What does core 2 duo mean? Processors
Core 2 Duo knocks out Athlon 64: game over?
The Intel processor line is based on a completely updated micro-architecture. Technical details new processor with Conroe core were announced back in March 2006, and first tests proved that Intel is not joking: Core 2 Duo should become the undisputed leader in performance and in terms of performance per watt. Well, it's time to separate the facts from the rumors.
Intel is not just talking about changes in the new micro-architecture of processors, but about a radical update. The company's engineers took some elements of the current Pentium D NetBurst micro-architecture and added to it the ingredients that made the Pentium M and Core Duo mobile processors so popular in the market, as a result of which a new micro-architecture was born Core 2. A key goal was to achieve the ideal balance between performance and power consumption. In principle, this goal is a direct result of the good performance-per-watt ratio of AMD processors, as well as criticism of Intel platforms for excessively high power consumption and cooling requirements.
Computer industry specialists were hardly surprised by the fact that the processors outperformed the Athlon 64. Let's not forget that the Core 2 Duo is a completely new and modern processor, and the Athlon 64 X2 architecture has been on the market for a long time. After two years of the Athlon 64's dominance, Intel made every effort to release a new superior product that could crush its competitor.
Well, sit back and put sharp objects away from you. Intel has become the new leader in performance. Re-describe technical and architectural details of the kernel Core 2 Duo "Conroe" we will not, but those who require them can visit our article with spring IDF. This time we will carefully consider the test results, conduct an analysis and draw conclusions. Let's see what impact it can have on AMD.
Core 2 Duo processor versions
On July 27, four models for the mass market and one high-end processor will be released. The leader in performance will be the Core 2 Extreme X6800 (be prepared to part with a lot of money if you want to buy this one), and the main striking force will be the models from E6300 to E6700.
| Model Core 2 Duo | Clock frequency (MHz) | Factor | FSB frequency (MHz) | L2 cache (MB) |
| Core 2 Extreme X6800 | 2933 | x11 | 266 (FSB1066 QDR) | 4 |
| Core 2 Duo E6700 | 2666 | X10 | 266 MHz (FSB1066 QDR) | 4 |
| Core 2 Duo E6600 | 2400 | X9 | 266 (FSB1066 QDR) | 4 |
| Core 2 Duo E6400 | 2133 | X8 | 266 (FSB1066 QDR) | 2 |
| Core 2 Duo E6300 | 1866 | X7 | 266 (FSB1066 QDR) | 2 |
All Core 2 Duo processors operate at a Front Side Bus (FSB) clock speed of 266 MHz, while most Pentium 4 and Pentium D models use a 200 MHz bus. Since quadruple the amount of information (QDR) is transmitted per clock cycle, we get a pleasant FSB1066 frequency with a throughput of 8.5 GB/s. With the exception of entry-level processors, all models are equipped with 4 MB of L2 cache, which is used by both processor cores. All processors support Intel 64-bit extensions (EM64T), multimedia instructions (SSE2 and SSE3), virtualization technology (VT), and execution disable bit (XD). In addition to these features, all models support the latest energy management technologies such as Thermal Monitor 2 (TM2), Enhanced Halt State (C1E) and Enhanced SpeedStep (EIST).
Core 2 Extreme X6800
The Extreme Edition processor is the only model that allows you to change the multiplier. Therefore, it is easy to overclock.
Core 2 Duo line
Core 2 Duo processors operate at frequencies from 1.86 to 2.66 GHz.
|
|||
|
| |||
And in order to not confirm the fears of numerous skeptics that with such an organization the cores can be “pushed by their elbows,” the cache memory size has been increased to an implausible 4 MB.
In addition, Core 2 Duo features the following technologies:
- Intel Wide Dynamic Execution Technology– Improves processor performance and efficiency by allowing each core to execute up to four instructions per clock using an efficient 14-stage pipeline.
- Intel Smart Memory Access Technology– Improves system performance by reducing memory access latency, thereby optimizing the use of available bandwidth so that the processor receives data when it is needed.
- Technology Intel Advanced Smart Cache– Shared Level 2 cache reduces power consumption by minimizing the amount of “traffic” in the memory subsystem, and improves system performance by providing one core with access to the entire cache when the other core is idle.
- Intel Advanced Digital Media Boost Technology– Doubles the speed of execution of commands often used in multimedia and graphics applications.
- Intel 64 Technology– provides support for 64-bit computing, giving, for example, the processor access to more memory.
You shouldn’t think that the number 2 in the name of the new processor is just a marketing ploy - the new processors actually make a lot of improvements compared to the progenitor Core Duo. The most important thing here is the following: increasing the speed of instruction execution, optimizing memory management, introducing support for 64-bit computing and, finally, a new set of SSE4 instructions.
The result is greater efficiency even at the same clock frequency. And considering that desktop processors are not faced with the task of ensuring minimal power consumption and, therefore, can use higher frequencies than those at which mobile processors operate, it is easy to guess that Core 2 on the Conroe core is noticeably superior in performance to Core on the Yonah core.
By the way, about energy consumption. This aspect of the “personal life” of the hero of our review is also of considerable interest, because Intel engineers paid perhaps no less attention to it than to ensuring high performance. Let's note the most significant points.
- Using 65 nm process technology. Of course, this is not new for Intel processors, but it distinguishes Core 2 from competing AMD Athlons.
- Support for Intel Enhanced SpeedStep technology - dynamically changing the processor clock frequency depending on the current needs for computing power.
- Ultra Fine Grained Power Control technology – the ability to turn off those processor units that are currently not in use. You can imagine how much energy this function saves under relatively light loads - office work or watching DVD movies, for example.
- Reducing the bus width. Again, in “light” modes, the lion’s share of the bus bandwidth is not used, so their bit capacity can be reduced without compromising current performance needs.
The result is the coolest dual-core processor found in desktop computers.
Testing new and old models using a new version of the test methodology
3D visualization
As expected, there is no increase from increasing the number of cores to more than two, but the clock speed and processor architecture matter. Well, cache memory too, but its “lack” can be compensated for by a higher frequency - the E7400 catches up with the E8200, while the E7600 overtakes it. In general, there is nothing surprising in the fact that Intel abandoned the expensive E8200 as soon as the same level of performance was obtained from cheaper processors with a higher clock frequency. As for the rest, we see that even for working with professional 3D modeling packages, inexpensive processors are quite sufficient. Of course, in the case when this particular computer is used exclusively for its creative component, and the final rendering is carried out on a dedicated render computer or even an entire render farm.
Rendering 3D scenes
Because here the difference is already striking - no dual-core processor is capable of competing with high-performance triple-core or even low-end quad-core devices. The ratio of the results is such that in order to catch up with at least the Q8200, dual-core processors would have to master a frequency of 4 GHz, with the current maximum of 3.33 GHz (note that a processor of the Core 2 Duo family can be overclocked to such frequencies independently is not accepted - Core 2 Quad is also quite suitable for overclocking, and the Phenom II X3 720 is not at all - even the multiplier is unlocked for increase :)). As, in general, it was expected: for these tasks no reasonable number of cores is “extra”: an increase in rendering is observed even in cases when we “feed” eight physical cores to the task, executing 16 threads simultaneously (i.e. ., for example, a system on two Xeons). And in desktop systems the saturation point is even further away. The increase is not linear, and the clock frequency has an effect (which is why, for example, the Q8200 and X3 720 showed almost the same result), but the general picture is obvious.
Scientific and engineering calculations
In this group of applications it is also obvious, but it’s not in favor of multi-core crystals: it’s better to have a couple of cores, but operating at a higher clock frequency. In addition, it is clearly noticeable that 2M cache memory is clearly not enough, which greatly spoils the results of the Pentium or Core 2 Quad Q8000, not to mention the Athlon II, where this volume is equally divided between the cores and cannot be used to exchange information between them, and Now more than 3M - it seems that there is no need. However, again, the differences between the processors are so small that it is irrational to make a choice based on this group of applications - here, perhaps, even Celeron would be quite appropriate. Although, it would seem, this is a “serious” group of programs, and not some kind of “home multimedia”.
Raster graphics
Here we generally have some kind of increase from increasing the number of cores, but we cannot say that it is significant. Result? The Pentium E6300 demonstrated the same performance as the Core 2 Quad Q8200, and the Core 2 Duo E7600 was on par with the Core 2 Quad Q9300. Yes, of course, dual-core processors operate at a higher clock frequency than quad-core processors comparable in overall performance, but the difference is not so great as to consider the latter more adequate solutions for these tasks. In short, even average models of dual-core processors are quite sufficient for working with raster graphics, and almost the only factor that can prevent you from choosing them is the dominance of quad-core crystals among solutions for maximum performance. Yes, all this is very familiar - at one time it was in this way that both Intel and AMD “squeezed” single-core processors out of the market. Now, however, this is being done in a softer form - in particular, older Core 2 Duo models are still ahead of their “composite” relatives in frequency, sometimes by a lot, which allows them to “save face”, but the trend is more than noticeable. Even on familiar and long-established platforms, not to mention promising ones - in particular, three quad-core processors are already ready for LGA1156, while dual-core processors will have to wait until next year.
Data compression
More than two cores are not necessary, a lot of cache memory is necessary, so the clear winner was the Core 2 Duo E8200. But a comparison of the results of the E7400 and E7600 forces us to speak not quite decently about the transition to DDR3 for LGA775. As we saw last time, even switching from DDR2 1066 to DDR3 1333 leads to a decrease in performance in this group of tests, but for processors with FSB 1066, the use of DDR3 generally gives a disastrous result: such a memory frequency is achievable for DDR2, the bandwidth obtained is accordingly, the same, but the delay is much less. Why don't we see such a fiasco with Pentium? The E5300 generally has an FSB 800 and was tested with DDR2 800. So, purely objectively, the E6300 is capable of “digesting” faster memory, but in this case, as they say, all the steam went to waste - to compensate for the harmful effect of DDR3. As a result, we got bash for bash (the existing increase in results is observed due to the higher clock frequency), well, thanks for that.
Compilation (VC++)
The number of cores, their frequency and, to some extent, cache memory capacity are the components of success, and when at least two of these points are present at the same time, it’s generally good: this is not the first time we’ve seen how a fairly high-frequency triple-core AMD processor is capable of equal compete not only with the Core 2 Duo (which is due to its rank), but also invades the habitat of junior quad-core devices from both companies. Dual-core processors are much slower. And any, but especially Pentium :) At the same time, the “giant” amount of cache memory allows the Core 2 Duo E8200 to play as much as 400 MHz of the frequency that separates it from the older representative of the E7000 line.
Java
Here the results are even more “canonically correct”, since triple-core processors are not trying to compete with quad-core processors. However, this doesn’t make things any easier for dual-core ones. And if we also take into account the smaller requirement of the Java virtual machine for cache memory capacity, everything is completely deplorable for their older families.
Audio encoding
And one more “finishing blow”, but not the last. Something else is more interesting here - as we have seen more than once, in this subtest AMD processors are traditionally worse than otherwise similar solutions from Intel. However, the “secret trick” in the form of the third core allows them to compete almost on an equal footing in the middle class. It’s a pity, of course, that we couldn’t get a Core 2 Duo E8600 in order to slightly shift the picture towards a more or less usual one :) However, it is obvious that the best thing this expensive processor could do is to slightly overtake the X3 720, but not at all come close to a level similar to the “Phenom” at a price of the Core 2 Quad Q8200.
But you can look at the current situation from a completely different perspective. The slowest modern processor we have is the Athlon II X2 250. It has the worst result when encoding OGG Vorbis. So, it is “only” 32, which means that an hour-long album will be compressed by this processor... in less than two minutes. Those. In terms of absolute results, it's hard to think of a situation in which audio encoding speed would make a real difference. About ten years ago, you had to copy an audio disc to your hard drive in the form of files for half an hour, and then leave the computer for several hours so that it could compress it into MP3. Today, the slowest operation will almost always be getting the source code, but you can compress it quickly. For example, in parallel with receiving or uploading the final files to a portable player.
Video encoding
But here everything goes somewhat beyond the everyday assumptions that for video encoding you need to have a multi-core processor. It turned out this way due to the fact that two of the five codecs (at least the versions we use) are relatively cool about the number of cores of more than two, one is completely ready to be content with one core, and even of the remaining two “the degree of utilization” The third and fourth cores are not the same. Mainconcept, when switching from C2D E7600 to C2Q Q8200, works 20 percent faster (that is, the doubling of cores is quite noticeably compensated by the difference in clock frequencies), but x264 shows “as it should” - under the same conditions the increase is more than one and a half times! If everyone were like this, we would get a picture like in the previous group, but due to the influence of the “burden of years”, not everything is smooth. However, again, the difference in one of the codecs is such (in two more, when comparing the same processors, we get an almost equivalent “exchange” of cores per frequency), that it becomes obvious that even “in the overall standings” the best of serial dual-core processors can no more than getting even closer to the younger quad-core processors, but not overtaking them. Moreover, to the greatest extent we owe this to the most “heavy” tasks, which it makes sense to speed up by all means and means :)
Gaming 3D
Until recently, it was believed that games were exactly the area where high-frequency dual-core processors with a large amount of cache memory and a fast system bus (all these requirements are best met by the E8000 family) are capable of easily not only fighting, but also defeat the younger “cut-off” quads with a crushing score. So - this is not entirely true. Yes, “on average” (as in the case of video encoding) Core 2 Duo or Athlon II X2 processors look good, but as soon as we turn to detailed results for individual games, the optimism begins to fade. Simply because the frame rate in games, unlike, for example, the rendering time of a three-dimensional scene in a modeling package, is much less amenable to conventional comparison using the rules of arithmetic. Games are interactive applications, therefore, they always have a certain lower limit of comfort, which cannot be crossed. At the same time, when coding or rendering, often a smaller value is just a smaller value. For example, if you encode films at night, in small quantities and from time to time, it makes no difference whether the work is completed in three hours or five: you will see the result only in the morning, and it will be impossible to “load” the computer with work, due to the lack of this the most extra work. Not so in games, where “punching” the comfortable limit simply means that it is essentially impossible to play a given game with given settings on a given computer. So, for example, with the settings we selected for testing, you should not try to play GTA IV on a Pentium or Athlon II :) An average FPS of around 30 or less with the corresponding minimum is not at all what we would like to see. The picture is similar in FarCry2, although less catastrophic. Moreover, replacing the processor with a Core 2 Duo E7600 still does not allow us to reach the 35 FPS limit in these two games. For comparison: Core 2 Quad Q8200 - approximately 49 and 39 FPS, Phenom II X3 720 - 52 and 39, respectively. The results of the Core 2 Duo E8200 are pleasing to the eye, especially considering that this is a junior (and already discontinued) processor in the E8000 line, and the older ones will be even faster, but do not forget that these devices are simply more expensive. So what to choose within the same limited budget for modern games is, it seems to us, a rhetorical question. For not the most modern ones, even more so - a Pentium, or even a Celeron, is usually enough.
Total
Above, we deliberately did not comment on the results of the “oldies” included in today’s testing - everything is already clear with them :) Yes, the Core 2 Duo E6600 was once the object of desire for many users, but now it can only compete with the Pentium. But, by the way, it is capable, despite the fact that three years have passed since its release :) And, obviously, there is no big point in replacing it today with one of the modern dual-core processors. If you really want to increase productivity (i.e. there really isn’t enough of it), it would be wise not to overdo it with savings.
Moreover, at current prices, dual-core processors, even when buying a system from scratch (that is, when there is no computer at all or there is one, but it is too outdated - for example, on a Pentium 4 or a similar processor) will not always be a justified choice. Of course, very often it doesn’t make sense to “reach out” for four cores, but at approximately the same (or even lower) price, this is not the worst option. At least then it won’t be “excruciatingly painful” when trying to launch GTA IV or some other new product from game makers. Yes, of course, such applications are usually obtained not at all because programmers use multithreading so well - they are often the result of poor optimization, but, honestly, what difference does it make? As they say, no matter how sick you are, as long as you die. The question “why is it so slow” is not of interest to all users - most simply want to solve their problems without bothering their heads with looking for the culprits (especially since, once found, the latter will still not return your money for an unsuccessful purchase :)).
Although all this is true if we talk specifically about purchasing. From the point of view of dry theory, we are simply once again faced with the fact that the optimization of applications for multiple computing cores is still far from being done in the best way. That is why the performance increase when increasing the number of cores to three or four does not always give a noticeable effect, and sometimes does not give it at all. Or it gives one that can be compensated by simply increasing the clock frequency, which, obviously, is easier for processors with fewer cores. And from this point of view, processors from the Core 2 Duo E8000 line could be the best choice for an ordinary home computer. They could... if, quite objectively, they weren’t too expensive :) 6M full-speed cache memory is very great from a performance point of view, but disgusting from a cost point of view. So much so that two crystals with 3M on each may well turn out to be cheaper. And, at a lower clock speed, it is still faster. So if earlier the main recommendation for choosing sounded like this: “Buy a quad-core processor if you know why you need it, buy a dual-core processor in all other cases,” now everything has changed places in it :) “Buy a dual-core processor if you are absolutely sure that you need the programs will cost you, buy a quad-core in all other cases.” Well, or you can limit yourself to a three-core one: as we can see, the Phenom II X3 720 looks very good given the limitations of today's software - it is not as reduced in clock speed and cache capacity as the Core 2 Quad Q8200, which allows it to sometimes outperform the latter even in multi-threaded applications .
Of course, all these “torments of choice” are true only for one (albeit very popular) price segment: $130-200. Above it, everything is quite clear: the domain of medium and older quad-core processors. Until recently, Core 2 Duo E8500/E8600 also invaded there, but it is obvious that next to the Core i5 750, for example, they have absolutely nothing to catch there. So, perhaps, this family has as little time left to live as the Core 2 Quad Q9x50 based on it. And below $130, there are no three-core processors yet (unless there are some old models, such as the Phenom X3 in stock) - the entire budget sector is completely occupied by dual-core models with the occasional outdated single-core one. However, there, most often, completely different questions have to be resolved - not “Which processor will be faster?”, but “How much more can I try to save painlessly?” It can be seen that if this desire is limited at least by Pentium, the result will be quite good - comparable to what buyers of processors in the middle and even upper (without fanaticism, such as extreme series) price ranges received a couple of years ago. But we’ll check what we can expect from the updated Celeron a little later, fortunately for now there are still a few “blank spots” left for us in the LGA775 processor family.
Product release date.
Lithography
Lithography indicates the semiconductor technology used to produce integrated chipsets and the report is shown in nanometer (nm), which indicates the size of the features built into the semiconductor.
Terms of Use
Conditions of use are the environmental factors and operating characteristics appropriate to the intended use of the system.
For terms of use specific to a specific SKU, please see the PRQ report.
Please refer to the Intel UC (non-disclosure agreement site)* for current terms of use information.
Number of Cores
Core count is a hardware term that describes the number of independent central processing units in a single computing component (chip).
Base processor clock speed
The base frequency of the processor is the speed at which the processor transistors open/close. The base frequency of the processor is the operating point where the design power (TDP) is set. Frequency is measured in gigahertz (GHz), or billions of cycles per second.
Cache memory
The processor cache is an area of high-speed memory located in the processor. Intel® Smart Cache refers to an architecture that allows all cores to dynamically share last-level cache access.
System bus frequency
A bus is a subsystem that transfers data between computer components or between computers. An example is the system bus (FSB), through which data is exchanged between the processor and the memory controller unit; DMI interface, which is a point-to-point connection between the integrated Intel memory controller and the Intel I/O controller assembly on the system board; and a Quick Path Interconnect (QPI) connecting the processor and integrated memory controller.
System bus parity
System bus parity provides the ability to check for errors in data sent to the FSB (system bus).
Design power
Thermal design power (TDP) indicates the average performance in watts when the processor's power is dissipated (running at base frequency with all cores engaged) under a challenging workload as defined by Intel. Read the requirements for thermoregulation systems presented in the technical description.
VID voltage range
The VID voltage range is an indicator of the minimum and maximum voltage values at which the processor should operate. The processor communicates the VID with the VRM (Voltage Regulator Module), which in turn ensures the correct voltage level for the processor.
Available options for embedded systems
Available options for embedded systems indicate products that provide extended purchasing availability for intelligent systems and embedded solutions. Product specifications and conditions of use are provided in the Production Release Qualification (PRQ) report. Contact your Intel representative for details.
Supported Connectors
A socket is a component that provides mechanical and electrical connections between the processor and the motherboard.
T CASE
The critical temperature is the maximum temperature allowed within the processor's integrated heat spreader (IHS).
Intel® Turbo Boost Technology‡
Intel® Turbo Boost Technology dynamically increases the processor frequency to the required level, using the difference between the nominal and maximum temperature and power parameters, allowing you to increase power efficiency or overclock the processor when necessary.
Intel® Hyper-Threading Technology‡
Intel® Hyper-Threading Technology (Intel® HT Technology) provides two processing threads for each physical core. Multithreaded applications can perform more tasks in parallel, making work much faster.
Intel® Virtualization Technology (VT-x)‡
Intel® Virtualization Technology for Directed I/O (VT-x) allows a single hardware platform to function as multiple “virtual” platforms. The technology improves management capabilities, reducing downtime and maintaining productivity by dedicating separate partitions for computing operations.
Intel® Virtualization Technology for Directed I/O (VT-d)‡
Intel® Virtualization Technology for Directed I/O complements virtualization support in IA-32 architecture-based processors (VT-x) and Itanium® processors (VT-i) with I/O device virtualization capabilities. Intel® Virtualization Technology for Directed I/O helps users increase system security, reliability, and I/O device performance in virtual environments.
Intel® 64‡ Architecture
Intel® 64 architecture, when combined with the right software, supports 64-bit applications on servers, workstations, desktops, and laptops.¹ Intel® 64 architecture delivers performance improvements that enable computing systems to utilize more than 4 GB of virtual and physical memory .
Command set
The instruction set contains the basic commands and instructions that the microprocessor understands and can execute. The value shown indicates which Intel instruction set the processor is compatible with.
Idle states
Idle state (or C-state) mode is used to save power when the processor is idle. C0 means operating state, that is, the CPU is currently performing useful work. C1 is the first idle state, C2 is the second idle state, etc. The higher the numerical indicator of the C-state, the more energy saving actions the program performs.
Advanced Intel SpeedStep® Technology
Enhanced Intel SpeedStep® technology delivers high performance while meeting the power requirements of mobile systems. Standard Intel SpeedStep® technology allows you to switch voltage and frequency levels depending on the load on the processor. Enhanced Intel SpeedStep® technology is built on the same architecture and uses design strategies such as voltage and frequency change separation, and clock distribution and recovery.
Intel® Demand Based Switching Technology
Intel® Demand Based Switching is a power management technology that keeps the microprocessor's application voltage and clock speed at the minimum required until increased processing power is required. This technology was introduced to the server market under the name Intel SpeedStep®.
Thermal control technologies
Thermal management technologies protect the processor chassis and system from failure due to overheating with multiple thermal management features. An on-chip Digital Thermal Sensor (DTS) senses core temperature, and thermal management features reduce processor chassis power consumption when necessary, thereby reducing temperatures to ensure operation within normal operating specifications.
New Intel® AES Commands
Intel® AES-NI (Intel® AES New Instructions) commands are a set of commands that enable you to quickly and securely encrypt and decrypt data. AES-NI commands can be used to solve a wide range of cryptographic problems, such as applications that provide bulk encryption, decryption, authentication, random number generation, and authenticated encryption.
The execution cancel bit is a hardware security feature that can reduce vulnerability to viruses and malicious code, and prevent malware from executing and spreading on a server or network.
This article will review an excellent CPU from 8 years ago - Intel Specifications This chip can no longer be called relevant today, but it still looks great as the basis for system units for office or budget purposes. It is in this context that its specifications will be discussed.
Processor niche
At the time of the start of sales, this processor belonged to middle-class solutions. Most of the existing software at that time could function quite successfully on it. Of course, some games on this hardware did not run at maximum settings, but they still ran without fail. But now the situation has changed. Some of the newest and most demanding toys check for the presence of 4 cores, but this chip has only 2. Therefore, such software will not work on it. As a result, such chips belong to entry-class semiconductor solutions.
Delivery options
The Core 2 DUO E7400 was supplied in two possible configuration options. Description on the manufacturer's official websiteindicateson BOX andTRAIL.The second of them was more modest and included the following:
- The chip itself.
- Branded sticker with the logo of the CPU model.
- Warranty card from the manufacturer.
- A quick guide to using the semiconductor product.
The first option was more expanded and, in addition to everything previously listed,included the following:
- Branded cooler.
- Thermal paste.
Processor socket. General CPU Specifications
The main and most common processor socket at that time was supposed to have an Intel Core 2 DUO E7400 installed.
Characteristics indicate supportLGA775.Today, all processors of this socket are obsolete and discontinued. But there are still stocks of it, and therefore it is still possible to buy such semiconductor products.This processor has only 2 computing modules. It also does not have support for NT technology and in this case it is impossible to achieve a second increase in the number of logical threads at the software level.
Production technology
In 2008, the Intel Core 2 DUO E7400 was produced using the most advanced technical process. Characteristics This silicon crystal indicates a tolerance standard of 45 nm. Nowadays, the most advanced CPUs are already manufactured at 14 nm. Taking into account the difference of 3 times and taking into account the time interval of 8 years, the difference is not that bigbetween the hero of this review and the latest generation budget central processors.
Cash
There are only 2 cache levels in the Kor 2 DUO E7400. In 2008, it was still impossible to find a 3-level cache memory among chips for ordinary personal computers. Therefore, in this regard, this chip did not stand out as anything special. Now this is one of the reasons why this CPU cannot compete in speed with the most affordable processors of the last few generations. The first level had a total size of 64 KB. Moreover, they were divided into 2 equal parts, the size of each of which was 32 KB. The second cache level was common to all CPU computing resources and had a size of 3 MB.
RAM
The Intel Core 2 DUO E7400 processor was designed for use in combination with DDR2 memory. The characteristics of this CPU indicate recommended frequencies of 800 MHz or 1.066 MHz. The RAM controller, unlike current chips, was not part of the CPU semiconductor chip. Therefore, its specific implementation depended on the set of system logic on the motherboard.
Frequency. Overclocking
The clock frequency for this semiconductor solution was set to 2.8 GHz. The multiplier for this CPU is set to 10.5. This value is fixed and it is impossible to overclock this chip by simply changing this parameter. Therefore, the only way to increase the performance of such a PC is to increase the frequency of the system bus on the motherboard. Its value is set to 266.7 MHz. In practice, with a high-quality cooling system, the system bus frequency could be raised to 390 MHz and the chip could reach 4.1 GHz. In percentage terms it is 46%. As a result, it can be noted that this CPU had excellent overclocking potential.
Reviews. Price
At the beginning of sales, the TRAIL configuration option was priced at $110 by the manufacturer of this chip. The more advanced BOX Intel Core 2 DUO E7400 package was priced at $125. Characteristics (reviews owners and specialists confirm this) this CPU is very modest, and it is inferior in performance to even the most budget processors of the latest generation. The key difference here lies in the frequency and cache memory, which currently has a three-level organization.You also need to take into account the fact that this processor was released quite a long time ago, and therefore it is not worth considering it as the basis for a gaming system. It is outdated and suitable only for solving the most simple tasks: playing video or audio recordings, web surfing and office programs. You can also add to this list the current least demanding or even outdated old toys.Something more to squeeze out of this semiconductor CPUwill not work.
Results
For 2008, an excellent processor solution was Intel Core 2 DUO E7400. Characteristics he actually had quite good ones at that time. But nowthis CPU is outdated both morally and physically. Over the past time, it has moved from the niche of middle-class products to the budget segment. As a result, such personal computers can now only solve the most simple tasks.Well, it won’t be possible to use such a computing system for anything more.
