The beginning of a new era. How DDR4 RAM works. DDR4 RAM specification Ddr4 description

We carried out a small express test of the operation of LGA1151 processors with memory, such as DDR3 and DDR4, last year, and this year we slightly expanded the studied area in the direction of budget models for this platform. In general, there was a feeling that the new type of memory does not have any performance advantages, but it does save some energy, which in recent years has become the main focus of Intel's efforts when developing new microarchitectures. True, the influence of memory on the power consumption of older models Intel processors we haven't explored. And in general - their tests were carried out using the old testing methodology, and very different motherboards etc., so the conclusions made last year may become outdated. Therefore, we decided to investigate the issue more carefully and in detail.

Test bench configuration

CPUIntel Celeron G3900Intel Pentium G4500TIntel Core i3-6100Intel Core i5-6400Intel Core i7-6700K
Kernel nameSkylakeSkylakeSkylakeSkylakeSkylake
Production technology14 nm14 nm14 nm14 nm14 nm
Core frequency std/max, GHz2,8 3,0 3,7 2,7/3,3 4,0/4,2
Number of cores/threads2/2 2/2 2/4 4/4 4/8
L1 cache (total), I/D, KB64/64 64/64 64/64 128/128 128/128
L2 cache, KB2×2562×2562×2564×2564×256
L3 (L4) cache, MiB2 3 3 6 8
RAM2×DDR3-1600 /
2×DDR4-2133
2×DDR3-1600 /
2×DDR4-2133
2×DDR3-1600 /
2×DDR4-2133
2×DDR3-1600 /
2×DDR4-2133
2×DDR3-1600 /
2×DDR4-2133
TDP, W51 35 51 65 91
Graphic artsHDG 510HDG 530HDG 530HDG 530HDG 530
Qty EU12 23 23 24 24
Frequency std/max, MHz350/950 350/950 350/1050 350/950 350/1150
PriceT-13475848T-12874617T-12874330T-12873939T-12794508

We used five processors, and two of them had already been tested earlier - which is why today we will use the results of the Pentium G4500T, and not the somewhat more relevant G4500/G4520 for retail buyers: the usual time savings. All the same, we are most interested not in them, but in processors a little more high class- for example, the younger ones in the Core i3-6100 and i5-6400 lines. Why the younger ones? It seems to us that it is these buyers who are most likely to want to save money when upgrading the system without changing the hardware from DDR3 to DDR4. Yes and upon purchase new system what's on this moment budget boards with DDR3 support are slightly cheaper than analogues with DDR4 slots, most importantly for those who collect budget computer. And if he can afford some Core i3-6320, then it would be better to “hold out” to the “real quad-core” Core i5-6400. But, nevertheless, we also couldn’t help but test the top-end Core i7-6700K together with DDR3 - after all, this is Intel’s fastest (and most power-hungry) offering for this platform, and therefore extremely necessary for assessing the maximum potential effect of switching to new memory standard.

As for the memory modules themselves, in both cases we used a pair of them with a total capacity of 8 GB. The frequency corresponded to that supported by the standard - 1600 MHz for DDR3 and 2133 MHz for DDR4. In principle, some motherboard manufacturers offer memory overclocking capabilities for DDR3, but there is one delicate point - to achieve high frequencies, the supply voltage is usually increased to 1.65 V (instead of the standard 1.5 V). At the same time, Intel has not recommended doing this since the days of LGA1156, warning that increased voltage can lead to damage to the processor. But officially, devices for LGA1151 are allowed to work not even with DDR3, but with DDR3L operating at a voltage of 1.35 V, i.e. for them this problem may be more pronounced. However, to be fair, over the past seven years we have never encountered processor failures, even when using “overclocker” modules. Moreover, we have not heard of situations in which it was possible to unambiguously declare the presence of such problems. But you know who saves the thrifty :) Moreover, various “high-end” modules with decorative radiators and other LEDs are still not suitable for the concept of minimizing the price of the system, since they are already more expensive than mass-produced DDR4. But the banal DDR3-1600 can still be useful.

Two motherboards were required. Ideally, of course, such testing should have been carried out on a universal model, three of which are already in ASRock’s assortment, but we haven’t gotten our hands on them yet. Therefore, we simply took two boards that were as similar as possible in design and even in purpose: ASRock Fatal1ty B150 Gaming K4 and Asus B150 Pro Gaming D3. And they are based on the same chipset, which can also be important, as well as a similar (ten-channel) processor power circuit.

Testing methodology

The technique is described in detail in a separate article. Let us briefly recall here that it is based on the following four pillars:

  • Methodology for measuring power consumption when testing processors
  • Methodology for monitoring power, temperature and processor load during testing

And detailed results of all tests are available in the form of a complete table with results (in Microsoft Excel 97-2003 format). In our articles, we use already processed data. This especially applies to application tests, where everything is normalized relative to the reference system (like last year, a laptop based on a Core i5-3317U with 4 GB of memory and a 128 GB SSD) and grouped by areas of application of the computer.

iXBT Application Benchmark 2016

The very first group of programs brought a surprise - on three out of five processors, DDR3 turned out to be faster than DDR4. Studying the detailed results shows that we have one program to thank for this, namely Adobe After Effects CC 2015. Its previous version, I remember, spoiled a lot of blood for us due to its requirements for memory capacity (and depending on the other hardware environment), now here’s a new misfortune - and it’s related specifically to memory. On slow processors, however, it is unnoticeable - there are confidence intervals different dimensions overlap significantly. But if it is possible to use four or more computation threads, the difference can no longer be attributed to error: on the Core i3-6100 and i5-6400 it exceeds 10%. And for the i7-6700K it decreases slightly: apparently, thanks to larger capacity cache memory. In general, “progress” can sometimes turn out to be like that. Locally, the rest of the group's programs work on a system with DDR4 either the same or a little faster, which ultimately leads to almost equal results. For different types memory, but not processors, of course, i.e. we have before us exactly the case when saving through saving old memory may allow you to purchase a faster processor, which will pay off handsomely.

In this case, on the contrary, we have some increase in results when using DDR4, and the faster the processor, the higher it is. But even in extreme cases it does not exceed 3%, i.e. it’s not worth rushing to change memory just because of performance.

Formally, the new memory is better, but in fact the difference of a fraction of a percent may be of interest only to fans of benchmarks, but not for practical use.

A similar case. No, of course, the results are consistently higher. But such an increase in performance cannot be recorded without a photo finish, so it is better to simply ignore it.

Again the differences are within 1%. Even where they exist at all. For buyers of entry-level systems, it makes even more sense not to worry, but to try to save money. Even when buying a new computer, you can still think about this, not to mention the case when a sufficient amount of DDR3 remains from the old one.

When packing the data, the Core i7-6700K still managed to heroically squeeze out as much as 2% of the difference due to the higher bandwidth. For the rest, DDR3-1600 is more than enough, and DDR4 may even get in the way due to still high latencies.

Over the last five years, file operations have been able to actively “load” memory, but in this case we are not inclined to attribute the effect to its performance. Rather, other third-party factors, such as the controller operating in the mode for which it is mainly designed.

Looking at the results of lower-end Intel processors, we felt that the higher latencies of DDR4 are generally contraindicated for this program. However, using faster models, you can see that as their performance increases, the requirements for memory bandwidth also increase. As a result, it is possible to “squeeze” up to 3-4%. Which, however, looks good only against the background of other groups of applications, but is too small for practical significance.

Ultimately, we come to almost complete equivalence of the two types of memory, since the difference between them is within the error. However, as we saw above, there are programs that “rigidly vote” for one of the options, but in such a strange way that it can generally be attributed to some kind of errors (or, what is the same thing, excessive and unnecessary optimization), which will be corrected over time. But it’s not even close that the results would increase by a third (in proportion to the effective frequency).

Energy consumption and energy efficiency

In order not to overdo it with the size of the diagrams, we decided to limit ourselves to three points - extreme and middle (the results of the other two systems can be viewed in the summary file). In principle, they demonstrate well why all this was started. And also the fact that for lower configurations the effect can, in principle, be neglected: some savings are also observed in the case of the Celeron G3900, but taking into account its very small “appetite” in general... Plus or minus five watts in a desktop system won't be a problem. 10-15 when using top processors is already something, but in relative terms it’s also not worth attention.

But, of course, it can bring a little moral satisfaction to a big fan of “greens.” Like the LGA1151 in general - according to tests, even when using DDR3, it is still the most “energy efficient” desktop platform today, not inferior even to surrogate systems, but with incomparably more high performance. However, the LGA1150 was not bad in this capacity, and the “old” LGA1155, if its life was extended and there were no new developments, would have looked good. In fact, among desktop platforms there has been no competition in terms of energy efficiency for a long time. So the “strengthening and deepening” of work in this direction are echoes of events in completely different markets.

However, another question still remains unsolved, namely the effect of different types of memory on the power consumption of the processor itself. “Platform” efficiency is understandable: after all, the memory modules themselves have different power consumption. Does this directly affect the operation of the controller integrated into the processor? You can't tell in advance. For example, a discrete video card also “spoils” energy efficiency indicators, but does not directly affect the processor in any way. This means we need to measure. Moreover, this is not a problem for new platforms - since the days of LGA1150, the company has “transferred” the processor power system directly to a dedicated power supply line in its entirety.

As we see, there is an effect - more modest than for the “platform”, but it cannot be called loyal to the memory of the old type. Again, for younger models in Intel’s range it can be neglected, but for older ones you can get an extra ten watts “under the hood”. And this is even for standard DDR3 modules with a supply voltage of 1.5 V - increasing the latter (when trying to increase the memory frequency), of course, will only worsen the situation. Thus, the recommendation “not to raise” the supply voltage of memory modules can be trusted - this will not bring anything good. Bad, quite possibly, too. But let everyone decide for themselves whether to take risks or not. In any case, the impact of using DDR3 memory on its own power consumption (and, accordingly, heat dissipation) central processor- a documented fact. As well as the small size of this “influence” in the case of processors budget segment. Or even mid-level models.

iXBT Game Benchmark 2016

In order not to overload the article with a large number of generally similar diagrams, we once again decided to make do with the integral score (remember: it does not reflect absolute indicators, but the ability of systems to somehow “pull” at least 30 frames per second in different games).

Actually, everything is obvious. Of course, higher memory bandwidth has a beneficial effect on the integrated GPU, but the situation cannot fundamentally change. In some places this allows, for example, to increase the frame rate from 28 to 31, which affects the overall result, but no wow effects are observed. This once again confirms that when purchasing a computer for gaming purposes, you need to “dance” from the video card. Then you can think about the processor, and everything else is up to your taste. If the money remains :) But the demands of modern (and even not so modern) games are such that they are unlikely to remain after the first step. So if using “old” memory allows you to purchase a slightly faster video card, you should definitely take advantage of it. And all attempts to improve the performance of integrated graphics without radical changes are not even worth the time spent, not to mention the money.

Total

So, we have clarified the previously obtained results and came to the conclusion that so far the effect of the transition to DDR4 is even more modest than it previously seemed. From which, however, it does not follow that this transition needs to be specifically counteracted in some way. First, the new memory saves some power. Moreover (which is also important) we are not only talking about greater efficiency of the entire system, but also the consumption of the processor turns out to be slightly lower, so the latter will work in a more gentle mode, and everything is easier to solve with cooling. Secondly, shipments of DDR3 are declining quite quickly, so this memory will certainly not become cheaper, unlike DDR4. To which we will have to switch sooner or later, and we will not be surprised if DDR3 support disappears over time and from new processors already within the LGA1151 framework. On the other hand, if you already have such memory, and in sufficient quantity, which is not planned to be increased in the near future, the moment of transition can be postponed until a more successful one financially. This will not pose any problems, even when purchasing a top-end processor, not to mention mid- and low-end devices. But, naturally, you should not get carried away with excessively increasing the voltage on the modules, since this has a certain negative impact on the processor.

The differences between generations of RAM are always quite significant. Last year's release of the DDR4 standard made the server segment and high-performance desktop somewhat out of the ordinary. The recent announcement of Intel Atom server processors brought with it SO-DIMM DDR4. Everything is ready for mass attack to the market, and not just a debut. Let's study a little theory and refresh our knowledge? Below are the key differences between DDR3 and DDR4.

Physical differences.

Of course, DDR3 and DDR4 memory sticks are physically incompatible. Instead of 240 pins for the “third”, the “fourth” has 288 contacts. The increase in the number of contacts was done in order to be able to address as much as possible more memory. In its maximum version, a DDR4 memory module can have a capacity of 512 gigabytes. The minimum module size is 2 gigabytes.

The connector key is shifted closer to the center. Protection against inattentive users works, protection against inattentive but very powerful users does not exist.

The height of the reference bar is 31.25 mm, which is slightly higher than that of its predecessor (30 mm). The length of the bar is the same - 133.35 mm (remind me how much is this in inches?), This parameter has not changed since the advent of the first generation of DDR RAM.

Electrical differences.

Instead of the standard supply voltage of 1.5V (1.35V for Haswell), a standard voltage of 1.2V (1.05V for energy-efficient systems) is offered. The advantages are obvious: less heating, less power consumption, and subsequently: longer battery life.

Frequency differences.

If DDR3 standards start at a frequency of 1066 MHz, then DDR4 starts at 2133 MHz. Formally, the frequency is doubled, but in reality the performance does not double. DDR4 modules with a frequency of 3000 MHz have already been officially released and there are even higher figures, but they are all aimed at enthusiasts and overclockers.

Architectural differences.

The most important thing that happened during the transition was a change in the architecture of access to modules. Previously, the Multi-Drop bus had only two channels, and even when working with four memory modules, they hung in pairs on one channel, which did not always have a positive effect on performance.

The new bus with the original name Point-to-Point will connect each channel with one memory module. That is, if the processor has a two-channel memory controller, two slots will be available, and if there is a four-channel one, four slots will be available. You tell me, what about boards with 8 memory slots? For them, digital switches are used - similar in meaning to those that branch lines PCI Express. Thus, RAM switches to using parallel access.

Another important point is the change in the organization of memory chips. Given the same size, a DDR4 chip will have twice as many memory banks and memory lines four times shorter. This suggests that the new standard will switch between banks much faster than DDR3.

In short, these are all the key differences between the two generations of DDR3 and DDR4 RAM, how does this translate in practice? We will find out in the following posts whether there are noticeable differences in performance. Stay with us.

Finally, it allowed us to compare memory of the DDR4 and DDR3 standards with each other under equal conditions. However, before moving on to the test results, we suggest that you first study the differences between these types of modules in more detail. This will give us a better idea of ​​what to expect from the new memory, not only now, but also in the near future.

The JEDEC association began developing the DDR4 standard back in 2005. At that time, stores were still selling DDR2 strips in full swing, and serial production of DDR3 modules was only planned. In other words, engineers already understood then that the capabilities of these standards are limited and sooner or later they will become limiting or not at all consistent with the level of other PC components.

Moreover, we are talking not only about memory bandwidth, but also about such important characteristics, such as the power consumption of the modules and their volume. As you can see from this diagram, DDR4 strips outperform their predecessors in all respects.

Increased throughput

The throughput of the memory subsystem directly depends on the speed of the modules: the higher it is, the faster writing and reading from memory is performed. Of course, not all applications constantly exchange large amounts of data, so in real-life operating conditions the user may not experience the benefits of installing more powerful kits. But if we are talking about specialized programs like video and photo editors, CAD systems or tools for creating 3D animation, then the result from using high-speed modules will be much more significant. Also high throughput The memory subsystem is important when using integrated graphics. After all, the iGPU does not have access to fast GDDR5 chips, so all the information it needs is placed in the PC's RAM. Accordingly, in this case, installing more powerful memory kits will directly affect the number of FPS on the screen.

For the DDR3 format, the standard frequencies are from 1066 MHz to 1600 MHz, and only recently a value of 1866 MHz has been added. For DDR4, the minimum operating speed starts at 2133 MHz. Yes, you will say that DDR3 modules can make up the difference with overclocking. But the same thing is available for DDR4 strips, which have higher overclocking potential. After all, with the help of parameter optimization, DDR3 modules usually reach the level of 2400 - 2666 MHz, while DDR4 can easily reach heights of 2800 - 3000 MHz.

If we compare the DDR4 and DDR3 standards from the point of view of enthusiastic overclockers, then the advantage here will be on the side of DDR4. The value of 4838 MHz has already been reached, and only one year has passed since the announcement of the new format. Let us remember that the record overclocking frequency for DDR3 modules is 4620 MHz, which was recorded only 7 years after the launch of the DDR3 standard into production. In short, in terms of operating speed, DDR4 memory has very great potential.

Improved Energy Efficiency

The second important advantage of DDR4 modules is the ability to operate at low voltages. Thus, for their correct operation at nominal frequencies (2133 - 2400 MHz), only 1.2 V is enough, which is 20% less than their predecessors (1.5 V). True, over time, energy-efficient memory of the DDR3L and DDR3U standards with a supply voltage of 1.35 and 1.25 V, respectively, was introduced to the market. However, it is more expensive and has a number of limitations (as a rule, its frequency does not exceed 1600 MHz).

DDR4 memory also received support for new energy-saving technologies. For example, a DDR3 module uses only one voltage, Vddr, which is boosted using internal converters to perform some operations. This generates excess heat and reduces the overall efficiency of the memory subsystem. For the DDR4 standard bar, the specification provides for the possibility of obtaining this voltage (Vpp equal to 2.5 V) from an external power converter.

DDR4 memory also received an improved input/output interface called “Pseudo-Open Drain” (POD). It differs from the previously used Series-Stub Terminated Logic (SSTL) in the absence of current leakage at the level of memory cell drivers.

In general, the use of the entire range of energy efficient technologies should lead to a 30% gain in energy consumption. Perhaps, within the framework of a desktop PC, this will seem like an insignificant saving, but if we are talking about portable devices(laptops, netbooks), then 30% is not such a small value.

Modernized structure

In the maximum configuration, the DDR3 chip contains 8 memory banks, while 16 banks are already available for DDR4. At the same time, the line length in the DDR3 chip structure is 2048 bytes, and in DDR4 - 512 bytes. As a result, the new type of memory allows you to quickly switch between banks and open arbitrary rows.

The DDR4 microarchitecture involves the use of 8-Gbit chips, while DDR3 modules are typically created on the basis of 4-Gbit chips. That is, with the same number of chips, we will get twice the volume. Today, the most common are 4 GB modules (by the way, this is the minimum capacity for a DDR4 memory stick). But in a number of foreign countries, more capacious modules are already offered: 8 and even 16 GB. Please note that we are talking about the mass market segment.

To solve highly specialized problems, you can create even larger modules without any problems. For these purposes, 16-gigabit chips are provided and special technology for their arrangement in a DRAM package (Through-silicon Via). For example, Samsung and SK Hynix have already presented sticks with capacities of 64 and 128 GB. Theoretically, the maximum capacity of one DDR4 module can be 512 GB. Although it is unlikely that we will ever see the practical implementation of such solutions, since their cost will be extremely high.

Despite the increase in all the main characteristics, the dimensions of the DDR4 and DDR3 memory sticks remained comparable: 133.35 x 31.25 mm versus 133.35 x 30.35 mm, respectively. In physical terms, only the location of the key and the number of contacts have changed (from 240 their number increased to 288). So, even with all the desire, a DDR4 module cannot be installed in a DDR3 memory slot and vice versa.

New communication interface with the memory controller

StandardDDR3

StandardDDR4

New standard memory also provides for the use of a more advanced communication bus between modules and the memory controller. The DDR3 standard uses a Multi-Drop Bus interface with two channels. When using four slots at once, it turns out that two modules are connected to one channel, which does not have the best effect on the performance of the memory subsystem.

The DDR4 standard has improved this interface by using a more efficient scheme - one module per channel. The new type of bus is called Point-to-Point Bus. Parallel access to slots is definitely better than sequential access, since in the future it allows you to more effectively increase the performance of the entire subsystem. Users may not feel any particular advantage now, but in the future, when the volume of transmitted information increases, it will become more significant. After all, it was precisely according to the same scheme that GDDR video memory and the PCI Express interface developed. Only the use of parallel access made it possible to significantly increase their productivity.

However, the Point-to-Point Bus imposes certain restrictions on the number of modules used. Thus, a two-channel controller can serve only two slots, and a four-channel controller can serve four. As the volume of DDR4 standard bars increases, this is not so critical, but it can still cause some inconvenience at first.

This problem is solved quite in a simple way− by installing a special switch (Digital Switch) between the controller and memory slots. Based on its operating principle, it resembles a PCI Express line switch. As a result, the user, as before, will have 4 or 8 slots available (depending on the platform level), while taking full advantage of the Point-to-Point Bus.

New error detection and correction mechanisms

Since the work is high speeds Since large data stacks increase the chance of errors, the developers of the DDR4 standard took care of implementing mechanisms to detect and prevent them. In particular, the new modules support the function of correcting errors associated with parity control of commands and addresses, as well as checking checksums before writing data to memory. On the side of the controller itself, it became possible to test connections without using initialization sequences.

Comparison of DDR4 and DDR3 memory performance in equal conditions

To conduct tests, we used the following bench configuration:

CPU

Intel Core i7-6700K (Socket LGA1151) @ 4.0 GHz

motherboards

ASUS MAXIMUS VIII GENE (DDR4)

ASUS Z170-P D3 (DDR3)

RAM kits

DDR3L-1600 HyperX Fury HX316LC10FBK2/16

DDR3-2400 G.SKILL Ripjaws X F3-2400C11D-16GXM

DDR4-2400 HyperX Fury HX424C15FBK2/16

DDR4-3200 KINGMAX Nano Gaming RAM GLOF63F-D8KAGA

Graphics adapter

Intel HD Graphics 530

HDD

Seagate Barracuda 7200.12 ST3500418AS

power unit

Seasonic X-660 (660 W)

operating system

Microsoft Windows 7 (64-bit version)

The primary goal of this experiment, of course, was to compare the capabilities of DDR4 and DDR3 memory kits at the same frequencies. To get a more objective picture, the test was carried out in the most popular operating modes of the memory subsystem: 1600 MHz, 2133 MHz and 2400 MHz:

Memory kit

Operating speed, MHz

Set of delays

In benchmarks that directly depend on the frequency of memory modules, both sets demonstrated comparable results in all modes. In most cases the difference was no more than 0.5%, so here there is parity between DDR4 and DDR3.

In tests that measure the latency when the processor reads data from memory and the speed of the PC in archiving-related tasks, the advantage was on the side of DDR3 standard modules. On average the difference was 4-5%. This gap is explained by the fact that DDR3 memory requires lower timings than DDR4 to operate at the same frequency.

Applications that are used to model objects and perform complex calculations respond better to increasing memory frequencies than to changing latency sets. Therefore, in this case, working at lower timings for DDR3 memory did not bring practically any dividends. At least, we are not inclined to consider an advantage at the level of 0.6 - 0.9% as an advantage that is worth paying serious attention to.

And now we come to the most interesting part - games. They were run on the Intel HD Graphics 530 graphics core built into the processor, since if available discrete video card The RAM subsystem is far from the most decisive factor.

From the graphs presented above, the conclusion suggests itself that when assembling a PC with an integrated GPU, it is still better to give preference to the good old DDR3 format. Regardless of the selected mode (1600, 2133 or 2400 MHz), the advantage was on the side of DDR3 modules (4 - 10% depending on the game).

Summing up the intermediate results, we can confidently say that for assembling a desktop configuration, where the memory subsystem operates in standard modes, there is no point in purchasing DDR4 modules. They often show slightly lower performance than their DDR3 counterparts, and at the same time cost more.

But let's not forget that the new format has one more trump card in reserve - the ability to operate at higher frequencies. For example, today on the market you can easily find DDR4 memory modules operating in DDR4-3000 MHz or DDR4-3200 MHz mode, while DDR3 kits are usually limited to frequencies of 2400 and 2666 MHz. So theoretically, in this case, the advantage should already be on the side of the new type of memory.

At this stage of the experiment, the following memory sets were used:

Memory kit

Operating speed, MHz

Set of delays

DDR3-2400 G.SKILL Ripjaws X F3-2400C11D-16GXM (2 x 8 GB)

A series of tests carried out fully confirmed our assumption. The configuration with DDR4 memory operating in DDR4-3200 MHz mode turned out to be faster than the one with DDR3 modules running at 2400 MHz. The greatest performance increase was recorded in the AIDA64 benchmark: the speed of all main processes (reading, writing and copying data) increased by approximately 18 - 29%. The difference in other tests turned out to be not so significant (at the level of several percent), but it is still there. Thus, if you want to get the most out of your system, and the money spent to achieve this goal does not matter to you, then buying fast DDR4 modules looks like a completely justified idea.

True, the above applies only to programs. In games, the balance between frequency and latency is still critical. In this regard, DDR3 memory looks better, even if we are talking about a PC with integrated graphics. Therefore, when assembling, strictly gaming systems There is no point in overpaying for DDR4 memory at any level. It would be more advisable to purchase a couple of DDR3 standard sticks, and use the money saved to purchase a faster video card, processor or SSD.

The last item in our testing was overclocking applications. Manufacturers of DDR4 memory modules very often mention overclocking enthusiasts in their advertising brochures. Therefore, we simply could not ignore this aspect. Testing was carried out in the popular overclocking discipline Super Pi 32M. The following memory kits were chosen as competitors:

Memory kit

Operating speed, MHz

Set of delays

DDR4-2400 HyperX Fury HX424C15FBK2/16 (2 x 8 GB)

DDR4-3200 KINGMAX Nano Gaming RAM GLOF63F-D8KAGA (2 x 4 GB)

Test results for DDR3 (left) and DDR4 (right) memory at 2400 MHz

Operating at the same frequency (2400 MHz), DDR3 and DDR4 memory modules demonstrated comparable results.

Test results for DDR4 memory at 3200 MHz

Replacing the DDR4-2400 HyperX Fury HX424C15FBK2/16 kit with the faster DDR4-3200 KINGMAX Nano Gaming RAM GLOF63F-D8KAGA allowed us to reduce the test time by about 7 seconds - a fairly large value by overclocker standards. So in this area, the advantage of DDR4 memory is beyond doubt. It seems that overclocking enthusiasts are primarily the main target audience of companies producing high-performance memory sets of the new standard.

conclusions

More than a year has passed since then, but, alas, the overall picture has not changed: the new standard has a lot of interesting innovations, but so far they have not been fully in demand in practice. For most real applications, the performance demonstrated by DDR3 standard modules is sufficient. Moreover, operating at the same frequencies, they even have a slight advantage due to the use of lower delays.

At least some benefit from DDR4 strips appears only when it comes to frequencies above 3000 MHz. After all, such values ​​are, as a rule, already unattainable for DDR3 standard kits, even when overclocked. True, whether those few extra percent of performance (in most games there will be no increase at all) are worth the overpayment is still a very big question.

AndSea Sonic Electronics for the equipment provided for the test bench.

Article read 203656 times

Subscribe to our channels

The evolution of technology is rapidly moving forward, giving way to more progressive, miniature and less resource-intensive standards in the production of processors, SSDs and RAM. Prices for previous product lines are rapidly falling, since they are no longer able to satisfy the ever-growing appetites of the user environment.

In the second half of 2014, a line of DDR4 RAM modules went into mass production. It took about two years until the new technology gained enough popularity and prices dropped, and now these chips have become available for purchase at the optimal price and in the optimal configuration. In connection with this important event, we decided to prepare for you a review of the new RAM standard and tell you what it is DDR4 RAM, how it differs from previous generations of RAM and how it stands out from its predecessors.

First, a few words about what RAM is in general. Let's imagine for a second that you are a middle manager in a company, and you have a department staff of several people under your command. Your company has a corporate portal where all internal company news is published. You, like everyone else, publish new tasks and requirements for your subordinates on this portal, and do this regularly, every morning, and old tasks are deleted so that there is no confusion from a pile-up of tasks. Every morning, your colleagues open the corresponding page in the browser and get acquainted with their tasks for the next day, while the requirements for the previous day have already been deleted. RAM works in exactly the same way. Essentially, this is a kind of information stack where service work data is written operating system. Every time you turn off your computer, the contents of RAM are cleared and refilled as new applications are launched. The amount of RAM can vary from approximately 1-2 GB to 16-32 GB for modern gaming systems that require a large amount of system resources. There were times when the amount of RAM was just a few MB, but that’s history.

The first platform on which it became possible installation DDR4 chips became the Intel Haswell-E line and, accordingly, the X99 Express platform, released in the third quarter of 2014. Based on it, a new flagship 8-core Core processor i7-5960X, and the first motherboard, which supports it, is ASUS X99-DELUXE. It is certainly worth noting that the main feature of this technology is support for the new RAM standard - DDR4.

Now a little reference to historical facts. In fact, the development of DDR4 was started back in 2005 by the JEDEC association, but the first devices based on it went on sale only in the spring of 2014. JEDEC engineers were tasked with achieving greater levels of power and stability compared to DDR3. Moreover, the goal was to increase the energy efficiency of the next standard. However, we hear such promises in literally every announcement. How much progress have engineers actually achieved?

Like earlier chip models, DDR4 managed to adopt 2n-prefetch technology (JEDEC calls it 8n-Prefetch in their developments). Any new memory chip can accommodate two or four discrete groups of banks.

To look at real example module, let's take a closer look at the DDR4 chip with a capacity of 8 gigabytes, equipped with a data bus with a 4-bit size. This board accommodates 4 groups of banks with 4 banks in an individual group. Each bank contains 131072 lines with a capacity of 512 bytes each. To have something to compare with, let's take a closer look at the corresponding DDR3 module. Such a chip contains only 8 autonomous banks. Each bank contains 65536 lines, and each line contains 2048 bytes of memory. As you may have noticed, the length of each line of a DDR4 module is four times shorter than the width of a DDR3 line. This means that DDR4 RAM performs memory bank revisions much faster than DDR3. Moreover, the memory banks themselves switch much faster. Here it should be noted that for each individual set of banks, a choice of various operations is provided (restore, extract, write or activate), which makes it possible to increase the level of aperture and memory efficiency.

Performance

A significant innovation in the DDR4 standard is the use of an interface that uses a topology called “point-to-point”, when DDR3 uses the Multii-Drop bus. Why is this necessary? The internal structure of the Multi-Drop bus implies the operation of only a pair of channels connecting the modules with the RAM controller. When four DIMM ports are enabled at once, the controller communicates with each pair of RAM cards using only one single channel. This state of affairs has the most negative impact on the efficiency of the RAM subsystem.

The bus design using a point-to-point aperture provides a discrete channel for an individual DIMM socket, meaning each individual module will be most directly connected to the controller without separating this channel with no one else. Similar innovative solution we could already observe during the transition of video cards from the PCI standard to PCI Express. Of course, the presented approach also has its own shortcomings. So, for example, 4-channel systems will be limited to four DIMM slots, and 2-channel systems will be limited to two. However, if we take into account the more significant capacity of DDR4 modules, this will in no way limit users. We will talk about this in more detail later.

Each DDR4 RAM module with a DIMM connector has 288 pins. The number of pins was increased in order to make it possible to address the largest possible amount of RAM. The largest volume of one RAM module is 128 GB (here we mean the use of crystals with a capacity of 8 GB and QPD technology, the purpose of which is to place four chips in a single package). It is also quite likely that 16 GB crystals with a larger capacity will be used, as well as more capacious packaging (up to 8 crystals in a single case). Under the indicated conditions, the capacity of one RAM module can be equal to 512 GB.

By the way, not only the capacity of RAM modules will be increased, but also their frequency. Within the DDR4 standard, the actual frequency can be 2133 MHz.

Energy efficiency

In order to reduce power consumption and heat generation, the DDR4 standard implies another reduction in the active voltage. This time to 1.2 V. In addition to this, the voltage in the chip itself was, in turn, increased, and this made it possible to guarantee faster access and, under similar conditions, minimize leakage current. Judging by the theoretical statements, the total energy consumption of DDR4 will be 30% lower than that of DDR3. Manufacturing companies will most likely use the resulting reserve to increase the frequency of RAM.

Reliability

The remaining changes relate primarily to the reliability of the devices. For example, DDR4 RAM chips are capable of independently detecting, identifying and fixing errors that relate to command and address parity management. In addition, the DDR4 standard supports a connection check operation, due to which the main controller has the right to identify errors without using the DRAM initialization chains. In addition, the memory register turned out to be polished. From now on, it is possible to configure it in such a way that commands that contain parity errors are blocked. The register in the previous standard, DDR3, did not have a similar function, and commands combining parity errors occasionally made their way to the RAM chips, which was one of the first causes of PC malfunctions. In addition to the previously listed features, the new DDR4 memory includes a number of auxiliary options that are aimed at improving the reliability of the memory subsystem. One of them is checking the check amounts before writing to memory.

Today, choosing DDR4 RAM in any case becomes a win-win option. The chips have already become widespread enough to make plans to purchase them. This is an excellent foundation for computer performance for the future, and given the constant decline in prices for small-volume modules, such chips are becoming a tasty morsel. For DDR4 chips, the price varies from 2,400 rubles for one low-power module of 8 GB with a frequency of 2133 MHz to 5,900 rubles for a set of two chips of 8 GB each with a frequency of 2666 MHz. It is important to note that it is better to purchase two low-power modules than one high-performance module, since a pair of modules of the same frequency with similar characteristics operate in parallel mode, which adds another 10-15% to overall speed PC operation.

This concludes the review of the innovations that DDR4 RAM has brought us. Having studied many descriptions and technical characteristics new standard, in theory everything looks quite promising. In addition to basic improvements (more high frequencies And low voltage), the technology began to support a new bus and a number of innovations designed to increase the reliability of RAM use. The last ability of those mentioned will be especially useful in the field of the server segment, which is already a huge “plus” for performing corporate tasks.

The JEDEC Solid State Technology Association, formerly known as the Electron Devices Engineering Council (JEDEC), is an independent engineering organization, semiconductor trade and standards body.
For more than 50 years, JEDEC has been a global leader in the development of open standards and publications for the microelectronics industry.

The standardizing organization JEDEC Solid State Technology Association has presented the official final version of the specification for the Synchronous DDR4 (Double Data Rate 4) RAM standard.

Its introduction is to ensure a new level of RAM performance, its reliability and reduction in energy consumption.

DDR4 memory includes a number of modern advances that will allow the new type of memory to become widespread in computer devices- from household appliances to servers and even more powerful computer systems.

The performance level per slot in DDR4 is set at 1.6 billion transfers per second, with the possibility of reaching a maximum level of 3.2 billion/s in the future.
The minimum operating frequency of DDR4 memory is 2133 MHz to 4266 MHz, which is 1000 MHz more than its predecessor (1333 MHz and 1666 MHz in the previous generation standard).

For 2133 MHz memory (the lowest frequency for DDR4 memory), the maximum bandwidth is 2133 x 8 = 17,064 MB/s.
For memory running at 4266 MHz (the highest frequency specified in the standard), the maximum throughput is 4266 x 8 = 34,128 MB/s.

The operating voltage is reduced: 1.1 V - 1.2 V versus 1.5 V in DDR3.
The proposed technical process is 32 and 36 nm.

The DDR4 architecture allows 8 bits of data per clock prefetch (8n prefetch) with two or four selectable groups of memory blocks.
This allows devices to perform independent activation, reading, writing and updating operations through separate memory blocks.

All of the above features, as well as a number of smaller changes and innovations, have significantly increased the efficiency of DDR4 memory.

A DDR4 module has 284 pins, while standard DDR3 modules only have 240 pins.
The SO-DIMM version will feature 256 pins, while DDR3 SO-DIMMs only have 204 pins.

In the DDR4 specifications, for the first time, a description of working with memory in multi-chip packaging appeared.
The standard allows a column (stack) of eight crystals.
Moreover, all crystals are “hung” on common signal lines.
This was done not because it is better this way (although it does simplify actions to expand the memory space), but for the reasons that, in general, the ideology of DDR4 memory is the connection of modules with controllers in a point-to-point manner.

There will be many channels, not two or four, so each of them needs to provide the highest possible performance without overloading the exchange mechanisms.
In the same vein, we must consider the possibility of independent simultaneous operation of two or four memory banks.
For each group of banks, all basic operations such as read, write and regeneration are architecturally allowed simultaneously.

According to iSuppli's forecast, by 2014 the level of penetration of the DDR4 memory market will be 12%, by 2015 - 56%.
However, manufacturers may rush to implement the new standard, prompted by the desire to raise prices for their products, which are currently at an extremely low level.

Micron, for example, announced back in May the development of the first full-featured module and plans to begin mass production at the end of this year.
Samsung has already demonstrated the 284-pin PC4-17000 memory (2133 MHz).
All that remains is to wait for their support from Intel and AMD.

Intel plans to begin DDR4 support in early 2014 in high-end 4-socket server systems on Haswell-EX processors, ordinary users will probably have to wait until 2015, since neither the 22 nm Haswell processors nor the subsequent 14 nm Broadwell processors support DDR4.

The DDR4 standard is just one of the first steps towards widespread adoption of next-generation memory.

Applications for DDR4 memory include servers, laptops, desktop PCs and consumer electronics products.
First, DDR4 will appear in server systems, and after that mass production of such memory for consumer computers will begin.

NVIDIA GeForce Experience updated to version 3.20.2

On December 23, 2019, NVIDIA updated the NVIDIA GeForce Experience (GFE) application for Windows to version 3.20.2.
The update fixes the dangerous vulnerability CVE-2019-5702.

Perhaps Microsoft will make life easier Windows users 10

According to insider WalkingCat, Microsoft plans to radically change the update scheme for its operating system. Windows systems 10.