What does cpu architecture mean?

cpu architecture is a specification set by CPU manufacturers for CPU products belonging to the same series. The main purpose is to distinguish important indicators of different types of CPUs. Currently, CPU classification is mainly divided into two camps, one is Intel and AMD The first is the complex instruction set CPU, and the other is the reduced instruction set CPU headed by IBM and ARM.

CPU architecture is a specification set by CPU manufacturers for CPU products belonging to the same series. The main purpose is to distinguish important indicators of different types of CPUs. Currently, the CPU classification on the market is mainly divided into two camps. One is the complex instruction set CPU led by Intel and AMD, and the other is the reduced instruction set CPU led by IBM and ARM. Two different brands of CPUs have different product architectures. For example, Intel and AMD's CPUs are based on X86 architecture, while IBM's CPUs are based on PowerPC architecture, and ARM's CPUs are based on ARM architecture.

Overall architecture

Core architecture Merom processor is indeed powerful. In multiple tests, the best proof is that the T7200 with a frequency of 2GHz can defeat the T2700 with a frequency of 2.33GHz. But you have also noticed that although Merom has strong performance on the mobile platform, it does not bring you much surprise. Although it is better than Yonah, it is not by much, and in some test items, the T7200 with a slightly lower frequency also loses to the T2700. Therefore, the advantages of the Core microarchitecture on the mobile platform may not be as outstanding as on the desktop platform - an E6300 with the lowest frequency can also completely wipe out the high-frequency Pentium D. The reason is that Yonah itself is better, unlike NetBurst, which failed. Moreover, the Core microarchitecture itself is improved from the Yonah microarchitecture, so it is reasonable that the results will not form a big contrast.

Core microarchitecture is a new generation microarchitecture improved by Intel's Israeli design team based on the Yonah microarchitecture. The most significant changes are enhancements in various key parts. In order to improve the efficiency of internal data exchange between the two cores, a shared L2 cache design is adopted. The two cores share a L2 cache of up to 4MB. Its core adopts a short 14-stage effective pipeline design. Each core has a built-in 32KB first-level instruction cache and a 32KB first-level data cache. Data can be directly transferred between the first-level data caches of the two cores. Each core has built-in 4 sets of instruction decoding units, supports microinstruction fusion and macroinstruction fusion technology, can decode up to 5 X86 instructions per clock cycle, and has improved branch prediction functions. Each core has built-in 5 execution unit subsystems, which has high execution efficiency. Added support for EM64T and SSE4 instruction sets. Since the support for EM64T allows it to have a larger memory addressing space, it makes up for the shortcomings of Yonah. After the popularity of the new generation of memory-consuming large-scale memory-Vista operating system, this advantage can make the Core micro-architecture have a longer life cycle. . It also uses Intel's latest five new technologies to improve performance and reduce power consumption, including: better power management functions; support for hardware virtualization technology and hardware anti-virus functions; built-in digital temperature sensor; providing power reports and temperature reports wait. In particular, the adoption of these energy-saving technologies is of great significance to mobile platforms.

In addition, Core supports 64-bit

Based on Core architecture processors, facing different consumer groups, Core processors have a small division of labor, specifically Conroe for desktop use, and notebook use Merom, the server uses WoodCrest, these three processors are all based on the Core core architecture.

Intel processors, including Core series desktop, mobile, Xeon processors, and even embedded processors, will all enter the 32nm process one after another, gradually replacing the current 45nm process. As CES is approaching, Intel has revealed that it will release a variety of Core i3 and i5 desktop and notebook processors at CES, including Arrandale for notebooks and Clarkdale for desktops, which will use the 32nm process, emphasizing smaller size and Power consumption design. On December 23, 2009, Intel revealed that the embedded Xeon processor to be launched in the first quarter of 2010 will also use a new process. The 32nm process that started production at the end of 2009, compared with the 45nm process at the end of 2008, uses second-generation high-k metal gate transistors and immersion lithography technology to strengthen the control of the internal electronic control tubes of the processor. , which is also 30% smaller than the 45nm process, simplifying system design. According to Intel's blueprint, the 32nm process will be launched for the embedded market in the first quarter of 2010. The embedded Xeon processor code-named Jasper Forest will have 30% to 70% higher performance per watt than processors using the old process and support PCI. 2.0 and I/O virtualization capabilities. As for enterprise server Xeon processors, with the launch of the desktop processor Clarkdale in 2010, the entry-level Xeon 3000 processor, which is closely related to the high-end desktop market, will also enter the new 32nm process in 2009.

As for the Xeon 5000, which adopted the Nehalem-EP architecture in 2009, although it still uses the Nehalem architecture, it will use the new 32-nanometer process in the first half of 2010 and launch the Westmere-EP processor. The Xeon 7000 processor that originally provided 6 cores will also launch Nehalem-EX with up to 8 cores in the first half of 2010, and Westmere-EX, which will also enter the new process in the second half of 2010.

In addition to embedded systems, servers, laptops and desktops that have successively entered the new process, currently only the Atom processor with low power consumption design has not yet entered, still using the 45nm process.

Compared to Intel entering a new process in 2010, AMD will begin to enter the 32nm process in 2011. At that time, it will adopt the new Bulldozer core architecture design, including Interlagos with performance levels of 12 to 16 cores, and an emphasis on energy Benefit from 6 to 8 cores of Valencia.

8-core CPU cannot currently be compatible with current motherboards, so it cannot be promoted with great fanfare. The cheapest 8-core CPU should be the CELL of SONY PS3. With 8 cores, the floating point performance is much better than that of Core Duo. times, and now 4 cores are not popular, AMD INTEL will not rush to mass-produce their 8-core CPUs. It can be said that the current INTEL 4 cores only encapsulate 2 Core cores in one core, and there is no connection between the 2 cores. There is no need for direct communication. AMD has released a true 4-core, but it is not selling well yet and cannot become mainstream. To sum up, in 5 years, 4 cores can basically replace the current dual core and become the mainstream, and 8 core or even 16 core CPU will become the high-end product at that time!

The above is the detailed content of What does cpu architecture mean?. For more information, please follow other related articles on the PHP Chinese website!