Cpugpu computing power of various models

1. The same power consumption, that is, the common CPU and GPU within 100 W, the graphics card is gtx1050ti power consumption of 75 W, like gtx1060 power consumption of 130 W, the CPU can be i7 six core 12 thread level, or the CPU performance is dedicated to data processing, the performance is relatively strong,
if you exclude the power consumption, the high-end single chip computing performance has already exceeded the CPU speed.

2.

Main differences between CPU and GPU:

1. CPU is the central processing unit of computer

GPU is the graphics processor of computer

CPU is a very large-scale integrated circuit, which includes Alu arithmetic logic unit, cache memory and bus

CPU is the core of a computer's control and operation, its main function is to interpret the instructions issued by the computer and process the big data in the computer software

GPU is the abbreviation of image processor. It is a kind of microprocessor which is specially used for PC or embedded device to perform image operation

The work of GPU is similar to that of CPU mentioned above, but not entirely. It is designed to perform complex mathematical and geometric calculations. This game has high requirements in this respect, so many game players also have deep feelings for GPU

so CPU and GPU are two completely different things, they just sound the same

extended data:

CPU and GPU are different in design because they are used to deal with different tasks at first, and some tasks are similar to the problems that GPU is used to solve at first, so we use GPU to calculate. The operation speed of GPU depends on how many pupils are employed, and the operation speed of CPU depends on how powerful professors are employed, The professor's ability to deal with complex tasks is very good, but for less complex tasks, it still can't hold many people

of course, today's GPU can also do some slightly complicated work, which is equivalent to upgrading to the level of junior high school students and senior high school students, but it still needs CPU to feed data to the mouth before it can start to work, which is still managed by CPU

3. That is, specific performance / power consumption. GPU is much better than CPU. At the beginning, it was precisely because CPU had to spend a lot of power consumption and transistors on control circuit and cache that GPU was made into independent chip, and further GPGPU.

4. The focus of the two is different, GPU is for images, CPU is for data, the two are not easy to compare, if you have to compare, GPU is better than CPU

5. To answer your question, it seems that you have to write a long article. The following can only be simply classified to facilitate you to draw inferences from one instance. First of all, APU is a series of CPUs. If you list the models of CPUs, it already includes the models of APU. So your question can be summarized as follows: list the models of CPU and GPU. There are two major manufacturers of CPU: Intel and AMD. Intel is divided into four series from low end to high end:
Celeron series:
representative models are: E3300, e3400 (775 interface), g440, g530 (1155 interface) with G for I architecture
Pentium series:
representative models are: E5200, E5700 E6500 (775 interface), G620, g840 (1155 interface) with G are I architecture
core 2 Series:
representative models are: E7500, e8400, Q8200, Q9550, QX9650 (775 interface) with Q are four core
core I Series:
representative models are: I3 530, i5 760, i7 920 (1156 interface) I3 2100, i5 2300 I7 2600 (1155 interface) I series is almost integrated with video card. AMD is divided into four series from low-end to high-end:
speedlong II Series:
the representative models are: x2250, X3 445, X4 640 (AM3 interface) the numbers behind x represent the number of cores
Yilong II Series:
the representative models are: x2550, x3720, X4 955, X3 550, X4 760, X4 550, X3 640, X4 550, X3 760, X4 550, X4 550, X4 760, X4 550, X3 640 The number after x61090t (AM3 interface) x represents the number of cores
a series (that is, APU Series):
represents models: a4-3300, a6-3650, a8-3850 (FM1 interface) with all integrated graphics cards
FX series:
represents models: fx-4100, fx-6100, fx-8150 (AM3 + interface) are the latest bulldozer architecture GPU, that is, the graphics core in the independent display market, There are AMD and NV families. AMD, named after hd0000, has hd4000, hd5000, hd6000 and hd7000 series from old to new
the representative models of hd4000 series are (from weak to strong): HD4350, HD4670, HD4830, HD4890, etc.
the representative models of hd5000 series are (from weak to strong): HD5450, Hd5670, HD5770, HD5850, etc.
the representative models of hd6000 series are (from weak to strong): hd6470, hd6750, hd6850, hd6950, etc.
the representative models of hd7000 series are (from weak to strong): hd7950 Hd7970 (new, model not completely released) NV, from the old to the new, there are gf9000, gf200, gf400, gf500 series
gf9000 series was born in 2008, the representative models are (from weak to strong) 9400gt, 9500GT, 9600GT, 9800gt and so on (currently discontinued)
gf200 series was born in 2009, and its representative models are G210, GT220, gt240, GTS250, gtx280, etc
gf400 series was born in 2010, and its representative models are gt430, gt440, gts450, gtx465, GTX480, etc
gf500 series was born in 2011, and its representative models are gt520, gt530, gtx550ti, gtx560ti, gtx580, etc.
there are AMD, NV and Intel in Jixian market, all of which have their own models. Amd uses the same hd0000 naming method as its own unique display< The 7-series chipsets include: 780g (hd3200), 790gx (hd3300), 785g (hd4200)
the 8-series chipsets include: 880g (hd4250), 890gx (hd4290)
later models are integrated into the A-Series CPU
the A4 series integrates hd6410d, the A6 series integrates hd6530d, and the A8 series integrates 6550d, It can replace low-end display (NV) and also use the same gf0000 naming method as its own display
the C61 chipset was gf6100
the C68 chipset was gf7050 or gf7025
the c73 chipset was gf7150 or gf7050
the C78 chipset was gf8300 or gf8200
the C7A chipset was gf9400 or gf9300
after that, NV withdrew from the chipset market without follow-up procts. In the aspect of Intel, it also has its naming method
let's not talk about the extreme graphics display of the old 800 Series chipset. Let's start with the 900 series< The results showed that the 915g chipset was gma900
945G chipset was GMA950
965G chipset was GMA3000
G31, G33 chipset was GMA3100
G33 chipset was x3500
G41, G43 chipset was x4500
G45 chipset was x4500hd
after 5-series chipset, there was no significant difference between the two chipsets, Intel's integrated display began to be integrated into core I series CPUs
the first generation of core I CPUs integrated HD graphic
the second generation of core I CPUs integrated HD graphic 2000 (although weaker than AMD's integrated display, it also reached the unique HD5450 level)

6. AMD's u with integrated display has the lowest A4
A6
A8 of APU series. No matter u or integrated display, its performance is relatively average. A6 is a 3-core integrated display, and its performance is good. A8 series is high-end. At the beginning, it was compared with i5. The integrated display card can't find the place for i5's integrated display, but u can't find the place for i5's integrated display. If you want to play the game, at least the A6 series, online games basically no problem, single machine, most of the low effect is no problem, the A8 series display performance can be said to be very strong, performance with the low-end unique show have a fight
if you have to buy an APU, it is recommended that A6
3670k / A8
3870k can be overclocking, and it is the kind that both u and graphics card can be overclocking. After the overclocking, the improvement is relatively large, and the game is basically no problem. In fact, I don't recommend buying APU directly. I suggest X4
651k (A8
3870k castrate the display) + 6770 graphics card. It looks like more than 1600 U + motherboard + graphics card, 130 memory and 300 chassis power. The total price is almost more than 2000, but the performance is much higher than the APU you choose.

7. Frequency
the main frequency is also called clock frequency, and its unit is MHz (or GHz), which is used to indicate the speed of CPU operation and data processing. Main frequency of CPU = external frequency × Frequency multiplication coefficient. Many people think that the main frequency determines the running speed of CPU, which is not only one-sided, but also biased for the server. So far, there is no definite formula that can realize the numerical relationship between the main frequency and the actual operation speed. Even Intel and AMD, the two major processor manufacturers, have great controversy on this point. From the development trend of Intel's procts, we can see that Intel attaches great importance to the development of its main frequency. Like other processor manufacturers, someone once compared a 1g quanmeida processor. Its running efficiency is equivalent to 2G Intel processor
there is a certain relationship between the main frequency and the actual operation speed, but it is not a simple linear relationship. Therefore, the main frequency of CPU has no direct relationship with the actual operation ability of CPU, and the main frequency represents the speed of digital pulse signal oscillation in CPU. In Intel's processor procts, we can also see such an example: 1 GHz Itanium chip can perform almost as fast as 2.66 GHz Xeon / Opteron, or 1.5 GHz Itanium 2 can perform about as fast as 4 GHz Xeon / Opteron. CPU operation speed also depends on the CPU pipeline, bus and other aspects of performance indicators
the main frequency is related to the actual operation speed. It can only be said that the main frequency is only one aspect of the performance of the CPU, and does not represent the overall performance of the CPU
external frequency
external frequency is the reference frequency of CPU, and the unit is MHz. The external frequency of CPU determines the running speed of the whole motherboard. Generally speaking, in the desktop computer, the overclocking is the external frequency of the CPU (of course, in general, the frequency doubling of the CPU is locked). I believe this is very easy to understand. But for the server CPU, overclocking is absolutely not allowed. As mentioned earlier, CPU determines the running speed of the motherboard. The two run synchronously. If the server CPU is overclocking and the external frequency is changed, asynchronous operation will occur. (many motherboards of desktop computers support asynchronous operation). This will cause instability of the whole server system
in most computer systems, the external frequency and the front-end bus of the motherboard are not synchronized, and the frequency of the external frequency and the front-end bus (FSB) can be easily confused. The following front-end bus introces the difference between the two
front end bus (FSB) frequency
front end bus (FSB) frequency (bus frequency) directly affects the speed of direct data exchange between CPU and memory. There is a formula to calculate, that is, data bandwidth = (bus frequency) × The maximum bandwidth of data transmission depends on the width and transmission frequency of all data transmitted at the same time. For example, the current Xeon nocona, which supports 64 bits, has a front-end bus of 800MHz. According to the formula, its maximum data transmission bandwidth is 6.4gb/s
the difference between external frequency and FSB frequency: the speed of front-end bus refers to the speed of data transmission, and external frequency refers to the speed of synchronous operation between CPU and motherboard. That is to say, 100MHz external frequency refers to the digital pulse signal, which vibrates 100 million times per second; The 100 MHz front-end bus refers to the amount of data transmission that the CPU can accept per second, which is 100 MHz × 64bit ÷ 8bit/Byte=800MB/s
in fact, the emergence of "HyperTransport" architecture has changed the frequency of FSB. IA-32 architecture must have three important components: memory controller hub (MCH), I / O controller hub and PCI hub. For example, Intel's typical chipsets, Intel 7501 and Intel 7505, are customized for al Xeon processors. Their MCH provides 533MHz front-end bus for CPU. With DDR memory, the front-end bus bandwidth can reach 4.3gb/s. But with the continuous improvement of processor performance, it brings many problems to the system architecture. The "HyperTransport" architecture not only solves the problem, but also improves the bus bandwidth more effectively. For example, the AMD Opteron processor and the flexible HyperTransport I / O bus architecture integrate the memory controller, so that the processor can directly exchange data with the memory without passing it to the chipset through the system bus. In this case, the front-end bus (FSB) frequency in AMD Opteron processor does not know where to start
bit and word length of CPU
bit: binary is used in digital circuit and computer technology, and the code is only "0" and "1", in which "0" or "1" is a "bit" in CPU
word length: in computer technology, the number of bits of binary number that can be processed by CPU in a unit time (at the same time) is called word length. So the CPU that can process 8-bit data is usually called 8-bit CPU. Similarly, 32-bit CPU can process 32-bit binary data in unit time. The difference between byte and word length: because the commonly used English characters can be represented by 8-bit binary, 8-bit is usually called a byte. The length of word length is not fixed. For different CPUs, the length of word length is not the same. An 8-bit CPU can only process one byte at a time, while a 32-bit CPU can process four bytes at a time. Similarly, a 64 bit CPU can process eight bytes at a time
frequency multiplication coefficient
frequency multiplication coefficient refers to the relative proportional relationship between CPU main frequency and external frequency. Under the same external frequency, the higher the frequency doubling, the higher the CPU frequency. But in fact, under the premise of the same external frequency, the CPU with high frequency doubling has little significance. This is because the data transmission speed between the CPU and the system is limited. If the CPU blindly pursues high dominant frequency and gets high frequency doubling, there will be an obvious "bottleneck" effect - the limit speed of the CPU getting data from the system can not meet the speed of CPU operation. In general, except for the engineering sample version of Intel's CPU, it is locked for frequency doubling. A small number of CPU, such as Pentium Dual Core E6500K with inter core 2 core and some supreme version of CPU, do not lock for frequency doubling. Amd did not lock for frequency doubling before. Now amd has launched the black box version of CPU (that is, it does not lock the frequency doubling version. Users can freely adjust the frequency doubling, and the way to adjust the frequency doubling is much more stable than adjusting the external frequency)
cache
cache size is also one of the important indicators of CPU, and the structure and size of cache have a great impact on CPU speed. The running frequency of cache in CPU is very high, generally operating at the same frequency as the processor, and the work efficiency is far greater than the system memory and hard disk. In practice, the CPU often needs to read the same data block repeatedly, and the increase of cache capacity can greatly improve the hit rate of data read inside the CPU, instead of searching in memory or hard disk, so as to improve the system performance. However, e to the CPU chip area and cost factors, the cache is very small
L1 cache is the first layer of CPU cache, which is divided into data cache and instruction cache. The capacity and structure of the built-in L1 cache have a great impact on the performance of CPU, but the cache is composed of static RAM, and the structure is complex. When the CPU chip area is not too large, the capacity of L1 cache can not be too large. The L1 cache capacity of general server CPU is usually 32-256kb
L2 cache is the second layer cache of CPU, which is divided into internal and external chips. The internal chip's L2 cache runs at the same speed as the main frequency, while the external L2 cache only runs at half of the main frequency. The L2 cache capacity will also affect the performance of CPU. The principle is that the larger the CPU, the better. In the past, the largest CPU capacity for home use was 512KB, but now it can reach 2m in notebook computers, while the L2 cache capacity for servers and workstations is higher, reaching more than 8m
L3 cache can be divided into two types: external cache in the early stage and built-in cache now. Its practical function is that the application of L3 cache can further rece the memory latency and improve the performance of processor in large amount of data computing. Recing memory latency and improving the computing power of large amount of data are very helpful to the game. However, in the server area, there is still a significant improvement in L3 buffer performance. For example, a configuration with a larger L3 cache can make more efficient use of physical memory, so its slower disk I / O subsystem can handle more data requests. Processors with larger L3 cache provide more efficient file system caching behavior and shorter message and processor queue length
in fact, the earliest L3 cache was applied to the k6-iii processor released by AMD. Limited by the manufacturing process, the L3 cache was not integrated into the chip, but integrated on the motherboard. In L3, which can only synchronize with the system bus frequency, the cache is not much different from the main memory. Later, the L3 cache was introced by Intel's Itanium processor for the server market. Then there are p4ee and Xeon MP. Intel also plans to launch a 9mb L3 cache Itanium 2 processor and a 24MB L3 cache al core Itanium 2 processor
but basically, L3 cache is not very important for processor performance improvement. For example, Xeon MP processor with 1MB L3 cache is still not an opponent of Opteron. It can be seen that the increase of front-end bus brings more effective performance improvement than the increase of cache
CPU expands instruction set
CPU relies on instructions to calculate and control the system, and each CPU is designed with a series of instruction systems matched with its hardware circuit. Instruction set is one of the most effective tools to improve the efficiency of microprocessor. From the current mainstream architecture, instruction set can be divided into two parts: complex instruction set and reced instruction set. From the specific application, such as Intel's MMX (multi media extended), SSE, SSE2 (streaming single instruction multiple data extensions 2), sse3, SSE4 series and AMD's 3DNOW! These are the extended instruction sets of CPU, which enhance the processing ability of multimedia, graphics and Internet. Generally, the extended instruction set of CPU is called "instruction set of CPU". Sse3 instruction set is also the smallest instruction set at present. Previously, MMX contained 57 commands, SSE contained 50 commands, SSE2 contained 144 commands, and sse3 contained 13 commands. At present, SSE4 is also the most advanced instruction set. Intel Core series processors already support SSE4 instruction set. AMD will add support for SSE4 instruction set to al core processors in the future, and the processor of quanmeida will also support this instruction set
working voltage of CPU core and I / O
starting from 586 CPU, the working voltage of CPU is divided into core voltage and I / O voltage. Generally, the core voltage of CPU is less than or equal to I / O voltage. The size of the core voltage is determined by the proction process of CPU. Generally, the smaller the proction process is, the lower the working voltage of the core is; I / O voltage is generally 1.6 ~ 5V. Low voltage can solve the problem of excessive power consumption and excessive heating
manufacturing process
the micron of manufacturing process refers to the distance between circuits in IC. The trend of manufacturing technology is to develop in the direction of higher density. The higher the density of IC circuit design, means that in the same size area of IC, can have a higher density, more complex circuit design. At present, the main procts are 180nm, 130nm, 90nm, 65nm and 45nm. Recently, inter has a 32 nanometer core I3 / i5 series
AMD, on the other hand, said that its procts will directly skip the 32nm process (proced in the third quarter of 2010)

8. CPU is the central processing unit, GPU is the graphics processor, the function of the two is impassable, there is no way to compare
I don't think the model is very good. Let's wait for others to answer
Qualcomm's is better, I think

9. Using the game plus hardware monitoring, you can know the computer hardware model, brand, memory and other hardware information in detail