A lot of readers on our website are interested in questions one way or another related to the choice random access memory and our site has a very great desire to answer everyone. To make it interesting for you in the process of gaining knowledge, this article is presented by the author in the form of a fascinating story from which you will learn EVERYTHING about computer RAM!

You will learn not only how to choose and buy RAM from a quality manufacturer, but also how to correctly install RAM modules in your computer and much more, for example:

1. How much RAM does a modern computer need for comfortable operation of all resource-intensive applications, for example: modern games at maximum settings, video and sound processing programs, etc. How powerful should it be? modern computer?
2. (follow the link and read a separate article).
3. (follow the link and read a separate article)?
4. What way out of the situation does he find? operating system due to lack of RAM?
5. Is having too much RAM good for your computer?
6. Do you need to completely disable the paging file if you have large volume physical RAM, for example 16 -32 GB?
7. How much better is dual-channel RAM operating mode than single-channel? What is better to buy, one 8GB memory stick or two 4GB sticks?
8. How to choose the right RAM modules for dual-channel operation?
9. What is the frequency of RAM and is it possible to install RAM sticks with different frequencies in a computer?
10. What is RAM latency (timings)? Is it possible to install RAM sticks with different timings in a computer?
11. What is the difference between the RAM sticks used on laptops and regular RAM?
12. Nowadays DDR3 memory is actively used, but are there DDR4 memory sticks on sale?
13. If you have old computer and you want to buy additional DDR2 RAM, then think several times, because DDR2 memory is expensive, maybe it’s better for you to replace the motherboard, processor and change the RAM to DDR3.
14. How to choose a RAM manufacturer and is all RAM made in China?
15. Is overclocking of RAM necessary and how much will RAM performance increase during overclocking?
16. Is a heatsink really necessary for RAM?
17. What is a RAM controller, why is it needed and where is it located?
18. What does ECC RAM marking mean?

How to choose RAM

Friends, in the last article we discussed the issue of choice and I was thinking about what article to write next. It seems logical to choose a motherboard for it after the processor, but I usually do it differently. After choosing the processor, I choose the memory and video card, I don’t know why, it’s probably just easier and you can immediately estimate how much to expect, since choosing a motherboard is the most difficult part of choosing a computer configuration. In view of this, I decided not to deviate from my chosen tradition and devote this article to the choice of random access memory (RAM). Since this site is dedicated to the repair of personal computers, of course the issue of choosing RAM will be considered not only for new, but also for older PCs.

Like choosing a processor, choosing RAM is not a difficult task at all. probably even easier. But, as with everything, there are some nuances. Often the choice of RAM comes down to its current price and the amount you are willing to spend. IN Lately Price trends for RAM modules are very ambiguous. Several years ago there was a real boom in increasing the amount of RAM in personal computers. And this was due not so much to the growing requirements of modern applications and operating systems, but to the incredible reduction in price.

A 4 gigabyte (GB) memory stick could be purchased for only $25 or even cheaper. As a result, solely for marketing purposes (to make computers more attractive and increase sales), this same memory began to be “stuffed” into new computers in huge volumes. Yes, the cheapest system unit, costing about $200-250, necessarily had 4 GB of memory, and the average one for $300-350 had all 8 GB. Salespeople in stores placed great emphasis on this, while keeping silent about the fact that this amount of memory would never be realized (fully used) by these PCs, since the rest of the “stuffing,” such as the processor and video card, left much to be desired. This, in essence, was a kind of deception of buyers or, to put it nicely, a marketing ploy...

Unfortunately, gone are the days when you could stock up on RAM for free without even playing around, and now the price for it has increased significantly. Looks like we've been hooked again technical progress... But is a large amount of RAM really needed?

How much RAM does a modern computer need?

I must say that until recently, I was fond of modern computer games. Therefore, I always tried to keep my PC up to date. Probably, since I built my first full-fledged PC in 1997, not a single year has passed that I haven’t treated myself to purchasing a new video card, processor or memory.

In those old (by computer standards) days, there was a certain division in how computers used operating system components. Games only needed a powerful video card, some RAM, and the processor almost didn’t matter, since all the calculations were performed by the video card, which has both its own processor and its own memory.

To encode video, on the contrary, it was necessary powerful processor and enough RAM, but the video card didn’t matter, etc. Modern gaming applications have “learned” to make full use of the previously “idle” powerful components of modern computers, such as the processor and RAM.

If we talk about using a PC as a gaming and entertainment platform, then, until recently, I had not come across games that could load at least 3 GB of memory 100% even at maximum graphics settings. But in some cases, the total memory load was close to this figure, despite the fact that the game itself consumed about 2 GB, and the rest was consumed by other applications, such as Skype, antivirus, etc.

Note: Please note that we were not talking about 4 GB, but about 3. The fact is that 32-bit Windows operating systems (OS) do not know how to use more than 3 GB of RAM and therefore the “excess” is simply “not seen”... In fairness, it is worth noting that for 32-bit OS built on the Linux kernel, such strict restrictions do not exist. So, friends, there is no point in installing more than 4 GB of memory on a 32-bit Windows; they simply will not be used.

For not very new, but also relatively old systems, on which you can put a lot of memory, using a 64-bit OS, in some cases, can be problematic. Since 64-bit versions of drivers for some equipment may simply not exist.

Not so long ago, just at the moment of total reduction in the price of memory, I purchased the same amount in addition to my 4 GB. But this was not caused by its shortcoming, but by the fact that on mine, quite powerful motherboard, due to some misunderstanding) there were slots for almost obsolete DDR2 memory and I was afraid that a little more and it might disappear completely or become wildly expensive, but here is such a “freebie”... After that I switched to a 64-bit operating system system, since otherwise this acquisition would not look so reasonable). You also need to take into account that I have a fairly powerful 4-core processor and an expensive modern video card, thanks to which I can play games at very high graphics settings, at which RAM consumption is maximum.

If you have an entry-level or mid-level PC, then 4 GB of RAM will be enough for you, since you can comfortably play modern games only at low or medium settings, which do not require large amounts of memory. In such conditions, installing, say, 8 GB of RAM is wasted money. But if your PC is powerful enough and is a gaming PC, then I would still recommend installing 8 GB, since there is a tendency towards a gradual increase in RAM consumption by modern games.

For example, the recently released game Call of Duty: Ghosts simply refused to launch if it detected that you had less than 6 GB of RAM installed. Again, in fairness, it should be noted that folk craftsmen made a fix that allowed you to bypass this limitation at launch and the game worked.

Regarding 64-bit operating systems, then you should know that it, like all 64-bit applications, consumes exactly 2 times more memory than 32-bit ones. Here this is already fully justified by memory addressing technology and significantly improves performance.

What should a fast computer be like?

We will not go into details, but you must understand that in order to feel the increase in speed, the following conditions must be met:

The central processing unit (CPU) must have a 64-bit architecture, the operating system must be 64-bit.

The application that you want to use to improve the performance of certain operations must be 64-bit, the data that is processed must be streaming (video conversion, archiving), since the speed increase is achieved through processing in one pass more information. In this case, the increase will be very significant – up to 2 times. Under such conditions, using an Intel processor (with a longer pipeline) you will get the highest possible performance for such operations. But, as you know, in games data is transferred in small portions (since it is impossible to predict the user’s next step), therefore, even in those games where 64-bit versions of the game engine are available for launch, there will be almost no increase. And yet the decisive role of the video card in them has not gone away.

As for professional applications, in areas such as video editing, 3D modeling, design, specialists in these areas know exactly what hardware and how much memory they need. Usually this is from 16 GB or more. And if, say, in 3D modeling there is no streaming data processing, then simply the volume and quality of models can be so high that a lot of RAM is “stupidly” needed to accommodate this model.

If you are not a professional, but really like to convert videos, then 4-8 GB will be enough for you.

Truly huge sizes of RAM can be in demand in scientific systems and highly loaded servers. In the latter, for example, a memory capacity of 64 GB or more is considered quite common. But the memory there is not cheap either - server memory (with parity checking and automatic error correction), since failures are not allowed on them.

Well, as an example, I’ll give you a situation from my real life. When I was training in network technologies And system administration, I often had to emulate a large number of simultaneously running operating systems and network equipment. Such combinations as 5-10 operating systems running in VirtualBox (or VMware) + the same number of emulated ones network devices GNS can use up a decent amount of RAM. And it’s good if, in addition to a powerful processor that supports modern virtualization technologies, there are 8-16 GB of RAM, otherwise the brakes are guaranteed...

Why can't you disable the page file?

What happens when there is not enough RAM? Yes, it’s very simple - the OS, in order to compensate for the lack of memory, begins to actively use HDD(the so-called swap file). By the way, God forbid you turn it off. The operation of the system is very deeply tied to the page file and disabling it will be more problems than it is worth. As a result, not only does the processor slow down, but also hard drive.

There is only one conclusion - there should be enough memory; if there is not enough memory, the computer starts to slow down terribly, but too much memory does not give any performance gain.

What types of RAM are there?

There is no such thing as memory...

A board with memory chips is usually called a memory module (or “stick”). There are single-sided and double-sided memory modules. On the first, the chips are placed on one side printed circuit board, on the second - on both sides. What's better? I don’t know) There is an opinion that double-sided modules “chase” better; read about what this means further in this article. On the other hand, the fewer chips, the higher the reliability of the module. I have seen cases more than once when one side of the chips on a strip failed and the computer saw only half of its volume. But now I would not focus on this.

The main thing you need to know is that if there are several memory modules in the computer, then it is desirable that they all be either single-sided or double-sided. Otherwise, the memory does not always get along well with each other and does not work at full speed.

Today the most modern memory is DDR3 type., which replaced the older DDR2, which in turn replaced the even older DDR. A new, more modern memory DDR4, but it has not yet reached the masses. We won't go deeper.

When building a new PC, you should only choose the latest memory standard. On this moment this is DDR3.

Sometimes replacing a motherboard and purchasing a new type of memory is equivalent in price to adding an old type of RAM to an old board.

The new memory will also be significantly cheaper than the older DDR2, which greedy manufacturers and sellers are “buying” (holding onto) high price, since there is little of it left and for those who want to upgrade their PC there is simply no other choice but to agree to such draconian conditions. In this case, it’s worth thinking about, maybe adding a little and buying more promising components? And if you sell the old one, you can actually get a profit, if you’re lucky, of course)

Laptop memory

Laptops use the same memory as PCs, but have a smaller module size and are called SO-DIMM DDR (DDR2, DDR3).

Memory characteristics. Frequency and timings

Memory is characterized primarily by type. The memory types used for desktop computers today are: DDR, DDR2, DDR3.

The main characteristic of memory is its frequency. The higher the frequency, the faster the memory is considered. But this frequency must be supported by the processor and motherboard, otherwise the memory will operate at a lower frequency, and the money you overpaid will go down the drain.

Memory modules, as well as its types, have their own markings, which begin with PC, PC2 and PC3, respectively.

Today, the most common memory is DDR3 PC3-10600 (1333 MHz). It will work at its native frequency on any computer. In principle, the speed of the computer does not greatly depend on the memory frequency. For example, in games this increase will be absolutely indistinguishable, but in some other applications it will be more noticeable. But the difference in price, for example in comparison with DDR3 PC3-12800 (1600 MHz) memory, will be very small. Here I usually follow the rule - if the price is slightly higher ($1-3) and the processor supports a higher frequency, then why not - we take faster memory.

Is it possible to install RAM sticks with different frequencies into a computer?

The frequency of the RAM does not have to be the same; the motherboard will set the frequency for all sticks to the slowest module, but very often a computer with sticks of different frequencies is unstable. For example, it may not turn on at all.

Timings

The next memory performance parameter is the so-called delays (timings). Roughly speaking, this is the time that has passed from the moment the memory is accessed until the moment it produces the necessary data. Accordingly, the shorter the timings, the better. There are dozens of different delays when reading, writing, copying, and various combinations of these and other operations. But there are only a few main ones that you can use to navigate.

Timings are indicated (though not always) on the label of memory modules in the form of 4 numbers with hyphens between them. The first and most important is latency, the rest are derivatives of it.

Delays depend on the manufacturing quality of the memory chips. Accordingly, higher quality, lower timings, higher price. However, it is worth noting that timings have a much smaller impact on performance than memory frequency. Therefore, I rarely attach importance to this, only if the price is approximately the same, you can buy memory with lower timings. Typically, modules with ultra-low timings are positioned as top-end, come complete with radiators (which we’ll talk about later), in beautiful packaging and are much more expensive.

Marking of main types, memory modules, their frequency and typical latency (CL)

DDR – outdated (completely)

DDR-266 - PC2100 - 266 MHz - CL 2.5

DDR-333 - PC2700 - 333 MHz - CL 2.5

DDR-400 - PC-3200 - 400 MHz - CL 2.5

DDR2 - obsolete (sometimes still found and can be used to add to an old PC)

DDR2-533 - PC2-4200 - 533 MHz - CL 5

DDR2-667 - PC2-5300 - 667 MHz - CL 5

DDR2-800 - PC2-6400 - 800 MHz - CL 5

DDR2-1066 - PC2-8500 - 1066 MHz - CL 5

DDR3 – modern

DDR3-1333 - PC3-10600 - 1333 MHz - CL 9

DDR3-1600 - PC3-12800 - 1600 MHz - CL 11

DDR3-1800 - PC3-14400 - 1800 MHz - CL 11

DDR3-2000 - PC3-16000 - 2000 MHz - CL 11

Is it possible to install RAM sticks with different timings in a computer?

The timings also do not have to match. The motherboard will automatically set timings for all modules according to the slowest module. There shouldn't be any problems.

Memory operating modes

Yes, yes... Perhaps not everyone knew, but RAM can work in different modes, so-called: Single Mode (single channel) and Dual Mode (two channel).

In single-channel mode, data is first written to one memory module, and when its capacity is exhausted, it begins to be written to the next free module.

In dual-channel mode, data recording is parallelized and recorded simultaneously on several modules.

This, friends, is where using dual-channel mode significantly increases memory speed. In reality, the memory speed in dual-channel mode is up to 30% higher than in single-channel mode. But in order for it to work, the following conditions must be met:

The motherboard must support dual-channel RAM operation

There should be 2 or 4 memory modules

Memory modules must be either all single-sided or all double-sided

If any of these conditions are not met, the memory will only operate in single-channel mode.

It is desirable that all the strips be as identical as possible: they have the same frequency, latency, and are even from the same manufacturer. Otherwise, no one can give any guarantees about the operation of the dual-channel mode. Therefore, if you want your memory to work in the fastest possible mode, it is very advisable to immediately purchase 2 identical memory sticks, because after a year or two you will definitely not find the same one.

Another question is if you need to increase the amount of memory on an old computer. In this case, you can try to find a memory module that is as similar as possible to the one you already have. If you have 2 of them, and there are 2 more free slots on the motherboard, then you will have to look for 2 more of the same modules. An ideal, but not always economical, option is to sell the old memory as used and buy 2 new identical modules of larger capacity.

Of course, if your old computer is very weak, then there may not be a big gain from the dual-channel mode. In this case, you can install any module, but it is still better to choose the most suitable one in order to eliminate a possible conflict with old modules and complete inoperability of the computer. Try to agree in advance with the seller about a return or bring the system unit to him and let him try to select a suitable module.

RAM controller

It should be noted that previously memory controllers were located in the chipset (logic set) of motherboards. In modern systems, memory controllers are located in processors. In this regard, the dual-channel memory mode now has 2 more submodes: Ganged (paired) and Unganged (unpaired).

In ganged mode, memory modules work the same as in old motherboards, but in unpaired mode, each processor memory controller (in modern processors there are 2 of them) can work separately with each stick. This mode can be set in Computer BIOS, but usually it is selected automatically by the processor. If the planks are identical, then Ganged (but not necessarily), if they are different, then only Unganged. In any case, the memory will operate in dual-channel mode. But I still recommend buying and installing 2 identical modules at once, this will eliminate distortions in their parameters and improve compatibility.

The dual-channel RAM mode has only one drawback - 2 memory sticks are slightly more expensive than one of the same size. Therefore, many stores and private collectors save money and set the same bar. As a result, we have a modern computer that does not work at full capacity.

Some modern expensive motherboards, which usually have 6 slots for memory modules, can even operate in three-channel mode.

By the way, if you have 2 or 3 memory sticks, then in order for the dual-channel or three-channel mode to work, all these sticks must be inserted into slots of the same color.

Some memory modules for desktops have the abbreviation ECC in their markings.

This is memory with parity, a technology used in server systems. You should not pay any attention to this, since on desktop PCs this technology is not critical and, in most cases, does not work at all. It's still the same marketing ploy.

Memory connectors

There's nothing to talk about here at all. Each type of memory DDR, DDR2, DDR3 has its own connector on the motherboard of the same type (DDR, DDR2, DDR3). You will not insert memory of one type into a slot of another type, since there is a special protrusion (key) in the motherboard slot,

Which should coincide with the slot on the memory module board. This was done precisely so as not to accidentally confuse and install the bracket in the wrong connector and, as a result, not damage both the memory and, possibly, the motherboard. When purchasing memory, you need to know exactly what type of memory the motherboard supports.

About RAM heatsinks

Some memory modules are equipped with so-called heatsinks, which are linings made of aluminum plates, sometimes painted copper or other colors, on both sides of the board. These pads are connected to the memory chips through special thermal pads, which are designed to better transfer heat from the chips to the heatsinks. Radiators can have additional fins to increase the cooling area and even better heat dissipation.

In practice, memory chips heat up slightly during normal operation and do not require additional cooling. Gaskets between chips and heatsinks do not transfer heat as well as thermal paste between the processor and cooler. In addition, in the free space between the board and the radiators there is an air gap that interferes with natural cooling and over time becomes clogged with dust, which is difficult to clean out. This design provides for active cooling using an additional fan or good air flow inside the case. In addition, such modules can often cost more.

So who needs such joy, you ask? Well, ask me)

Answer: enthusiasts who never have enough of everything, who want to overclock everything, overtake everyone, etc. Besides, it’s just beautiful) Yes, friends, if you consider yourself to be in this group of users, then this memory is for you! Because such a cooling system will be effective only with sufficiently high heating as a result of overclocking with increased voltage and mandatory additional airflow. Remember - regular memory, operating in normal mode, radiators are not needed.

An example of the correct use of memory with heatsinks in a powerful system

Overclocking RAM

Overclocking is a slang word in the computer lexicon, which implies manually setting more aggressive parameters for the operation of electronic components, such as processors, memory and video cards, than those provided by the manufacturer. Such parameters are usually the frequency (in processors there is also a multiplier). At particularly high overclocking, the voltage is also increased to ensure relatively stable operation of these components. As a result, higher heating of the elements occurs, requiring improved cooling. The so-called overclocking itself is possible thanks to a certain margin laid down by the manufacturer so that the product works stably, and not at the edge of its capabilities, or especially for advanced users) In any case, this event makes the operation of the entire system less stable and shortens the service life of overclocked components . If you still decide to experiment, then first thoroughly study all aspects and act strictly according to the instructions. By the way, if components fail as a result of overclocking, you may lose your warranty.

RAM Manufacturers

Like other components, memory modules are manufactured by many manufacturers. And, as always, they have different quality. I recommend paying attention to the following brands that have an optimal price/quality ratio: AMD, Crucial, Goodram, Hynix, Kingston, Micron, Patriot, Samsung, TakeMS, Transcend.

Enthusiast brands include: Corsair, G.Skill, Mushkin, Team. These companies produce a wide range of modules with radiators and increased technical characteristics. I recommend avoiding cheap Chinese brands: A-Data, Apacer, Elixir, Elpida, NCP, PQI and other little-known manufacturers.

Memory modules that are not manufactured in China deserve special mention. Currently, there are not many of these, for example, modules that are labeled as Hynix Original and Samsung Original are produced in Korea. The quality of such modules is considered higher; they cost a little more, but usually have a longer warranty (up to 36 months).

To be fair, it should be noted that even if you purchased memory from a well-known and reputable brand, this, unfortunately, does not mean that you will not encounter defective modules or modules damaged during transportation. Of course, products from top brands in individual packaging will have fewer defects (damages) than the cheapest modules that are transported and sold in bulk.

Memory module in individual packaging

How to choose memory for a new computer

First of all, choose the most modern type of memory used. Today it is DDR3. Decide on the volume you need. Briefly summarizing this article, I will give general recommendations on the minimum amount of RAM for PCs of different purposes:

For an office or weak home PC – 2 GB

4. It is better to select the most identical strips (single-sided or double-sided), with the same frequency and latency. The ideal option is to sell the old memory as used and install new memory in the required volume.

5. If you install memory with a higher frequency than your processor or motherboard supports, it will operate at a lower frequency.

Make the right choice with us, friends, and there will be no trouble for you)

When faced with the problem of optimizing the operation of a computer and increasing its performance, the first step to solving the problem, which is easiest to do, is to increase amount of RAM or optimize it by increasing performance. The best option among those proposed is to purchase an additional memory stick (RAM) or replace existing memory sticks with those that have large capacity.

Difficulty in choosing when replacing an operational module Windows memory lies in the particular influence of its parameters on computer performance. It is worth remembering that RAM exchanges data with central processor. The stronger the relationship between these components, the faster the necessary calculations are carried out in the system. Therefore, the choice of memory must be approached based on the above, and then the RAM will work with maximum efficiency.

But before you go to the store for new trims, you need to install:

• What amount of memory is currently installed and what is the maximum amount supported by the board?
• What type of memory is supported motherboard and processor?
• How many memory slots are there and in what mode do they operate?
• What is the memory frequency supported by the processor?

Let's start in order. In general, what is RAM needed for? To temporarily store data to perform ongoing processor operations. The larger it is, the easier it is for the processor to simultaneously perform several tasks.

RAM is volatile, which means that after the computer is turned off, all data on it will be deleted, unlike data stored on the hard drive.

How to find out the current amount of RAM?

To do this, it is not even necessary to open the computer lid - we launch the Speccy utility we already know and find the current characteristics in the corresponding section. In principle, all the main characteristics are already presented here, which we will consider in detail below.

At the moment we are interested in capacity - I have 2 slots on my laptop, both of which are occupied. The total size is 2000 MB (2GB), that is, there are 2 1 GB sticks on the laptop.

For normal daily Windows operation This is quite enough, but if you plan to play games with complex graphics or use heavy graphics or video programs, then it is advisable to set more.

By the way, each version of the operating system has minimum requirements on RAM, without which it simply will not work.

• For Windows XP— At least 64 MB of RAM (at least 128 MB recommended)
• Windows 10, 7 and 8- 1 gigabyte (GB) (for a 32-bit system) or 2 GB (for a 64-bit system) of random access memory (RAM).

Even when planning the volume for increase, you should find out from the characteristics of the motherboard or processor which maximum size supported. This is indicated in detailed description in the memory section. Yes, in the model Intel Core i54430 maximum size - 32 GB.

For an office PC on which you will only work with office documents, 1 GB of memory is sufficient.
For home viewing of videos, photos, and using various applications, it is recommended to use at least 2 GB.
For a powerful gaming computer - 8GB and above.

However, keep in mind that 4 GB or more will only work fully on a 64-bit OS; Windows 32 and up will see no more than 3 GB.

Supported RAM type

The next indicator characterizing the RAM is its type. We list them as technologies develop - SDRAMM DIMM, DDR (or PC), DDR2 (PC-2) and DDR3 (PC-3).

As you can see from the above screenshot from the Speccy program, my laptop supports DDR3 memory, although today the latest modern standard is DDR4.

All modern processors work with this standard, however, older standards can also be found on older boards. If your computer is many years old, then it is likely that it uses an outdated type and the memory module must be selected of this particular standard. Memory modules different types are incompatible with “foreign” slots on system board.

You can also find out the type of supported RAM from the characteristics of the processor (CPU) or motherboard model on the manufacturer’s official website - these models are also easy to find out in Speccy program or its analogues.

If you have spare sticks of RAM, it can also sometimes be difficult to determine what type it is. Usually they have a sticker indicating the type - PC, PC-2, PC-3 or DDR, DDR2, DDR3. But if there is no sticker, then we will determine it as follows.

The DDR and DDR2 strips are very similar in appearance and have 1 key (cutout) located almost in the center. But DDR has 180 contacts - 92 on each side. And on DDR2 - 240 - 120 on each side, and they are visually narrower than DDR2. It's easy to count them because they are numbered.

DDR3 modules have the same number of pins as PC-2, but the key is not in the middle, but shifted to the edge.

The memory module of the very old SDRAM standard is distinguished by the presence of two keys.

Number of slots for memory sticks and their operating mode

We also saw the number of slots intended for installing brackets in the program - I have 2 of them. If you open the lid of the computer case, you can see several characteristic one- or multi-colored connectors on the board. This is the place where the memory sticks are placed. There are 4 of them in the picture below.

The multicolored color tells us that the memory on this board can operate in dual-channel mode - that is, data is simultaneously transmitted to the controller to the processor or northbridge (depending on) via two channels, which increases the speed of data processing.

To activate this mode, you should purchase at least 2 strips and, as a rule, insert them into two same-color connectors. Which ones exactly? This is written in the instructions for the board and colors may differ in different models. If you buy 4 modules at once, then use all the slots at once.

You also need to take into account that if you currently have a total memory of 2 GB, like me, and you plan to increase it to 4 GB, then it is optimal to purchase 2 modules of 2 GB each rather than one 4 GB, since you can use them to the maximum in in two-channel mode.

It should also be noted here that when purchasing several modules, it is advisable to choose one manufacturer, or even better, take a ready-made kit (KIT) consisting of several strips at once - such a kit is guaranteed to work without problems.

Clock frequency

Another important indicator of memory is its clock frequency, which is measured in megahertz (MHz). The speed of information processing depends on it. When choosing a module, be sure to look at what frequency your processor officially supports. The model that was shown in the screenshot above works with PC3-12800 (DDR3 1600 MHz), PC3-10600 (DDR3 1333 MHz), PC3-8500 (DDR3 1066 MHz) memory. The same characteristics can be seen on online store websites in the detailed description of memory modules. For example, let's look at a gaming kit of 4 4 GB sticks Corsair XMS3 DDR-III DIMM 32Gb KIT 4*8Gb:

RAM Bandwidth

A parameter such as throughput also depends on the frequency, which shows how much data can be transferred maximum per certain time. It is measured in megabytes per second (MB/s) and is calculated by multiplying the frequency by 8. That is, in our example, the memory has a frequency of 1333 MHz * 8 = 10667 MB/s, which is also visible in the description.

The higher the bandwidth, the higher the speed of the RAM module. However, we take into account the fact that

modern processors support memory with a maximum frequency of 1600 MHz.

If you buy an expensive stick with a higher frequency, it will work the same as a cheaper one at 1600 MHz.

Timing

Here we can also talk about such a characteristic as timing. This is the delay time when processing operations inside the RAM module chips themselves. The timing is recorded as a sequence of several numbers - in our example it is 9-9-9-24. The last 4th two-digit parameter characterizes the performance of the entire microcircuit as a whole.

Timing can also be indicated by the letters CL and a number, which indicates the first value in the detailed sequence. In our example, the short version would be designated as CL9.

The lower the timings, the better, but such modules also cost more. However, this only matters for high-performance, high-speed PCs - for home and office on this parameter you can ignore it.

Gamers can take advantage BIOS settings and manually play with changing the timings downward, but you need to do this carefully, otherwise you risk damaging the modules.

RAM for a laptop or desktop computer?

In theory, this is the first question that we should ask ourselves, but essentially it is not the most important, since it is simply impossible to confuse the form factor. For a laptop, the modules are wide and short, for a PC they are long and narrow.

On the websites in the characteristics they are indicated as follows:

• DIMM- for PC,
• SODIMM- for laptop.

Type of cooling of memory strips

If you are purchasing a RAM module for a powerful gaming computer, then you should pay attention to the type of cooling. During intensive work or “overclocking” by decreasing the timings, they can heat up, so the work of the internal case fans may not be enough to cool them.

On simple strips there is no cooling at all - you will see open soldered microcircuit chips. On more expensive models, the most common type of cooling is installed - a metal radiator.

For the most avid gamers, they even came up with such a thing as water cooling - such modules, together with the system, can significantly exceed the cost of both the motherboard and processor combined.

Decoding the RAM module

Now let's decipher the name of the memory module presented in one of the popular online stores:

Crucial Ballistix Sport XT BLS2C4G3D18ADS3CEU DDR-III DIMM 8Gb KIT 2*4Gb PC3-14900 CL10

• So, manufacturer Cruisal, the kit consists of 2 modules of 4 Gb each.
• Memory standard DDR-III and form factor DIMM, that is, for a desktop PC.
• Bandwidth - 14900 Mb/s
• Timing - CL10
• In this case, the frequency must be looked at detailed specifications product, or calculate it yourself by dividing the throughput (14900) by 8.

Tips to follow when buying RAM

• It is worth buying RAM from trusted manufacturers. The price of branded brands is much higher, but the quality guarantee and stable operation of the computer are worth it. Here is a list of verified companies: Corsair, Kingston, Kingmax, Transcend, OCZ, Hynix, Hyundai, Samsung.
• RAM paired with a good quality chipset is the key to maximum performance, considering that the former has a maximum operating frequency.
• Remember that RAM should always be paired. It is necessary that the modules match in operating frequency; modules installed with different frequencies work at the memory frequency, which is the slowest of those that you installed, or do not work together at all. For example, if you have two channels for RAM and one of the slots has a 2GB stick, then you need to purchase another module with the same capacity, timings and from the same manufacturer.
  And the best option is to buy a set of modules (Kit), which is guaranteed by the manufacturer that these strips are compatible
• For gaming computers preference should be given to RAM with the lowest time delays. Even at low frequencies, the memory always works at maximum efficiency.
• Be sure to ensure that your motherboard, processor, and operating system are compatible with the amount of memory you choose. If your computer system is 32-bit, then you should purchase a stick of no more than 4GB, since a 32-bit system sees up to 3GB of RAM.
• When purchasing memory to increase existing RAM, it would be better to purchase a model whose characteristics are similar to those installed in your computer. Purchasing a better or worse specification bar will lead to deterioration in computer performance.

In conclusion, here is a detailed video on installing a memory module in a computer.

Story random access memory, or RAM, began back in 1834, when Charles Babbage developed the “analytical engine” - essentially a prototype of a computer. He called the part of this machine, which was responsible for storing intermediate data, a “warehouse.” Memorizing information there was still organized in a purely mechanical way, through shafts and gears.

In the first generations of computers, cathode ray tubes and magnetic drums were used as RAM; later magnetic cores appeared, and after them, in the third generation of computers, memory on microcircuits appeared.

Nowadays RAM is made using technology DRAM in form factors DIMM and SO-DIMM, is dynamic memory organized in the form of semiconductor integrated circuits. It is volatile, meaning data disappears when there is no power.

Choosing RAM is not a difficult task today; the main thing here is to understand the types of memory, its purpose and main characteristics.

Memory types

SO-DIMM

Memory of the SO-DIMM form factor is intended for use in laptops, compact ITX systems, monoblocks - in short, where the minimum physical size memory modules. It differs from the DIMM form factor in that the length of the module is approximately halved and there are fewer pins on the board (204 and 360 pins for SO-DIMM DDR3 and DDR4 versus 240 and 288 on boards of the same types of DIMM memory).
In terms of other characteristics - frequency, timings, volume, SO-DIMM modules can be of any kind, and do not differ in any fundamental way from DIMMs.

DIMM

DIMM - RAM for full-size computers.
The type of memory you choose must first be compatible with the socket on the motherboard. Computer RAM is divided into 4 types – DDR, DDR2, DDR3 And DDR4.

DDR memory appeared in 2001 and had 184 contacts. The supply voltage ranged from 2.2 to 2.4 V. The operating frequency was 400 MHz. It is still available for sale, although the selection is small. Today the format is outdated - it is suitable only if you do not want to update the system completely, and the old motherboard only has connectors for DDR.

The DDR2 standard came out in 2003 and received 240 pins, which increased the number of threads, significantly speeding up the processor data bus. The operating frequency of DDR2 could be up to 800 MHz (in some cases - up to 1066 MHz), and the supply voltage was from 1.8 to 2.1 V - slightly less than that of DDR. Consequently, power consumption and heat dissipation of memory have decreased.
Differences between DDR2 and DDR:

· 240 contacts versus 120
· New slot, not DDR compatible
· Less power consumption
Improved design, better cooling
Higher maximum operating frequency

Just like DDR, it is an outdated type of memory - now it is only suitable for old motherboards, in other cases there is no point in buying it, since the new DDR3 and DDR4 are faster.

In 2007, RAM was updated to the DDR3 type, which is still widely used. The same 240 pins remain, but the connection slot for DDR3 has changed - there is no compatibility with DDR2. The operating frequency of the modules is on average from 1333 to 1866 MHz. There are also modules with frequencies up to 2800 MHz.
DDR3 differs from DDR2:

· DDR2 and DDR3 slots are not compatible.
· The clock frequency of DDR3 is 2 times higher - 1600 MHz versus 800 MHz for DDR2.
· Features a reduced supply voltage - about 1.5V, and lower power consumption (in the version DDR3L this value is on average even lower, about 1.35 V).
· The delays (timings) of DDR3 are greater than those of DDR2, but the operating frequency is higher. In general, the speed of DDR3 is 20-30% higher.

DDR3 is a good choice today. Many motherboards on sale have DDR3 memory connectors, and due to the massive popularity of this type, it is unlikely to disappear soon. It is also slightly cheaper than DDR4.

DDR4 is a new type of RAM, developed only in 2012. It is an evolutionary development of previous types. Memory bandwidth has increased again, now reaching 25.6 GB/s. The operating frequency also increased - from an average of 2133 MHz to 3600 MHz. If we compare the new type with DDR3, which lasted on the market for 8 years and became widespread, then the performance increase is insignificant, and not all motherboards and processors support the new type.
DDR4 differences:

· Incompatible with previous types
· Reduced supply voltage - from 1.2 to 1.05 V, power consumption has also decreased
· Memory operating frequency up to 3200 MHz (can reach 4166 MHz in some trims), with, of course, timings increasing proportionally
May be slightly faster than DDR3

If you already have DDR3 sticks, then there is no point in rushing to change them to DDR4. When this format spreads massively, and all motherboards already support DDR4, the transition to a new type will happen by itself with an update of the entire system. Thus, we can summarize that DDR4 is more of a marketing product than a real new type of RAM.

Which memory frequency should I choose?

Choosing a frequency should begin by checking the maximum supported frequencies by your processor and motherboard. It makes sense to take a frequency higher than that supported by the processor only when overclocking the processor.

Today you should not choose memory with a frequency lower than 1600 MHz. The 1333 MHz option is acceptable in the case of DDR3, unless these are ancient modules lying around the seller, which will obviously be slower than the new ones.

The best option for today is memory with a frequency range from 1600 to 2400 MHz. A higher frequency has almost no advantage, but it costs much more, and as a rule, these are overclocked modules with raised timings. For example, the difference between modules of 1600 and 2133 MHz in a number of work programs will be no more than 5-8%; in games the difference may be even smaller. Frequencies of 2133-2400 MHz are worth taking if you are engaged in video/audio encoding and rendering.

The difference between frequencies of 2400 and 3600 MHz will cost you quite a lot, without significantly increasing speed.

How much RAM should I take?

The amount you need depends on the type of work performed on the computer, the operating system installed, and the programs used. Also, do not lose sight of the maximum supported memory capacity of your motherboard.

Volume 2 GB- today, it may only be enough to browse the Internet. More than half will be consumed by the operating system; the rest will be enough for the leisurely work of undemanding programs.

Volume 4 GB– suitable for a mid-range computer, for a home PC media center. Enough to watch movies and even play undemanding games. Modern ones, alas, are difficult to cope with. (will become best choice, if you have a 32-bit operating system Windows system, which sees no more than 3 GB of RAM)

Volume 8 GB(or a 2x4GB kit) is the recommended volume today for a full-fledged PC. This is enough for almost any games, for working with any resource-demanding software. The best choice for a universal computer.

A capacity of 16 GB (or sets of 2x8GB, 4x4GB) will be justified if you work with graphics, heavy programming environments, or constantly render video. It’s also perfect for online streaming – with 8 GB there may be stutters, especially with high-quality video broadcasts. Some games in high resolutions and with HD textures can behave better with 16 GB of RAM on board.

Volume 32 GB(set 2x16GB, or 4x8GB) – still a very controversial choice, useful for some very extreme work tasks. It would be better to spend money on other computer components; this will have a stronger effect on its performance.

Operating modes: is it better to have 1 memory stick or 2?

RAM can operate in single-channel, dual-, triple- and quad-channel modes. Definitely, if your motherboard has a sufficient number of slots, then it is better to take several identical smaller memory sticks instead of one. The speed of access to them will increase from 2 to 4 times.

In order for the memory to work in dual-channel mode, you need to install the sticks in slots of the same color on the motherboard. As a rule, the color is repeated through the connector. It is important that the memory frequency in the two sticks be the same.

- Single chanell Mode– single-channel operating mode. It turns on when one memory stick is installed, or different modules operating at different frequencies. As a result, the memory operates at the frequency of the slowest stick.
- Dual Mode– two-channel mode. Works only with memory modules of the same frequency, increases operating speed by 2 times. Manufacturers produce sets of memory modules specifically for this purpose, which can contain 2 or 4 identical sticks.
-Triple Mode– works on the same principle as two-channel. In practice it is not always faster.
- Quad Mode- four-channel mode, which works on the principle of two-channel, accordingly increasing the speed of operation by 4 times. It is used where exceptionally high speed is needed - for example, in servers.

- Flex Mode– a more flexible version of the two-channel operating mode, when the bars are of different volumes, but only the frequency is the same. In this case, in dual-channel mode, the same volumes of modules will be used, and the remaining volume will function in single-channel mode.

Does memory need a heatsink?

Now we are long gone from the days when, at a voltage of 2 V, an operating frequency of 1600 MHz was achieved, and as a result, a lot of heat was generated, which had to be removed somehow. Then the radiator could be a criterion for the survival of an overclocked module.

Nowadays, memory power consumption has decreased significantly, and a heatsink on a module can be justified from a technical point of view only if you are into overclocking and the module will operate at frequencies that are prohibitive for it. In all other cases, radiators can be justified, perhaps, by their beautiful design.

If the radiator is massive and noticeably increases the height of the memory bar, this is already a significant disadvantage, since it may prevent you from installing a processor super cooler in the system. By the way, there are special low-profile memory modules designed for installation in compact cases. They are slightly more expensive than regular size modules.

What are timings?

Timings, or latency (latency)- one of the most important characteristics RAM, which determine its performance. Let us outline the general meaning of this parameter.

Simply put, RAM can be thought of as a two-dimensional table in which each cell carries information. Cells are accessed by column and row numbers, and this is indicated by the row access strobe RAS(Row Access Strobe) and column access gate CAS (Access Strobe) by changing the voltage. Thus, for each cycle of work, accesses occur RAS And CAS, and between these calls and the write/read commands there are certain delays, which are called timings.

In the description of the RAM module you can see five timings, which for convenience are written as a sequence of numbers separated by a hyphen, for example 8-9-9-20-27 .

· tRCD (time of RAS to CAS Delay)- timing, which determines the delay from the RAS pulse to the CAS
· CL (time of CAS Latency)- timing, which determines the delay between the write/read command and the CAS pulse
· tRP (time of Row Precharge)- timing, which determines the delay when transitioning from one line to the next
· tRAS (time of Active to Precharge Delay)- timing, which determines the delay between the activation of the line and the end of working with it; considered the main meaning
· Command rate– defines the delay between the command to select an individual chip on the module until the command to activate the line; this timing is not always indicated.

To put it even more simply, it is important to know only one thing about timings - the lower their values, the better. In this case, the strips can have the same operating frequency, but different timings, and a module with lower values ​​will always be faster. So it’s worth choosing the minimum timings; for DDR4, timings for average values ​​will be 15-15-15-36, for DDR3 - 10-10-10-30. It is also worth remembering that timings are related to the memory frequency, so when overclocking you will most likely have to increase the timings, and vice versa - you can manually lower the frequency, thereby reducing the timings. It is most beneficial to pay attention to the totality of these parameters, choosing rather a balance, and not chasing the extreme values ​​of the parameters.

How to decide on a budget?

With a larger amount, you can afford more RAM. The main difference between cheap and expensive modules will be in the timings, operating frequency, and brand - well-known, advertised modules may cost a little more than noname modules from an unknown manufacturer.
In addition, the radiator installed on the modules costs additional money. Not all planks need it, but manufacturers are not skimping on them now.

The price will also depend on the timings; the lower they are, the higher the speed, and, accordingly, the price.

So, having up to 2000 rubles, you can purchase a 4 GB memory module, or 2 2 GB modules, which is preferable. Choose depending on what your PC configuration allows. DDR3 type modules will cost almost half as much as DDR4. With such a budget, it makes more sense to take DDR3.

To the group up to 4000 rubles includes modules with a capacity of 8 GB, as well as sets of 2x4 GB. This optimal choice for any task except professional video work and in any other difficult environments.

In total up to 8000 rubles It will cost 16 GB of memory. Recommended for professional purposes, or for avid gamers - even enough in reserve, while waiting for new demanding games.

If it's not a problem to spend up to 13,000 rubles, then the best choice would be to invest them in a set of 4 4 GB sticks. For this money you can even choose more beautiful radiators, perhaps for later overclocking.

I don’t recommend taking more than 16 GB without the purpose of working in professional heavy environments (and even then not in all), but if you really want it, then for the amount from 13,000 rubles you can climb to Olympus by purchasing a 32 GB or even 64 GB kit. True, this will not make much sense for the average user or gamer - it is better to spend money on, say, a flagship video card.

I received a question from Alexander Shilin:

Folks, I have this question, but if my mother’s ceiling says 600+, then 667 strips will do? I didn’t see anything with a frequency of 600 at all, I only saw 667 and higher.

To be honest, it was not possible to find a motherboard that supports memory with an operating frequency of no higher than 600 MHz, and RAM with a frequency of 667 MHz has almost disappeared from sale.

But we were able to find motherboards whose specifications stated support for DDR2 667/533/400, but not a word about DDR2 800. One of these boards is ASUS P5LD2 on Intel chipset 945P.

The chipset is old, and, most likely, when a computer with such a motherboard was assembled, no more than 1GB of memory was installed in it, or even only 512MB. However, no one has canceled the desire to increase computer performance by increasing the amount of RAM.

Only memory stores with the required characteristics of DDR2 667/533/400 are not available in stores, but only DDR2 800. Is it possible to install it? Will it work?

Can.

To verify this, let’s run the CPU-Z program, which I already praised when I wrote about it. Only this time we’ll open the SPD tab.

Here is an example for DDR2 PC2-5300, 667MHz:

DDR2 PC6400, 800MHz:

And here is the memory, officially labeled as DDR2 PC6400, 800 MHz, but supporting operation at 1066 MHz:

The most interesting line for us in this case is the Frequency line in the Timings Table section. Only the frequency value must be multiplied by 2 to obtain the values ​​​​indicated in the price lists and manuals for the mat. boards

In general, SPD is a system of profiles hardwired into RAM, which tells the motherboard through the BIOS at what frequency a given stick is capable of operating.

And then it is clear that DDR2 PC2-5300, 667 MHz can operate not only at 667 MHz, but also at 533 MHz, and even 400 MHz.

The same can be said about DDR2 PC6400, 800MHz. The lack of mention in the plate about the possibility of operating at a frequency of 667 MHz is caused, I believe, to save space.

I think that the latest bar will work even at a frequency of 400 MHz. But from an economic point of view, buying in this case is very strange.

So buy DDR2 PC6400, 800MHz and feel free to install it on a motherboard that only supports DDR2 667/533/400. Everything will work great and even more reliably, because... such a bar will have a noticeable margin of safety, instead of working at the limit. 🙂

28 comments

1. Ilya(29 July 2009, 15:56)

On boards that support only slow memory, you can install fast memory - it will simply work on the maximum supported motherboard. speed board (i.e. low).

2. (29 July 2009, 16:01)

Ilya, in fact, wrote about this, only in order not to be unfounded, he added several images. 🙂

3. Anton Molodoy(30 July 2009, 11:30)

>ASUS P5LD2 on Intel 945P chipset.
I have exactly such a mother :)

>when a computer with such a motherboard was assembled, no more than 1GB of memory was installed in it, or even only 512MB.
I'm probably ebony. but I have 3GB. I love it when there is a LOT of memory.

4. (30 July 2009, 13:40)

Anton, geeks don't count. 🙂
I meant the standard configs that are sold to people.

5. Igor(27 August 2009, 00:56)

In general, I'm one radish confused in this memory. The laptop supports 533MHz, there was a double bank of 512MB PC4200 running at 266MHz. I installed the PC6400 (800) and thought it would work at 533 MHz. But it is not at all like that - 399 MHz. In short, I “clicked” the screenshots and pasted them here: http://komp-kompyuterov.narod.ru/index.html What’s what? Or is everything right 400x2=800.=)…I guess my enlightenment is later. Then why are they fooling people with eight hundred megahertz?

6. (27 August 2009, 07:01)

Igor, 800 is, obviously, when the two-channel mode is activated: 2 channels of 400 MHz in total give 800.

In the case of laptops, it's even trickier. This screenshot clearly shows that the maximum frequency (RAM Max support) is 533 MHz. Those. in the case of one bracket - 266 MHz.

But there is no need to be upset. 🙂 2GB is in any case much better than 512MB, and 800MHz is now no more expensive than 533.

7. Igor(28 August 2009, 09:51)

Well then at least The issue with “grabbing” from the swap has now been resolved. And sometimes it slowed down like a child. :)
Well, in short, I didn’t manage to indulge myself enough in the innovation. A terrible thing happened to the laptop. (I didn’t shed my mother’s blood, but..) By the way, as a result of what happened, when I tried to open an MP3 with Windows, MP writes that “the operation could not be completed due to lack of memory.” Well, isn’t it a mockery? :) And the classic player opens Fine. And there are still a lot of bad things present. Well, this already applies to Windows or security problems. Maybe there is a relevant topic here somewhere? Or are we going off-topic here? Then I’ll write about the problem globally.

8. (28 August 2009, 09:55)
9. Igor(30 August 2009, 04:06)

Well, as they say, once such a p... uh... sorting out began. 🙂 First, the total of the 1st episode; objects (folders, shortcuts, etc.) seemed to be nailed down and were not moved by any click, the “insert” context menu stopped working (always inactive), these same errors were not clicked in the error logs to see the description when entering Accounts empty window without selecting anything, in the task manager the absence of a loved one in the users tab and generally loss of administrator rights, partial or complete xs (message when trying to launch an application on drive D), processes in the task manager instead of +50 remained 30+, periodic reboots with blue screen (flickering quickly, you don’t have time to look at what’s written there), later we managed to figure out the error code
Error code 10000050, parameter1 8f640cec, parameter2 00000001, parameter3 805b641a, parameter4 00000000.
Error code 10000050, parameter1 c399ff20, parameter2 00000000, parameter3 bf80dd9b, parameter4 00000000.
something like this, when I try to scan for viruses, there is also a reboot (in fact, I tried to fight them for 3 days), messages about a broken file system in C, and so on and so forth. The main problem was to remove texts with passwords/logins. I was already mentally ready to rewrite it manually, but remembering about the Windows disk, I successfully used the file transfer wizard. (fine-soft ones are not as bad as they really are =))) I don’t remember how it all started, but definitely after that As soon as I started manipulating the memory, I still remember there was something freezing, scandisk and off we go. I tried to restore the system - again an error and a reboot. (now in the pad I write Ctrl+S after each sentence, because the reptile regularly reboots:(). Everything described was running with home edishin, the second XP (cut off from game edit) also almost didn’t start at all, complaining about the broken C. C safe mode nothing good came of it either. Having pushed around, I pulled up the heavy artillery and restored Acronis True Image Home 11.0 sector-by-sector logical C. Everything seemed to work normally (although right now there is such confusion in my head that I can’t guarantee anything :)) And the second axis started working. I exchanged the memory (goodram) I think maybe the bracket was buggy. I inserted it, everything seemed to be fine in PC Wizard 2008, I even tested it, it showed something like my old 4200. Oh well, I connected to DSL and let’s download new things. The image of Acronis was already in October 2008, albeit with almost all the necessary programs. Well, here I am sitting here, stuffing an iron friend... and bam. Again the old song. There hasn't been a reboot... mother... for a long time. Similar codes, application error log is already corrupted. Something was freezing (again, beyond my memory:), Scandisk was checking something there. True, this time there was no folder on the disk where there is 000 at the end.
So I'm back again after the reboot. :) Some crap wanted to go to the Internet (it's disabled), I banned it in Komodo. Then I went into it to see in more detail what it was, clicked in the log... an error window and a reboot. After the error message savedump.exe and now there is no record of this event. Somehow I don’t even know what to think. Maybe it really is some kind of virus. Maybe some idiot (I can’t hold back anymore) registered in the MBR? Well, Acronis is registered there (recovery at boot). True, launching it with the choice F11 (recovery) 2-3 times yesterday, and even now displays MBR error 2. Maybe there’s something wrong here? In short, I have no strength. I lay it out and go to bed. Tomorrow (today) I’ll restore it again with aronise and see how it develops with the old memory. PS By the way, the day before I fitted the mouse with a double-click button... Maybe there’s something here? =)))))) ZYY I’m stuck, I can’t tear myself away. Overloaded again. And again I got into some kind of small-soft synchronizer. Something like this. ZYYY I couldn’t go into reboot with firelis, I spat and installed my RAM. It seems to last for some minutes. :) That memory was so hot...even though it’s a laptop.

10. Igor(30 August 2009, 04:09)

How do I feel about banning unique content? :) True, I didn’t make any paragraphs...
The peephole test turned out well. :))

11. (30 August 2009, 08:33)

Igor, this doesn’t look like a memory anymore, especially considering its replacement.
It looks like:

1. Virus. It would be nice to boot from some Live CD and check “Dr.Web CureIt!”, since it doesn’t need installation.

2. But it looks even more like the death of the hard drive. Again, it’s better to run the check from a Live CD, but as a last resort, you can just try a Windows one. And look for a utility from the HDD manufacturer.

12. Igor(30 August 2009, 15:49)

3. And it also looks like a poltergeist. :)
In short, it’s memory, Goodram’s RAM. Probably some kind of incompatibility. Now on its native Hyundai Electronics, a real branded Korean, with civil stamping everything works without failures already in the morning. Even from the night - as established. And the other system started without problems - I ran through Perfect World. True, the remaining damage will have to be repaired. For the first time, I returned my memory to a much more dead system, so there was apparently no result.
Tested the system - no failures. The event log remains damaged
day. In Comodo Firewall, everything is also normal in its log. Dawes-
I installed some updates on my computer and after that the following appeared:
fight. msfeedssync.exe is breaking into the network. Firefox using IE
not running at all. Why the hell does it bother checking news feeds?
or whatever. Well, as for the HDD, my health is 88%, but before the crisis it worked fine in my opinion. Maybe he felt bad
when did you install the new memory? In general, I will restore it somehow
OS, I will update all the other hardware and the disk image in Acronis. Then maybe I’ll stick it in with goodram if I don’t give it back before then. And I need to think about what kind of memory to look for, or rather, find at least something that works for my machine. At that point, this is the only one in stock for laptops. And we know and use CureIt, since literally half a month ago I picked up “something” (Neshta) and tried to treat it on two computers. Now I checked with CureIt - everything is clean.
True, he always swears at Giljabi.exe from my lg_swupdate directory. But I think everything is fine here. :)

PS I wonder if there might be a virus in my memory that was already stored before me? (type from the manufacturer) :))

13. Igor(1 September 2009, 19:30)

Heh, in the chaos, such a detail as the amount of memory was not noticed
in one slot. Now I installed 1GB Kingston and so far everything is ok. And thinking
that it will continue to be ok. Now it’s M1 and M2 and not like in the “PC Wizard 2008 physical memory_2Gb” screenshot. With another M1 Yes
and I remember that I support 2GB, 1GBx2. Those. in two slots.
All that remains is, if necessary, to put another one in the “bottom” and voila - two-channel
Naya. Well, those who came here according to the subject will now know what horrors
may follow after a seemingly routine operation.

14. Sergey(November 18, 2009, 20:50)

Hello, Vladimir! I'd be glad to hear your advice.
The memory stick is DDR1 3200, 512 MB. What is better, installing another stick with the same characteristics (DDR1 3200, 512 MB) or a 1 GB stick (to get 1.5 GB)? By the way, the motherboard (Foxconn P4M800P7MA-RS2) has 2 slots for DDR1 and two slots for DDR2. Does it make sense to install DDR2?

15. (18 November 2009, 20:57)

Sergey, it’s better to install another 1GB and get 1.5GB in total.
You most likely will not notice the difference between DDR1 and DDR2, and in most cases it is impossible to install both types of memory at the same time.

16. Sergey(19 November 2009, 21:14)

Thank you. What is the probability that the new 1GB stick will work with the old 512MB? I heard that strips with the same parameters, plus a double channel, work better with each other.

17. Igor(24 November 2009, 16:58)

Absolutely nothing prevents them from working together if the mother supports such a number and in such slots. Memory needs to be increased for running applications. There will be no significant difference between 1.5 and 2 GB if, for example, 1 GB is consumed during operation of the most capacious one. The difference will be if it costs 1 GB and when the program is running, 1.5 GB is taken, i.e. “grabbed” from the swap and, accordingly, slows down due to access to the HDD. See: task manager->performance->peak. How much, when your favorite heavy machine is working, is how much RAM is needed. =) A two-channel system gives an increase of less than 10%, if I’m not mistaken, which is not the point, as important as described above. Well, as they say, this is my opinion, although it rules at noob-level users. =)

18. Sergey(February 25, 2010, 00:57)
2. But here it’s more difficult. There is a possibility that the manufacturer played it safe. Or during the development of the motherboard and writing the documentation, it was simply not possible to install more than 4GB of memory. For example, there were only 1GB modules. And then he can earn more than 4GB.
But perhaps the manufacturer had some technical problems, due to which the volume was limited.
Or look for reviews about your mat. payment throughout the Internet, or try. 🙂
19. Artyom(September 15, 2010, 12:51)

mat. My board is exactly from the series that is mentioned in this article, Asus soket 775 P5LD2 SE. Thank you, Vladimir) I’ll try.

20. Anton(31 January 2013, 14:05)

Hello, the following question:
ASUS motherboard P5LD2 in its description it is written that the maximum RAM memory can be installed with a frequency of 667 MHz, but I bought 2 sticks of 2 GB and a frequency of 800 MHz, installed the computer and I really liked it because Previously there was 1GB OP.
But after that, space on the hard drive began to disappear, namely on drive “C” (Windows XP is installed on it)
Could this be due to a Motherboard limitation?
Or did I catch some kind of virus? because At the moment, Kaspersky without a license is not paid for = does not work.

21. (January 31, 2013, 2:09 pm)

Anton, is there a lot of space missing?
Windows has a page file, it can sometimes depend on the size of the RAM.
There is a sleep mode, when the entire contents of the RAM are saved to the hard drive - and the system always reserves a volume equal to the amount of memory. You can turn it off and the place will return.

Or maybe it's just some kind of coincidence.

22. Vas!(19 May 2013, 19:34)

Hello! Can you tell me: the Asus motherboard supports memory up to 800 MHz, now it costs 2 x 512 at 533 speed (pc-4300). Is it possible to expand by adding 1 or 2 GB but 800th memory? Zs-4300 is nowhere to buy. Will this combination of 2x512 MB on 533 and 1 or 2 GB on 800 work??? Thank you.

23. Opana(23 October 2015, 15:43)

Hello, I have slots for DDR3 and DDR4 on my motherboard, is it possible to add another 8Gb*2 DDR3@2133MHz to the 8Gb*2 DDR4@3200MHz?

24. Tony(27 March 2017, 16:29)

My question is, will this work in Toshiba laptop Satelit A 215? There the frequency will definitely be 667 hertz at the 800 hertz bar, and is there a risk that it won’t start at all? And in general, can you cram more than 4 gigs of RAM there? Or is there 4, the maximum?

25. Guest(2 July 2018, 10:22)

Ha, P5RD2-VM does not start with 800 memory (officially the ceiling is 667). But she found a crutch - if you stick one 667 and the other 800 together, then everything works.

26. Vadim(10 October 2018, 12:08)

asrock 945gcm-s does not support 800 MHz memory

Theoretical foundations and first results of low-level testing

DDR2 new standard memory approved by the Joint Electronic Device Engineering Council, which includes many manufacturers of chips and memory modules, as well as chipsets. Early versions of the standard were published already in March 2003, it was finally approved only in January 2004 and received the name DDR2 SDRAM SPECIFICATION, JESD79-2, revision A (). DDR2 is based on the well-known and proven DDR (Double Data Rate) technology. You could even say this: “DDR2 begins where DDR ends.” In other words, the first DDR2 will operate at frequencies that are the limit for the current generation of DDR-400 memory (PC3200 standard, clock frequency 200 MHz), and its further variants will significantly exceed it. The first generation of DDR2 memory, already currently produced by such vendors as , and , are its varieties DDR2-400 and DDR2-533, operating at frequencies of 200 MHz and 266 MHz, respectively. Next, a new generation of DDR2-667 and DDR2-800 modules is expected to appear, although it is noted that they are unlikely to appear at all and, moreover, will become widespread even by the end of this year.

To be fair, it is worth noting that DDR2 memory, as such, has appeared quite a long time ago - of course, this refers to memory on video cards. However, this variant of DDR2 (called GDDR2) is actually a special type of memory designed specifically for the video card market and is slightly different from the “desktop” version of DDR2, which is the focus of this review. general information

So, “desktop” DDR2-SDRAM is considered as an evolutionary replacement for the current generation of DDR memory. The principle of its operation is absolutely the same - data transfer (at the memory module level) is carried out via a 64-bit bus on both parts of the clock signal (ascending "edge" and descending "cut"), which provides twice the effective data transfer rate in relation to its frequency. Of course, at the same time, DDR2 implements a number of innovations that make it possible to make a leap to much higher frequencies (and, therefore, greater bandwidth) and larger capacities of chip arrays, on the one hand, and reduced power consumption of modules, on the other. How this is achieved, we will see later, but for now let’s turn to the “macroscopic” facts. DDR2 memory modules are manufactured in a new form factor, in the form of 240-pin DIMM modules, which are electrically incompatible with slots for DDR memory modules (in terms of number of pins, pin spacing and module pinout). Thus, the DDR2 standard does not provide backward compatibility with DDR.

The table below shows the approved naming conventions and specifications for the first three DDR2 standards. It is easy to see that DDR2-400 has the same bandwidth as the current DDR-400 memory type.

The first DDR2 memory modules will be available in 256 MB, 512 MB and 1 GB variants. However, the standard provides for the possibility of building modules of significantly higher capacity, up to 4 GB, which, however, are specialized modules (not compatible with desktop options, at least for the moment). In the future, modules with even greater capacity are expected to appear.

DDR2 chips will be manufactured using FBGA (Fine Ball Grid Array) packaging, which is more compact than the traditional TSOP-II version, allowing for larger chip capacities at smaller size and improved electrical and thermal performance. This packaging method is already used by some DDR manufacturers as an option, but is recommended for use in terms of the JEDEC standard.

The voltage consumed by DDR2 modules, according to the standard, is 1.8 V, which is significantly less compared to the supply voltage of DDR devices (2.5 V). A quite expected (although not so obvious) consequence of this fact is a reduction in power consumption, which is important for manufacturers of both laptops and large workstations and servers, where the problem of power dissipated by memory modules is far from the least important. DDR2 from the inside

The DDR2 standard includes several important data-related changes to the DDR specification that allow higher frequencies to be achieved at lower power consumption. We will look at how exactly the reduction in power dissipation is achieved while simultaneously increasing the speed of the modules.

Data sampling

The main change in DDR2 is the ability to fetch 4 bits of data per clock cycle (4n-prefetch), as opposed to 2-bit fetch (2n-prefetch) implemented in DDR. Essentially, this means that at each clock cycle of the memory bus, DDR2 transfers 4 bits of information from the logical (internal) banks of the memory chip to the I/O buffers along a single data interface line, while conventional DDR is only able to transfer 2 bits per clock per line . The question quite naturally arises: if this is so, then why is the effective bandwidth of DDR2-400 the same as that of regular DDR-400 (3.2 GB/s), and not double?

To answer this question, first let's look at how regular DDR-400 memory works. In this case, both the memory core and I/O buffers operate at a frequency of 200 MHz, and the “effective” frequency of the external data bus, thanks to DDR technology, is 400 MHz. According to the 2n-prefetch rule, at each memory clock (200 MHz), 2 bits of information enter the I/O buffer along each data interface line. The task of this buffer is multiplexing/demultiplexing (MUX/DEMUX) of the data stream - in simple terms, “distilling” a narrow high-speed stream into a wide low-speed one, and vice versa. Since in a DDR SDRAM memory chip the logic banks have a data bus width between them and the level amplifier that is twice as wide as from the read latches to the external interface, the data buffer includes a 2-1 type multiplexer. In general, since memory chips, unlike modules, can have different data bus widths - usually x4/x8/x16/x32, the use of such a MUX/DEMUX (2-1) scheme implemented in DDR means that the internal the data stream of width X and frequency Y from the array is converted into an external stream of width X/2 and frequency 2Y. This is called peak throughput balancing.

Let us now consider the operating diagram of a DDR2 SDRAM type memory chip device, equal frequency and “equal width” (i.e. the same data bus width) relative to the DDR chip of the DDR-400 memory module. First of all, we note that the width of the external data bus remains exactly the same 1 bit/line, as does its effective frequency (in this example 400 MHz). Actually, this is already enough to answer the question posed above: why the theoretical bandwidth of equal-frequency memory modules such as DDR2 and DDR are equal to each other. Further, it is obvious that the use of a 2-1 multiplexer used in DDR SDRAM is no longer suitable in the case of DDR2 SDRAM, which fetches data according to the 4n-prefetch rule. Instead, it requires introducing more complex circuit with an additional conversion stage multiplexer type 4-1. This means that the core output has become four times wider than the external interface of the microcircuit and the same number of times lower in operating frequency. That is, by analogy with the example discussed above, in the general case, the MUX/DEMUX 4-1 circuit converts the internal data stream of width X and transmission frequency Y from the array into an external stream of width X/4 and frequency 4Y.

Since in this case the core of the memory chips is synchronized at a frequency half as high as the external one (100 MHz), while in DDR the synchronization of the internal and external data stream occurs at the same frequency (200 MHz), among the advantages of this approach there is an increase in the percentage of usable data. chips and reduction in energy consumption modules. By the way, this also helps explain why the DDR2 standard assumes the existence of memory modules with an “effective” frequency of 800 MHz, which is twice as high as the current generation of DDR memory. After all, it is precisely this “effective” DDR2 frequency that can be achieved now with DDR-400 memory chips operating at a native frequency of 200 MHz, if data is sampled according to the 4n-prefetch rule according to the scheme discussed above.

Thus, DDR2 means a rejection of the extensive development path of memory chips in the sense of a simple further increase in their frequency, which significantly complicates the production of stably operating memory modules in large quantities. It is being replaced by an intensive development path associated with the expansion of the internal data bus (which is a mandatory and inevitable solution when using more complex multiplexing). We would venture to assume that in the future we can expect the appearance of DDR4 type memory, which fetches not 4, but 8 bits of data from memory chips at once (according to the 8n-prefetch rule, using an 8-1 type multiplexer), and working at a frequency no longer 2, but 4 times lower in relation to the frequency of the I/O buffer :). Actually, there is nothing new in this approach; something similar has already been seen in memory chips like Rambus DRAM. However, it is not difficult to guess that the downside of this development path is the complication of the MUX/DEMUX I/O buffer device, which in the case of DDR2 must serialize four bits of data read in parallel. First of all, this should affect such an important characteristic of memory as its latency, which we will consider below.

On-chip termination

The DDR2 standard includes a number of other improvements that improve various characteristics new type of memory, including electrical ones. One of these innovations is on-chip signal termination. Its essence lies in the fact that to eliminate excess electrical noise (due to signal reflection from the end of the line), resistors are used on the memory bus to load the line not on the motherboard (as was the case with previous generations of memory), but inside the chips themselves. These resistors are deactivated when the chip is in operation and, conversely, are activated as soon as the chip enters the standby state. Because the signal is now attenuated much closer to its source, it eliminates electrical noise within the memory chip when transmitting data.

By the way, in connection with on-chip termination technology, one cannot help but dwell on such a point as... the heat dissipation of the module, which, in general, is primarily designed to actively reduce the new DDR2 standard. Indeed, such a signal termination scheme leads to the emergence of significant static currents inside the memory chips, which leads to their heating. Well, this is true, although we note that the power consumed by the memory subsystem generally, this shouldn’t increase at all (it’s just that the heat is now dissipated elsewhere). The problem here is slightly different, namely, the possibility of increasing the frequency of operation of such devices. It is very likely that this is why the first generation of DDR2 memory is not DDR2-800 modules at all, but only DDR2-400 and DDR2-533, for which the heat dissipation inside the chips still remains at an acceptable level.

Additional delay

Incremental Latency (also known as Lazy CAS) is another enhancement introduced in the DDR2 standard that is designed to minimize instruction scheduler downtime during data transfers from/to memory. To illustrate this (using a reading example), let's first consider reading Bank Interleave data from a DDR2 device with an added latency of zero, which is equivalent to reading from regular DDR memory.

The first step is to open a bank using the ACTIVATE command along with the first address component (the row address), which selects and activates the required bank and row in its array. During the next cycle, information is transferred to the internal data bus and sent to the level amplifier. When the amplified signal level reaches the required value (after a time called the delay between determining the row and column addresses, t RCD (RAS-to-CAS Delay), a read command with auto-precharge (RD_AP) can be issued for execution together with column address to select the exact address of the data to be read from the level amplifier.After issuing the read command, the column selection strobe delay t CL (CAS signal delay, CAS Latency) is executed, during which the data selected from the level amplifier is synchronized and transmitted to the external pins of the microcircuit. In this case, a situation may arise when the next command (ACTIVATE) cannot be sent for execution, since the execution of other commands has not yet finished at that moment in time. So, in the example under consideration, activation of the 2nd bank must be delayed by one clock cycle, since at this moment the read with auto-recharge command (RD_AP) from bank 0 is already executed. Ultimately, this leads to a break in the sequence of data output on the external bus, which reduces the actual memory bandwidth.

To eliminate this situation and increase the efficiency of the command scheduler, DDR2 introduces the concept of an additional (additional) delay, t AL. When t AL is non-zero, the memory device monitors the READ (RD_AP) and WRITE (WR_AP) commands, but delays their execution for a time equal to the value of the additional delay. The differences in the behavior of a DDR2 memory chip with two different values ​​of t AL are shown in the figure.

The upper figure describes the operating mode of the DDR2 chip at t AL = 0, which is equivalent to the functioning of the DDR memory chip device; the lower one corresponds to the case t AL = t RCD - 1, standard for DDR2. With this configuration, as can be seen from the figure, the ACTIVATE and READ commands can be executed one after the other. The actual implementation of the READ command will be delayed by the amount of additional delay, i.e. in reality it will be executed at the same moment as in the diagram above.

The following figure shows an example of reading data from a DDR2 chip assuming t RCD = 4 clock cycles, which corresponds to t AL = 3 clock cycles. In this case, by introducing additional latency, ACTIVATE/RD_AP commands can be executed consecutively, in turn allowing data to be issued continuously and maximizing actual memory throughput.

CAS issuance delay

As we saw above, DDR2, in terms of external bus frequency, operates at more high speeds than DDR SDRAM. At the same time, since the new standard does not involve any significant changes in the production technology of the chips themselves, static delays at the DRAM device level should remain more or less constant. The typical intrinsic latency of DDR DRAM devices is 15 ns. For DDR-266 (with a cycle time of 7.5 ns.) this is equivalent to two clock cycles, and for DDR2-533 (with a cycle time of 3.75 ns.) four.

As memory frequencies further increase, it is necessary to multiply the number of supported delay values ​​for the CAS signal output (towards b O higher values). The CAS delay values ​​defined by the DDR2 standard are presented in the table. They are in the range of integers from 3 to 5 measures; the use of fractional delays (multiples of 0.5) is not allowed in the new standard.

DRAM device latencies are expressed by the cycle dimension (t CK), i.e. are equal to the product of the cycle time by the selected CAS delay value (t CL). Typical latency values ​​for DDR2 devices fall in the range of 12-20 ns, based on which the CAS latency value used is selected. Use b O Larger delay values ​​are impractical for reasons of performance of the memory subsystem, and smaller ones due to the need for stable operation of the memory device.

Recording delay

The DDR2 standard also makes changes to the write latency specification (WRITE commands). The differences in the behavior of the write command in DDR and DDR2 devices are shown in the figure.

DDR SDRAM has a write latency of 1 clock cycle. This means that the DRAM device begins to “capture” information on the data bus on average one clock cycle after the WRITE command is received. However, given the increased speed of DDR2 devices, this period of time is too short for the DRAM device (namely, its I/O buffer) to successfully prepare to “capture” the data. In this regard, the DDR2 standard defines write latency as the CAS issuance delay minus 1 clock cycle (t WL = t CL - 1). It is noted that linking the WRITE delay to the CAS delay not only allows you to achieve higher frequencies, but also simplifies the synchronization of read and write commands (setting up Read-to-Write timings).

Recovery after recording

The procedure for writing to SDRAM memory is similar to the reading operation with the difference in the additional interval t WR, which characterizes the recovery period of the interface after the operation (usually a two-cycle delay between the end of data output to the bus and the initiation of a new cycle). This time interval, measured from the moment the write operation ends until the moment it enters the regeneration stage (Auto Precharge), ensures the restoration of the interface after the write operation and guarantees the correctness of its execution. Note that the DDR2 standard does not change the write recovery period specification.

Thus, the latencies of DDR2 devices in general can be considered one of the few characteristics in which the new standard is inferior to the DDR specifications. In this regard, it is quite obvious that using equal-frequency DDR2 is unlikely to have any advantages in terms of speed compared to DDR. How this really is, as always, will be shown by the results of the relevant tests. Test results in RightMark Memory Analyzer

Well, now is the time to move on to the test results obtained in the test package version 3.1. Let us recall that the main advantages of this test in relation to others available tests memory is broad functionality, openness of the methodology (the test is available to everyone for review in the form) and carefully developed documentation.

Test bench and software configurations

Test bench No. 1

• Processor: Intel Pentium 4 3.4 GHz (Prescott core, Socket 478, FSB 800/HT, 1 MB L2) at 2.8 GHz
• Motherboard: ASUS P4C800 Deluxe on Intel 875P chipset
• Memory: 2x512 MB PC3200 DDR SDRAM DIMM TwinMOS (timings 2.5-3-3-6)

Test stand No. 2

• Processor: Intel Pentium 4 3.4 GHz (Prescott core, Socket 775, FSB 800/HT, 1 MB L2) at 2.8 GHz
• Motherboard: Intel D915PCY based on Intel 915 chipset
• Memory: 2x512 MB PC2-4300 DDR2 SDRAM DIMM Samsung (timings 4-4-4-8)

Software

• Windows XP Professional SP1
• Intel Chipset Installation Utility 5.0.2.1003

Maximum Real Memory Bandwidth

The maximum real memory bandwidth was measured using the subtest Memory Bandwidth, presets Maximal RAM Bandwidth, Software Prefetch, MMX/SSE/SSE2. As the name of the selected presets itself suggests, this series of measurements uses a standard method for optimizing read operations from memory Software Prefetch, the essence of which is to prefetch data that will be later required from RAM in the L2 cache of the processor. To optimize writing to memory, the method is used direct storage data (Non-Temporal Store), which avoids cache clogging. The results using the MMX, SSE and SSE2 registers turned out to be almost identical; for example, below is the picture obtained on the Prescott/DDR2 platform using SSE2.

Prescott/DDR2, maximum real bandwidth

Note that there are no significant qualitative differences between DDR and DDR2 on equal-frequency Prescotts in this test. But what’s more interesting is that the quantitative characteristics of DDR-400 and DDR2-533 memory bandwidth turn out to be very close! (see table). And this is despite the fact that DDR2-533 memory has a maximum theoretical memory bandwidth of 8.6 GB/s (in dual-channel mode). Actually, we don’t see anything surprising in the result obtained - after all, the processor bus is still an 800 MHz Quad-Pumped Bus, and its bandwidth is 6.4 GB/s, so it is the limiting factor.

As for the efficiency of write operations in relation to reading, it is easy to see that it remains the same. However, this again looks quite natural, since in this case the write bandwidth limit (2/3 of the read bandwidth) is clearly set by the microarchitectural features of the Prescott processor.

Memory latency

First of all, let's take a little more detail on how and why we measured the “true” memory latency, since measuring it on Pentium 4 platforms is, in fact, a far from trivial task. This is due to the fact that processors of this family, in particular the new Prescott core, are characterized by the presence of a rather “advanced” asynchronous hardware data prefetcher, which makes it very difficult to objectively measure this characteristic of the memory subsystem. Obviously, using sequential memory traversal methods (direct or reverse) to measure its latency is completely unsuitable in this case; the Hardware Prefetch algorithm in this case works with maximum efficiency, “masking” latencies. The use of random memory bypass modes is much more justified, however, truly random memory bypass has another significant drawback. The fact is that such a measurement is performed under conditions of almost 100% D-TLB miss, and this introduces significant additional delays, as we have already written about. Therefore the only possible option(among the methods implemented in RMMA) is pseudorandom a memory traversal mode in which each subsequent page is loaded linearly (negating D-TLB misses), while traversal within the memory page itself is truly random.

However, the results of our previous measurements showed that even this measurement technique significantly underestimates the latency values. We believe that this is due to another feature of Pentium 4 processors, namely, the ability to “capture” two 64-byte lines from memory into the L2 cache each time it is accessed. To demonstrate this phenomenon, the figure below shows the dependence of the latency of two consecutive accesses to the same memory line on the offset of the second element of the line relative to the first, obtained on the Prescott/DDR2 platform using the test D-Cache Arrival, preset L2 D-Cache Line Size Determination.

Prescott/DDR2, data arrival via L2-RAM bus

It is clear from them (the random bypass curve is the most indicative) that access to the second element of the line is not accompanied by any additional delays up to 60 bytes inclusive (which corresponds to the true size of the L2 cache line, 64 bytes). The 64-124 byte area corresponds to reading data from the next memory line. Since latency values ​​in this area increase only slightly, this means that the subsequent memory line is actually “pumped” into the processor’s L2 cache immediately after the requested one. What can be made of all this? practical conclusion? The most direct: in order to “deceive” this feature of the Hardware Prefetch algorithm, which works in all cases of memory bypass, it is enough to simply bypass the chain with a step equal to the so-called “effective” length of the L2 cache line, which in our case is 128 bytes.

So, let's move directly to the results of latency measurements. For clarity, here are the L2-RAM bus unloading graphs obtained on the Prescott/DDR2 platform.

Prescott/DDR2, memory latency, line length 64 bytes

Prescott/DDR2, memory latency, line length 128 bytes

As in the case of real bandwidth tests, the latency curves on another platform Prescott/DDR look absolutely the same at the qualitative level. Only the quantitative characteristics differ somewhat. It's time to contact them.

* latency in the absence of L2-RAM bus offload

It is easy to see that the latency of DDR2-533 was higher than that of DDR-400. However, there is nothing supernatural here according to the above theoretical foundations new DDR2 memory standard, that's exactly how it should be.

The difference in latency between DDR and DDR2 is almost imperceptible with a standard 64-byte memory bypass (3 ns in favor of DDR), when the hardware prefetcher is actively running, however, with a “two-line” (128-byte) chain bypass it becomes much more noticeable. Namely, the minimum latency of DDR2 (55.0 ns) is equal to the maximum latency of DDR; if we compare the minimum and maximum latencies with each other, the difference is approximately 7-9 ns (15-16%) in favor of DDR. At the same time, it must be said that the almost equal values ​​of “average” latency obtained in the absence of L2-RAM bus offload are somewhat surprising, both in the case of a 64-byte bypass (with data prefetch) and a 128-byte bypass (without it). ). Conclusion

The main conclusion that suggests itself based on the results of our first comparative testing of DDR and DDR2 memory is general view can be formulated this way: “DDR2’s time has not yet come.” The main reason is that it is still pointless to fight to increase the theoretical memory bandwidth by increasing the frequency of the external memory bus. After all, the bus of the current generation of processors still operates at a frequency of 800 MHz, which limits the real bandwidth of the memory subsystem at 6.4 GB/s. This means that at present there is no point in installing memory modules with higher theoretical memory bandwidth, since the currently existing and widely used DDR-400 memory in dual-channel mode fully justifies itself, and in addition has lower latency. By the way, about the latter - an increase in the frequency of the external memory bus is inevitably associated with the need to introduce additional delays, which, in fact, is confirmed by the results of our tests. Thus, we can assume that the use of DDR2 will be justified, at least, not earlier than the moment when the first processors with a bus frequency of 1066 MHz and higher appear, which will overcome the limitation imposed by the processor bus speed on the real bandwidth of the memory subsystem as a whole.