Series
The main manufacturers of processors nowadays are
Intel and
AMD, also in 2020, Apple introduced its
M1 series CPUs (with further development as
M1 Max and
M1 Ultra), later showing the next generation
M2(
M2 Pro,
M2 Max,
M2 Ultra). The list of current Intel series includes
Atom,
Celeron,
Pentium,
Core i3,
Core i5,
Core i7,
Core i9,
Core Ultra 9 and
Xeon. For AMD, in turn, this list looks like this:
AMD Athlon,
AMD FX,
Ryzen 3,
Ryzen 5,
Ryzen 7,
Ryzen 9 and
Ryzen Threadripper.
In general, each series includes processors of different generations, similar in general level and positioning. Here is a more detailed description of each of the options described above:
— Atom. Processors originally designed for mobile devices. Accordingly, they are distinguished by compactness, high energy efficiency and low heat dissipation, but they “do not shine” with performance. Perfect for microcomputers (see "Type"), among the more "large-format" systems are extremely rare — mostly in the most modest configurations.
— Celeron. Low-cost-level processors, the most simple and inexpensive consumer-level desktop chips from Intel, with the appropriate characteristics.
— Pentium. A family of low-cost desktop processors from Intel that is slightly more advanced than Celeron, but inferior to models from the Core i* series.
— Core i3. The simplest and most inexpensive series of desktop Core chips from Intel includes chips of the low-cost and inexpensive middle class, which, nevertheless, surpass Celerons and Pentiums in terms of performance.
— Core i5. Medium-level family among Intel Core processors; and in general, the chips of this series can be attributed to the average level by the standards of desktop systems.
— Core i7. A series of high-performance processors that has long been the top among Core chips; only in 2017 did it lose this position to the i9 family. However, the presence of an i7 processor still means a fairly powerful and advanced configuration; in particular, such CPUs are found in premium-level monoblocks, and are also quite popular in gaming systems.
— Core i9. The top series among Core processors, the most powerful among general purpose Intel desktop chips. In particular, the number of cores even in the most modest models is at least 6. Such chips are used mainly in gaming PCs.
— Xeon. High-end Intel processors, the capabilities of which go beyond the standard desktop chips. Designed for specialized applications, among PCs they are found mainly in powerful workstations.
— AMD FX. A family of processors from AMD, positioned as high-performance and at the same time inexpensive solutions, including for gaming systems. Interestingly, some models come standard with liquid cooling.
— Ryzen 3. AMD Ryzen chips (all series) are promoted as high-end solutions for gamers, developers, graphic designers and video editors. It was among these chips that AMD pioneered the Zen microarchitecture, which introduced simultaneous multithreading, which made it possible to significantly increase the number of operations per clock at the same clock frequency. And Ryzen 3 is the most inexpensive and modest family among the "ryzens" in terms of characteristics. Such processors are produced using the same technologies as the older series, however, half of the computing cores are deactivated in Ryzen 3. Nevertheless, this line includes quite performant models, designed, among other things, for gaming configurations and workstations.
— Ryzen 5. A family related to the middle level among Ryzen processors. The second series on this architecture, released in April 2017 as a more affordable alternative to Ryzen 7 chips. Ryzen 5 chips have slightly more modest performance characteristics (in particular, lower clock speeds and, in some models, L3 cache size). Otherwise, they are completely similar to the "sevens" and are also positioned as high-performance chips for gaming and workstations.
— Ryzen 7. Historically the first series of AMD processors based on the Zen microarchitecture (for more details, see "Ryzen 3" above). One of the older families among the "ryzens", in terms of performance it is second only to the Threadripper line; many PCs based on these chips are gaming.
— Ryzen Threadripper. Specialized Hi-End processors designed for maximum performance. They are mainly installed in gaming systems and workstations.
— Apple M1. A series of processors from Apple introduced in November 2020. They belong to mobile solutions (see "Type" above), are performed according to the system-on-chip scheme: a single module combines a CPU, a graphics adapter, RAM (in the first models — 8 or 16 GB), an NVMe solid-state drive and some other components (specifically Thunderbolt 4 controllers). Accordingly, among PCs, the main scope of such chips are compact nettops. As for the characteristics, in the initial configurations, the M1 processors are equipped with 8 cores — 4 performant and 4 economical; the latter, according to the creators, consume 10 times less energy than the former. This, combined with the 5nm process technology, has made it possible to achieve very high energy efficiency and at the same time performance.
— Apple M1 Max. An uncompromisingly powerful SoC with a focus on maximizing Apple desktop productivity for complex tasks. The Apple M1 Max line was introduced in the fall of 2021, it debuted on board Mac Studio computers.
Apple M1 Max consists of 10 cores: 8 of them are productive, and 2 more are energy efficient. The maximum amount of built-in combined memory reaches 64 GB, the “ceiling” of its bandwidth is 400 GB / s. The graphics performance of the Max version of the M1 single-chip system is about twice that of the Apple M1 Pro. The chip contains over 57 billion transistors. An additional accelerator for the professional ProRes video codec has also been introduced into its design, which allows you to easily play multiple streams of high-quality ProRes video in 4K and 8K frame resolutions.
— Apple M1 Ultra. Formally, the M1 Ultra chip consists of two Apple M1 Max processors on a single UltraFusion substrate, which allows information transfer at speeds up to 2.5 Tbps. In the language of "dry" numbers, this bundle consists of 20 ARM computing cores (16 high-performance and 4 energy efficient), a 64-core graphics subsystem and a 32-core neural computing unit. The system-on-chip supports up to 128 GB of combined memory. About 114 billion transistors are packed into the processor package. The main purpose of the Apple M1 Ultra is to confidently work with complex resource-intensive applications in the manner of processing 8K video or 3D rendering. In life, the processor can be found on board Mac Studio desktop computers.
In addition to the series described above, in modern PCs you can find the following processors:
—
AMD Fusion A4.... The entire Fusion processor family was originally created as integrated graphics devices, combining a central processing unit and a graphics card in one chip; such chips are called APU — Accelerated Processing Unit. Series with the index "A" are equipped with the most powerful integrated graphics in the family, which in some cases can compete on equal terms with inexpensive discrete video cards. The higher the number in the series index, the more advanced it is; A4 is the most modest series among Fusion A.
— AMD Fusion A6. A series of processors from the Fusion A line, relatively modest, but somewhat more advanced than the A4. For common features of all Fusion A, see "AMD Fusion A4" above.
— AMD Fusion A8. A rather advanced series of Fusion A processors, the middle option between the relatively modest A4 and A6 and the high-end A10 and A12. For common features of all Fusion A, see "AMD Fusion A4" above.
— AMD Fusion A9. Another advanced series from the Fusion A family, slightly inferior only to the A10 and A12 series. For common features of all Fusion A, see "AMD Fusion A4" above.
— AMD Fusion A10. One of the top series in the Fusion A line. See "AMD Fusion A4" above for general features of this line.
— AMD Fusion A12. The top series in the APU Fusion A line, introduced in 2015; positioned as professional-level processors with advanced (even by APU standards) graphics capabilities. For general features of the Fusion A range, see "AMD Fusion A4" above.
— AMD E-series. This series of processors belongs to the APU, like the Fusion A described above, however, it is fundamentally different in specialization: the main scope of the E-Series are compact devices, in the case of PCs, mostly nettops (see "Type"). Accordingly, these processors have compactness, low heat dissipation and power consumption, but their computing power is also low.
— Athlon X4. A series of low-cost consumer-level processors, originally released in 2015 as relatively inexpensive and at the same time relatively performant solutions for the FM + socket.
— AMD G. A family of ultra-compact and energy-efficient processors from AMD, made on the principle of "system on a chip" (SoC). Unlike many similar chips, it uses the x86 architecture, not ARM. Positioned as a solution for devices with an emphasis on graphics, in particular, gaming. However, we are not talking about gaming PCs: like most processors of a similar "weight category", AMD G is found mainly in thin clients (see "Type").
— VIA. Processors from the company of the same name, mainly related to energy-efficient "mobile" solutions — in particular, many VIA models are directly compared with Intel Atom. However, despite the modest performance, such CPUs are found even among desktop systems; and in the future, the company plans to create full-fledged desktop chips, competing with AMD and Intel.
— ARM Cortex-A. A group of processors from ARM, the creator of the microarchitecture of the same name and the largest manufacturer of chips based on it. A feature of this microarchitecture compared to the classic x86 is the so-called reduced instruction set (RISC): The processor operates with a simplified instruction set. This somewhat limits the functionality, but allows you to create more compact, "cold" and at the same time performant chips. For a number of reasons, the ARM architecture is mainly used in "mobile" processors designed for smartphones, tablets, etc. This is also true for the ARM Cortex-A series; in PCs, such CPUs are rarely installed, and usually we are talking about a compact, modest device like a “thin client” (see “Type”).
— Nvidia Tegra. Initially, these processors were created for portable devices, but recently they have also been installed in PCs, mainly in monoblocks. They are "system-on-chip" devices that do not use the "desktop" x86 architecture, but the "mobile" ARM architecture, which requires the use of appropriate operating systems; the most commonly used is Android (see "Preinstalled OS").
— Armada. Another type of ARM architecture processors, positioned as high-performance solutions for cloud computing and home servers, including NAS. It is found in single models of "thin clients" (see "Type").
— Tera. A specialized family of processors designed specifically for "thin clients" (see "Type") and fundamentally different from classic CPUs (both full-size and compact). Tera-based systems are usually full-fledged "zero clients" (zero client), absolutely not capable of autonomous operation. In other words, these are devices designed to create a "virtual desktop": the user works with the interface and terminal equipment (monitor, keyboard, mouse, etc.), but all operations take place on the server. This allows you to provide increased security when working with sensitive data. But in more traditional PCs, Tera processors are practically inapplicable.
Of the outdated series of processors that can still be found in use (but not for sale), we can mention the Sempron, Phenom II and Athlon II from AMD, as well as the Core 2 Quad and Core 2 Duo from Intel.
Note that on the market there are configurations that are not equipped with a processor — in the expectation that the user can pick it up on his own; however, this is a rather rare option.Model
The specific model of the processor installed in the PC, or rather, its index within its series (see "Processor"). The full model name consists of the series name and this index — for example, Intel Core i3 3220; knowing this name, you can find detailed information about the processor (characteristics, reviews, etc.) and determine how suitable it is for your purposes.
Speed
Clock speed of the CPU installed in the PC.
In theory, higher clock speeds have a positive effect on performance because they allow the CPU to perform more operations per unit of time. However, this indicator is rather weakly related to real productivity. The fact is that the actual capabilities of the CPU strongly depend on a number of other factors - the overall architecture, cache size, number of cores, support for special instructions, etc. As a result, you can compare by this indicator only chips from the same or similar series (see “CPU”), and ideally, also from the same generation. And that's pretty approximate.
Memory type
The type of RAM used in the computer. This indicator describes both the general level of "RAM" and the possibilities for replacing and upgrading it: different types of RAM are not compatible with each other.
Here are the types of memory that are relevant for modern PCs:
—
DDR3. The third generation of RAM with the so-called double data transfer. Some time ago, this standard was the most popular in computer technology, but now it is increasingly losing ground to newer and more advanced standards, primarily DDR4. In compact computers, there is a "mobile", energy-saving version of this memory standard — LPDDR3.
—
DDR3L. A modification of DDR3 memory that supports operation at a reduced voltage — 1.35 V instead of 1.5 V (Low Voltage — hence the index L). Lower voltage improves performance. These modules are compatible with classic DDR3 slots.
—
DDR4. Further, after DDR3, the development of the DDR standard, released in 2014. It features both increased performance and increased volumes — the capacity of one bar can be from 2 to 128 GB. Thus, the maximum amount of RAM in most PCs is limited more by the capabilities of the motherboard than by the characteristics of existing brackets. DDR4 is very popular in modern computer technology, including desktop PCs.
Speed
The clock speed of the RAM that comes with the PC. This is one of the parameters that determine the capabilities of RAM: with the same amount and type of memory (see above), a higher clock frequency will mean faster performance. However such details are rarely required by an ordinary user, but they are important for enthusiasts and professionals.
Also note that this indicator can be used to determine the possibilities for upgrading the system: the motherboard will be able to work normally with brackets that have the same or lower clock frequency, but compatibility with faster memory should be specified separately.
Graphics card type
The type of graphics card used in the PC. Modern computers can be equipped with both
integrated modules (among those you can find products of
Apple and
Intel –
HD Graphics,
UHD Graphics and
Iris) and
discrete video cards (including
professional ones), which can be installed in several pieces using
SLI or CrossFire technology. In addition, on the market you can find configurations that are not equipped with graphics adapters at all. Here is a more detailed description of each option:
— Integrated. Video cards that are built directly into the processor (less often, into the motherboard) and do not have their own dedicated memory: the memory for video processing is taken from the general “RAM”. The main advantages of such modules are low cost, low power consumption, minimal heat release (which does not require special cooling systems), and extremely compact dimensions. On the other hand, the performance of this type of graphics is low: it is enough for simple everyday tasks like web surfing, watching videos and undemanding games, but for more serious purposes it is still desirable to have a discrete video adapter in the system. And the fact that integrated systems take
...up part of the system RAM during operation does not contribute to performance either.
— Discrete. Video cards in the form of separate modules with a specialized processor and their own memory. They are noticeably more expensive than integrated ones, take up more space and consume more energy, but all these shortcomings are offset by a key advantage — high performance. This allows you to work even with “heavy” graphic content like modern games, 3D rendering, high-resolution video editing, etc. (although the specific characteristics of discrete graphics, of course, may be different). In addition, graphics processing in such systems does not use the main RAM, which is also an important advantage. For additional performance enhancement, discrete video adapters can be combined into SLI / CrossFire systems, this option is indicated separately (see below). Also note that in most modern PCs, such graphics are combined with a processor with an integrated graphics core, and often work in hybrid mode: the integrated module is used for simple tasks, and when the load increases, the system switches to a discrete graphics card.
— SLI/CrossFire. Several discrete video cards (see above) bundled using SLI technology (NVIDIA is used) or Crossfire (AMD is used). From the point of view of an ordinary user, there are no fundamental differences between these technologies: both of them allow you to combine the computing power of several video cards, thus increasing graphics performance. However, such graphics are not cheap, and therefore they are used exclusively in high-performance PCs with an emphasis on graphic capabilities — in particular, gaming ones.
— Sold separately. The absence of any graphics card in the initial configuration of the PC. A rather rare option found in some high-end workstations: such configurations are equipped with professional processors without an integrated graphics core and do not have discrete graphics — it is assumed that such an adapter is more convenient for the user to buy separately.Graphics card model
The main manufacturers of video cards nowadays are
AMD,
NVIDIA and Intel, and each has its own specifics. NVIDIA produces primarily discrete solutions; Among the most common are
the GeForce MX1xx,
GeForce MX3xx,
GeForce GTX 10xx series (in particular
GTX 1050,
GTX 1050 Ti and
GTX 1060),
GeForce GTX 16xx,
GeForce RTX 20xx,
GeForce RTX 30xx(
GeForce RTX 3060,
GeForce RTX 3060 Ti,
GeForce RTX 3070,
GeForce RTX 3070 Ti,
GeForce RTX 3080,
GeForce RTX 3080 Ti, GeForce RTX 3090,
GeForce RTX 3090 Ti),
GeForce RTX 4060 , GeForce RTX 4060 Ti,
GeForce RTX 4070,
GeForce RTX 4070 SUPER,
GeForce RTX 4070 Ti,
GeForce RTX 4070 Ti SUPER,
Ge Force RTX 4080,
GeForce RTX 4080 SUPER,
GeForce RTX 4090 and separate
Quadro series. AMD offers both discrete and integrated graphics - including the popular
Radeon RX 500,
Radeon RX 5000,
Radeon RX 6000,
Radeon RX 7000 and
AMD Radeon Pro series. And Intel deals exclusively with modules integrated into processors of its own production - these can be HD Graphics, UHD Graphics and Iris.
Note that many configurations with discrete graphics also have an integrated graphics module; in such cases, the name of the discrete video card is indicated as more advanced.
Graphics memory
The amount of native memory provided by the discrete graphics card (see "Graphics card type").
The larger this volume, the more powerful and advanced the video adapter is, the better it handles with complex tasks and, accordingly, the more expensive it is. Nowadays,
2 GB and
3 GB are considered quite modest,
4 GB are not bad,
6 GB and
8 GB are very solid, and more than 8 GB means that we have a specialized PC built for maximum graphics performance.
Memory type
The type of graphics memory used by the discrete graphics card (see "Video Card Type").
In most of these adapters, GDDR graphics memory is installed — a kind of regular DDR "RAM", optimized for use with graphics tasks. This memory is available on the market in several versions; in addition, there are other varieties. Here is a more detailed description of the different options:
— GDDR3. At one time — a fairly common type of graphic memory; today, however, it is considered obsolete and is not used in new PCs.
— GDDR5. The most popular (for 2020) type of GDDR graphic memory. At a reasonable cost, it provides good performance, due to which it is found in computers of different price categories.
— GDDR5X. Modification of the above-mentioned GDDR5, characterized by a 2-fold increased throughput. Accordingly, the performance of such memory (with the same volumes) is noticeably higher; on the other hand, such modules are expensive.
— GDDR6. The newest of the GDDR standards for 2020 — the first video cards based on this type of memory were introduced in 2018. It differs from its immediate predecessor — GDDR5X — in both increased bandwidth and lower operating voltage, which provides both increased efficiency and reduced power consumption. It is also worth noting that GDDR6 was developed with specific applications in mind, such as VR or work with resolutions above 4K UHD.
— HBM2. The original HBM is a type of RAM d...esigned to maximize the speed of data exchange; HBM2 is the second version of this technology, in which the bandwidth compared to the original HBM has been doubled. Such a memory is fundamentally different from DDR in terms of device — in particular, the memory cells in it are placed in layers and allow simultaneous access. Thanks to this, HBM is several times faster than the fastest versions of GDDR, which makes this technology perfect for high workloads such as processing UltraHD graphics and virtual reality. At the same time, the clock frequency of such modules is low and, accordingly, power consumption and heat dissipation are small. The disadvantage of this option is traditional — the high price.
— DDR3. Memory that does not have a specialization for graphics — in other words, the same DDR3 that is used in RAM sticks (see "Memory Type" above). In the case of video cards, such solutions are completely obsolete and are almost never used nowadays.