresh for dynamic random access memory devices after an extended interval |
US6791859B2 (en) * | 2001-11-20 | 2004-09-14 | Micron Technology, Inc. | Complementary bit PCRAM sense amplifier and method of operation |
US6873538B2 (en) * | 2001-12-20 | 2005-03-29 | Micron Technology, Inc. | Programmable conductor random access memory and a method for writing thereto |
US6909656B2 (en) * | 2002-01-04 | 2005-06-21 | Micron Technology, Inc. | PCRAM rewrite prevention |
US6791885B2 (en) * | 2002-02-19 | 2004-09-14 | Micron Technology, Inc. | Programmable conductor random access memory and method for sensing same |
US6891749B2 (en) * | 2002-02-20 | 2005-05-10 | Micron Technology, Inc. | Resistance variable ‘on ’ memory |
US6849868B2 (en) * | 2002-03-14 | 2005-02-01 | Micron Technology, Inc. | Methods and apparatus for resistance variable material cells |
US6751114B2 (en) * | 2002-03-28 | 2004-06-15 | Micron Technology, Inc. | Method for programming a memory cell |
US6864500B2 (en) * | 2002-04-10 | 2005-03-08 | Micron Technology, Inc. | Programmable conductor memory cell structure |
US6731528B2 (en) * | 2002-05-03 | 2004-05-04 | Micron Technology, Inc. | Dual write cycle programmable conductor memory system and method of operation |
US7010644B2 (en) * | 2002-08-29 | 2006-03-07 | Micron Technology, Inc. | Software refreshed memory device and method |
-
2001
- 2001-10-24 US US10/002,707 patent/US6560155B1/en not_active Expired - Lifetime
-
2003
- 2003-04-18 US US10/418,945 patent/US6930944B2/en not_active Expired - Lifetime
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2932006A1 (en) * | 2008-06-03 | 2009-12-04 | E2V Semiconductors | Integrated circuit for use on electronic chip of electronic matrix image sensor, has logic authorization circuits associated to corresponding groups for authorizing or preventing activation of lines by decoders based on content of cells |
US12022666B2 (en) | 2018-08-13 | 2024-06-25 | Micron Technology, Inc. | Memory cell stack and via formation for a memory device |
US12087358B2 (en) | 2018-08-13 | 2024-09-10 | Micron Technology, Inc. | Access line grain modulation in a memory device |
US11373695B2 (en) * | 2019-12-18 | 2022-06-28 | Micron Technology, Inc. | Memory accessing with auto-precharge |
US20230042731A1 (en) * | 2021-08-06 | 2023-02-09 | Winbond Electronics Corp. | Semiconductor memory device |
US11798609B2 (en) * | 2021-08-06 | 2023-10-24 | Winbond Electronics Corp. | Semiconductor memory device including control unit controlling time interval of refresh operation on memory to shorten interval between memory refresh operations corresponding to read/write access requirement |
Also Published As
Publication number | Publication date |
---|---|
US6560155B1 (en) | 2003-05-06 |
US6930944B2 (en) | 2005-08-16 |
US20040032782A1 (en) | 2004-02-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US6560155B1 (en) | System and method for power saving memory refresh for dynamic random access memory devices after an extended interval | |
JP4979589B2 (en) | System and method for reducing power consumption during an extended refresh period of a dynamic random access memory device | |
US7164615B2 (en) | Semiconductor memory device performing auto refresh in the self refresh mode | |
JP5767778B2 (en) | Memory with selective precharge | |
US6711093B1 (en) | Reducing digit equilibrate current during self-refresh mode | |
US10585597B2 (en) | Wear leveling | |
WO2000054159A1 (en) | Method and system for selective dram refresh to reduce power consumption | |
US7345940B2 (en) | Method and circuit configuration for refreshing data in a semiconductor memory | |
EP1761932B1 (en) | Dram with half and full density operation | |
US7298661B2 (en) | Semiconductor memory device | |
JP2013037760A (en) | Memory with front end precharge | |
US6646941B1 (en) | Apparatus for operating an integrated circuit having a sleep mode | |
US20080080284A1 (en) | Method and apparatus for refreshing memory cells of a memory | |
US8909849B2 (en) | Pipeline architecture for scalable performance on memory | |
US7042786B2 (en) | Memory with adjustable access time | |
US9361972B1 (en) | Charge level maintenance in a memory | |
KR900007998B1 (en) | Random access memory device formed on a semiconductor substrate having an array of memory cells divided into sub-arrays | |
US20230221871A1 (en) | Memory device and operating method thereof | |
US7561489B2 (en) | System and method of selective row energization based on write data | |
KR102483906B1 (en) | Nas memory cell combined with nand flash memory and static random access memory and nas memory array using the same | |
JPS62154293A (en) | Semiconductor storage device | |
JPH0757460A (en) | Refreshing control circuit | |
JPH09251783A (en) | Refresh control method, semiconductor storage device, and data processing device | |
JPH09330595A (en) | Semiconductor memory and data processor | |
JPS63276785A (en) | Address buffer circuit for dynamic type semiconductor memory |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: MICRON TECHNOLOGY, INC., IDAHO Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:HUSH, GLEN;REEL/FRAME:012388/0846 Effective date: 20011012 |
|
FEPP | Fee payment procedure |
Free format text: PAYOR NUMBER ASSIGNED (ORIGINAL EVENT CODE: ASPN); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
CC | Certificate of correction | ||
FPAY | Fee payment |
Year of fee payment: 4 |
|
FPAY | Fee payment |
Year of fee payment: 8 |
|
FPAY | Fee payment |
Year of fee payment: 12 |
|
AS | Assignment |
Owner name: U.S. BANK NATIONAL ASSOCIATION, AS COLLATERAL AGENT, CALIFORNIA Free format text: SECURITY INTEREST;ASSIGNOR:MICRON TECHNOLOGY, INC.;REEL/FRAME:038669/0001 Effective date: 20160426 Owner name: U.S. BANK NATIONAL ASSOCIATION, AS COLLATERAL AGEN Free format text: SECURITY INTEREST;ASSIGNOR:MICRON TECHNOLOGY, INC.;REEL/FRAME:038669/0001 Effective date: 20160426 |
|
AS | Assignment |
Owner name: MORGAN STANLEY SENIOR FUNDING, INC., AS COLLATERAL AGENT, MARYLAND Free format text: PATENT SECURITY AGREEMENT;ASSIGNOR:MICRON TECHNOLOGY, INC.;REEL/FRAME:038954/0001 Effective date: 20160426 Owner name: MORGAN STANLEY SENIOR FUNDING, INC., AS COLLATERAL Free format text: PATENT SECURITY AGREEMENT;ASSIGNOR:MICRON TECHNOLOGY, INC.;REEL/FRAME:038954/0001 Effective date: 20160426 |
|
AS | Assignment |
Owner name: U.S. BANK NATIONAL ASSOCIATION, AS COLLATERAL AGENT, CALIFORNIA Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE REPLACE ERRONEOUSLY FILED PATENT #7358718 WITH THE CORRECT PATENT #7358178 PREVIOUSLY RECORDED ON REEL 038669 FRAME 0001. ASSIGNOR(S) HEREBY CONFIRMS THE SECURITY INTEREST;ASSIGNOR:MICRON TECHNOLOGY, INC.;REEL/FRAME:043079/0001 Effective date: 20160426 Owner name: U.S. BANK NATIONAL ASSOCIATION, AS COLLATERAL AGEN Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE REPLACE ERRONEOUSLY FILED PATENT #7358718 WITH THE CORRECT PATENT #7358178 PREVIOUSLY RECORDED ON REEL 038669 FRAME 0001. ASSIGNOR(S) HEREBY CONFIRMS THE SECURITY INTEREST;ASSIGNOR:MICRON TECHNOLOGY, INC.;REEL/FRAME:043079/0001 Effective date: 20160426 |
|
AS | Assignment |
Owner name: JPMORGAN CHASE BANK, N.A., AS COLLATERAL AGENT, ILLINOIS Free format text: SECURITY INTEREST;ASSIGNORS:MICRON TECHNOLOGY, INC.;MICRON SEMICONDUCTOR PRODUCTS, INC.;REEL/FRAME:047540/0001 Effective date: 20180703 Owner name: JPMORGAN CHASE BANK, N.A., AS COLLATERAL AGENT, IL Free format text: SECURITY INTEREST;ASSIGNORS:MICRON TECHNOLOGY, INC.;MICRON SEMICONDUCTOR PRODUCTS, INC.;REEL/FRAME:047540/0001 Effective date: 20180703 |
|
AS | Assignment |
Owner name: MICRON TECHNOLOGY, INC., IDAHO Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:U.S. BANK NATIONAL ASSOCIATION, AS COLLATERAL AGENT;REEL/FRAME:047243/0001 Effective date: 20180629 |
|
AS | Assignment |
Owner name: MICRON TECHNOLOGY, INC., IDAHO Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS COLLATERAL AGENT;REEL/FRAME:050937/0001 Effective date: 20190731 |
|
AS | Assignment |
Owner name: MICRON TECHNOLOGY, INC., IDAHO Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:JPMORGAN CHASE BANK, N.A., AS COLLATERAL AGENT;REEL/FRAME:051028/0001 Effective date: 20190731 Owner name: MICRON SEMICONDUCTOR PRODUCTS, INC., IDAHO Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:JPMORGAN CHASE BANK, N.A., AS COLLATERAL AGENT;REEL/FRAME:051028/0001 Effective date: 20190731 |