The labeling of AMD Athlon 64 processors is so complex and confusing that it confuses even experts.

Model numbers, or ratings, were invented by AMD back when it was struggling to compete with Intel. The idea behind the processor pseudo-frequency is to explain to the user which counterpart of which Intel processor he is buying. Even then, AMD began to promote the thesis that processor performance depends not only on the clock frequency, but also on other parameters, primarily on the microarchitecture and the amount of built-in cache memory. The processor rating ("pseudo-frequency") just takes into account the difference in other parameters and can be used to compare processors from different manufacturers. And AMD began to assign "plus" numbers to its processors, indicating the clock speed of similar performance Intel processors.

The starting point for the processor rating was indeed calculated based on benchmark results. However, further AMD began to assign ratings simply in ascending order. And when different versions of the Athlon 64 appeared, the situation with the ratings completely got out of control: now with the help of the rating it was necessary to mark not only the difference in frequencies, but also different caches, different processor sockets, etc. Therefore, in the pivot table you will find many processors with the same numbers but different parameters. You can distinguish them only by the marking line (OPN), which is printed on the processor case directly under its name.

When AMD introduced a new manufacturing technology, it decided not to change either the name or the way processors were labelled. And that's why Athlon 64 with different core revisions, differing in support for different frequencies and memory types, instruction set support, power consumption and overclocking potential, can only be distinguished by OPN. Luckily, the Athlon 64 box packaging has a transparent window through which the processor markings can be easily read. And do not accidentally buy a processor on an old core, which may not support DDR400 or not be overclocked at all.

Note that AMD has been starting to improve lately. There are no models with the same numbers and different parameters among the processors based on the latest modification of the Venice core. We can already talk about the unambiguous correspondence of the number to the frequency and size of the cache. Let's say 3200+ will always have a frequency of 2 GHz and a cache of 512 KB, and only two numbers are "reserved" for processors with a 1 MB cache - 3700+ and 4000+.

Especially for overclockers, we would like to inform you that Venice (E3, E6) core processors, regardless of the number, usually overclock to 2.8-2.9 GHz. Therefore, it makes sense to buy the most affordable model - 3000+, since even with proper luck it will allow you to reach the theoretical limit of its core.

Deciphering processor numbers and markings Athlon 64

The processor is the main component of the computer, nothing will work without it. Since the release of the first processor, this technology has been developing by leaps and bounds. The architectures and generations of AMD and Intel processors have changed.

In one of the previous articles, we considered, in this article we will look at the generations of AMD processors, consider how it all started, and how it improved until the processors became what they are now. Sometimes it's very interesting to understand how technology has evolved.

As you already know, initially, the company that produced processors for the computer was Intel. But the US government did not like that such an important part for the defense industry and the country's economy is produced by only one company. On the other hand, there were others who wanted to release processors.

Was founded AMD, Intel shared with them all its developments and allowed AMD to use its architecture to release processors. But this did not last long, after a few years Intel stopped sharing new developments and AMD had to improve their processors themselves. By the concept of architecture, we will mean microarchitecture, the arrangement of transistors on a printed circuit board.

Early processor architectures

First, a brief look at the first processors produced by the company. The very first was the AM980, it was full of an eight-bit Intel 8080 processor.

The next processor was AMD 8086, a clone of Intel 8086, which was produced under a contract with IBM, which forced Intel to license this architecture to a competitor. The processor was 16-bit, had a frequency of 10 MHz, and the 3000 nm manufacturing process was used for its manufacture.

The next processor was a clone of Intel 80286 - AMD AM286, compared to the device from Intel, it had a higher clock frequency, up to 20 MHz. The process technology has been reduced to 1500 nm.

Next was the AMD 80386 processor, a clone of Intel 80386, Intel was against the release of this model, but the company managed to win a lawsuit. Here, too, the frequency was raised to 40 MHz, while Intel had only 32 MHz. The technical process is 1000 nm.

AM486 is the latest processor released on the basis of Intel's developments. The processor frequency was raised to 120 MHz. Further, due to litigation, AMD was no longer able to use Intel technologies and they had to develop their processors.

Fifth generation - K5

AMD released its first processor in 1995. It had a new architecture that was based on the previously developed RISC architecture. Ordinary instructions were recoded into microinstructions, which helped to greatly improve performance. But here AMD could not bypass Intel. The processor had a clock speed of 100 MHz, while the Intel Pentium was already running at 133 MHz. For the manufacture of the processor, the 350 nm process technology was used.

Sixth generation - K6

AMD did not develop a new architecture, but decided to acquire NextGen and use its Nx686 developments. Although this architecture was very different, it also used instruction conversion to RISC, and it also did not bypass the Pentium II. The processor frequency was 350 MHz, the power consumption was 28 watts, and the manufacturing process was 250 nm.

The K6 architecture had several improvements going forward, K6 II added several additional instruction sets to improve performance, and K6 III added L2 cache.

Seventh generation - K7

In 1999, a new microarchitecture of AMD Athlon processors appeared. Here, the clock frequency was significantly increased, up to 1 GHz. The second level cache was placed on a separate chip and had a size of 512 kb, the first level cache was 64 kb. For manufacturing, the 250 nm process technology was used.

Several more processors based on the Athlon architecture were released, in Thunderbird the second level cache returned to the main integrated circuit, which allowed to increase productivity, and the process technology was reduced to 150 nm.

In 2001, processors based on the AMD Athlon Palomino processor architecture were released with a clock speed of 1733 MHz, a 256 MB L2 cache and a 180 nm process technology. Power consumption reached 72 watts.

Architecture improvements continued, and in 2002 the company launched the Athlon Thoroughbred processors, which used the 130nm process and clocked at 2GHz. Barton's next improvement increased the clock speed to 2.33 GHz and doubled the size of the L2 cache.

In 2003, AMD released the K7 Sempron architecture, which had a clock speed of 2 GHz, also with a 130 nm process technology, but already cheaper.

Eighth generation - K8

All previous processor generations were 32 bit depth and only the K8 architecture began to support 64-bit technology. The architecture has undergone many changes, now the processors could theoretically work with 1 TB random access memory, the memory controller was moved to the processor, which improved performance compared to K7. A new HyperTransport data exchange technology has also been added here.

The first processors based on the K8 architecture were Sledgehammer and Clawhammer, they had a frequency of 2.4-2.6 GHz and the same 130 nm process technology. Power consumption - 89 W. Further, as with the K7 architecture, the company performed a slow improvement. In 2006, Winchester, Venice, San Diego processors were released, which had a clock speed of up to 2.6 GHz and a 90 nm manufacturing process.

In 2006, Orleans and Lima processors came out, which had a clock speed of 2.8 GHz, the latter already had two cores and supported DDR2 memory.

Along with the Athlon line, AMD released the Semron line in 2004. These processors had a lower frequency and cache size, but were cheaper. Frequency up to 2.3 GHz and L2 cache up to 512 KB were supported.

In 2006, the development of the Athlon line continued. The first dual-core Athlon X2 processors were released: Manchester and Brisbane. They had a clock frequency of up to 3.2 GHz, a 65 nm manufacturing process and a power consumption of 125 watts. In the same year, the Turion budget line was introduced, clocked at 2.4 GHz.

Tenth generation - K10

The next architecture from AMD was the K10, which is similar to the K8, but has received many improvements, including an increase in cache, an improvement in the memory controller, an IPC mechanism, and most importantly, a quad-core architecture.

The first was the Phenom line, these processors were used as server processors, but they had a serious problem that led to the processor freezing. AMD later fixed it in software, but this reduced performance. Processors were also released in the Athlon and Operon lines. The processors ran at 2.6 GHz, had 512 KB of L2 cache, 2 MB of L3 cache, and were manufactured using the 65 nm process technology.

The next architectural improvement was the Phenom II line, in which AMD made a process transition to 45 nm, which significantly reduced power consumption and heat consumption. Quad core Phenom processors II had a frequency of up to 3.7 GHz, a cache of the third level up to 6 MB. The Deneb processor already supported DDR3 memory. Then the dual-core and tri-core Phenom II X2 and X3 processors were released, which did not gain much popularity and worked at lower frequencies.

In 2009, budget processors AMD Athlon II were released. They had clock speeds up to 3.0 GHz, but the third level cache was cut out to reduce the price. The lineup included a quad-core Propus and a dual-core Regor. In the same year, the Semton product line was updated. They also did not have an L3 cache and ran at a clock speed of 2.9 GHz.

In 2010, the six-core Thuban and the quad-core Zosma were released, which could run at 3.7 GHz. The processor frequency could change depending on the load.

Fifteenth generation - AMD Bulldozer

In October 2011, a new architecture came to replace the K10 - Bulldozer. Here the company tried to use a large number of cores and high clock speeds to get ahead of Intel's Sandy Bridge. The first Zambezi chip couldn't even beat the Phenom II, let alone Intel.

A year after the release of Bulldozer, AMD released an improved architecture codenamed Piledriver. Here, clock speed and performance have been increased by about 15% without increasing power consumption. The processors had a clock speed of up to 4.1 GHz, consumed up to 100 W, and were manufactured using a 32 nm process technology.

Then the FX processor line was released on the same architecture. They had clock speeds up to 4.7 GHz (5 GHz when overclocked), were versions for four, six and eight cores, and consumed up to 125 watts.

The next Bulldozer improvement, the Excavator, came out in 2015. Here the process technology has been reduced to 28 nm. The processor clock speed is 3.5GHz, the number of cores is 4, and the power consumption is 65W.

Sixteenth generation - Zen

This is a new generation of AMD processors. The Zen architecture was designed by the company from the ground up. Processors will be released this year, it is expected that in the spring. For their manufacture, the 14 nm process technology will be used.

The processors will support DDR4 memory and generate 95 watts of heat. The processors will have up to 8 cores, 16 threads, clocked at 3.4 GHz. Power efficiency has also been improved, and automatic overclocking has been announced as the processor adjusts to your cooling capabilities.

conclusions

In this article, we looked at AMD processor architectures. Now you know how they developed AMD processors and how things are on this moment now. You can see that some generations of AMD processors are missing, this is mobile processors, and we deliberately excluded them. I hope this information was helpful to you.

This article only presents best processors AMD in 2017.

If you don't want to figure out all the specs of each processor model on your own, or if you're not sure you can choose the best option, take a look at our CPU rating from AMD.

Content:

A good processor is the main indicator of power and. AMD is one of the leaders in the processor market.

AMD produces the following types of processors:

• CPU – central computing units
• GPU - a separate device that renders video. Often used in gaming computers to reduce the load on the central unit and to ensure best quality video sequence;
• APU – central processing units with built-in video accelerator. They are also called hybrid, because such a component is a combination of the central and in one crystal.

#5 - Athlon X4 860K

The AMD Athlon line is designed for Socket FM2+. X4 860K is the best and most productive model in the entire series, into which three processors go:

• Athlon X4 860K;
• Athlon X4840;
• and model Athlon X2.

The Athlon family is designed for desktop personal computers. All models of the line are distinguished by good multithreading.

The best results in the Athlon group were shown by the X4 860K model.

The first detail to note is the support for practically 95W, along with quiet operation and no loss in performance.

If the processor has been overclocked with special programs, there may be an increase in noise in the operation of the cooling system.

Main characteristics:

• Family: Athlon X4;
• Number of processor cores: 4;
• Clock frequency - 3.1 MHz;
• There is no unlocked multiplier;
• Core type: Kaveri;
• Approximate cost: $50.

There is no integrated graphics in the CPU.

The X4 860K processor is able to support fast work only general-purpose systems.

CPU operation was tested using the AIDA64 utility. In general, the model shows nice results for a mid-range processor.

If you are looking for an inexpensive multitasking CPU for your home computer, Athlon X4 860K is one of the suitable options.

testing Athlon X4 860K

#4 - AMD FX-6300

AMD's FX-6300 is a Piledriver CPU. Processors with this architecture have already become worthy competitors to new products from Intel.

All processors from AMD FX group have excellent overclocking potential.

Features of FX-6300:

• Series: FX-Series;
• Supported connector: Socket AM3+;
• Number of cores: 6;
• No integrated graphics;
• The clock frequency is 3.5 MHz;
• Number of contacts: 938;
• The average cost of the model is $85.

A characteristic feature of the processor is its flexibility.

The clock frequency declared by the developer is 3.5 MHz, which is a rather mediocre indicator among.

However, this CPU provides the ability to overclock the frequency up to 4.1 MHz.

AMD FX series boxing devices

Acceleration of work occurs during intense loads. More often in the process of rendering video or working with games.

It should be noted that this CPU model is equipped with a dual-channel memory controller.

Processor performance testing was carried out in just cause 2.

The final results showed that the Athlon X4 860K maintains a maximum graphics resolution of 1920 x 1200 pixels.

The computer also used an integrated GTX 580 graphics card.

In the figure below, you can see a comparative analysis of the performance of other processors that were tested with identical software and hardware environment conditions.

Athlon X4 860K test result

#3 - A10-7890K

The A10-7890K is a hybrid CPU from AMD. Despite the announcement of the development of a fundamental new technology and generation of processors, AMD decided to release another model of the A10 line.

The company positions this series of devices as an excellent choice for desktop PCs.

The A10-7890K is the best in class playback solution.

Of course, the graphics settings will have to be lowered, but as a result, you will get good performance without severe overheating of the PC hardware.

packing model A10-7890K

This processor has an integrated Radeon graphics unit that allows you to:

The processor comes with a Wraith cooler, which features a very quiet operation. Also, the cooler supports backlight mode. Specifications A10-7890K:

• CPU family - A-Series;
• Clock frequency: 4.1 MHz;
• Connector type: Socket FM2+;
• Number of cores: 4 cores;
• There is an unlocked multiplier;
• Number of contacts: 906;
• Estimated cost is $130.

The main advantage of the A10-7890K is the improved interaction with Windows 10.

The detailed characteristics of the processor are indicated to us in the figure below:

APU A10-7890K detailed specifications

The results of testing the component with a standard test:

Cinebench R15 test result

As you can see, the tested component surpassed some AMD models in the A-10 and Athlon line in terms of its parameters.

At the same time, the results obtained were not enough to outperform analogs from Intel in terms of performance.

#2 - Ryzen 5 1600X

The first two places in our TOP are occupied by models of the Ryzen line. It was in the last few years that the architecture of these processors has become a key one for Advanced Micro Devices.

The presented Zen microarchitecture gradually returns the leading position in the market to the manufacturer.

Ryzen 5 is a direct competitor for the . The CPU performs best in gaming systems. This is also stated by the CEO of AMD.

Characteristics:

• AMD Ryzen 5 Family;
• 6 cores;
• Without integrated graphics;
• There is an unlocked multiplier;
• Clock frequency 3.6 MHz;
• Socket AM4;
• The cost is about $260.

Most modifications of the 1600X lack the native . Users will have to purchase this component separately.

The base frequencies do not cross the 3.6 MHz mark. When working in turbo mode (as a result of overclocking the processor), the clock frequency reaches 4.0 MHz.

All fifth-generation Ryzen models support SMT, Surface Mount Technology.

Thus the CPU is easily mounted on the surface printed circuit board without the need to cut parts of the component.

Ryzen 5 bundle

In the process of testing the CPU operation even with the most resource-intensive programs, the maximum CPU temperature did not exceed 58 degrees. , Test results:

1600X performance test

Together with a line of powerful CPUs, AMD also released a special firmware for them. initial setting- AGESA.

The utility allows you to reconfigure the memory to avoid delays and interruptions in work.

#1 - Ryzen 7 1800X

The Ryzen 7 1800X is a great choice for building a powerful PC or for layered data server support.

AT this moment AMD is developing another powerful member of the Ryzen family.

In March 2017, the Ryzen 2000 X APU model was announced, which should go on sale by the end of the year.

Characteristics:

• Family: AMD Ryzen 7;
• 8 cores;
• Clock frequency 3.6 MHz with the possibility of overclocking to 4 MHz;
• Support for unlocked multiplier;
• No support for integrated graphics;
• The average price is $480.

1800X can run up to 16 threads simultaneously program code. The processor works with SMT multi-threading technology.

All Zen cores provide effective use others. Increased throughput by supporting a three-level cache.

Comparison of test results of Ryzen 7 1800X with competitive models from Intel.

Compared to Intel, AMD has a slightly different development strategy in terms of processors. So, there is a clear division of the model range into two parts: with and without an integrated video core. The set of processor sockets is also more diverse - Socket AM3, Socket AM3+, Socket FM1, Socket FM2. Before a more detailed analysis of each CPU family, it is worth noting right away that AMD has no analogue to Intel SandyBridge-E (Socket LGA2011) processors in terms of performance. That is, when assembling an extreme top-level computer, the user simply has no alternative to the Socket LGA2011 platform.

But in the mass market segment, AMD has quite a few models. Let's start the analysis of the AMD lineup with processors without an integrated video core. To date, two platforms meet this criterion: Socket AM3 and Socket AM3+. Socket AM3 processors by computer standards appeared quite a long time ago, back in early 2009, as a response to the first generation of CPU IntelCore i7/i5/i3. We must admit that AMD's answer turned out to be quite tangible, both in terms of cost and performance. It is not for nothing that these processors are still being sold at full speed today, while the first generation Intel Core i7/i5/i3 completely disappeared from store shelves, giving way to Intel SandyBridge / IvyBridge.

With the Socket AM3 platform, AMD has taken a big step forward in processor development. First of all, there was a complete transition to a new 45-nm process technology (previously 65-nm was used). This made it possible to significantly increase the number of transistors (from 450 to 758 million), while at the same time reducing the crystal area from 285 sq. mm up to 258 sq. mm. The "top" models had an increase in L3 cache memory from 2 MB to 6 MB, although it still remained common for all cores. Support for DDR3 memory has also been added, the clock frequency has increased, branch prediction has been improved, and the execution of some instructions has been optimized.

All this made it possible to significantly increase the performance of processors built on the K10.5 architecture compared to the previous generation of CPUs. In addition, the introduction of a smaller process technology and the use of advanced Cool "n" Quiet 3.0 power-saving technology had a positive effect on the processor's power consumption, both in operation and in idle. This, in turn, increased its overclocking potential.

In addition, interest from overclockers and ordinary users to the Socket AM3 platform has intensified after the release of three-core models. Not only do such processors themselves have an excellent indicator in terms of "price / capabilities", but there is always a chance to successfully unlock the 4th core and get more performance for free. Plus, 2-core models were produced in a limited volume, which could be turned into 4-core ones, as well as 1-core models with a second hidden core.

Another no less important factor that influenced such popularity of processors with the K10.5 architecture was their great “upgradability”. They are no problem (in some cases after a simple BIOS updates) work on Socket AM2+/ Socket AM3 / Socket AM3+ platforms. This gave users the ability to gradually improve their hardware, rather than immediately change the entire system with the next upgrade.

But with the release of the 6-core AMDPhenomII X6, the potential of the K10.5 family processors was actually exhausted. The next step in the development of the Socket AM3 platform was the emergence of the Socket AM3+ platform and new processors for it.

Today, processors with two types of architecture are presented on the market for Socket AM3+: Bulldozer and Piledriver. Moreover, from a technological point of view, it was the Bulldozer architecture for AMD that became a big step forward, and Piledriver, in fact, is just a slightly improved version of Bulldozer.

AMDZambezi processors (the code name for CPUs based on the Bulldozer architecture) are already made using the 32nm process technology, which is currently the most progressive for AMD. The engineers decided to abandon independent cores in favor of dual-core modules. This module includes two x86 compute units with shared resources such as the prefetcher, instruction decoder, FPU, and L2 cache (2 MB per module). Such technical solution allowed to reduce the number of transistors used for the efficient operation of a single core. In addition, the area of ​​the crystal and its power consumption decreased. As a consequence of all this, in model range Zambezi introduced 4-, 6- and 8-core processors. Moreover, AMD immediately announced that a 2-core module will provide 80% of the performance of two full-fledged cores. It would seem that Intel processors have no chance, especially since AMDZambezi are cheaper than their counterparts.

But the first results immediately showed that AMD's statements about performance were, to put it mildly, too optimistic. Two Bulldozer cores worked as one full-fledged IntelSanyBridge, and even then not in all applications. The "top-end" 8-core AMDFX-8150 outperformed the 4-core Intel i5-2500K in terms of performance, even in tasks where, it would seem, a larger number of cores should play a role.

No matter how AMD advertised the AMDLlano hybrid processor, it could not force users to abandon the external video accelerator. The integrated video core, although it overtook its integrated competitors, was still very far from a discrete video card in terms of performance.

Most recently, the second generation of Trinity APUs has been released, based on AMD's most advanced Piledriver architecture. We described the Piledriver architecture a little higher, so we will only consider integrated graphics in more detail. We only note that, like APULlano, APUTrinity lacks L3 cache memory, which again greatly affected performance compared to full-fledged AMDVishera processors. The APUTrinity video core has slightly increased in size and now occupies half the area of ​​the crystal. Also added full support DirectX 11, OpenCL 1.1 and DirectCompute 11. In addition, thanks to Eyefinity technology, it is possible to connect four display devices. And finally, the most important thing that AMD representatives repeatedly focus on is the DualGraphics mode, which allows you to combine the power of integrated and discrete video. But real benefit from this mode is small, since the performance gain from its use is minimal, and it is supported only with the outdated generation GPUs AMDRadeonHD 6000 series (and even then not with all models).

For example, here is the processor marking: AMD Phenom X2 GS-6xxx

Phenom
Athlon
Sempron

GP-7xxx
GS-6xxx
BE-2xxx
LS-2xxx
LE-1xxx

The first character defines the class:

G - high-end
B - Mainstream (middle class)
L - Low-End (budget)

The second character determines the power consumption of the processor:

P - more than 65 W
S - 65W
E - less than 65 W (Energy Efficient class)

The first digit indicates that the processor belongs to a particular family:

1 - single core Sempron
2 - dual-core Athlon
6 - dual-core Phenom X2
7 - quad-core Phenom X4

The second digit indicates the performance level of a particular processor within the family.

The last two digits determine the processor modification.

The notorious number 64, indicating support for 64-bit architecture, disappears from the name of the Athlon processor.

Because of its complexity new system designations did not find a response among the company's customers.
In this regard, the company decided to change the rating system and simplify the writing of models.

Today, she reveals the names of the following series of AMD desktop processors:

Phenom FX - quad-core Agena FX (dual-processor and single-processor FASN8 systems). The name hasn't changed.
Phenom 9xxx - quad-core Agena. Formerly Phenom X4 GP-7xxx.
Phenom 7xxx - tri-core Toliman.
Athlon 6xxx - dual-core Kuma. Formerly Phenom X2 GS-6xxx.
Athlon LE-1xxx - single core Lima. Formerly Athlon LS-2xxx.
Sempron LE-1xxx - single core Sparta. The designation has not changed.

The LS-2xxx series is supposed to be filled with dual-core AMD K10 Rana processors.

More and more details appear on the Web about Intel's Comet Lake-S processors.

Intel LGA1200 socket for PC processors

Processor output Intel Core Comet Lake 10th Gen Desktop and motherboards based on 400-series chipsets (Z490, W480, Q470 and H410) is expected in the second half of 2020.

NVIDIA GeForce Experience has been updated to version 3.20.2

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

Maybe 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.