DDR2 or SDRAM full report
project report tiger|
Active In SP
Joined: Feb 2010
12-02-2010, 10:12 AM
DDR2 SDRAM.doc (Size: 118 KB / Downloads: 133)
DDR2 SDRAM or double-data-rate two synchronous dynamic random access memory is a computer memory technology. It is a refinement to the existing DRAM technology. JEDEC (Joint Electron Device Engineering Council) which provides standards for memory technologies has standardized this technology.
Double Data Rate and Dual channel Architecture enhances memory performance. DDR2 requires less space and provides high density modules .Power consumption is also less which makes DDR2 a favorite user choice.
DDR2 increases bandwidth, provides reliability, has good signal integrity. DDR2 achieves these by using some prominent technologies. They are On Die Termination, Off Chip Driver Calibration, Posted CAS and Additive Latency, etc. DDR2 memory is supported by all motherboard manufactures.
DDR2 SDRAM or double-data-rate two synchronous dynamic random access memory is a computer memory technology. It is a part of the SDRAM family of random access memory technologies, which is one of many DRAM implementations. -
DDR or Double Data Rate SDRAM is so called because data is transferred twice per clock, once each for the crest and through edges of a signal. In comparison, earlier SDRAM could only manage one transaction per clock. The data transfer rate is therefore twice as much as the frequency of the memory cells, that is, 200MHz DDR memory is called DDR 400.
The existing memory technology DDR peaks out at 500 MHz, with some manufactures going into the 550 MHz realm. But the problem was, DDR architecture was left with no headroom for future speed-ups. Although almost no amount of time was bandwidth increments will bring memory anywhere close to satisfying the processor's bandwidth requirements, DDR2 seems like a step in a logical direction, offering steep increments in raw clock speeds at least. With DDR2 promising that 1066 MHz will become mainstream by late 2007, and 800 MHz already available in goodly doses, it seems right on track to greet the latest monsters from Intel & AMD the Conroe and AM2 processors respectively.
DDR2's clock frequency is further boosted by electrical interface improvements, on-die termination, prefetch buffers and off-chip drivers. However, latency is greatly increased as a trade-off. The DDR2 prefetch buffer is 4 bits wide, whereas it is 2 bits wide for DDR
Power savings are achieved primarily due to an improved manufacturing process, resulting in a drop in operating voltage (1.8 V compared to DDR's 2.5 V). The lower memory clock frequency could also help DDR2 can use a real clock frequency 1/2 that of SDRAM whilst maintaining the same bandwidth.
DDR2 SDRAM has 240 pins as opposed to 184 pins on DDR and 168 pins on SDRAM. So DDR is not backward compatible with DDR2
2. NEED FOR FASTER MEMORY
The performance of any PC depends upon just five major devices-the CPU, the chipset/motherboard, the RAM the graphics solution and the hard disks. It is known fact that the hard drives are by far the most serious bottleneck as far as data transmission goes. However, the processor and Graphics card on a PC are fed directly by the system memory, and due to the speed limitations that plague RAM and latencies, another bottleneck emerges.
With today's gigahertz CPUs and dual and quad core cores, number crunching is never going to be an issue, and the main challenge remains supplying these processors with sufficient data to satiate their enormous appetite. The RAM is that vital link entrusted with supplying this data, and the performance of the memory used in a PC will directly impact the overall system performance. To increase the system performance the bandwidth should be increased.
To represent bandwidth in a simple formula: Bandwidth=Frequency*Bus Width.
"Frequency" here means the rate of data transfer (mostly measured in MHz), while bus width is measured in bits and represents the width of the path that the data flows through. We can visualize RAM as a highway with multiple lanes. Traffic could be regarded as data. The wider the lanes, that is, the bus width, the more data can pass through in a given amount of time. Conversely greater data speed (the speed of the traffic) will give the same result-more throughput. The first assumption about increasing the bus width of the memory isn't practical for all purposes. Memory width remains at 64 bits (it's DDR so 32*2).
For example DDR 400 MHz memory runs at 200 MHz internally (200*2 because it's DDR), while the bit width is 64, which gives us a bandwidth figure of 3200 MBps. In megabits we'd get 400*64=25600 megabits per second. To arrive at the figure in megabytes, 25600/8=3200 (MBps or Mega Bytes per second). DDR 400 MHz memory is therefore also called PC 3200 RAM.
Fig: Graphic illustrating bottleneck between CPU, RAM, and other peripherals
If we look at the bandwidth figure of a 32-bit, 3.2GHz processor: 3200*32 = 102400 Mbps or 12800 MBps.
Add to this fact that memory has latency - a wasted-clock-cycles figure that is astronomical as compared to that of a processor- and it's no wonder that even the fastest memory available bottleneck today's CPUs.
So an increase in the memory speed is essential to improve system performance, and that demands DDR2.
The first commercial product to claim using the "DDR2" technology was the NVIDIA GeForce FX 5800 graphics card. However, it is important to note that the "DDR2" memory used on graphics cards (officially referred to as GDDR-2) is not DDR2 per se but an early midpoint of DDR and DDR2 technologies. In particular, the (very important) doubling of the I/O clock rate is missing. It had severe overheating issues due to the nominal DDR voltages. ATI has since designed the GDDR format further, into GDDR3, which is more true to the DDR2 specifications, though with several additions suited for graphics cards.
After GDDR2's introduction with the FX 5800 series, the 5900 and 5950 series reverted to DDR, but NVIDIA's old mainstream card, the 5700 Ultra, used GDDR2 clocked at 450 MHz (compared to 400 MHz on the regular 5800 or 500 MHz on the 5800 Ultra)
ATI Technologies's Radeon 9800 Pro with 256 MiB memory (not the 128 MiB version) also used GDDR2, but this was because it required fewer pins than DDR. The Radeon 9800 Pro 256 MiB only runs its memory at 20 MHz faster than the 128 MiB versions, and primarily to counter the performance hit caused by higher latency and the increased number of chips. It is speculated that the GDDR2 used on ATI's 9800 Pro 256 MiB was actually supposed to be used on the GeForce FX 5800 series, but ended up unused after NVIDIA decided to halt the 5800 line's production. The 9800XT that followed reverted to DDR and later on ATI began to use GDDR3 memory on their Radeon X800 line.
GDDR3 is now commonly used in most NVIDIA- or ATI-based video cards. However, further confusion has been added to the mix with the appearance of budget and mid-range graphics cards which claim to use "DDR2". These cards do not actually use GDDR2, but in fact use standard DDR2 designed for use as main system memory. This cannot achieve the speeds that GDDR3 can, but is fast and cheap enough to use as memory on mid-range cards.
4. DDR2-SDRAM BASIC CONCEPTS
DDR2 SDRAM or double-data-rate two synchronous dynamic random access memory is a computer memory technology. It is a part of the SDRAM family of random access memory technologies, which is one of many DRAM implementations. 4.1) SDRAM
SDRAM means synchronous dynamic random access memory which is a kind of solid state computer memory. Other dynamic random access memories (DRAM) have an asynchronous interface which means that it reacts as quickly as possible to changes in control inputs. SDRAM has a synchronous interface, meaning that it waits for a clock signal before responding to its control inputs. It is synchronized with the computer's system bus, and thus with the processor. The clock is used to drive an internal finite state machine that pipelines incoming commands. This allows the chip to have a more complex pattern of operation than DRAM which does not have synchronizing control circuits. Pipelining means that the chip can accept a new command before it has finished processing the previous one. In a pipelined write, the write command can be immediately followed by another command without waiting for the data to be written to the memory array. In a pipelined read, the requested data appears a fixed number of clock pulses after the read command. This delay is called the latency and is an important parameter to be considered when purchasing SDRAM for your computer. It is not necessary to wait for the data to appear before sending the next command. SDRAM chips are rated according to their maximum clock rate and their read cycle time. Clock rate is directly proportional to maximum bandwidth and is affected primarily by the speed of the internal state machine and interface circuitry. Read cycle time affects the delay between issuing a command and initiating the corresponding operation and is determined primarily by the speed of the memory cells themselves.
CAS latency is the delay between specifying a column address and receiving the first data output and is closely related to read cycle time. It is specified in clock cycles, typically with the assumption that the module is running at its maximum speed. However, CAS latency is actually programmable by the memory controller, and a lower CAS latency setting may be viable if the module is running slower than its rated clock speed. .
4.2) DDR & DUAL CHANNEL ARCHITECTURE
In computing, a computer bus operating with double data rate transfers data on both the rising and falling edges of the clock signal, effectively nearly doubling the data transmission rate without having to deal with the additional problems of timing skew that increasing the number of data lines would introduce. This is also known as double pumped, dual-pumped, and double transition.
Dual-channel architecture DDR SDRAM describes a motherboard technology that effectively doubles data throughput from RAM to the memory controller. Dual Channel-enabled memory controllers utilize two 64-bit data channels, resulting in a total bandwidth of 128 bits, to move data from RAM to the CPU. In order to achieve this, the DDR SDRAM memory modules must be installed into matching memory slots, which are usually color coded on the motherboard. Each memory module in each slot should be identical to the one in its matching slot. It's also possible to use similar memory sticks from different manufacturers or different production series as long they are of the same size, specification, the same number of memory chips and internal organization.
Dual channel technology was created to address the issue of bottlenecks. Increased processor speed and performance requires other, less prominent components to keep pace. The most conspicuous of these parts is the memory controller, which regulates data flow between CPU and the system memory (RAM). The memory controller determines the types and speeds of RAM as well as the maximum size of each individual memory module and the overall memory capacity of the system. There are many memory controller designs; prior to 2003, the most common was the single channel configuration. Among its advantages are its low cost and flexibility. Its ability to produce a bottleneck effect arises when it is unable to keep up with the processor, leaving it with nothing to process while the memory controller is struggling to keep up with the data flow. Under the single channel architecture, any CPU with a bus speed that is greater than the memory speed would be liable to fall prey to this bottle-neck effect.
The dual channel configuration alleviates the problem by doubling the amount of available memory bandwidth. Instead of a single memory channel, a second parallel channel is added. With two channels working simultaneously, the bottleneck is reduced. Rather than wait for memory technology to improve, dual channel architecture simply takes the existing RAM technology and improves the method in which it is handled.
5. SPECIFICATION STANDARDS
Â¢ DDR2-400: DDR-SDRAM memory chips specified to run at 100 MHz, I/O
clock at 200 MHz
Â¢ DDR2-533: DDR-SDRAM memory chips specified to run at 133 MHz, I/O
clock at 266 MHz
Â¢ DDR2-667: DDR-SDRAM memory chips specified to run at 166 MHz, I/O
clock at 333 MHz
Â¢ DDR2-800: DDR-SDRAM memory chips specified to run at 200 MHz, I/O
clock at 400 MHz
Â¢ PC2-3200: DDR2-SDRAM memory stick specified to run at 200 MHz using
DDR2-400 chips, 3.200 GB/s bandwidth
Â¢ PC2-4200: DDR2-SDRAM memory stick specified to run at 266 MHz using
DDR2-533 chips, 4.267 GB/s bandwidth
Â¢ PC2-5300: DDR2-SDRAM memory stick specified to run at 333 MHz using
DDR2-667 chips, 5.333 GB/s bandwidthl
Â¢ PC2-6400: DDR2-SDRAM memory stick specified to run at 400 MHz using
DDR2-800 chips, 6.400 GB/s bandwidth
6. 4-bit Prefetch
The prefetch buffer is a memory cache located on modern RAM modules which stores data before it is actually needed. In addition to increased operation frequencies, decreased heat production, and decreased latency, the width of the prefetch buffer is improved with each successive standard of modern DDR SDRAM modules.DDR2 SDRAM achieves high-speed operation by 4-bit prefetch architecture.
In 4-bit prefetch architecture, DDR2 SDRAM can read/write 4 times the amount of data as an external bus from/to the memory cell array for every clock, and can be operated 4 times faster than the internal bus operation frequency.
Â¢ External clock frequency = 2 times faster than internal bus operation frequency
Â¢ Double data rate output = 2 times faster than external clock frequency
A comparison between DDR2 SDRAM, DDR SDRAM, and SDR SDRAM with a DRAM core operating frequency of 133MHzis shown below.
7. ON DIE TERMINATION
On Die Termination (ODT) eliminates one of the major drawbacks to extracting more speed out of the memory. Any signal moving along a bus reflects to a certain degree when it hits its intended target. These reflected signals are called mirror signal. These signal directions could go either way along the bus, and the reflected signal causes interference in the original signal, or could even cancel out the original signal depending on the original signal strength.
DDR2simply introduces a termination point to the original signal once it reached its target by adding a resistor to ground it. This eliminates any reflection voltage as the resistor simply swallows up any signal
In DDR2 SDRAM, the mount termination register conventionally mounted on the motherboard is incorporated inside the DRAM chip. The DRAM controller can set the termination register for each signal (data I/O, differential data strobe, and write data mask) on and off.
The Advantages of ODT are
Â¢ Improved signal integrity by controlling reflected noise on the transfer line.
Â¢ Reduction of parts costs by reducing the parts counts on the motherboard.
Â¢ Easier system design by eliminating the complicated placement and routing for the termination register.
8. OFF-CHIP DRIVER CALIBRATION
When the drive performance varies, the transition time (rise time or fall time) needed for an output signal to reach any specified voltage also varies. Generally, a higher drive performance means a faster signal transition time (rise time or fall time). Conversely, a lower drive performance means a slower signal transition time (rise time or fall time).
The DQS and /DOS signals(differential strobe signals) that are used by DDR2 SDRAM are phase related. When the DQS and /DQS signals have the same drive performance, each signal's intermediate level and cross point also match. However, if either signal has weaker (or stronger) drive performance than the other, the cross point and intermediate level do not match
DDR2 SDRAM uses the cross point between the DQS and /DQS signals as a reference clock for I/O data. The memory controller latches data from the DQ signal in synchronization with this reference clock. The DQ signal is referenced to distinguish the high and low levels of the VREF signal. When the DQS and /DQS signals have different drive performances, the cross point between the DQS and /DQS signals will be Offset from each signal's intermediate level. Consequently, a delay time (DQ-DQS skew) occurs between the cross point of the DQS and /DQS signals on the one hand and the cross point of the DQ and VREF signals on the other hand. When such DQ-DQS skew exists, the time (valid data window) provided for latching data during data input or output is reduced. Reduction of this valid data window is a serious issue for DDR2 SDRAM, which require high-speed operations.
OCD is used to adjust the impedance value of the DRAM's internal output driver. This function can adjust the voltage to equalize the pull-up resistance and pullÃ‚Â¬down resistance of the output signals (DQ, DQS, and /DQS).When OCD is used to adjust the voltage, the cross point between the DQS and /DQS signals can be made to match the each signal's intermediate level. Optimizing the cross point between the DQS and /DQS signals minimizes the delay time for the cross point between the DQ and VREF signals. When OCD is used to adjust the voltage with DDR2 SDRAM, DQ-DQS skew can be minimized, which maximizes the time valid data window) provided for latching data when data is being input or output.
fDross point ofN OQS and /DQS
Valid daa widow on
iic data window is reduced in prosortson ic DQ-DQS skew
Cross point of y \DQ and VREF/'
Figure 1-3 DQS Signal. /DOS Signal and Valid Data Window
/ \ /
* Cras pourt of1 '. DO and VREF Â¢
Figure 1-4 Expansion of \*alid Data Window by Voltage Adjusrment
9. POSTED CAS & ADDITIVE LATENCY
DDR2 SDRAM introduces posted CAS and additive latency (AL) to make the command and data bus efficient for sustainable bandwidths. The Command bus is responsible for issuing commands. Commands may be issued externally but held by the device internally prior to execution, for the duration of AL, in order to improve system scheduling. A command buffer is placed on the DRAM chip that "bundles" these commands, that is holds a command and issues at a later time.
The command bus is freed from the burden of addressing exactly when to release that particular command. It can now activate the next bank. This is called the Posted CAS. CAS (Column Address Strobe) latency is the delay between specifying a column address and receiving the first data output and is closely related to read cycle time. It is specified in clock cycles, typically with the assumption that the module is running at its maximum speed. However, CAS latency is actually programmable by the memory controller, and a lower CAS latency setting may be viable if the module is running slower than its rated clock speed. The delay that is specified during initialization of the DRAM chip is called Additive Latency. Specifically, it helps avoid collision on the command bus and gaps in data input/output bursts.
The AL function is controlled by an extended mode register and programmed via bits E3-E5 of the EXTENDED MODE REGISTER SET command. AL of 0,1, 2, 3, or 4 clocks is supported.
Additive latency (AL = 1) is only used for READ commands and will not affect WRITE Command timing
10. FINE-PITCH BALL GRID ARRAY PACKGE
DDR2 chips comes in FBGA(Fine-pitch Ball Grid Array) package which is physically smaller and uses a grid of tiny solder balls on bottom to make electrical contact with the board. FBGA is a smaller package which requires less space on the memory module. That means more chips can fit onto a shorter module. The greatest benefit is that it has less electrical noise than TSOP (Thin Small Outline Package) chips which result in improved signal integrity.
A further advantage of FBGA packages over leaded packages (i.e. packages with legs) is the lower thermal resistance between the package and the PCB. This allows heat generated by the integrated circuit inside the package to flow more easily to the PCB, preventing the chip from overheating.
The shorter an electrical conductor, the lower its inductance, a property which causes unwanted distortion of signals in high-speed electronic circuits. FBGA s, with their very short distance between the package and the PCB, has low inductances and therefore has far superior electrical performance to leaded devices.
Due to FBGA packaging, higher density memory modules are possible and DDR2 can be available in 2 and 4 GB densities in a single DIMM (Dual In-line Memory Module).
11. DISADVANTAGE- LATENCY
One of the most important characteristics of memory and a significant performance affecting factor is latency. Latency can be quite simply defined as the wasted clock cycles. It occurs since DRAM memory cells have to continually refresh themselves. Latency therefore basically represents delay; it's the time taken for the memory to get ready for a fetch or deliver data transaction. There is also a certain amount of unavoidable latency that occurs between the activation of a column or row, due to the time required to set up the address of the same. Latency is an omnipresent factor; it can only be minimized, and never completely done away with.
Latency is directly proportional to clock speeds, so when a MHz bump occurs, the latency figures also rise. Let's compare a DDR 400 and DDR2 400 MHz module. Typical latencies would be 2.5-3-3-6 for a DDR 400 MHz module, while a DDR2 400 MHz would manage 3-4-4-8, making it slower as far as data accessibility goes. So DDR2 scores bandwidth wise, but loses out latency wise.
The figures 3-4-4-8 represents delay. The smaller these values can get, the faster the memory is (clock speeds remaining constant). It's worth noticing that these figures represent minimum latency, meaning the timings cannot get any smaller, that is, tighter.
The first figure in the above example is the most significant speed-wise. It represents the CAS or Column Address Strobe Latency figure.
As we know RAM first has to read a command send to it,and then output some data based on that command. The CAS represents the delay between a registered read and data output. It's measured in clock cycles. Therefore a CAS latency value of 3 means three clock cycles will complete before data is ready to be sent forward. CAS latency is often abbreviated as CL.
The second figure represents the RCD or Row-Column Delay. It is defined as the number of clock cycles required between RAS and CAS. As latency it's the time delay between defining a row and column in a particular memory block, and the read/write operation to that particular location.
RP is the Row Pre-charge time. It's denoted by the third 4 in our example. In memory each row in the bank needs to be closed, that is terminated before the next row
can be accessed. The RP represents in clock cycles, the time needed to terminate and open a row of memory (open being the current state), and to access the next row.
RAS stands for Row Address Strobe. This is the last number in our example, i.e. 8. There is a delay between requesting of data and actual issue or a pre-charge command. This difference is basically the amount of clock cycles spent in order to access a certain row of data in memory. This delay between data request and pre-charge is called RAS or active to pre-charge delay.
A paradoxical situation-with one solution -bump up the clock speeds further. And DDR2 has exactly done that, delivering 667 MHz and 800 MHz, with 1066 MHz promised in the near future.
DDR2 memory offers more bandwidth than other existing memories. Power consumption wise DDR2 is the hands-down winner, with a 1.8V operating voltage as compared to the 2.5 that DDR requires. Also DDR2 offers higher density due to the FBGA package. In DDR2 signal integrity is high. Noise is less since mirror signals are avoided. Due to low inductance high speed can be achieved with high reliability.
All these make DDR2 the best memory available now.
13. FUTURE SCOPE
Generally, DDR2 is expected to have little competition in main computer memory sector. However, there are three alternatives:
The first is Rambus XDR DRAM (eXtreme Data Rate DRAM). This technology can achieve very high clock speeds, but Rambus has been virtually disowned by IBM PC compatible chipset makers, and it is considered more likely that XDR will find use in set-top appliances and the like. Sony has selected XDR for use in PlayStation 3.
Next is Kentron Quad Band Memory (QBM), which uses DDR modules with effectively two channels routed to the module. This was briefly supported by VIA, but they have dropped support for the technology, and there are doubts about Kentron's commercial viability.
The third alternative is Quad Data Rate SDRAM (QDR), which is considered the natural successor to DDR technologies (DDR2 uses some QDR transfer methods, though is still very much based on DDR technology). However, QDR is not currently considered to be even a remotely viable product due to high production costs and poor speeds currently achieved by such modules - most barely achieve 66 MHz (266 MHz effective), and the technology may not be viable until late in the decade.Many new chipsets use these memory types in dual-channel or even quad channel configurations, which doubles or quadruples the effective bandwidth.
JEDEC (Joint Electron Device Engineering Council) is also trying to develop and standardize DDR3 & DDR4.
1. Digit Magazine -August 2006
3. micron .com
1. INTRODUCTION 1
2. NEED FOR FASTER MEMORY 2
3. HISTORY 4
4. DDR2-SDRAM BASIC CONCEPTS 5
4.1) SDRAM 5
4.2) DDR & DUAL CHANNEL ARCHITECTURE 6
5. SPECIFICATION STANDARDS 7
6. 4-BIT PREFETCH 8
7. ON DIE TERMINATION 9
8 OFF-CHIP DRIVER CALIBRATION 10
9 POSTED CAS & ADDITIVE LATENCY 12
10 FINE-PITCH BALL GRID ARRAY 13
11. DISADVANTAGE - LATENCY 14
12 CONCLUSION 16
13 FUTURE SCOPE 17
14 BIBLIOGRAPHY 18
Active In SP
Joined: Mar 2010
22-03-2010, 11:02 PM
SDRAM.doc (Size: 101.5 KB / Downloads: 60)
DDR2 SDRAM is a double data rate synchronous dynamic random access memory interface. It supersedes the original DDR SDRAM specification and the two are not compatible. In addition to double pumping the data bus as in DDR SDRAM (transferring data on the rising and falling edges of the bus clock signal), DDR2 allows higher bus speed and requires lower power by running the internal clock at one quarter the speed of the data bus. The two factors combine to require a total of 4 data transfers per internal clock cycle.
With data being transferred 64 bits at a time, DDR2 SDRAM gives a transfer rate of (memory clock rate) Ãƒâ€” 2 (for bus clock multiplier) Ãƒâ€” 2 (for dual rate) Ãƒâ€” 64 (number of bits transferred) / 8 (number of bits/byte). Thus with a memory clock frequency of 100 MHz, DDR2 SDRAM gives a maximum transfer rate of 3200 MB/s.
Since the DDR2 clock runs at half the DDR clock rate, DDR2 memory operating at the same external data bus clock rate as DDR will provide the same bandwidth but with higher latency, resulting in inferior performance. Alternatively, DDR2 memory operating at twice the external data bus clock rate as DDR may provide twice the bandwidth with the same latency. The best-rated DDR2 memory modules are at least twice as fast as the best-rated DDR memory modules.
Like all SDRAM implementations, DDR2 stores memory in memory cells that are activated with the use of a clock signal to synchronize their operation with an external data bus. Like DDR before it, the DDR2 I/O buffer transfers data both on the rising and falling edge of the clock (a technique called "double pumping"). The key difference between DDR and DDR2 is that for DDR2 the memory cells are clocked at 1 quarter (rather than half) the rate of the bus. This requires a 4 bit deep prefetch queue, but, without changing the memory cells themselves, DDR2 can effectively operate at twice the bus speed of DDR.
DDR2's bus frequency is boosted by electrical interface improvements, on-die termination, prefetch buffers and off-chip drivers. However, latency is greatly increased as a trade-off. The DDR2 prefetch buffer is 4 bits deep, whereas it is 2 bits deep for DDR and 8 bits deep for DDR3. While DDR SDRAM has typical read latencies of between 2 and 3 bus cycles, DDR2 may have read latencies between 4 and 6 cycles. Thus, DDR2 memory must be operated at twice the data rate to achieve the same latency.
Another cost of the increased bandwidth is the requirement that the chips are packaged in a more expensive and more difficult to assemble BGA package as compared to the TSSOP package of the previous memory generations such as DDR SDRAM and SDR SDRAM. This packaging change was necessary to maintain signal integrity at higher bus speeds.
Power savings are achieved primarily due to an improved manufacturing process through die shrinkage, resulting in a drop in operating voltage (1.8 V compared to DDR's 2.5 V). The lower memory clock frequency may also enable power reductions in applications that do not require the highest available data rates.
According to JEDEC the maximum recommended voltage is 1.9 volts and should be considered the absolute maximum when memory stability is an issue (such as in servers or other mission critical devices). In addition, JEDEC states that memory modules must withstand up to 2.3 volts before incurring permanent damage (although they may not actually function correctly at that level).
Chips and modules
For use in computers, DDR2 SDRAM is supplied in DIMMs with 240 pins and a single locating notch. Laptop DDR2 SO-DIMMs have 200 pins and often come identified by an additional S in their designation. DIMMs are identified by their peak transfer capacity (often called bandwidth).
Standard name Memory clock Cycle time I/O Bus clock Data transfers per second Module name Peak transfer rate TimingsDDR2-400 100 MHz 10 ns 200 MHz 400 Million PC2-3200 3200 MB/s
DDR2-533 133 MHz 7.5 ns 266 MHz 533 Million PC2-4200
PC2-43001 4266 MB/s 3-3-3
DDR2-667 166 MHz 6 ns 333 MHz 667 Million PC2-5300
PC2-54001 5333 MB/s 4-4-4
DDR2-800 200 MHz 5 ns 400 MHz 800 Million PC2-6400 6400 MB/s 4-4-4
DDR2-1066 266 MHz 3.75 ns 533 MHz 1066 Million PC2-8500
PC2-86001 8533 MB/s 6-6-6
Note: DDR2-xxx denotes data transfer rate, and describes raw DDR chips, whereas PC2-xxxx denotes theoretical bandwidth (though it is often rounded up or down), and is used to describe assembled DIMMs. Bandwidth is calculated by taking transfers per second and multiplying by eight. This is because DDR2 memory modules transfer data on a bus that is 64 data bits wide, and since a byte comprises 8 bits, this equates to 8 bytes of data per transfer.
1 Some manufacturers label their DDR2 modules as PC2-4300 instead of PC2-4200, PC2-5400 instead of PC2-5300 and PC2-8600 instead of PC2-8500. At least one manufacturer has reported this reflects successful testing at a higher-than standard data rate whilst others simply use the alternate rounding as the name, as described above.
In addition to bandwidth and capacity variants, modules can
1. Optionally implement ECC, which is an extra data byte lane used for correcting minor errors and detecting major errors for better reliability. Modules with ECC are identified by an additional ECC in their designation. PC2-4200 ECC is a PC2-4200 module with ECC.
2. Be "registered", which improves signal integrity (and hence potentially clock rates and physical slot capacity) by electrically buffering the signals at a cost of an extra clock of increased latency. Those modules are identified by an additional R in their designation, whereas non-registered (a.k.a. "unbuffered") RAM may be identified by an additional U in the designation. PC2-4200R is a registered PC2-4200 module, PC2-4200R ECC is the same module but with additional ECC.
3. Be fully buffered modules, which are designated by F or FB and do not have the same notch position as other classes. Fully buffered modules cannot be used with motherboards that are made for registered modules, and the different notch position physically prevents their insertion.
Note: registered and un-buffered SDRAM generally cannot be mixed on the same channel.
Note that the highest-rated DDR2 modules in 2009 operate at 533 MHz (1066 MT/s), compared to the highest-rated DDR modules operating at 200 MHz (400 MT/s). At the same time, the CAS latency of 11.2 ns = 6 / (Bus clock rate) for the best PC2-8500 modules is comparable to that of 10 ns = 4 / (Bus clock rate) for the best PC-3200 modules.
DDR2 was introduced in the second quarter of 2003 at two initial clock rates: 200 MHz (referred to as PC2-3200) and 266 MHz (PC2-4200). Both performed worse than the original DDR specification due to higher latency, which made total access times longer. However, the original DDR technology tops out at a clock rate around 200 MHz (400 MT/s). Higher performance DDR chips exist, but JEDEC has stated that they will not be standardized. These modules are mostly manufacturer optimizations of highest-yielding chips, drawing significantly more power than slower-clocked modules, and usually do not offer much, if any, greater real-world performance.
DDR2 started to become competitive with the older DDR standard by the end of 2004, as modules with lower latencies became available.
DDR, DDR2 and DDR3 for Desktop PC's Comparison Graphic
DDR2 DIMMs are not designed to be backward compatible with DDR DIMMs. The notch on DDR2 DIMMs is in a different position from DDR DIMMs, and the pin density is higher than DDR DIMMs in desktops. DDR2 is a 240-pin module, DDR is a 184-pin module. Notebooks have 200-pin modules for DDR and DDR2, however the notch on DDR modules is in a slightly different position than that on DDR2 modules.
Higher performance DDR2 DIMMs are compatible with lower performance DDR2 DIMMs; however, the higher performance module runs at the lower module's frequency. Using lower performing DDR2 memory in a system capable of higher performance results in the bus running at the rate of the lowest performance memory in use; however, in many systems this performance hit can be mitigated to a small extent by setting the timings of the memory to a lower latency setting.
Use Search at http://topicideas.net/search.php wisely To Get Information About Project Topic and Seminar ideas with report/source code along pdf and ppt presenaion