What do the letters at the end of the processor mean? Processor markings from Intel and AMD. New letter indices

When choosing a processor from Intel, the question arises: which chip from this corporation to choose? Processors have many characteristics and parameters that affect their performance. And in accordance with it and some features of the microarchitecture, the manufacturer gives the appropriate name. Our task is to highlight this issue. In this article, you will learn what exactly the names of Intel processors mean, and also learn about the microarchitecture of chips from this company.

Note

It should be noted in advance that solutions before 2012 will not be considered here, since technology is moving at a fast pace and these chips have too little performance with high power consumption, and are also difficult to buy in new condition. Also, server solutions will not be considered here, since they have a specific scope and are not intended for the consumer market.

Attention, the nomenclature set out below may not be valid for processors older than the period indicated above.

And if you encounter any difficulties, you can visit the website. And read this article, which talks about. And if you want to know about integrated graphics from Intel, then you should.

Tick-Tock

Intel has a special strategy for releasing its “stones”, called Tick-Tock. It consists of annual consistent improvements.

• A tick means a change in microarchitecture, which leads to a change in socket, improved performance and optimized power consumption.
• This means that it leads to a reduction in power consumption, the possibility of placing a larger number of transistors on a chip, a possible increase in frequencies and an increase in cost.

This is what this strategy looks like for desktop and laptop models:

“TICK-TOCK” MODEL IN DESKTOP PROCESSORS

MICROARCHITECTURE	STAGE	EXIT	TECHNICAL PROCESS
Nehalem	So	2009	45 nm
Westmere	Teak	2010	32 nm
Sandy Bridge	So	2011	32 nm
Ivy Bridge	Teak	2012	22 nm
Haswell	So	2013	22 nm
Broadwell	Teak	2014	14 nm
Skylake	So	2015	14 nm
Kaby Lake	So+	2016	14 nm

But for low-power solutions (smartphones, tablets, netbooks, nettops), the platforms look like this:

MICROARCHITECTURES OF MOBILE PROCESSORS

CATEGORY	PLATFORM	CORE	TECHNICAL PROCESS
Netbooks/Nettops/Notebooks	Braswell	Airmont	14 nm
	Bay Trail-D/M	Silvermont	22 nm
Top tablets	Willow Trail	Goldmont	14 nm
	Cherry Trail	Airmont	14 nm
	Bay Tral-T	Silvermont	22 nm
	Clower Trail	Satwell	32 nm
Top/mid-range smartphones/tablets	Morganfield	Goldmont	14 nm
	Moorefield	Silvermont	22 nm
	Merrifield	Silvermont	22 nm
	Clower Trail+	Satwell	32 nm
	Medfield	Satwell	32 nm
Mid-range/budget smartphones/tablets	Binghamton	Airmont	14 nm
	Riverton	Airmont	14 nm
	Slayton	Silvermont	22 nm

It should be noted that Bay Trail-D is made for desktops: Pentium and Celeron with the index J. And Bay Trail-M for is a mobile solution and will also be designated among Pentium and Celeron by its letter - N.

Judging by the company's latest trends, performance itself is progressing quite slowly, while energy efficiency (performance per unit of energy consumed) is growing year by year, and soon laptops will have the same powerful processors as large PCs (although such representatives still exists).

Choosing a processor is quite a serious task, which should be approached only after you have thoroughly familiarized yourself with all the nuances and characteristics. Much can be learned from the name of the processor, its markings, which contain information about the main characteristics of this model. What these characteristics mean is possible, and in this article we will talk about how to decipher the processor markings.

Intel processor markings

1. Intel processor series
   • I7– top processors that support all Intel technologies, have 4 cores, and are equipped with an 8 MB L3 cache memory.
   • I5– mid-price segment processors can have from 2 to 4 cores. Equipped with L3 cache memory with a capacity of 3 to 6 MB. There is no support for Trusted Execution, Hyper-Threading and Virtualization Technology.
   • I3– a budget series of processors, has 2 cores and an L3 cache with a capacity of 3 MB.
2. Indicates the generation of the processor series Core i-x. SandyBridje is marked with the number 2, IvyBridge is marked with the number 3.
3. Indicates position in the series. The higher the number, the faster the processor runs. Depends on the clock frequency.
4. Processor version
   • K– such a processor has an unlocked multiplier, which means it can be overclocked.
   • M– processor used in mobile devices (smartphone, tablet).
   • P– processor without automatic overclocking.
   • S– such processors have reduced power consumption to 65 W.
   • T– these processors have reduced power consumption to 45/35 W.

AMD processor markings

Processors without a GPU video core.

1. Indicates the processor series.
2. Talks about the number of cores in the processor.
3. Indicates the processor architecture: number 2 – Bulldozer , 3 – Piledriver.
4. Determines the position of the model in the family; in most cases, it depends on the processor clock speed.

Processors with a built-in GPU video core.

1. Talks about the number of processor cores and the presence of a GPU video core.
   • A10– there are 4 CPU cores and a Radeon HD 7660D video core (here and below for the Trinity architecture).
   • A8— 4 CPU cores and a Radeon HD 7560D video core.
   • A6— 2 CPU cores and a Radeon HD 7540D video core are available.
   • A4— 2 CPU cores and a Radeon HD 7480D video core are available.
2. Indicates the processor generation.
3. This marking depends on the frequency; the higher the frequency, the greater the value.

The processors I presented are mainly used in the home segment. Since server processors are designed for their own purposes, they should be considered in a separate topic.

Today, the fastest on the list are the PHENOM II processors. They are released on the new K10.5 architecture with Shanghai (Deneb), Propus cores. A special feature compared to the K10 architecture presented below is the transition to a 45 nm process technology, which significantly reduces the heat dissipation (TDP) of processors! It consists of ~705 million transistors and has an area of ​​243 mm2. (versus 463 million and 283 mm square, respectively, for 65 nm Barcelona). PHENOM II processors differ from their predecessors PHENOM by an increased L3 cache (from 2 MB to 6 MB), as well as minor architectural optimizations.

K10.5 Architecture Specifications
-technical process: 45nm SOI
-core area: 243 sq.mm
-number of transistors: ~705 million
-voltage:0.875-1.5V
-Socket: AM3(941 pin)

K10 Architecture Specifications
-technical process: 65nm SOI
-core area: 283 sq.mm
-number of transistors: 463 million
-voltage:1.05V-1.38V
-Socket: AM2+(940 pin)/F(1207 pin)

Architecture Features

The main difference between K10 generation processors and their predecessors based on K8 is the combination of four cores on one chip, updates to the Hyper-Transport protocol to version 3.0, a common L3 cache for all cores, as well as promising support for DDR3 memory controller. The cores themselves have also been upgraded from the K8 cores.

Direct Connect Architecture
-Allows you to increase performance and efficiency by directly connecting the memory controller and I/O channel to the core.
-Designed to perform both 32-bit and 64-bit calculations simultaneously.
Integration of a DDR2 memory controller (up to 533 (1066) MHz mode, as well as future support for DDR3)
Advantages:
-Increasing application performance by reducing latency when accessing memory
-Distributes memory bandwidth depending on requests
-Hyper-Transport technology delivers connections at peak speeds of up to 16.0 GB/sec to prevent latency
-Up to 33.1 GB/sec total bandwidth between processor and system (including Hyper-Transport bus and memory controller)

AMD Balanced Smart Cache
-2 MB L3 cache shared across all cores in addition to 512 KB L2 cache per core
Advantages:
-Reduce latency when accessing frequently used data to improve performance

AMD Wide Floating Point Accelerator
-128-bit FPU (floating point unit) for each core
Advantages:
-Acceleration of data sampling and processing in floating point calculations.

HyperTransport™ technology
-One 16-bit channel with a speed of 4000Mt/s
-Hyper-Transport connection with peak speeds up to 8.0Gb/sec and up to 16.0Gb/sec when operating in Hyper-Transport 3.0 mode
-Up to 33.1 GB/sec total bandwidth between the processor and the system (including the Hyper-Transport bus and memory controller)
Advantages:

Integrated DDR2 DRAM Controller with AMD Memory Optimizer Technology
-Integrated memory controller with high bandwidth and low latency
-Support PC2-8500 (DDR2-1066); PC2-6400 (DDR2-800), PC2-5300 (DDR2-667), PC2-4200 (DDR2-533) and PC2-3200 (DDR2-400) unbuffered memory modules
-Supports 64-bit DDR2 SDRAM
-Bandwidth up to 17.1Gb/sec
Advantages:
-Quick access to system resources to increase productivity

AMD Virtualization™ (AMD-V™) With Rapid Virtualization Indexing
-Hardware feature set designed to improve performance, reliability and security in current and future virtualization environments, allowing virtual machines to directly access allocated memory
Advantages:
-Allows software to create more secure and efficient virtual machines

AMD Cool'n'Quiet™ 2.0 technology
-Advanced power management system that automatically adjusts processor performance depending on load
-Reduced power consumption and cooler rotation speed during idle mode
Advantages:
-Allows the system to consume less power and minimize cooling system noise

AMD CoolCore™ Technology & Dual Dynamic Power Management™
-Allows you to reduce power consumption by turning off unused parts of the processor.
- Separate system for memory controller and processor logic allows voltage control and shutdown independently of each other
-Works automatically without the need for driver or BIOS support
-Allows independent control of the frequencies of each core
-The speed of switching operating modes is equal to one cycle of the processor core
Advantages:
-Allows you to more efficiently use the processing power of the kernel by disabling its unused parts

TLB bug
In connection with Agena and Barcelona processors (AMD), the so-called TLB bug or TLB error is often mentioned. This error occurs in all quad-core AMD processors revision B2 and can, in very rare cases, lead to unpredictable system behavior under high loads. This error is critical in the server segment, which caused the suspension of all deliveries of Barcelona (AMD) processors of revision B2. For desktop Phenom processors, a TLB patch was proposed that prevents the error from occurring by disabling part of the TLB logic. This patch, although it saves us from the TLB bug, also negatively affects performance. The error was fixed in revision B3.

AMD PHENOM PROCESSOR SPECIFICATIONS
Model Frequency L2 cache L3 cache Core Technology Stepping Power System Bus Mt/s
Socket AM3 compatible with AM2+
AMDPhenom II X4 9553200Mhz512KBx46MBDeneb45nm C2 125W4000 Black Edition HDZ955FBK4DGI
AMDPhenom II X4 9453000Mhz512KBx46MBDeneb45nm C2 125W4000
AMDPhenom II X4 9252800Mhz512KBx46MBDeneb45nm C2 95W4000
AMDPhenom II X4 9102600Mhz512KBx46MBDeneb45nm C2 95W4000
AMDPhenom II X4 8102600Mhz512KBx44MBDeneb45nm C2 95W4000
AMDPhenom II X4 8052500Mhz512KBx44MBDeneb45nm C2 95W4000
AMDPhenom II X3 7202800Mhz512KBx36MBHeka45nm C2 95W4000 Black Edition HDZ720WFK3DGI
AMDPhenom II X3 7102600Mhz512KBx36MBHeka45nm C2 95W4000
Socket AM2+ compatible with AM2
AMD Phenom II X4 9403000Mhz512KBx46MBDeneb45nm C2 125W 3600 Black Edition HDZ940XCJ4DGI
AMD Phenom II X4 9202800Mhz512KBx46MBDeneb45nm C2 125W 3600
AMD Phenom X4 9950 2600Mhz512KBx42MBAgena65nm B3 140W4000 Black Edition HD995ZFAJ4BGH
AMDPhenom X4 99502600Mhz512KBx42MBAgena65nm B3 125W4000 Black Edition HD995ZXAJ4BGH
AMDPhenom X4 98502500Mhz512KBx42MBAgena65nm B3 125W4000 Black Edition* HD985ZXAJ4BGH
AMDPhenom X4 97502400Mhz512KBx42MBAgena65nm B3 125W3600
AMDPhenom X4 97502400Mhz512KBx42MBAgena65nm B3 95W3600
AMDPhenom X4 96502300Mhz512KBx42MBAgena65nm B3 95W3600
AMDPhenom X4 96002300Mhz512KBx42MBAgena65nm B2 95W3600 Black Edition HD960ZWCJ4BGD
AMDPhenom X4 95502200Mhz512KBx42MBAgena65nm B3 95W3600
AMDPhenom X4 95002200Mhz512KBx42MBAgena65nm B2 95W3600
AMDPhenom X4 9450e2100Mhz512KBx42MBAgena65nm B3 65W3600
AMDPhenom X4 9350e2000Mhz512KBx42MBAgena65nm B3 65W3200
AMDPhenom X4 9150e1800Mhz512KBx42MBAgena65nm B3 65W3200
AMDPhenom X4 9100e1800Mhz512KBx42MBAgena65nm B2 65W3200
AMDPhenom X3 88502500Mhz512KBx32MBToliman65nm B3 95W3600
AMDPhenom X3 87502400Mhz512KBx32MBToliman65nm B3 95W3600 Black Edition HD875ZWCJ3BGH
AMDPhenom X3 86502300Mhz512KBx32MBToliman65nm B3 95W3600
AMDPhenom X3 86002300Mhz512KBx32MBToliman65nm B2 95W3600
AMDPhenom X3 85502200Mhz512KBx32MBToliman65nm B3 95W3600
AMDPhenom X3 84502100Mhz512KBx32MBToliman65nm B3 95W3600
AMDPhenom X3 8450e2100Mhz512KBx32MBToliman65nm B3 65W3600
AMDPhenom X3 84002100Mhz512KBx32MBToliman65nm B2 95W3600
AMDAthlon X2 7850 2800Mhz512KBx22MBKuma65nm B3 95w3600 Black Edition AD785ZWCJ2BGH
AMDAthlon X2 7750 2700Mhz512KBx22MBKuma65nm B3 95W3600 Black Edition* AD775ZWCJ2BGH
AMDAthlon X2 7550 2500Mhz512KBx22MBKuma65nm B3 95W3600

*Attention! Some versions of the same processors with an unlocked Black Edition multiplier may come without the Black Edition prefix, i.e. with a locked multiplier. You can find out more information on the AMD website!
Deciphering the markings of Phenom processors using the example of HDZ940XCJ4DGI:
H - brand: Phenom (for Athlon processors it would be letter A)

Z - Black Edition unlocked multiplier (for locked X)
940 - model: 940
XC - series: 125 W, desktop, dual power (models with 65 and 95 W thermal packages have different letter combinations)
J - packaging: AM2r2 (corresponds to AM2+)
4 - number of cores: 4 (sometimes 3 or 2)
D - cache size: L2 512 KB per core and shared L3 6 MB (the symbol B means L2 512 KB per core and shared L3 2 MB)
GI - revision: C2 (there may be other letters for other revisions - B2/B3)

Athlon 64 is AMD's first 64-bit processor for home and mobile use, which was introduced on September 23, 2003. The processor is built on the AMD64 architecture and belongs to the eighth generation (K8).

The development of the K8 architecture was first announced in 1999. Processors based on this core were supposed to be the first 64-bit AMD processors fully compatible with the x86 standard.
The processor comes in 3 variants: Athlon 64, Athlon 64 FX and dual-core Athlon 64 X2. The Athlon 64 FX is positioned as a product for computer enthusiasts, always remaining one step faster than the Athlon 64. Although their frequencies are generally higher, all Athlon 64 FX processors are single-core designs, with the exception of the Athlon 64 FX-60 and Athlon FX- 62. They are now available for Socket 939 and Socket AM2. This release is similar to the Athlon 64 FX-53, which was initially only available for the high-end Socket 940 platform, with a Socket 939 version introduced later. All Athlon 64 FX processors have an unlocked multiplier for easy overclocking, unlike the Athlon 64, which can only be set to a multiplier less than or equal to the factory preset one. Since all these processors are built on the AMD64 architecture, they are capable of working with 32-bit x86, 16-bit and AMD64 code.

The original Athlon 64 core is codenamed "Clawhammer", despite the fact that the first Athlon 64 FX was based on the first Opteron core, codenamed "Sledgehammer". Athlon 64 had several kernel revisions; a list of them can be found in the list.

The Athlon 64 has a built-in copper plate - the Integrated Heat Spreader (IHS) which prevents damage to the core when installing and removing the cooling system (a common problem with open-core processors such as the Athlon XP).

In 2006, AMD announced the discontinuation of all Socket 939 processors, all single-core socket AM2 processors, and all 2-1 MB X2 processors (except for the FX-62).

Basic properties

The main quality of the Athlon 64 processors is the memory controller integrated into the core, which was not the case in previous generations of CPUs. Not only the fact that this controller operates at the frequency of the processor core, but also the fact that an extra link, the north bridge, has disappeared from the processor-memory connection, which has made it possible to significantly reduce delays when accessing RAM.

The Translation Lookaside Buffer (TLB) has also been increased, while latency has been reduced and the branch prediction module has been improved. These and other architectural enhancements, especially support for SSE extensions and increased instructions per clock (IPC), increased performance over the previous generation Athlon XP. To make it easier to select and understand performance, AMD has developed a so-called performance index system (PR rating (Performance Rating)) for labeling the Athlon 64 processor, which numbers processors depending on their performance compared to Pentium 4 processors. That is, if the Athlon 64 is labeled 3200+, this means that this processor has performance similar to that of the Pentium 4 processor at 3.2 GHz.

The Athlon 64 also has a technology for changing the processor clock speed, called Cool"n"Quiet. If the user runs applications that do not require a lot of processing power from the processor, then the processor independently lowers its clock frequency, as well as the core voltage. The use of this technology makes it possible to reduce heat dissipation at maximum load from 89 W to 32 W (C0 stepping, core frequency reduced to 800 MHz), and even to 22 W (CG stepping, core frequency reduced to 1 GHz).

No Execute bit (NX bit) technology, supported by Windows XP Service Pack 2, Windows XP Professional x64 Edition, Windows Server 2003 x64 Edition and Linux kernel 2.6.8 and older, is designed to protect against a common attack - buffer overflow errors. Hardware-based access levels are a much more reliable means of protecting against intrusion to seize control of the system. This makes 64-bit computing more secure.

The Athlon 64 processor is manufactured using a 130 nm process technology and 90 nm SOI. All the latest cores (Winchester, Venice and San Diego) are produced using the 90 nm process technology. The Venice and San Diego cores are also manufactured using Dual Stress Liner technology, developed jointly with IBM.
Since the memory controller is integrated into the processor core, the system bus is no longer used to transfer data from the processor to memory. Instead, system memory speed is obtained from the following formula (using rounding up to the nearest integer):
Notes:
The processor speed value (CPU speed) is obtained by multiplying the base frequency by the multiplication factor. The base frequency for all Socket 754, 939 and 940 Athlon 64 models is 200 MHz;
Socket 754, 939 and 940 Athlon 64 processors were designed to work with 100 MHz (DDR 200 or PC1600), 133 MHz (DDR 266 or PC2100), 166 MHz (DDR 333 or PC2700) and 200 MHz (DDR 400 or PC3200) modules DRAM. The most commonly used modules are DDR 400, in which the memory and processor operate in synchronous mode (the divisor is 1:1). However, the E4 and earlier Athlon 64 and Socket 754 Sempron processor steppings had a memory controller capable of handling non-JEDEC-approved 216.7 MHz (DDR 433 or PC3500), 233 MHz (DDR 466 or PC3700) and 250 MHz (DDR 500 or PC4000) without overclocking the processor.

Athlon 64 (Clawhammer/K8)
Clawhammer processors are based on the new AMD K8 architecture, which is a significant improvement and extension of the AMD K7 architecture. A new mode of 64-bit integer and x86-64 address arithmetic has been added, new RAM addressing modes have been added, and support for the Intel SSE2 instruction has been added. The branch prediction mechanism has been significantly improved. Larger second level cache. The decoders have been significantly redesigned, which has eliminated a number of unpleasant delays in performance inherent in the K7. The number of conveyor stages has increased to 12, versus 10 for K7. The L2 cache has become dual-port: it is connected to the core by a 64-bit write bus + 64-bit read bus. K8 processors also abandoned the use of FSB (Front Side Bus). Instead, the memory controller is integrated into the processor core, which significantly reduces latency when accessing RAM.

In fact, Clawhammer consists of three partially asynchronous blocks connected into a single whole by a special switch (X-bar): the actual core of the K8 architecture with 1 MB of L2 cache; a memory controller that allows the use of single-channel or dual-channel DDR memory; I/O controller that provides high-speed serial HyperTransport buses, which serve for communication with other processors and the chipset. The Clawhammer core has three 16-bit coherent HyperTransport buses operating at 800 MHz (1600 megatransfers per second), which provides a memory bandwidth of 3.2 GB/s for transmitting + 3.2 GB/s for receiving simultaneously on each of the buses. In fact, the combination of up to 8 processors using the NUMA architecture (“Non-Uniform Memory Access”) with direct connections between processors is supported. The Athlon 64 processor is also equipped with a heat dissipation cover similar to that used by the Pentium 4. K8-core processors use a new Cool"n"Quiet technology designed to reduce processor power consumption when idle.

The first Athlon 64 models based on the Clawhammer core were released in September 2003. All of them were manufactured using a 130 nm process technology. The L1 cache remains the same as it was in the Athlon on the K7 core. The core supply voltage is 1.5 V, the number of transistors is 105.9 million, and the die area is 193 mm2. The L2 cache size for Clawhammer processors was 256 KB (Athlon 64 3300+, which was produced specifically for HP), 512 KB (Athlon 64 2800+, 3000+, 3500+, 3400+, the latter was produced specifically for HP) or 1024 KB ( Athlon 64 3200+, 3400+, 3700+, 4000+). Processors were produced in OmPGA cases for both Socket 754 (Athlon 64 2800+, 3000+, 3200+, 3300+, 3400+, 3700+) and Socket 939 (Athlon 64 3400+, 3500+, 4000+), the first The latter were equipped with a single-channel, and the latter with a dual-channel DDR400 memory controller. When operating at maximum frequency, it consumes 57.4 A and dissipates 89.0 W of heat. Athlon 64 processors were released with the following ratings (operating frequency in MHz is indicated in brackets): 2800+ (1800), 3000+ (2000), 3200+ (2000), 3300+ (2400), 3400+ (2200), 3500+ (2200), 3700+ (2400), 4000+ (2400).

Athlon 64 (Newcastle/K8)
The first models based on this core were released in April 2004. In essence, Newcastle is the same Clawhammer, which has undergone a slight modernization. This kernel introduced the NX-bit function, which serves to prevent the execution of arbitrary code when errors related to buffer overflow occur (buffer overflow is very often used by viruses to penetrate the victim’s computer). The cache memory for all processors based on this core is 512 KB. The core supply voltage is 1.5 V, the number of transistors included in the core is 68.5 million, and the core die area is 144 mm2. Processors on this core were produced for Socket 754 (Athlon 64 2600+, 2800+, 3000+, 3200+, 3400+) and had a single-channel DDR400 memory controller; all other processors were produced for Socket 939, had a dual-channel DDR400 memory controller and differed from similar processors for Socket 754 with a clock frequency reduced by 200 MHz. When operating at maximum frequency, it consumes 57.4 A and dissipates 89.0 W of heat. Athlon 64 processors were released with the following ratings (operating frequency in MHz is indicated in brackets): 2600+ (1600), 2800+ (1800), 3000+ (2000), 3000 (1800), 3200+ (2200), 3200+ ( 2000), 3400+ (2400), 3400+ (2200), 3500+ (2200), 3800+ (2400).

Athlon 64 (Winchester/K8)
The first processor models based on this core were released in September 2004. The core is Newcastle, manufactured using a 90 nm process technology. Characterized by the same number of transistors, the same amount of cache memory (with the exception of the Athlon 64 3700+ model, equipped with 1024 KB L2). All processor models based on this core are designed for Socket 939 and are equipped with a 2-channel DDR400 memory controller. The supply voltage of this core is 1.4 V, the crystal area, due to the use of the latest technological process, has been reduced to 84 mm?. When operating at maximum frequency, it consumes 54.8 A and dissipates 67.0 W of heat. Athlon 64 processors were released with the following ratings (operating frequency in MHz is indicated in brackets): 3000+ (1800), 3200+ (2000), 3500+ (2200), 3700+ (2200).

Athlon 64 (San Diego/K8)
The first models were released in April 2005. This core is a redesigned Winchester-Newcastle core. New instructions have been added to provide compatibility with Intel SSE3 instructions. The memory controller has been updated: according to official information, it is now capable of working in dual-channel mode with memory types DDR433, DDR466 and DDR500. The processor is released only for Socket 939 (at least, Athlons based on this core have not yet been seen for Socket 754). The L2 cache has a capacity of 1024 KB, except for the Athlon 64 3500+, in which the L2 cache is 512 KB. The core voltage is 1.35-1.4 V (variable CPU core voltage). The core includes 114 million transistors and has an area of ​​115 mm2. When operating at maximum frequency, it consumes 57.4 A and dissipates 89.0 W of heat. Athlon 64 processors were released with the following ratings (operating frequency in MHz is indicated in brackets): 3500+ (2200), 3700+ (2200), 4000+ (2400).

Athlon 64 (Venice/K8)
The first models were released in April 2005. Essentially, this core is a San Diego with 512 KB of L2 cache. The number of transistors included in the core is 76 million, the core crystal area is 84 mm2. When operating at maximum frequency, it consumes 57.4 A and dissipates 89.0 W of heat. Athlon 64 processors were released with the following ratings (operating frequency in MHz is indicated in brackets): 3000+ (1800), 3200+ (2000), 3400+ (2200), 3500+ (2200), 3800+ (2400).

Athlon 64 FX (ClawHammer - SledgeHammer/K8)
The first model was released in September 2003. It is an “extreme” version of the Athlon 64. The core is a kind of hybrid between the ClawHammer and SledgeHammer cores (used in AMD Opteron server processors), although AMD claims that this core is exclusively a ClawHammer. The first models were released in the CmPGA package and were intended for Socket 940 (used by Opteron processors), these were the Athlon 64 FX-51 and FX-53. Then processors were released in the OmPGA package for Socket 939 (Athlon 64 FX-53 and FX-55.). The core supply voltage is 1.5 V. The number of transistors making up the core is 105.9 million, the crystal area is 193 mm2. The processor was produced using a 130 nm process technology. The L2 cache size is 1024 KB. When operating at maximum frequency, it consumes 67.4 A and dissipates 104.0 W of heat. Athlon 64 processors were released with the following indices (operating frequency in MHz is indicated in brackets): FX-51 (2200), FX-53 (2400), FX-55 (2600).

Athlon 64 FX (San Diego/K8)
The first model was released in April 2005. It is an “extreme” version of the Athlon 64 based on the San Diego core. When operating at maximum frequency, it consumes 80 A and dissipates 110.0 W of heat. Athlon 64 processors were released with the following indices (operating frequency in MHz is indicated in brackets): FX-55 (2600), FX-57 (2800). A little later, Athlon 64 on the San Diego core was released: 4000+(2400), 3700+(2200).

K9
The K9 core (K9 is the unofficial name for a series of multi-core processors built on the AMD K8 base. AMD itself does not use this name due to its consonance with “canine” - Latin dog) is a processor with two cores housed in one package (chip) .

Athlon 64 X2 (Manchester/Toledo/K8)
Each core has its own L1 and L2 cache, the memory controller and HyperTransport bus controller for both cores are common. The Athlon 64 X2 has an OmPGA case and is designed for Socket 939. There is also a dual-channel memory controller with support for DDR400. The core functionality is similar to San Diego and Venice. The Manchester core is characterized by the presence of 512 KB of L2 on board for each core. Processors based on the Toledo core were initially equipped with 1024 KB L2 for each core, but then processors based on the Toledo core were released with 512 KB L2 for each core (Toledo 1M, which replaced the Manchester core).

The first models were released in June 2005. The core supply voltage is 1.35-1.4 V. Cores with 512 KB L2 per core (Manchester and Toledo 1M) contain 154 million transistors, and the core die area is 147 mm?, cores with 1024 KB L2 per core (Toledo) contains 233 million transistors, and the core die area is 205 mm square. When operating at maximum frequency, it consumes 80 A and dissipates 110 W of heat. Athlon 64 X2 processors were released with the following indices (the operating frequency in MHz is indicated in parentheses, the total L2 capacity in MB is indicated after a slash): 3800+ (2000/1), 4200+ (2200/1), 4400+ (2200/2) , 4600+ (2400/1), 4800+ (2400/2).

Athlon 64 FX-60 (Toledo)
The model was released in January 2006. This is the first dual-core processor in the FX series. The cache memory size is 1024 KB for each core. In general, it is identical to the Athlon 64 X2 processors based on the Toledo core. The processor clock frequency is 2600 MHz.

Mobile Athlon XP-M (Dublin)
The first model was released in May 2004. The core is based on the K8 core. Only two models of Mobile Athlon XP-M 2800+ and 3000+ were released, the first has an L2 cache of 128 KB, the second - 256 KB. The core supply voltage is 1.4 V in normal mode and 0.95 V in energy-saving mode (PowerNow! technology). The processors are designed for Socket 754 and have an OmPGA package type. The number of transistors making up the core is 68.5 million, the area of ​​the core crystal is 144 mm2, the processor was manufactured using a 130 nm process technology. The clock speed of both processors is 1600 MHz in normal mode and 800 MHz in energy-saving mode. When operating at maximum frequency, it consumes 42.7 A and dissipates 62 W of heat.

Mobile Athlon 64 (ClawHammer)
The first models were presented in September 2003. Features a ClawHammer core with energy-saving PowerNow! technology. The processor is designed for Socket 754 and has an OmPGA package. The L2 cache size is 1024 KB. The number of transistors making up the core is 105.9 million, the core crystal area is 193 mm2. Several different types of processors based on this kernel were released:

Mobile Athlon 64 DTR (Desktop replacement). The core supply voltage is 1.5 V in normal mode and 1.1 V in power-saving mode. When operating at maximum frequency, it consumes 52.9 A and dissipates 81.5 W of heat. Mobile Athlon 64 DTR processors were released with the following ratings (operating frequency in MHz is indicated in brackets): 2800+ (1600), 3000+ (1800), 3200+ (2000), 3400+ (2200), 3700+ (2400);

Mobile Athlon 64. The core supply voltage is 1.4 V in normal mode and 0.95 V in energy-saving mode. When operating at maximum frequency, it consumes 24.7 mA and dissipates 62.0 W of heat. Mobile Athlon 64 processors were released with the following ratings (operating frequency in MHz is indicated in brackets): 2800+ (1600), 3000+ (1800), 3200+ (2000), 3400+ (2200).

Mobile Athlon 64 (Odessa)
The first models were presented in April 2004. Features a Newcastle core with energy-saving PowerNow! technology. The processor is designed for Socket 754. The L2 cache size is 512 KB. The number of transistors making up the core is 68.5 million, the core crystal area is 144 mm2. Several different types of processors based on this kernel were released:

Mobile Athlon 64 DTR (Desktop replacement). The core supply voltage is 1.5 V in normal mode and 1.1 V in power-saving mode. When operating at maximum frequency, it consumes 52.9 A and dissipates 81.5 W of heat. The Mobile Athlon 64 DTR processor was released (operating frequency in MHz is indicated in brackets): 2800+ (1600).

Mobile Athlon 64 LP (Low Power). The core supply voltage is 1.2 V in normal mode and 0.9 V in power-saving mode. When operating at maximum frequency, it consumes 27.3 A and dissipates 35.0 W of heat. Mobile Athlon 64 processors were released with the following ratings (operating frequency in MHz is indicated in brackets): 2700+ (1600), 2800+ (1800), 3000+ (2000).

Mobile Athlon 64 LP (Oakville)
The first models were presented in August 2004. It is a Winchester core with energy-saving PowerNow! technology. The processor is designed for Socket 754. The L2 cache size is 512 KB. The number of transistors making up the core is 68.5 million, the core crystal area is 84 mm2. The core supply voltage is 1.35 V. When operating at maximum frequency, the processor dissipates 35 W of heat. Mobile Athlon 64 LP processors were released with the following ratings (operating frequency in MHz is indicated in brackets): 2700+ (1600), 2800+ (1800), 3000+ (2000).

Mobile Athlon 64 (Newark)
The first models were presented in April 2005. Represents the San Diego core with energy-saving PowerNow! technology. The processor is designed for Socket 754. The L2 cache size is 1 MB. The number of transistors making up the core is 114 million, the area of ​​the core crystal is 115 mm2. The core supply voltage is 1.35 V. When operating at maximum frequency, the processor dissipates 62 W of heat. Mobile Athlon 64 processors were released with the following ratings (operating frequency in MHz is indicated in brackets): 3000+ (1800), 3200+ (2000), 3400+ (2200), 3700+ (2400), 4000+ (2600), 4400 + (2800).

Development of the Athlon 64 line

Athlon 64 (Orleans/K8)
AMD released processors based on this core in the second quarter of 2006. Processors released on this core are designed for Socket AM2 and have an OmPGA package type. Equipped with a dual-channel DDR2 memory controller. The HyperTransport bus frequency has increased to 333 MHz. The L2 cache size will be 1 MB. Models released: Athlon 64 3500+, 3700+, 4000+, 4300+, 4500+.

Athlon 64 X2/FX (Windsor)
AMD released processors based on this core in the second quarter of 2006. Processors built on the Windsor core are dual-core processors. Processors released on this core are designed for Socket AM2 and have an OmPGA package type. Equipped with a dual-channel DDR2 memory controller (presumably PC2-5300). The HyperTransport bus frequency has increased to 333 MHz. Processors are produced using the 90 nm process technology. The L2 cache size is 1 MB per core. Models released: Athlon 64 X2 4200+, 4600+, 4800+, 5000+, as well as Athlon 64 FX-60 and FX-62 processors.

Connectors (sockets)

Socket 754- budget Athlon 64 line, 64-bit memory interface (single-channel mode);
Socket 939- productive line of Athlon 64, Athlon 64 X2, some Opteron models and the new Athlon 64 FX, 128-bit memory interface (dual-channel mode);
Socket 940- Opteron and older Athlon 64 FX, 128-bit memory interface, require DDR registered memory;
Socket F, 1207 contacts - high-performance Opterons;
Socket AM2, 940 pins (but not compatible with Socket 940) - dual-core Athlon 64 X2/Sempron, requires DDR2 SDRAM.
By the time the Athlon 64 was presented in September 2003, only Socket 754 and Socket 940 (for Opteron) were available. The integrated memory controller was not ready to work with non-buffered (non-registered) memory in dual-channel mode at the time of release; A temporary measure was the introduction of Athlon 64 on Socket 754, and offering enthusiasts products for Socket 940 similar to the Intel Pentium 4 Extreme Edition, from the point of view of positioning in the market as a solution of the highest performance.

In June 2004, AMD introduced Socket 939 Athlon 64 for the mass market, with a dual-channel memory interface, leaving Socket 940 for server solutions (Opteron), and moved Socket 754 into the segment of budget solutions, for Semprons and not very productive versions of Athlon 64. Ultimately Socket 754 replaced Socket A for Sempron.

Athlon 64 FX models

Sledgehammer (130 nm SOI)
CPU stepping: C0, CG



Socket 940, 800 MHz HyperTransport (HT800)
Requires registered DDR-SDRAM
Core supply voltage: 1.50/1.55 ​​V

Clawhammer (130 nm SOI)
CPU stepping: CG
L1-CACHE: 64 + 64 KB (Data + Instructions)
L2-CACHE: 1024 KB, full speed
MMX, Extended 3DNow!, SSE, SSE2, AMD64


Power Consumption (TDP): 89 W (FX-55: 104 W)
First introduced: June 1, 2004

San Diego (90 nm SOI)
CPU stepping: E4, E6
L1-CACHE: 64 + 64 KB (Data + Instructions)
L2-CACHE: 1024 KB, full speed

Socket 939, 1000 MHz HyperTransport (HT1000)

Power Consumption (TDP): 104W maximum

Toledo (90 nm SOI)
Dual-core CPU
CPU stepping: E6


MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool"n"Quiet, NX Bit
Socket 939, 1000 MHz HyperTransport (HT1000)

Power Consumption (TDP): 110W maximum
First introduced: January 10, 2006

Windsor (90 nm SOI)
Dual-core CPU
CPU stepping: F
L1-CACHE: 64 + 64 KB (Data + Instructions), per core
L2-CACHE: 1024 KB full-speed, per core
MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool"n"Quiet, NX Bit, AMD Virtualization

Core supply voltage: 1.30 V - 1.35 V
Power Consumption (TDP): 125W maximum

Athlon 64 models

ClawHammer (130 nm SOI)
CPU stepping: C0, CG
L1-CACHE: 64 + 64 KB (Data + Instructions)
L2-CACHE: 1024 KB, full speed, 512 KB for Clawhammer-512 2800+
MMX, Extended 3DNow!, SSE, SSE2, AMD64, Cool"n"Quiet, NX Bit (CG only)

Socket 939, 1000 MHz HyperTransport (HT1000)
Core supply voltage: 1.50 V
Power Consumption (TDP): 89 W maximum
First introduced: September 23, 2003

Newcastle (130 nm SOI)
Trimmed ClawHammer with only 512KB L2-CACHE
CPU stepping: CG
L1-CACHE: 64 + 64 KB (Data + Instructions)


Socket 754, 800 MHz HyperTransport (HT800)
Socket 939, 1000 MHz HyperTransport (HT1000)
Core supply voltage: 1.50 V
Power Consumption (TDP): 89 W maximum

Winchester (90 nm SOI)
CPU stepping: D0
L1-CACHE: 64 + 64 KB (Data + Instructions)
L2-CACHE: 512 KB, full speed
MMX, Extended 3DNow!, SSE, SSE2, AMD64, Cool"n"Quiet, NX Bit
Socket 939, 1000 MHz HyperTransport (HT1000)
Core supply voltage: 1.40 V

First introduced: 2004

Venice (90 nm SOI)
CPU stepping: E3, E6
L1-CACHE: 64 + 64 KB (Data + Instructions)
L2-CACHE: 512 KB, full speed
MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool"n"Quiet, NX Bit
Socket 754, 800 MHz HyperTransport (HT800)
Socket 939, 1000 MHz HyperTransport (HT1000)
Socket AM2, 2000 MHz HyperTransport (HT2000)
Core supply voltage: 1.25/1.35/1.40 V
Power Consumption (TDP): 67W maximum
First introduced: April 4, 2005

San Diego (90 nm SOI)
CPU stepping: E4, E6
L1-CACHE: 64 + 64 KB (Data + Instructions)
L2-CACHE: 1024 KB, full speed
MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool"n"Quiet, NX Bit
Socket 939, 1000 MHz HyperTransport (HT1000)
Core supply voltage: 1.35 V or 1.40 V
Power Consumption (TDP): 89 W maximum
First introduced: April 15, 2005

Orleans (90 nm SOI)
CPU stepping: F
L1-CACHE: 64 + 64 KB (Data + Instructions)
L2-CACHE: 512 KB, full speed
MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool"n"Quiet, NX Bit
Socket AM2, 1000 MHz HyperTransport (HT1000)
Core supply voltage: 1.35 V or 1.40 V
Power Consumption (TDP): 62W maximum
First introduced: May 23, 2006

Explanation of markings for K7/K8 architecture processors:
Explanation of marking using the example of ADA5600IAA6CZ:
A - Athlone model
D - segment: desktop processor
A - heat dissipation (TDP) A - 89 W, D - 35 W, O - 65 W, X - 125 W
5600 - processor model

example: AXDA3200DKV4E
AXDA - Architecture/Brand;
3200 - model number;
D - body type;
K - rated core supply voltage;
V - maximum permissible temperature;
4 - second level cache size;
E - system bus frequency (FSB);
Note:
For K8 architecture processors, instead of the FSB, a product description is written after the cache.
Options:
Architecture/Brand:
OSA - AMD Opteron
OSB - AMD Opteron EE
OSK - AMD Opteron HE
ADA - AMD Athlon 64
ADAFX - AMD Athlon 64 FX
SDA/SDC - AMD Sempron
AXDA/AXDC - AMD Athlon XP 130nm
AX - AMD Athlon XP 180nm
AMSN - AMD Athlon MP 130nm
AMP/AHX - AMD Athlon MP 180nm
K7/A - AMD Athlon 180nm
AHM - Mobile AMD Athlon 4 180nm
AXMS/AXMD/AXDH - Mobile AMD Athlon XP 130nm
D/DHD/DHM/DHL - AMD Duron 180 nm
type of shell:
A - CPGA
B-OBGA
D-OPGA
E-uPGA
F-OPGA
G - uPGA
rated core supply voltage:
Y - 1.1v
C - 1.15v
T - 1.2v
X - 1.25v
W - 1.3v
J - 1.35v
V - 1.4v
Q - 1.45v
L - 1.5v
H - 1.55v
U - 1.6v
K - 1.65v
P - 1.7v
M - 1.75v
N - 1.8v
maximum permissible temperature:
R - 70 C
V - 85 C
T - 90 C
S - 95 C
Q - 100 C
second level cache size:
1 - 64Kb
2 - 128Kb
3 - 256Kb
4 - 512Kb
5 - 1024Kb
6 - 2048Kb
system bus frequency (FSB):
B - 200MHz
C - 266MHz
D - 333MHz
E - 400MHz
Product Description:
code - case - model - revision - multiprocessing - technology
AG-940-5-B3-1cpu-130nm
AH-940-5-B3-2cpu-130nm
AI-940-5-B3-8cpu-130nm
AK-940-5-C0-1cpu-130nm
AL-940-5-C0-2cpu-130nm
AM-940-5-C0-3cpu-130nm
AP-754-4-C0-1cpu-130nm
AR-754-4-CG-1cpu-130nm
AS-939-7-CG-1cpu-130nm
AT-940-5-CG-1cpu-130nm
AU-940-5-CG-2cpu-130nm
AV-940-5-CG-8cpu-130nm
AW-939-F-CG-1cpu-130nm
AX-754-C-CG-1cpu-130nm
BI-939-F1-D0-1cpu-90nm
BK-940-25-E4-1cpu-90nm
BL-940-25-E4-2cpu-90nm
BM-940-25-E4-8cpu-90nm
BN-939-27-E4-1cpu-90nm
BP-939-2F-E3-1cpu-90nm

Conclusion

This article was prepared based on Internet materials. AMD did not include older processors due to their irrelevance today. Considering the time of writing, new processors will be added to the AMD line soon in June.

On June 2, AMD will present two dual-core Socket AM3 processors: Athlon II X2 250 (3.0 GHz) and Phenom II X2 550 (3.1 GHz). Both processors are equipped with 2 x 512 KB of second-level cache and support DDR-2 and DDR-3 memory types, but only the second has a 6 MB third-level cache. The TDP value for Athlon II X2 processors is 65 W, for Phenom II X2 processors - 80 W.

The Athlon II X4 6xx (Propus) and Athlon II X3 4xx (Rana) processors will be presented in August-September of this year.

In conclusion, I ask you not to judge harshly for mistakes if there are any. I look forward to your suggestions to add to this article.

Labeling, positioning, use cases

This summer, Intel released to the market a new, fourth generation of Intel Core architecture, codenamed Haswell (processor markings begin with the number “4” and look like 4xxx). Intel now sees increasing energy efficiency as the main direction of development for Intel processors. Therefore, the latest generations of Intel Core do not show such a strong increase in performance, but their overall energy consumption is constantly decreasing - due to both the architecture, the technical process, and the effective management of component consumption. The only exception is integrated graphics, whose performance increases noticeably from generation to generation, albeit at the expense of worsening energy consumption.

This strategy predictably brings to the fore those devices in which energy efficiency is important - laptops and ultrabooks, as well as the nascent (because in its previous form it could only be attributed to the undead) class of Windows tablets, the main role in the development of which should be played by new processors with reduced energy consumption.

We remind you that we recently published brief overviews of the Haswell architecture, which are quite applicable to both desktop and mobile solutions:

Additionally, the performance of quad-core Core i7 processors was examined in an article comparing desktop and mobile processors. The performance of the Core i7-4500U was also examined separately. Finally, you can read reviews of Haswell laptops, including performance testing: MSI GX70 on the most powerful Core i7-4930MX processor, HP Envy 17-j005er.

In this material we will talk about the Haswell mobile line as a whole. IN first part We will look at the division of Haswell mobile processors into series and lines, the principles of creating indexes for mobile processors, their positioning and the approximate level of performance of different series within the entire line. In second part- Let’s take a closer look at the specifications of each series and line and their main features, and also move on to conclusions.

For those who are not familiar with the Intel Turbo Boost algorithm, we have provided a brief description of this technology at the end of the article. We recommend using it before reading the rest of the material.

New letter indices

Traditionally, all Intel Core processors are divided into three lines:

• Intel Core i3
• Intel Core i5
• Intel Core i7

Intel's official position (which company representatives usually voice when answering the question why there are both dual-core and quad-core models among the Core i7) is that the processor is classified into one or another line based on its overall performance level. However, in most cases there are architectural differences between processors of different lines.

But already in Sandy Bridge, and in Ivy Bridge, another division of processors became full - into mobile and ultra-mobile solutions, depending on the level of energy efficiency. Moreover, today this classification is the basic one: both the mobile and ultramobile lines have their own Core i3/i5/i7 with very different levels of performance. At Haswell, on the one hand, the division deepened, and on the other, they tried to make the line more harmonious, less misleading by duplicating indices. In addition, another class has finally taken shape - ultra-ultramobile processors with the index Y. Ultramobile and mobile solutions are still marked with the letters U and M.

So, in order not to get confused, let’s first look at what letter indices are used in the modern line of fourth-generation Intel Core mobile processors:

• M - mobile processor (TDP 37-57 W);
• U - ultramobile processor (TDP 15-28 W);
• Y - processor with extremely low consumption (TDP 11.5 W);
• Q - quad-core processor;
• X - extreme processor (top solution);
• H - processor for BGA1364 packaging.

Since we mentioned TDP (thermal package), let’s look at it in a little more detail. It should be taken into account that the TDP in modern Intel processors is not “maximum”, but “nominal”, that is, it is calculated based on the load in real tasks when operating at the standard frequency, and when Turbo Boost is turned on and the frequency increases, the heat dissipation goes beyond the declared nominal heat package - There is a separate TDP for this. The TDP when operating at the minimum frequency is also determined. Thus, there are as many as three TDPs. In this article, the tables use the nominal TDP value.

• The standard nominal TDP for mobile quad-core Core i7 processors is 47 W, for dual-core processors - 37 W;
• The letter X in the name raises the thermal package from 47 to 57 W (there is currently only one such processor on the market - 4930MX);
• Standard TDP for U-series ultramobile processors is 15 W;
• Standard TDP for Y-series processors is 11.5 W;

Digital indexes

The indices of the fourth generation Intel Core processors with Haswell architecture begin with the number 4, which precisely indicates that they belong to this generation (for Ivy Bridge the indices began with 3, for Sandy Bridge - with 2). The second digit indicates the processor line: 0 and 1 - i3, 2 and 3 - i5, 5–9 - i7.

Now let's look at the last numbers in the processor names.

The number 8 at the end means that this processor model has an increased TDP (from 15 to 28 W) and a significantly higher nominal frequency. Another distinctive feature of these processors is the Iris 5100 graphics. They are aimed at professional mobile systems that require stable high performance in any conditions for constant work with resource-intensive tasks. They also have overclocking using Turbo Boost, but due to the greatly increased nominal frequency, the difference between the nominal and maximum is not too great.

The number 2 at the end of the name indicates that the TDP of the processor from the i7 line has been reduced from 47 to 37 W. But you have to pay for lower TDP with lower frequencies - minus 200 MHz to the base and boost frequencies.

If the second from the end digit in the name is 5, then the processor has a GT3 graphics core - HD 5xxx. Thus, if the last two digits in the processor name are 50, then the graphics core GT3 HD 5000 is installed in it, if 58 is installed, then Iris 5100, and if 50H, then Iris Pro 5200, because only processors with BGA1364.

For example, let's look at a processor with the 4950HQ index. The processor name contains H - which means BGA1364 packaging; contains 5 - which means the graphics core is GT3 HD 5xxx; a combination of 50 and H gives Iris Pro 5200; Q - quad core. And since quad-core processors are only available in the Core i7 line, this is the Core i7 mobile series. This is confirmed by the second digit of the name - 9. We get: 4950HQ is a mobile quad-core eight-thread processor of the Core i7 line with a TDP of 47 W with GT3e Iris Pro 5200 graphics in BGA design.

Now that we have sorted out the names, we can talk about dividing processors into lines and series, or, more simply, about market segments.

4th generation Intel Core series and lines

So, all modern Intel mobile processors are divided into three large groups depending on power consumption: mobile (M), ultramobile (U) and “ultramobile” (Y), as well as three lines (Core i3, i5, i7) depending on productivity. As a result, we can create a matrix that will allow the user to select the processor that best suits his tasks. Let's try to summarize all the data into a single table.

Series/line	Options	Core i3	Core i5	Core i7
Mobile (M)	Segment	laptops	laptops	laptops
	Cores/threads	2/4	2/4	2/4, 4/8
	Max. frequencies	2.5 GHz	2.8/3.5 GHz	3/3.9 GHz
	Turbo Boost	No	There is	There is
	TDP	high	high	maximum
	Performance	above average	high	maximum
	Autonomy	below the average	below the average	low
Ultra mobile (U)	Segment	laptops/ultrabooks	laptops/ultrabooks	laptops/ultrabooks
	Cores/threads	2/4	2/4	2/4
	Max. frequencies	2 GHz	2.6/3.1 GHz	2.8/3.3 GHz
	Turbo Boost	No	There is	There is
	TDP	average	average	average
	Performance	below the average	above average	high
	Autonomy	above average	above average	above average
Ultramobile (Y)	Segment	ultrabooks/tablets	ultrabooks/tablets	ultrabooks/tablets
	Cores/threads	2/4	2/4	2/4
	Max. frequencies	1.3 GHz	1.4/1.9 GHz	1.7/2.9 GHz
	Turbo Boost	No	There is	There is
	TDP	short	short	short
	Performance	low	low	low
	Autonomy	high	high	high

For example: a buyer needs a laptop with high processor performance and a moderate cost. Since it’s a laptop, and a powerful one at that, an M-series processor is needed, and the requirement for moderate cost forces us to choose the Core i5 line. We emphasize once again that first of all you should pay attention not to the line (Core i3, i5, i7), but to the series, because each series may have its own Core i5, but the performance level of Core i5 from two different series will be significantly differ. For example, the Y-series is very economical, but has low frequencies, and the Y-series Core i5 processor will be less powerful than the U-series Core i3 processor. And the Core i5 mobile processor may well be more productive than the ultramobile Core i7.

Approximate performance level depending on the line

Let's try to go a step further and create a theoretical rating that would clearly demonstrate the difference between processors of different lines. For 100 points, we will take the weakest processor presented - the dual-core, four-threaded i3-4010Y with a clock frequency of 1300 MHz and a 3 MB L3 cache. For comparison, we take the highest-frequency processor (at the time of writing) from each line. We decided to calculate the main rating by overclocking frequency (for those processors that have Turbo Boost), in brackets - the rating for the nominal frequency. Thus, a dual-core, four-thread processor with a maximum frequency of 2600 MHz will receive 200 conditional points. Increasing the third level cache from 3 to 4 MB will bring it a 2-5% (data obtained based on real tests and research) increase in conditional points, and increasing the number of cores from 2 to 4 will accordingly double the number of points, which is also achievable in reality with good multi-threaded optimization.

Once again, we strongly emphasize that the rating is theoretical and is based largely on the technical parameters of the processors. In reality, a large number of factors come together, so the performance gain relative to the weakest model in the line will almost certainly not be as large as in theory. Thus, you should not directly transfer the resulting relationship to real life - final conclusions can only be drawn based on the results of testing in real applications. However, this assessment allows us to roughly estimate the processor’s place in the lineup and its positioning.

So, some preliminary notes:

• Core i7 U-series processors will be about 10% faster than Core i5 thanks to slightly higher clock speeds and more L3 cache.
• The difference between Core i5 and Core i3 U-series processors with a TDP of 28 W excluding Turbo Boost is about 30%, i.e., ideally, performance will also differ by 30%. If we take into account the capabilities of Turbo Boost, the difference in frequencies will be about 55%. If we compare Core i5 and Core i3 U-series processors with a TDP of 15 W, then with stable operation at maximum frequency, Core i5 will have a frequency 60% higher. However, its nominal frequency is slightly lower, i.e. when operating at the nominal frequency, it may even be slightly inferior to the Core i3.
• In the M-series, the presence of 4 cores and 8 threads in the Core i7 plays a big role, but we must remember that this advantage only manifests itself in optimized software (usually professional). Core i7 processors with two cores will have slightly higher performance due to higher overclocking frequencies and a slightly larger L3 cache.
• In the Y series, the Core i5 processor has a base frequency of 7.7% and a boost frequency of 50% higher than the Core i3. But even in this case, there are additional considerations - the same energy efficiency, noise level of the cooling system, etc.
• If we compare processors of the U and Y series with each other, then only the frequency gap between the U- and Y-processors Core i3 is 54%, and for Core i5 processors it is 63% at the maximum overclocking frequency.

So, let's calculate the score for each line. Let us remind you that the main score is calculated based on maximum overclocking frequencies, the score in brackets is calculated based on nominal frequencies (i.e., without overclocking using Turbo Boost). We also calculated the performance factor per watt.

¹ max. - at maximum acceleration, nom. - at rated frequency
² coefficient - conditional performance divided by TDP and multiplied by 100
³ overclocking TDP data for these processors is unknown

From the table above, the following observations can be made:

• Dual-core Core i7 U and M series processors are only slightly faster than Core i5 processors of similar series. This applies to comparisons for both base and boost frequencies.
• Core i5 processors of the U and M series, even at base frequency, should be noticeably faster than Core i3 of similar series, and in Boost mode they will go far ahead.
• In the Y series, the difference between the processors at minimum frequencies is small, but with Turbo Boost overclocking, the Core i5 and Core i7 should go far ahead. Another thing is that the magnitude and, most importantly, stability of overclocking is very dependent on the cooling efficiency. And with this, given the orientation of these processors towards tablets (especially fanless ones), there may be problems.
• The Core i7 U series is almost equal in performance to the Core i5 M series. There are other factors involved (it is more difficult to achieve stability due to less efficient cooling, and it costs more), but overall this is a good result.

As for the relationship between power consumption and performance rating, we can draw the following conclusions:

• Despite the increase in TDP when the processor switches to Boost mode, energy efficiency increases. This is because the relative increase in frequency is greater than the relative increase in TDP;
• Processors of various series (M, U, Y) are ranked not only by decreasing TDP, but also by increasing energy efficiency - for example, Y-series processors show greater energy efficiency than U-series processors;
• It is worth noting that with an increase in the number of cores, and therefore threads, energy efficiency also increases. This can be explained by the fact that only the processor cores themselves are doubled, but not the accompanying DMI, PCI Express and ICP controllers.

An interesting conclusion can be drawn from the latter: if the application is well parallelized, then a quad-core processor will be more energy efficient than a dual-core processor: it will finish calculations faster and return to idle mode. As a result, multi-core may be the next step in the fight to improve energy efficiency. In principle, this trend can be noted in the ARM camp.

So, although the rating is purely theoretical, and it is not a fact that it accurately reflects the real balance of power, it even allows us to draw certain conclusions regarding the distribution of processors in the line, their energy efficiency and the relationship between these parameters.

Haswell vs Ivy Bridge

Although Haswell processors have been on the market for quite some time, the presence of Ivy Bridge processors in ready-made solutions even now remains quite high. From the consumer’s point of view, there were no special revolutions during the transition to Haswell (although the increase in energy efficiency for some segments looks impressive), which raises questions: is it necessary to choose the fourth generation or can you get by with the third?

It is difficult to directly compare fourth-generation Core processors with the third, because the manufacturer has changed the TDP limits:

• the M series of the third generation Core has a TDP of 35 W, and the fourth - 37 W;
• the U series of the third generation Core has a TDP of 17 W, and the fourth - 15 W;
• the Y series of the third generation Core has a TDP of 13 W, and the fourth - 11.5 W.

And if for ultramobile lines TDP has decreased, then for the more productive M series it has even increased. However, let's try to make a rough comparison:

• The top-end quad-core Core i7 processor of the third generation had frequencies of 3 (3.9) GHz, the fourth generation had the same 3 (3.9) GHz, that is, the difference in performance can only be due to architectural improvements - no more than 10%. Although, it is worth noting that with heavy use of FMA3, the fourth generation will be 30-70% ahead of the third.
• The top dual-core Core i7 processors of the third generation M-series and U-series had frequencies of 2.9 (3.6) GHz and 2 (3.2) GHz, respectively, and the fourth - 2.9 (3.6) GHz and 2. 1(3.3) GHz. As we can see, if the frequencies have increased, then only slightly, so the level of performance can increase only minimally, due to optimization of the architecture. Again, if the software knows about FMA3 and knows how to actively use this extension, then the fourth generation will receive a solid advantage.
• The top dual-core Core i5 processors of the third generation M-series and U-series had frequencies of 2.8 (3.5) GHz and 1.8 (2.8) GHz, respectively, and the fourth - 2.8 (3.5) GHz and 1.9(2.9) GHz. The situation is similar to the previous one.
• The top-end dual-core Core i3 processors of the third generation M-series and U-series had frequencies of 2.5 GHz and 1.8 GHz, respectively, and the fourth - 2.6 GHz and 2 GHz. The situation is repeating itself again.
• The top dual-core processors Core i3, i5 and i7 of the third generation Y-series had frequencies of 1.4 GHz, 1.5 (2.3) GHz and 1.5 (2.6) GHz, respectively, and the fourth - 1.3 GHz, 1.4(1.9) GHz and 1.7(2.9) GHz.

In general, clock speeds in the new generation have practically not increased, so a slight gain in performance is achieved only by optimizing the architecture. The fourth generation of Core will gain a noticeable advantage when using software optimized for FMA3. Well, don’t forget about the faster graphics core - optimization there can bring a significant increase.

As for the relative difference in performance within the lines, the third and fourth generations of Intel Core are close in terms of this indicator.

Thus, we can conclude that in the new generation Intel decided to reduce TDP instead of increasing operating frequencies. As a result, the increase in operating speed is lower than it could have been, but it was possible to achieve increased energy efficiency.

Suitable tasks for different fourth generation Intel Core processors

Now that we have figured out performance, we can roughly estimate what tasks this or that fourth-generation Core line is best suited for. Let's summarize the data in a table.

Series/line	Core i3	Core i5	Core i7
Mobile M	surfing web office environment old and casual games	All the previous plus: professional environment on the verge of comfort	All the previous plus: professional environment (3D modeling, CAD, professional photo and video processing, etc.)
Ultramobile U	surfing web office environment old and casual games	All the previous plus: corporate environment (for example, accounting systems) undemanding computer games with discrete graphics professional environment on the verge of comfort (it’s unlikely that you’ll be able to work comfortably in 3ds max)
Ultra-ultramobile Y	surfing web simple office environment old and casual games		office environment old and casual games

This table also clearly shows that first of all you should pay attention to the processor series (M, U, Y), and only then to the line (Core i3, i5, i7), since the line determines the ratio of processor performance only within the series, and Performance varies noticeably between series. This is clearly seen in the comparison of the i3 U-series and i5 Y-series: the first in this case will be more productive than the second.

So, what conclusions can be drawn from this table? Core i3 processors of any series, as we have already noted, are interesting primarily for their price. Therefore, it’s worth paying attention to them if you are short on funds and are willing to accept a loss in both performance and energy efficiency.

The mobile Core i7 stands apart due to its architectural differences: four cores, eight threads and noticeably more L3 cache. As a result, it is able to work with professional resource-intensive applications and show an extremely high level of performance for a mobile system. But for this, the software must be optimized for the use of a large number of cores - it will not reveal its advantages in single-threaded software. And secondly, these processors require a bulky cooling system, i.e. they are installed only in large laptops with great thickness, and they do not have much autonomy.

Core i5 mobile series provide a good level of performance, sufficient to perform not only home-office, but also some semi-professional tasks. For example, for processing photos and videos. In all respects (power consumption, heat generation, autonomy), these processors occupy an intermediate position between the Core i7 M-series and the ultramobile line. Overall, this is a balanced solution suitable for those who value performance over a thin and light body.

Dual-core mobile Core i7s are approximately the same as the Core i5 M-series, only slightly more powerful and, as a rule, noticeably more expensive.

Ultramobile Core i7s have approximately the same level of performance as mobile Core i5s, but with caveats: if the cooling system can withstand prolonged operation at high frequencies. And they get quite hot under load, which often leads to strong heating of the entire laptop body. Apparently, they are quite expensive, so their installation is justified only for top models. But they can be installed in thin laptops and ultrabooks, providing a high level of performance in a thin body and good battery life. This makes them an excellent choice for frequently traveling professional users who value energy efficiency and light weight, but often require high performance.

Ultramobile Core i5s show lower performance compared to the “big brother” of the series, but cope with any office workload, have good energy efficiency and are much more affordable in price. In general, this is a universal solution for users who do not work in resource-intensive applications, but are limited to office programs and the Internet, and at the same time would like to have a laptop/ultrabook suitable for travel, i.e. lightweight, lightweight and long-lasting batteries

Finally, the Y-series also stands apart. In terms of performance, its Core i7, with luck, will reach the ultra-mobile Core i5, but, by and large, no one expects this from it. For the Y series, the main thing is high energy efficiency and low heat generation, which allows the creation of fanless systems. As for performance, the minimum acceptable level that does not cause irritation is sufficient.

Briefly about Turbo Boost

In case some of our readers have forgotten how Turbo Boost overclocking technology works, we offer you a brief description of its operation.

Roughly speaking, the Turbo Boost system can dynamically increase the processor frequency above the set one due to the fact that it constantly monitors whether the processor goes beyond its normal operating modes.

The processor can only operate in a certain temperature range, i.e., its performance depends on heat, and heat depends on the ability of the cooling system to effectively remove heat from it. But since it is not known in advance which cooling system the processor will work with in the user’s system, two parameters are indicated for each processor model: operating frequency and the amount of heat that must be removed from the processor at maximum load at this frequency. Since these parameters depend on the efficiency and proper operation of the cooling system, as well as external conditions (primarily ambient temperature), the manufacturer had to lower the frequency of the processor so that it would not lose stability even under the most unfavorable operating conditions. Turbo Boost technology monitors the internal parameters of the processor and allows it, if external conditions are favorable, to operate at a higher frequency.

Intel originally explained that Turbo Boost technology uses the "temperature inertia effect." Most of the time, in modern systems, the processor is idle, but from time to time, for a short period, it is required to perform at its maximum. If at this moment you greatly increase the frequency of the processor, it will cope with the task faster and return to the idle state sooner. At the same time, the processor temperature does not increase immediately, but gradually, therefore, during short-term operation at a very high frequency, the processor will not have time to heat up enough to go beyond safe limits.

In reality, it quickly became clear that with a good cooling system, the processor is capable of operating under load even at an increased frequency indefinitely. Thus, for a long time, the maximum overclocking frequency was absolutely operational, and the processor returned to the nominal only in extreme cases or if the manufacturer made a poor-quality cooling system for a particular laptop.

In order to prevent overheating and failure of the processor, the Turbo Boost system in its modern implementation constantly monitors the following parameters of its operation:

• chip temperature;
• current consumption;
• power consumption;
• number of loaded components.

Modern Ivy Bridge systems are capable of operating at higher frequencies in almost all modes, except for simultaneous heavy load on the central processor and graphics. As for Intel Haswell, we do not yet have sufficient statistics on the behavior of this platform under overclocking.

Note author: It is worth noting that the temperature of the chip indirectly affects power consumption - this influence becomes clear upon closer examination of the physical structure of the crystal itself, since the electrical resistance of semiconductor materials increases with increasing temperature, and this in turn leads to an increase in electricity consumption. Thus, a processor at a temperature of 90 degrees will consume more electricity than at a temperature of 40 degrees. And since the processor “heats up” both the PCB of the motherboard with the tracks, and the surrounding components, their loss of electricity to overcome higher resistance also affects energy consumption. This conclusion is easily confirmed by overclocking both “in the air” and extreme. All overclockers know that a more productive cooler allows you to get additional megahertz, and the effect of superconductivity of conductors at temperatures close to absolute zero, when electrical resistance tends to zero, is familiar to everyone from school physics. That is why when overclocked with liquid nitrogen cooling it is possible to achieve such high frequencies. Returning to the dependence of electrical resistance on temperature, we can also say that to some extent the processor also heats itself up: as the temperature rises and the cooling system cannot cope, the electrical resistance also increases, which in turn increases power consumption. And this leads to an increase in heat generation, which leads to an increase in temperature... In addition, do not forget that high temperatures shorten the life of the processor. Although manufacturers claim fairly high maximum temperatures for chips, it is still worth keeping the temperature as low as possible.

By the way, it is quite likely that “spinning” the fan at higher speeds, when it increases the system’s power consumption, is more profitable in terms of power consumption than having a processor with a high temperature, which will entail losses of electricity due to increased resistance.

As you can see, temperature may not be a direct limiting factor for Turbo Boost, that is, the processor will have a completely acceptable temperature and will not throttle, but it indirectly affects another limiting factor - power consumption. Therefore, you should not forget about temperature.

To summarize, Turbo Boost technology allows, under favorable external operating conditions, to increase the processor frequency above the guaranteed nominal and thereby provide a much higher level of performance. This property is especially valuable in mobile systems, where it allows for a good balance between performance and heat.

But it should be remembered that the other side of the coin is the inability to evaluate (predict) the pure performance of the processor, since it will depend on external factors. This is probably one of the reasons for the appearance of processors with “8” at the end of the model name - with “raised” nominal operating frequencies and an increased TDP because of this. They are intended for those products where consistent high performance under load is more important than energy efficiency.

The second part of the article provides a detailed description of all modern series and lines of Intel Haswell processors, including technical characteristics of all available processors. And also conclusions were drawn about the applicability of certain models.

The marking of AMD processors is called OPN(Ordering Part Number).

At first glance, it is quite complex and looks more like some kind of cipher, although if you understand it, you can get quite detailed information about their main technical parameters.

The first two letters indicate the processor type:

AX- Athlon XP (0.18 microns);
AD- Athlon 64, Athlon 64 FX, Athlon 64 X2;
SD- Sempron.

The third letter indicates the TDP of the processor

A- 89-125 W;
O- 65 W;
D- 35 W;
H- 45 W;
X- 125 W.

For Sempron processors, the third letter has a slightly different meaning:

A- Desktop;
D- Energy Efficient.

It is a number that (from AMD's point of view) characterizes the performance of a given CPU in abstract units.
Although there are some exceptions - in Athlon 64 FX processors, for example, instead of rating numbers, the letter index “FX (model index)” is indicated.

The first letter of the three-letter index indicates the type of processor case:

A- Socket 754;
D- Socket 939;
C- Socket 940;
I- Socket AM2;
G- Socket F.

The second letter of the three-letter index indicates the supply voltage of the processor core:

A- 1.35-1.4 V
WITH- 1.55 V;
E- 1.5 V;
I- 1.4 V;
K- 1.35 V;
M- 1.3 V;
Q- 1.2 V;
S- 1.15 V.

The third letter of the three-letter index indicates the maximum temperature of the processor core:

A- 71 °C;
K- 65 °C;
M- 67 °C;
O- 69 °C;
P- 70 °C;
X- 95 °C.

The next number indicates the size of the second level cache (total for dual-core processors):

2 - 128 KB;
3 - 256 KB;
4 - 512 KB;
5 - 1024 KB;
6 - 2048 KB.

The two-letter index indicates the type of processor core:

AX, A.W.- Newcastle;
AP, AR, AS, AT- Clawhammer;
A.K.- Sledge Hammer;
B.I.- Winchester;
BN- San Diego;
B.P., B.W.- Venice;
B.V.- Manchester;
CD- Toledo;
C.S., C.U.- Windsor F2; CZ- Windsor F3;
CN, CW- Orleans, Manila;
DE- Lima;
DD, D.L.- Brisbane;
D.H.- Orleans F3
AX- Paris (for Sempron);
B.I.- Manchester (for Sempron);
B.A., B.O., A.W., BX, B.P., B.W.- Palermo (for Sempron).

For example, the AMD Sempron 3000+ processor (Manila core) is labeled as SDA3000IAA3CN.

But nothing lasts forever in our world, and AMD is soon going to rename its processor lines, introducing a new, much more descriptive alphanumeric scheme.
The new system assumes, along with the traditional brand and class designation, an alphanumeric model code:

Phenom X4 GP-7xxx
Phenom X2 GS-6xxx
Athlon X2 BE-2xxx
Athlon X2 LS-2xxx
Sempron LE-1xxx

The first character in the processor model name determines its class:

G- High-end;
B- Mainstream;
L- Low-End.

The second character determines the processor's power consumption:

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

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

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

The second digit will indicate the performance level of a specific processor within the family.

The last two digits will determine the processor modification.

Thus, the latest dual- and quad-core processors will be designated as AMD Phenom X2 GS-6xxx and Phenom X4 GP-7xxx.

Economical mid-class dual-core processors are Athlon X2 BE-2xxx, and budget AMD Athlon and Sempron will be called Athlon X2 LS-2xxx and Sempron LE-1xxx.
And the notorious number 64, indicating support for 64-bit architecture, will disappear from the name of the Athlon processor.

AMD Radeon Software Adrenalin Edition 19.9.2 Optional Driver

The new AMD Radeon Software Adrenalin Edition 19.9.2 Optional driver improves performance in Borderlands 3 and adds support for Radeon Image Sharpening technology.

Windows 10 Cumulative Update 1903 KB4515384 (Added)

On September 10, 2019, Microsoft released a cumulative update for Windows 10 version 1903 - KB4515384 with a number of security improvements and a fix for a bug that broke Windows Search and caused high CPU usage.