The most significant event in 2005 in the field of microprocessors was the appearance on sale of CPUs with two cores. Moreover, the appearance on sale of dual-core processors happened very quickly, and without much difficulty. The biggest advantage of the new products was that the transition to a dual-core system did not require a platform change. In fact, any user of a modern computer could come to the store and change only one processor without changing motherboard and the rest of the hardware. At the same time, the already installed operating system instantly detected the second core (the second processor appeared in the list of equipment), and no specific settings software was not required (not to mention a complete reinstallation of the OS).
The idea of appearance of such processors lies on the surface. The fact is that CPU manufacturers have almost reached the ceiling of increasing the performance of their products. In particular, AMD ran into a frequency of 2.4 GHz in the mass production of Athlon 64 processors. In fairness, we note that the best specimens are capable of operating at frequencies of 2.6-2.8 GHz, but they are carefully selected and put on sale under the Athlon FX brand (respectively, a model with 2.6GHz is labeled FX-55 and 2.8GHz is labeled FX-57). However, the output of such successful crystals is very small (this can be easily verified by overclocking 5-10 processors). The next jump in clock speed is possible with the transition to a thinner process technology, but this step is planned by AMD only for the end of this year (at best).
Intel has a worse situation: the NetBurst architecture turned out to be uncompetitive in terms of performance (max. frequency 3.8 GHz) and heat dissipation (~150 W). The change of focus and the development of a new architecture should take some time (even with a lot of developments from Intel). Therefore, for Intel, the release of dual-core processors is also a big step forward in terms of performance. In combination with a successful transition to 65 nm process technology, such processors will be able to compete on equal terms with AMD products.
The main initiator in the promotion of dual-core processors was AMD, which first introduced the corresponding Opteron. As for desktop processors, here the initiative was seized by Intel, which announced Intel processors Pentium D and Intel Extreme Edition. And a few days later, the announcement of the Athlon64 X2 processor line took place. manufactured by AMD.
So, we start our review of dual-core processors with Athlon64 X2
AMD Athlon 64 X2 Processors
Initially, AMD announced the release of 4 processor models: 4200+, 4400+, 4600+ and 4800+ with clock speeds of 2.2-2.4 GHz and different L2 cache sizes. The price of processors is within the range from ~430$ to ~840$. As we can see, the general price policy does not look very friendly to the average user. Moreover, the cheapest dual-core Intel processor costs ~$260 (Pentium D 820 model). Therefore, to increase the attractiveness of the Athlon 64 X2, AMD is releasing the X2 3800+ with a clock speed of 2.0 GHz and L2 cache = 2x512Kb. The price for this processor starts at $340.
Since two cores (Toledo and Manchester) are used for the production of Athlon 64 X2 processors, for a better understanding, we will summarize the characteristics of the processors in a table:
| Name | Core stepping | Clock frequency | L2 cache size |
| X2 4800+ | Toledo (E6) | 2400MHz | 2 x 1Mb |
| X2 4600+ | Manchester (E4) | 2400MHz | 2 x 512Kb |
| X2 4400+ | Toledo (E6) | 2200MHz | 2 x 1Mb |
| X2 4200+ | Manchester (E4) | 2200MHz | 2 x 512Kb |
| X2 3800+ | Manchester (E4) | 2000MHz | 2 x 512Kb |
All processors have a cache memory of the first level of 128Kb, a nominal supply voltage (Vcore) of 1.35-1.4V, and the maximum heat dissipation does not exceed 110 watts. All of the above processors have the Socket939 form factor, use the HyperTransport = 1GHz bus (HT multiplier = 5) and are manufactured according to the 90nm process technology using SOI. By the way, it was the use of such a "thin" technical process that made it possible to achieve profitability in the production of dual-core processors. For example, the core of Toledo has an area of 199 square meters. mm., and the number of transistors reaches 233.2 million!
If you look at appearance processor Athlon 64 X2, then it is completely no different from other Socket processors 939 (Athlon 64 and Sempron). Running the CPU-Z utility allows us to obtain the following information:
It is worth noting that the Athlon X2 line of dual-core processors inherited from Athlon64 support for the following technologies: Cool "n" Quiet power saving function, AMD64 instruction set, SSE - SSE3, NX-bit information security function.
Like the Athlon64 processors, the Dual-Core Athlon X2 has a dual-channel DDR memory controller with a maximum bandwidth of 6.4 Gb/s. And if for Athlon64 bandwidth DDR400 was enough, then for a processor with two cores this is a potential bottleneck that negatively affects performance. However, there won't be a serious drop in speed, since multi-core support was taken into account when developing the Athlon64 architecture. In particular, in the Athlon X2 processor, both cores are inside the same die; and the processor has one memory controller and one HyperTransport bus controller.
In any case, the memory bandwidth mismatch will be eliminated after the transition to Socket M2. Let me remind you that this will happen this year and the corresponding processors will have a DDR-II memory controller.
A few words about the compatibility of the new Athlon X2 processors. On all the latest motherboards tested, the top-end X2 4800+ processor worked without any problems. As a rule, these were boards based on nVidia nForce4 (Ultra & SLI) chipsets, as well as a board based on the ATI Xpress 200 CrossFire™ chipset (ECS KA1 MVP Extreme). When I installed this processor on the Epox 9NDA3+ (nVidia nForce3 Ultra) board, the second processor core was not detected by the operating system. And firmware latest version BIOS didn't fix it. But this is a special case, and in general, the statistics of the compatibility of dual-core processors with motherboards are very, very positive.
It would be appropriate to note here that the new dual-core processors do not have any specific requirements for the design of the motherboard power module. Moreover, the maximum heat dissipation of Athlon X2 processors is no higher than that of Athlon FX processors produced according to the 130 nm process technology (ie, slightly above 100W). At the same time, dual-core Intel processors consume almost one and a half times more energy.
Let's say a few words about overclocking.
Of all AMD processors the unlocked multiplier is available only for technical samples and processors of the FX line. And the dual-core Athlon X2, as well as the single-core Athlon 64 / Sempron, have a multiplier locked upwards. And towards the decrease, the multiplier is unlocked, since it is by lowering the multiplier that the Cool "n" Quiet energy saving technology works. And for overclocking the processor, we would like to have an unlocked multiplier in the direction of increase, so that all other components of the system would work in normal mode. But AMD followed in the footsteps of Intel and with a certain moment banned overclocking in this way.
However, no one has yet canceled or banned overclocking by increasing HTT. But at the same time, we will have to choose high-quality memory, or use a down-scale memory frequency divider. In addition, it is necessary to reduce the HT bus multiplier, which, however, does not have any effect on the performance level.
So using air cooling we managed to overclock the Athlon X2 4800+ processor from the stock frequency of 2.4 GHz to 2.7 GHz. At the same time, the supply voltage (Vcore) was increased from 1.4V to 1.55V.
Overclocking statistics show that this instance showed not the worst increase in frequency. However, one cannot count on more, since AMD selects the most "successful" cores for the production of processors with a frequency of 2.6GHz and 2.8GHz.
The search module is not installed.
Single core or dual core?
Viktor Kuts
The most significant recent event in the field of microprocessors has been the widespread availability of CPUs equipped with two computing cores. The transition to a dual-core architecture is due to the fact that traditional methods to increase the productivity of processors have completely exhausted themselves - the process of increasing their clock frequencies has recently stalled.
For example, in Last year before the advent of dual-core processors, Intel was able to increase the frequencies of their CPUs by 400 MHz, and AMD even less - by only 200 MHz. Other performance enhancements, such as increasing bus speed and cache size, have also lost their effectiveness. Thus, the introduction of dual-core processors, which have two processor cores in one chip and share the load, has now turned out to be the most logical step on the complex and thorny path of increasing the performance of modern computers.
What is a dual core processor? In principle, a dual-core processor is an SMP system (Symmetric MultiProcessing - symmetric multiprocessing; a term for a system with several equal processors) and is essentially no different from an ordinary two-processor system consisting of two independent processors. In this way, we get all the benefits of dual-processor systems without the need for complex and very expensive dual-processor motherboards.
Prior to this, Intel has already made an attempt to parallelize the instructions being executed - we are talking about HyperThreading technology, which provides the sharing of resources of one "physical" processor (cache, pipeline, execution units) between two "virtual" processors. The performance gain (in separate, HyperThreading-optimized applications) was about 10-20%. Whereas a full-fledged dual-core processor, which includes two "honest" physical cores, provides an increase in system performance by 80-90% and even more (naturally, with full use of the capabilities of both of its cores).
The main initiator in the promotion of dual-core processors was AMD, which in early 2005 released the first Opteron dual-core server processor. As for desktop processors, the initiative was seized by Intel, which at about the same time announced Intel Pentium D and Intel Extreme Edition processors. True, the announcement of a similar line of Athlon64 X2 processors manufactured by AMD was only a few days late.
Intel Dual Core Processors
The first dual-core Intel Pentium D processors of the 8xx family were based on the Smithfield core, which is nothing more than two Prescott cores combined on a single semiconductor chip. An arbiter is also located there, which monitors the state of the system bus and helps to share access to it between the cores, each of which has its own 1 MB L2 cache. The size of such a crystal, made according to the 90-nm process technology, reached 206 square meters. mm, and the number of transistors is approaching 230 million.
For advanced users and enthusiasts, Intel offers Pentium Extreme Edition processors, which differ from Pentium D in support of HyperThreading technology (and an unlocked multiplier), due to which they are defined by the operating system as four logical processors. All other functions and technologies of both processors are completely identical. Among them are support for the 64-bit EM64T (x86-64) instruction set, EIST (Enhanced Intel SpeedStep), C1E (Enhanced Halt State) and TM2 (Thermal Monitor 2) energy saving technologies, as well as the NX-bit information protection function. Thus, the considerable price difference between the Pentium D and Pentium EE processors is largely artificial.
As for compatibility, Smithfield processors can potentially be installed in any LGA775 motherboard, as long as it meets Intel's power supply requirements.
But the first pancake, as usual, came out lumpy - in many applications (most of which are not optimized for multithreading), dual-core Pentium D processors not only did not outperform single-core Prescott running at the same clock frequency, but sometimes even lost to them. Obviously, the problem lies in the interaction of the cores via the Quad Pumped Bus processor bus (during the development of the Prescott core, it was not planned to scale its performance by increasing the number of cores).
To eliminate the shortcomings of the first generation of dual-core Intel processors, processors based on the 65-nm Presler core (two separate Cedar Mill cores placed on the same substrate), which appeared at the very beginning of this year, were called upon. More "thin" technical process allowed to reduce the area of the cores and their power consumption, as well as increase the clock speeds. Dual-core processors based on the Presler core were named Pentium D with indexes 9xx. If we compare the Pentium D processors of the 800th and 900th series, in addition to a noticeable reduction in power consumption, the new processors received a doubling of the second-level cache (2 MB per core instead of 1 MB) and support for the promising Vanderpool virtualization technology (Intel Virtualization Technology). In addition, the Pentium Extreme Edition 955 processor was released with HyperThreading technology enabled and running at a system bus frequency of 1066 MHz.
Officially, processors based on the Presler core with a bus frequency of 1066 MHz are only compatible with motherboards based on the i965 and i975X series chipsets, while the 800 MHz Pentium D in most cases will work on all motherboards supporting this bus. But, again, the question arises about the power supply of these processors: the thermal package of Pentium EE and Pentium D, with the exception of the younger model, is 130 W, which is almost a third more than that of the Pentium 4. According to Intel itself, stable work dual-core system is possible only when using power supplies with a capacity of at least 400 W.
The most efficient modern Intel dual-core desktop processors are without a doubt Intel Core 2 Duo and Core 2 eXtreme (Conroe core). Their architecture develops basic principles architectures of the P6 family, however, the number of fundamental innovations is so great that it is time to talk about the new, 8th generation of the processor architecture (P8) from Intel. Despite the lower clock frequency, they noticeably outperform the P7 family (NetBurst) processors in terms of performance in the vast majority of applications - primarily due to an increase in the number of operations performed in each clock cycle, as well as by reducing losses due to the large length of the P7 pipeline.
Desktop processors of the Core 2 Duo line are available in several versions:
- E4xxx series - FSB 800 MHz, 2 MB L2 cache common for both cores;
- E6xxx series - FSB 1066 MHz, cache size 2 or 4 MB;
- X6xxx series (eXtreme Edition) - FSB 1066 MHz, cache size 4 MB.
The letter code "E" denotes the power consumption range from 55 to 75 watts, "X" - above 75 watts. Core 2 eXtreme differs from Core 2 Duo only in increased clock speed.
All Conroe processors use the well established Quad Pumped Bus and LGA775 socket. Which, however, does not mean compatibility with old motherboards at all. In addition to supporting 1067 MHz, motherboards for new processors must include new module voltage regulation (VRM 11). These requirements are met mainly by updated versions of motherboards based on Intel chipsets 975 and 965 series, as well as NVIDIA nForce 5xx Intel Edition and ATI Xpress 3200 Intel Edition.
In the next two years, Intel processors of all classes (mobile, desktop and server) will be based on the Intel Core architecture, and the main development will go towards increasing the number of cores on a chip and improving their external interfaces. In particular, for the desktop PC market, this processor will be Kentsfield - the first quad-core Intel processor for the high-performance desktop PC segment.
AMD Dual Core Processors
The AMD Athlon 64 X2 line of dual-core processors uses two cores (Toledo and Manchester) inside a single die, manufactured using a 90-nm process technology using SOI technology. Each of the Athlon 64 X2 cores has its own set of execution units and a dedicated L2 cache, they have a common memory controller and HyperTransport bus controller. The differences between the cores are in the size of the L2 cache: Toledo has a L2 cache of 1 MB per core, while Manchester has half that size (512 KB each). All processors have 128 KB L1 cache, their maximum heat dissipation does not exceed 110 W. The core of Toledo consists of about 233.2 million transistors and has an area of about 199 square meters. mm. The core area of Manchester is noticeably smaller - 147 sq. mm., the number of transistors is 157 million.
Athlon64 X2 dual-core processors inherited from Athlon64 support for Cool`n`Quiet power-saving technology, a set of 64-bit extensions AMD64, SSE - SSE3, NX-bit information protection function.
Unlike dual-core Intel processors that work only with DDR2 memory, Athlon64 X2 can work with both DDR400 (Socket 939) memory, which provides a maximum bandwidth of 6.4 GB / s, and DDR2-800 (Socket AM2), peak throughput is 12.8 GB/s.
On all fairly modern motherboards, Athlon64 X2 processors work without any problems - unlike Intel Pentium D, they do not impose any specific requirements on the design of the motherboard power module.
Until very recently, AMD Athlon64 X2 was considered the most productive among desktop processors, but with the release of Intel Core 2 Duo, the situation has changed radically - the latter have become the undisputed leaders, especially in gaming and multimedia applications. In addition, the new Intel processors have lower power consumption and much more efficient power management mechanisms.
This state of affairs did not suit AMD, and as a response, it announced the release in mid-2007 of a new 4-core processor with an improved microarchitecture, known as the K8L. All its cores will have separate 512 KB L2 caches and one shared cache Level 3, 2 MB in size (in future versions of the processor, the L3 cache may be increased). The promising AMD K8L architecture will be discussed in more detail in one of the next issues of our magazine.
One core or two?
Even a cursory glance at the current state of the desktop processor market indicates that the era of single-core processors is gradually becoming a thing of the past - both of the world's leading manufacturers have switched to producing mainly multi-core processors. However, the software, as it happened more than once before, still lags behind the level of hardware development. Indeed, in order to fully utilize the capabilities of several processor cores, the software must be able to "break" into several parallel threads processed simultaneously. Only with this approach does it become possible to distribute the load across all available computing cores, reducing the computation time more than could be done by increasing the clock frequency. Whereas the vast majority of modern programs are not able to use all the features provided by dual-core or, moreover, multi-core processors.
What types of user applications can be most effectively parallelized, that is, without much reworking of the program code, they allow you to select several tasks (program threads) that can be executed in parallel and, thus, load several processor cores at once? After all, only such applications provide any noticeable increase in performance from the introduction of multi-core processors.
The greatest gains from multiprocessing are received by applications that initially allow natural parallelization of calculations with data sharing, for example, packages of realistic computer rendering - 3DMax and the like. You can also expect a good performance boost from multiprocessing in applications for encoding multimedia files (audio and video) from one format to another. In addition, the tasks of editing two-dimensional images lend themselves well to parallelization in graphic editors like the popular Photoshop "a.
It is not for nothing that applications of all the above categories are widely used in tests when they want to show the advantages of Hyper-Threading virtual multiprocessing. And there is nothing to say about real multiprocessing.
But in modern 3D gaming applications, one should not expect any serious increase in speed from several processors. Why? Because a typical computer game is not so easy to parallelize into two or more processes. Therefore, the second logical processor, at best, will be engaged in the execution of only auxiliary tasks, which will give almost no performance gain. And developing a multi-threaded version of a game from the very beginning is quite complex and requires a lot of work - sometimes much more than for creating a single-threaded version. These labor costs, by the way, may still not pay off from an economic point of view. After all, manufacturers computer games Traditionally, they focus on the most massive part of users and begin to use the new capabilities of computer hardware only if it is widely used. This is clearly seen in the use of video card capabilities by game developers. For example, after new video chips supporting shader technologies appeared, game developers still for a long time ignored them, focusing on the possibilities of truncated mass solutions. So even advanced players who bought the most sophisticated video cards of those years did not wait for normal games that use all their capabilities. Approximately similar situation with dual-core processors is observed today. Today there are not so many games that really use even HyperThreading technology, despite the fact that mass processors with its support have been produced for many years now.
In office applications, the situation is not so unambiguous. First of all, programs of this class rarely work alone - it is much more common for a computer to have several running in parallel. office applications. For example, the user works with text editor, and at the same time the web site is loaded into the browser, as well as scanning for viruses in the background. Obviously, multiple running applications allow you to easily use multiple processors and get a performance boost. Moreover, everything Windows versions XP, including Home Edition (which was initially denied support for multi-core processors), is already able to take advantage of dual-core processors by distributing program threads between them. This ensures high efficiency in the execution of numerous background programs.
Thus, one can expect some effect even from non-optimized office applications if they are run in parallel, but it is difficult to understand whether such a performance increase is worth a significant increase in the cost of a dual-core processor. In addition, a certain disadvantage of dual-core processors (especially with Intel Pentium D processors) is that applications whose performance is limited not by the processing power of the processor itself, but by the speed of memory access, may not benefit as much from having multiple cores.
Conclusion
Undoubtedly, the future belongs to multi-core processors, but today, when most of the existing software is not optimized for new processors, their advantages are not as obvious as manufacturers try to show in their promotional materials. Yes, a little later, when there will be a sharp increase in the number of applications that support multi-core processors (first of all, this applies to 3D games, in which next-generation CPUs will help significantly offload graphics system), purchasing them would be expedient, but now... It has long been known that buying processors "for growth" is far from the most efficient investment.
On the other hand, progress is rapid, and for a normal person, the annual change of computer is perhaps too much. Thus, all owners have enough modern systems based on single-core processors in the near future you should not worry too much - your systems will be "on the level" for some time, while those who are going to purchase new computer, we would still recommend turning your attention to relatively inexpensive junior models of dual-core processors.
|
The most significant event in 2005 in the field of microprocessors was the appearance on sale of CPUs with two cores. Moreover, the appearance on sale of dual-core processors happened very quickly, and without much difficulty. The biggest advantage of the new products was that the transition to a dual-core system did not require a platform change. In fact, any user of a modern computer could come to the store and change only one processor without changing the motherboard and the rest of the hardware. At the same time, the already installed operating system instantly detected the second core (the second processor appeared in the list of equipment), and no specific software configuration was required (not to mention full reinstallation OS).
The idea of appearance of such processors lies on the surface. The fact is that CPU manufacturers have almost reached the ceiling of increasing the performance of their products. In particular, AMD ran into a frequency of 2.4 GHz in the mass production of Athlon 64 processors. In fairness, we note that the best specimens are capable of operating at frequencies of 2.6-2.8 GHz, but they are carefully selected and put on sale under the Athlon FX brand (respectively, a model with 2.6GHz is labeled FX-55 and 2.8GHz is labeled FX-57). However, the output of such successful crystals is very small (this can be easily verified by overclocking 5-10 processors). The next jump in clock speed is possible with the transition to a thinner process technology, but this step is planned by AMD only for the end of this year (at best).
Intel has a worse situation: the NetBurst architecture turned out to be uncompetitive in terms of performance (max. frequency 3.8 GHz) and heat dissipation (~150 W). The change of focus and the development of a new architecture should take some time (even with a lot of developments from Intel). Therefore, for Intel, the release of dual-core processors is also a big step forward in terms of performance. In combination with a successful transition to 65 nm process technology, such processors will be able to compete on equal terms with AMD products.
The main initiator in the promotion of dual-core processors was AMD, which first introduced the corresponding Opteron. As for desktop processors, the initiative was seized by Intel, which announced Intel Pentium D and Intel Extreme Edition processors. And a few days later, the announcement of the line of Athlon64 X2 processors manufactured by AMD took place.
So, we start our review of dual-core processors with Athlon64 X2
AMD Athlon 64 X2 Processors
Initially, AMD announced the release of 4 processor models: 4200+, 4400+, 4600+ and 4800+ with clock speeds of 2.2-2.4 GHz and different L2 cache sizes. The price of processors is within the range from ~430$ to ~840$. As we can see, the general pricing policy does not look very friendly to the average user. Moreover, the cheapest dual-core Intel processor costs ~$260 (Pentium D 820 model). Therefore, to increase the attractiveness of the Athlon 64 X2, AMD is releasing the X2 3800+ with a clock speed of 2.0 GHz and L2 cache = 2x512Kb. The price for this processor starts at $340.
Since two cores (Toledo and Manchester) are used for the production of Athlon 64 X2 processors, for a better understanding, we will summarize the characteristics of the processors in a table:
| Name | Core stepping | Clock frequency | L2 cache size |
| X2 4800+ | Toledo (E6) | 2400MHz | 2 x 1Mb |
| X2 4600+ | Manchester (E4) | 2400MHz | 2 x 512Kb |
| X2 4400+ | Toledo (E6) | 2200MHz | 2 x 1Mb |
| X2 4200+ | Manchester (E4) | 2200MHz | 2 x 512Kb |
| X2 3800+ | Manchester (E4) | 2000MHz | 2 x 512Kb |
All processors have a cache memory of the first level of 128Kb, a nominal supply voltage (Vcore) of 1.35-1.4V, and the maximum heat dissipation does not exceed 110 watts. All of the above processors have the Socket939 form factor, use the HyperTransport = 1GHz bus (HT multiplier = 5) and are manufactured according to the 90nm process technology using SOI. By the way, it was the use of such a "thin" technical process that made it possible to achieve profitability in the production of dual-core processors. For example, the core of Toledo has an area of 199 square meters. mm., and the number of transistors reaches 233.2 million!
If you look at the appearance of the Athlon 64 X2 processor, it does not differ at all from other Socket 939 processors (Athlon 64 and Sempron).
It is worth noting that the Athlon X2 line of dual-core processors inherited from Athlon64 support for the following technologies: Cool "n" Quiet power saving function, AMD64 instruction set, SSE - SSE3, NX-bit information security function.
Like the Athlon64 processors, the Dual-Core Athlon X2 has a dual-channel DDR memory controller with a maximum bandwidth of 6.4 Gb/s. And if DDR400 bandwidth was enough for Athlon64, then for a processor with two cores this is a potential bottleneck that negatively affects performance. However, there won't be a serious drop in speed, since multi-core support was taken into account when developing the Athlon64 architecture. In particular, in the Athlon X2 processor, both cores are inside the same die; and the processor has one memory controller and one HyperTransport bus controller.
In any case, the memory bandwidth mismatch will be eliminated after the transition to Socket M2. Let me remind you that this will happen this year and the corresponding processors will have a DDR-II memory controller.
A few words about the compatibility of the new Athlon X2 processors. On all the latest motherboards tested, the top-end X2 4800+ processor worked without any problems. As a rule, these were boards based on nVidia nForce4 (Ultra & SLI) chipsets, as well as a board based on the ATI Xpress 200 CrossFire™ chipset (ECS KA1 MVP Extreme). When I installed this processor on the Epox 9NDA3+ (nVidia nForce3 Ultra) board, the second processor core was not detected by the operating system. And the firmware of the latest version of the BIOS did not correct the situation. But this is a special case, and in general, the statistics of the compatibility of dual-core processors with motherboards are very, very positive.
It would be appropriate to note here that the new dual-core processors do not have any specific requirements for the design of the motherboard power module. Moreover, the maximum heat dissipation of Athlon X2 processors is no higher than that of Athlon FX processors produced according to the 130 nm process technology (ie, slightly above 100W). At the same time, dual-core Intel processors consume almost one and a half times more energy.
Let's say a few words about overclocking
Of all AMD processors, only technical samples and processors of the FX line have an unlocked multiplier. And the dual-core Athlon X2, as well as the single-core Athlon 64 / Sempron, have a multiplier locked upwards. And towards the decrease, the multiplier is unlocked, since it is by lowering the multiplier that the Cool "n" Quiet energy saving technology works. And for overclocking the processor, we would like to have an unlocked multiplier in the direction of increase, so that all other components of the system would work in normal mode. But AMD followed in the footsteps of Intel and banned overclocking in this way from a certain point.
However, no one has yet canceled or banned overclocking by increasing HTT. But at the same time, we will have to choose high-quality memory, or use a down-scale memory frequency divider. In addition, it is necessary to reduce the HT bus multiplier, which, however, does not have any effect on the performance level.
So, using air cooling, we managed to overclock the Athlon X2 4800+ processor from the stock frequency of 2.4 GHz to 2.7 GHz. At the same time, the supply voltage (Vcore) was increased from 1.4V to 1.55V.
Overclocking statistics show that this instance showed not the worst increase in frequency. However, one cannot count on more, since AMD selects the most "successful" cores for the production of processors with a frequency of 2.6 GHz and 2.8 GHz
Intel Dual Core Processors
The first dual-core Intel processors were based on the Smithfield core, which is nothing more than two Prescott E0 stepping cores combined on a single die. The cores interact with each other through the system bus using a special arbiter. Accordingly, the crystal size reached 206 square meters. mm., and the number of transistors increased to 230 million.
It is interesting to consider how the HyperThreading technology is implemented in dual-core processors based on the Smithfield core. For example, Pentium D processors do not support this technology at all. Intel marketers felt that two "real" cores were enough for most users. But in the Pentium Extreme Edition 840 processor, it is enabled, and thanks to this, the processor can execute 4 instruction streams simultaneously. By the way, HyperThreading support is the only difference between Pentium Extreme Edition processor and Pentium D. All other functions and technologies are completely identical. Among them are support for the EM64T command set, EIST, C1E and TM2 power saving technologies, as well as the NX-bit information security function. As a result, the difference between Pentium D and Pentium EE processors is completely artificial.
Let's list the models of processors based on the Smithfield core. These are Pentium D with indices 820, 830 and 840 as well as Pentium Extreme Edition 840. All of them operate at a system bus frequency of 200 MHz (800QPB), are produced according to the 90nm process technology, have a nominal supply voltage (Vcore) of 1.25-1.388 V, maximum heat dissipation ~130 W (although according to some estimates, the heat dissipation of the EE 840 is at the level of 180 W).
To be honest, any positive aspects I did not find any processors on the Smithfield core. The main complaint is the level of performance, when in many applications (which are not optimized for multithreading) dual-core Smithfield processors lose out to single-core Prescotts running at the same clock frequency. At the same time, AMD processors do not have such a situation. Obviously, the problem lies in the interaction of the cores via the processor bus (during the development of the Prescott core, performance scaling by increasing the number of cores was not provided). Perhaps for this reason, Intel decided to compensate for the shortcomings with a lower price. In particular, the price tag for the junior model Pentium D 820 was set at ~$260 (the cheapest Athlon X2 costs $340).
When buying a flash drive, many people ask themselves the question: "how to choose the right flash drive." Of course, choosing a flash drive is not so difficult if you know exactly for what purposes it is purchased. In this article I will try to give a complete answer to the question posed. I decided to write only about what to look for when buying.
A flash drive (USB drive) is a drive designed to store and transfer information. The flash drive works very simply without batteries. You just need to connect it to USB port at your PC.
1. Flash drive interface
On the this moment There are 2 interfaces: USB 2.0 and USB 3.0. If you decide to buy a flash drive, then I recommend taking a flash drive with USB interface 3.0. This interface was made recently main feature is high speed data transmission. We'll talk about speeds a little later.
This is one of the main parameters that you need to look at first. Now flash drives are sold from 1 GB to 256 GB. The cost of a flash drive will directly depend on the amount of memory. Here you need to immediately decide for what purpose a flash drive is bought. If you are going to store text documents, then 1 GB is enough. For downloading and transferring movies, music, photos, etc. you need to take the more, the better. To date, the most popular are flash drives with a capacity of 8GB to 16GB.
3. Body material
The body can be made of plastic, glass, wood, metal, etc. Flash drives are mostly made of plastic. There is nothing I can advise here, it all depends on the preferences of the buyer.
4. Transfer rate
Earlier I wrote that there are two standards USB 2.0 and USB 3.0. Now I will explain how they differ. USB standard 2.0 has a read speed of up to 18 Mbps, and a write speed of up to 10 Mbps. The USB 3.0 standard has a read speed of 20-70 Mbps, and a write speed of 15-70 Mbps. Here, I think, nothing needs to be explained.
Now in stores you can find flash drives of different shapes and sizes. They can be in the form of jewelry, fancy animals, etc. Here I would advise taking flash drives that have a protective cap.
6. Password protection
There are flash drives that have a password protection feature. Such protection is carried out using a program that is located in the flash drive itself. The password can be set both on the entire flash drive, and on part of the data in it. Such a flash drive will primarily be useful to people who transfer corporate information in it. According to the manufacturers, if you lose it, you don't have to worry about your data. Not so simple. If such a flash drive falls into the hands of an understanding person, then hacking it is just a matter of time.
Such flash drives look very beautiful, but I would not recommend buying them. Because they are very fragile and often break in half. But if you are a neat person, then feel free to take it.
Conclusion
Nuances, as you noticed, a lot. And this is just the tip of the iceberg. In my opinion, the most important parameters when choosing: the standard of a flash drive, the volume and speed of writing and reading. And everything else: design, material, options - this is just a personal choice of everyone.Good afternoon my dear friends. In today's article, I want to talk about how to choose the right mouse pad. When buying a rug, many do not attach any importance to this. But as it turned out, this moment needs to be given special attention, because. mat determine one of the indicators of comfort while working at a PC. For an avid gamer, choosing a rug is a completely different story. Consider what options for mouse pads have been invented today.
Mat options
1. Aluminum2. Glass
3. Plastic
4. Rubberized
5. Double sided
6. Helium
And now I would like to talk about each species in more detail.
1. First, I want to consider three options at once: plastic, aluminum and glass. These mats are very popular with gamers. For example, plastic mats are easier to find commercially. On such mats, the mouse glides quickly and accurately. And most importantly, these mats are suitable for both laser and optical mice. Aluminum and glass mats will be a little more difficult to find. And yes, they will cost a lot. The truth is for what - they will serve for a very long time. Rugs of these types have small flaws. Many people say that they rustle and feel a little cool when used, which may cause discomfort for some users.
2. Rubberized (rag) mats have a soft glide, but the accuracy of their movements is worse. For ordinary users such a rug will be just right. Yes, and they are much cheaper than the previous ones.
3. Double-sided mousepads are, in my opinion, a very interesting kind of mousepads. As the name implies, these rugs have two sides. As a rule, one side is high-speed, and the other is high-precision. It happens that each side is designed for a certain game.
4. Helium pads have a silicone cushion. She allegedly supports her hand and relieves tension from it. For me personally, they were the most uncomfortable. By appointment, they are designed for office workers, since they sit at the computer all day. For ordinary users and gamers, these mats are not suitable. The mouse slides very poorly on the surface of such rugs, and their accuracy is not the best.
Mat sizes
There are three types of rugs: large, medium and small. It all depends on the taste of the user. But as is commonly believed, large rugs are well suited for games. Small and medium ones are taken mainly for work.Rugs design
In this regard, there are no restrictions. It all depends on what you want to see on your rug. The blessing now on rugs that only do not draw. The most popular are the logos of computer games such as DotA, Warcraft, ruler, etc. But if it happened that you could not find a rug with the pattern you need, do not be upset. Now you can order a print on the rug. But such rugs have a minus: when printing is applied to the surface of the rug, its properties deteriorate. Design for quality.
On this I want to end the article. From myself I wish to make you right choice and be happy with it.
Who does not have a mouse or wants to replace it with another, I advise you to look at the article:.
Monoblocks from Microsoft have replenished with a new monoblock model called Surface Studio. Microsoft presented its new product recently at an exhibition in New York.
On a note! I wrote an article a couple of weeks ago where I reviewed the Surface monoblock. This monoblock was presented earlier. Click on to view the article.
Design
Microsoft calls its new product the thinnest monoblock in the world. With a weight of 9.56 kg, the thickness of the display is only 12.5 mm, the other dimensions are 637.35x438.9 mm. The display dimensions are 28 inches with a resolution greater than 4K (4500x3000 pixels), aspect ratio 3:2.
On a note! The display resolution of 4500x3000 pixels corresponds to 13.5 million pixels. This is 63% more than 4K resolution.
The monoblock display itself is touch-sensitive, enclosed in an aluminum case. On such a display, it is very convenient to draw with a stylus, which ultimately opens up new possibilities for using a monoblock. In my opinion, this monoblock model will appeal to creative people (photographers, designers, etc.).
On a note! For people of creative professions, I advise you to look at an article where I considered monoblocks of similar functionality. Click on the selected one: .
To everything written above, I would add that the main feature of the monoblock will be its ability to instantly turn into a tablet with a huge work surface.
On a note! By the way, Microsoft has another amazing candy bar. To find out about it, go to.
Specifications
I will present the characteristics in the form of a photograph.
From the periphery, I note the following: 4 USB ports, Mini-Display Port connector, network port Ethernet, card-reader, 3.5 mm audio jack, 1080p webcam, 2 microphones, 2.1 Dolby Audio Premium audio system, Wi-Fi and Bluetooth 4.0. It also supports Xbox wireless controllers.
Price
When buying a monoblock, it will be installed with Windows 10 Creators Update. This system due out in the spring of 2017. In this operating system there will be an updated Paint, Office, etc. The price of a monoblock will be from $ 3,000.Dear friends, write in the comments what you think about this monoblock, ask your questions. I'll be glad to chat!
OCZ has demonstrated new VX 500 SSDs. These drives will be equipped with Serial ATA 3.0 interface and are made in 2.5-inch form factor.
On a note! For those who are interested in how SSD drives work and how long they live, you can read in an article I wrote earlier:.The novelties are made using 15-nanometer technology and will be equipped with Tochiba MLC NAND flash memory microchips. The controller in SSD drives will be used by Tochiba TC 35 8790.
The lineup VX 500 drives will consist of 128 GB, 256 GB, 512 GB and 1 TB. According to the manufacturer, the sequential read speed will be 550 Mb/s (this is for all drives in this series), but the write speed will be from 485 Mb/s to 512 Mb/s.
The number of input / output operations per second (IOPS) with data blocks of 4 KB in size can reach 92,000 when reading, and 65,000 when writing (this is all arbitrary).
The thickness of OCZ VX 500 drives will be 7 mm. This will allow them to be used in ultrabooks.
Prices of new products will be as follows: 128 GB - $ 64, 256 GB - $ 93, 512 GB - $ 153, 1 TB - $ 337. I think in Russia they will cost more.
Lenovo has unveiled its new IdeaCentre Y910 gaming all-in-one at Gamescom 2016.
On a note! Earlier I wrote an article where I already considered gaming monoblocks different manufacturers. This article can be viewed by clicking on this one.
The novelty from Lenovo received a 27-inch frameless display. The display resolution is 2560x1440 pixels (this is QHD format), the refresh rate is 144 Hz, and the response time is 5 ms.
The monoblock will have several configurations. Processor 6 is provided in the maximum configuration Generations of Intel Core i7 volume hard drive up to 2 TB or 256 GB. Volume random access memory equals 32 GB DDR4. The graphics card will be responsible for the graphics NVIDIA GeForce GTX 1070 either GeForce GTX 1080 with Pascal architecture. Thanks to such a video card, it will be possible to connect a virtual reality helmet to the monoblock.
From the periphery of the monoblock, I would single out the Harmon Kardon audio system with 5-watt speakers, the Killer DoubleShot Pro Wi-Fi module, a webcam, USB ports 2.0 and 3.0, HDMI connectors.
In the basic version, the IdeaCentre Y910 monoblock will be available in September 2016 at a price of 1800 euros. But the monoblock with the version of "VR-ready" will appear in October at a price of 2200 euros. It is known that this version will have GeForce graphics card GTX 1070.
MediaTek has decided to upgrade its Helio X30 mobile processor. So now the developers from MediaTek are designing a new mobile processor called Helio X35.
I would like to briefly talk about Helio X30. This processor has 10 cores, which are combined into 3 clusters. Helio X30 has 3 variations. The first - the most powerful - consists of Cortex-A73 cores with a frequency of up to 2.8 GHz. There are also blocks with Cortex-A53 cores with a frequency of up to 2.2 GHz and Cortex-A35 with a frequency of 2.0 GHz.
The new Helio X35 processor also has 10 cores and is being created using 10nm technology. The clock frequency in this processor will be much higher than that of its predecessor and ranges from 3.0 Hz. The novelty will allow you to use up to 8 GB LPDDR4 RAM. The Power VR 7XT controller will most likely be responsible for the graphics in the processor.
The station itself can be seen in the photographs in the article. In them we can observe the drive bays. One bay with a 3.5" jack and the other with a 2.5" jack. Thus, it will be possible to connect both a solid state disk (SSD) and HDD(HDD).
The dimensions of the Drive Dock station are 160x150x85mm, and the weight is no less than 970 grams.
Many people probably have a question about how the Drive Dock connects to a computer. The answer is: this happens through a USB 3.1 Gen 1 port. According to the manufacturer, the sequential read speed will be 434 Mb / s, and in write mode (serial) 406 Mb / s. The novelty will be compatible with Windows and Mac OS.
This device will be very useful for people who work with photo and video materials at a professional level. The Drive Dock can also be used to backups files.
The price for a new device will be acceptable - it is $ 90.
On a note! Previously, Renduchinthala worked at Qualcomm. And since November 2015, he moved to a competing company Intel.
In his interview, Renduchinthala did not talk about mobile processors, but only said the following, and I quote: "I prefer to talk less and do more."
Thus, the top manager of Intel made an excellent intrigue with his interview. We just have to wait for more announcements in the future.
Migration to a new, more efficient computing environment based on AMD's existing system infrastructure and industry standard architecture is simple, and corporate clients can look forward to an increase computing power without any costs in the form of increased power consumption or heat dissipation. The AMD Opteron dual-core processor for servers and workstations, scheduled for general release in mid-2005, is expected to provide the best performance per watt of any comparable product on the market.
This announcement follows a slew of impressive groundbreaking achievements from AMD. It was the first company to ship high-performance products that support both 32-bit and 64-bit x86-based computing, and in doing so, initiated the industry's transition to 64-bit ubiquity. In addition, AMD was the first company to implement 64-bit processing and advanced antivirus protection(based on Windows(r) Service Pack) service pack 2) in low power desktop and mobile processors.
Industry Support
Backed by strong partner support, AMD continues to lead the x86 industry's technological innovation by demonstrating the technology that will enable the transition to dual-core products.
"Dual-core processor technologies for industry-standard servers will redefine how we optimize scalability, performance, and business value for large corporations and small business customers," said Paul Miller, vice president of Marketing at HP Industry Standard Servers - Showcasing the industry's first dual-core x86 processors from AMD running on HP ProLiant servers demonstrates the value of HP's partnership with AMD and our continued commitment to our customers, who we strive to supply with the best new products as quickly as possible. technologies."
Industry leader innovation
Based on the existing Socket-940 infrastructure, the forthcoming dual-core AMD Opteron processor, AMD predicts that it will increase the performance of servers and workstations in virtually all operating modes by combining two processor cores on a single die. Form factor, power consumption and performance requirements force the search for innovative solutions for modern computer chips. Dual core processor technology will provide users with more balanced performance based on a system architecture that is fully compliant with industry standards.
Dual-core processors are a natural extension of AMD64 technology with a direct connection architecture. AMD was not only the first company to eliminate x86 front-end bus bottlenecks, but it was also the first to successfully combine two cores on a single die, along with a memory controller, I/O subsystem, and other processors, to improve overall system performance. and improve processing efficiency.
Release dates
In mid-2005, AMD plans to introduce a full line of Socket 940-based dual-core processors for 1-/8-socket servers and workstations. They should be followed in the second half of 2005 by dual-core processors for the client market.