Getting Started: Understanding Server-Related Parameters

  
1, Server Processor Main Frequency


The server processor main frequency is also called the clock frequency, and the unit is MHz, which is used to indicate the CPU's operation speed. The main frequency of the CPU = FSB × multiplier. Many people think that the clock speed determines the speed of the CPU, which is not only one-sided, but also for the server, this understanding has also deviated. So far, there is no definitive formula to achieve the numerical relationship between the main frequency and the actual computing speed. Even the two major processor manufacturers Intel and AMD have great controversy at this point. We are from Intel. The development trend of the products, it can be seen that Intel is very focused on strengthening its own frequency development. Like other processor manufacturers, some people have used a fast 1G Transmeta to compare, its operating efficiency is equivalent to 2G Intel processor.

Therefore, the CPU clock speed and the actual computing capacity is not directly related to the CPU, the CPU clock speed represents the speed of the digital pulse signal shock. In Intel's processor products, we can also see examples of this: the 1 GHz Itanium chip can behave almost as fast as the 2.66 GHz Xeon/Opteron, or the 1.5 GHz Itanium 2 is about as fast as the 4 GHz Xeon/Opteron. The CPU's operating speed depends on the performance of all aspects of the CPU's pipeline.

Of course, clock speed and the actual speed of operation is related only say that frequency is only one aspect of CPU performance, and do not represent the overall CPU performance.


2, the server front-side bus (FSB) frequency


front side bus (FSB) frequency (i.e., frequency bus) directly affect the CPU and a direct memory exchange data speed. There is a formula that can be calculated, that is, data bandwidth = (bus frequency × data bandwidth) /8, the maximum bandwidth of data transmission depends on the width and transmission frequency of all simultaneously transmitted data. For example, the current support for 64-bit Xeon Nocona, the front side bus is 800MHz, according to the formula, its data transmission maximum bandwidth is 6.4GB /sec.

difference FSB front side bus (FSB) frequency: front side bus speed refers to the data transmission speed, FSB is the synchronous operation between the CPU and the speed of the motherboard. That is to say, the 100MHz FSB specifically refers to the digital pulse signal oscillating 10 million times per second; and the 100MHz front side bus refers to the acceptable data transmission amount per second CPU is 100MHz × 64bit ÷ 8Byte /bit = 800MB /s.

fact, "HyperTransport" architecture appear, so front-side bus on the actual meaning of this (FSB) frequency change. Before we knew that the IA-32 architecture must have three important components: the memory controller Hub (MCH), the I/O controller Hub and the PCI Hub, and the typical Intel chipset Intel 7501 and Intel7505 chipset, which are dual-strong. The processor is tailor-made, and the MCH it contains provides a front-side bus with a frequency of 533MHz for the CPU. With DDR memory, the front-side bus bandwidth can reach 4.3GB/sec.

but with the processor performance continues to increase at the same time brings a lot of 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, the flexible HyperTransport I/O bus architecture allows it to integrate the memory controller so that the processor does not pass through the system bus. Exchange data directly with the memory for the chipset. In this case, the front side bus (FSB) frequency is not known in the AMD Opteron processor.

3, the processor FSB


CPU FSB is the reference frequency, the unit is MHz. The CPU's FSB determines the speed of the entire board. To put it bluntly, in the desktop, what we call overclocking is the FSB's FSB (of course, the CPU multiplier is locked). I believe this is well understood. But for server CPUs, overclocking is absolutely not allowed. As mentioned above, the CPU determines the running speed of the motherboard. The two are running synchronously. If the CPU of the server is overclocked and the FSB is changed, asynchronous operation will occur. (Many motherboards of the desktop support asynchronous operation) This will cause the entire server. The system is unstable.

present in the vast majority of computer systems are FSB speed synchronous operation between the memory and the motherboard, in such a manner, as will be appreciated CPU FSB directly communicating with the memory, to achieve between the two Synchronous running state. The FSB and Front Side Bus (FSB) frequencies are easily confused. The following front side bus introduces us to the difference between the two.

4, CPU bit and word length


bits: binary digital circuits and computer technology, the only code "0" and "1", regardless of which Whether it is "0" or "1" is a "bit" in the CPU.

Word length: The number of bits in a computer technology that can be processed once per CPU time (at the same time) by the CPU is called the word length. Therefore, a CPU that can process 8-bit data is usually called an 8-bit CPU. Similarly, a 32-bit CPU can process binary data with a word length of 32 bits per unit time. The difference between byte and word length: Since commonly used English characters can be represented by 8-bit binary, 8 bits are usually called one byte. The length of the word length is not fixed, and the length of the word length is different for different CPUs. An 8-bit CPU can only process one byte at a time, while a 32-bit CPU can process 4 bytes at a time. A CPU with the same 64-bit length can process 8 bytes at a time.

5, the multiplication factor


multiplier factor means the ratio between the relative frequency of the CPU FSB. At the same FSB, the higher the multiplier, the higher the CPU frequency. But in fact, under the premise of the same FSB, the high-frequency CPU itself does not mean much. This is because the data transmission speed between the CPU and the system is limited. The CPU that achieves high frequency multiplication and high frequency will have obvious "bottleneck" effect. The limit speed of the CPU to obtain data from the system cannot satisfy the CPU operation. speed. In general, except for the engineering version of Intel's CPU, the multiplier is locked, and AMD has no lock before.

6, an important indicator of CPU cache


also CPU cache size, and influence the structure and size of the cache on the CPU speed is very large, in the CPU cache The operating frequency is extremely high, generally operating at the same frequency as the processor, and the working efficiency is far greater than the system memory and the hard disk. In actual work, the CPU often needs to repeatedly read the same data block, and the increase of the cache capacity can greatly improve the hit rate of the internal read data of the CPU, instead of looking into the memory or the hard disk, thereby improving system performance. . However, due to the factor of CPU chip area and cost, the cache is very small.

L1 Cache (cache) is the CPU of the first level cache, data cache and instruction cache divided. The capacity and structure of the built-in L1 cache have a great impact on the performance of the CPU. However, the cache memory is composed of static RAM. The structure is more complicated. The capacity of the L1 cache is not large when the CPU die area is not too large. It may be too big. The capacity of the L1 cache of a general server CPU is usually 32-256 KB.


L2 Cache (secondary cache) is a second level cache of the CPU, both internal and external sub-chip. The internal chip L2 cache runs at the same speed as the main frequency, while the external L2 cache is only half the main frequency. The L2 cache capacity also affects the performance of the CPU. The principle is that the bigger the better, the largest CPU capacity for home use is 512KB, and the L2 cache for CPUs on servers and workstations is up to 256-1MB, and some are up to 2MB or 3MB. .

L3 Cache (three cache), divided into two types, early is external, are now built. The practical effect of this is that L3 cache applications can further reduce memory latency while improving the performance of processors in large data volumes. Reducing memory latency and increasing the amount of computing power can be very helpful for games. The increase in L3 cache in the server space is still a significant improvement in performance. For example, a configuration with a larger L3 cache can be more efficient with physical memory, so its slower disk I/O subsystem can handle more data requests. Processors with larger L3 caches provide more efficient file system caching behavior and shorter message and processor queue lengths.

fact, the first L3 cache is used in AMD released the K6-III processor, when the L3 cache is limited by the manufacturing process, and not integrated into the chip, but integrated on the motherboard. The L3 cache, which can only synchronize with the system bus frequency, is not much different from the main memory. Later, using the L3 cache was Intel's Itanium processor for the server market. Then there is P4EE and Xeon MP. Intel also plans to introduce a 9MB L3 cached Itanium2 processor and a dual-core Itanium2 processor with 24MB L3 cache.

but basically L3 cache to improve the performance of the processor it is not very important, for example, is equipped with 1MB L3 cache Xeon MP processor Opteron is still not the opponent, we can see an increase in front side bus, cache than Increases bring more effective performance gains.
Copyright © Windows knowledge All Rights Reserved