imported>KrisTHL181：修正笔误

2025-12-07T17:20:22Z

修正笔误

新页面

{{noteTA|G1=IT}}
{{Rough translation|time=2023-06-28T09:36:23+00:00}}
{{Expand language|en|time=2023-06-28T09:36:23+00:00}}
'''BogoMips''' ("bogus"與[[每秒百萬指令|MIPS]]，伪MIPS) 是一种衡量CPU速度的不科学方法。当计算机内核启动时，将执行一个计数循环。

对于特定的CPU，BogoMips可用来查看它是否个合适的值。它的时钟频率和它潜在的CPU缓存。但是它不可在不同的CPU间进行比较演示。<ref name="howto">{{cite web | first = Wim | last = Van Dorst | url = http://www.clifton.nl/bogomips.html | title = BogoMips Mini-Howto | edition = V38 | date = 2 March 2006 | accessdate = 2008-08-22 | archive-date = 2013-08-27 | archive-url = https://www.webcitation.org/6JAzWvwZk?url=http://www.clifton.nl/bogomips.html | dead-url = no }}</ref>

== 合适的BogoMips比率 ==
作为一个参考向导，BogoMips可以用下列的表格进行预计算。给出的比率是以应用到LINUX版本的CPU作为例子。指数是指其它CPU同Intel 386DX CPU的BogoMips/clock speed比率.
{| class="sortable wikitable"
!CPU!!比率!!指数
|-
|[[Intel 8088]] ||clock * 0.004||0.02
|-
|[[Intel 80386|Intel/AMD 386SX]] ||clock * 0.14||0.8
|-
|[[Intel 80386|Intel/AMD 386DX]] ||clock * 0.18||1 (definition)
|-
|[[Motorola 68030]]||clock * 0.25||1.4
|-
|[[Cyrix]]/[[IBM]] 486||clock * 0.34||1.8
|-
|Intel [[Intel P5|Pentium]]||clock * 0.40||2.2
|-
|[[Intel 80486|Intel 486]] ||clock * 0.50||2.8
|-
|[[AMD 5x86]]||clock * 0.50||2.8
|-
|[[MIPS Technologies|MIPS]] R4000/R4400||clock * 0.50||2.8
|-
|[[ARM9]]||clock * 0.50||2.8
|-
|[[Motorola 8081]]||clock * 0.65||3.6
|-
|[[Motorola 68040]]||clock * 0.67||3.7
|-
|[[PowerPC]] 603||clock * 0.67||3.7
|-
|Intel [[StrongARM]]||clock * 0.66||3.7
|-
|[[NexGen]] Nx586||clock * 0.75||4.2
|-
|[[PowerPC]] 601||clock * 0.84||4.7
|-
|[[Alpha 21064]]/21064A||clock * 0.99||5.5
|-
|[[Alpha 21064|Alpha 21066]]/21066A||clock * 0.99||5.5
|-
|[[Alpha 21164]]/21164A||clock * 0.99||5.5
|-
|Intel [[Pentium Pro]]||clock * 0.99||5.5
|-
|[[Cyrix Cx5x86|Cyrix 5x86]]/[[Cyrix 6x86|6x86]] ||clock * 1.00||5.6
|-
|Intel [[Pentium II]]/[[Pentium III|III]]||clock * 1.00||5.6
|-
|[[Athlon|AMD K7/Athlon]]||clock * 1.00||5.6
|-
|Intel [[Celeron]]||clock * 1.00||5.6
|-
|Intel [[Itanium]]||clock * 1.00||5.6
|-
|[[R4600]]||clock * 1.00||5.6
|-
|[[Hitachi, Ltd.|Hitachi]] SH-4||clock * 1.00||5.6
|-
|Intel [[Itanium 2]]||clock * 1.49||8.3
|-
|[[Alpha 21264]]||clock * 1.99||11.1
|-
|[[VIA Technologies|VIA Centaur]]||clock * 1.99||11.1
|-
|[[AMD K6|AMD K5/K6/K6-2/K6-III]]||clock * 2.00||11.1
|-
|AMD [[Duron]]/[[Athlon]] XP||clock * 2.00||11.1
|-
|AMD [[Sempron]]||clock * 2.00||11.1
|-
|[[SPARC|UltraSparc]] II||clock * 2.00||11.1
|-
|Intel [[Pentium MMX]]||clock * 2.00||11.1
|-
|Intel [[Pentium 4]]||clock * 2.00||11.1
|-
|Intel [[Pentium M]]||clock * 2.00||11.1
|-
|Intel [[Core Duo]]||clock * 2.00||11.1
|-
|Intel [[Core 2 Duo]]||clock * 2.00||11.1
|-
|Intel [[Intel Atom|Atom]] N455||clock * 2.00||11.1
|-
|Centaur C6-2||clock * 2.00||11.1
|-
|[[PowerPC]] 604/604e/750||clock * 2.00||11.1
|-
|Intel [[Pentium III#Coppermine|Pentium III Coppermine]]||clock * 2.00||11.1
|-
|Intel [[Xeon#Pentium_III_Xeon|Pentium III Xeon]]||clock * 2.00||11.1
|-
|[[Motorola 68060]]||clock * 2.01||11.2
|-
|Intel [[Xeon#Xeon_.28DP.29_.26_Xeon_MP_.2832-bit.29|Xeon MP (32-bit)]] ([[hyper-threading]])||clock * 3.97||22.1
|-
|[[IBM eServer zSeries|IBM S390]]||not enough data (yet)||
|-
|[[ARM architecture|ARM]]||not enough data (yet)||
|}

== BogoMIPS 怎么计算的? ==
在当前内核(2.6.x),BogoMIPS实现在内核源文件<code>/usr/src/linux/init/calibrate.c</code>。它计算了Linux内核定时参数<code>loops_per_jiffy</code> (see {{tsl|en|Jiffy (time)||Jiffy}} ) 值。源码解释如下：
<pre><nowiki>
/*
* A simple loop like
* while ( jiffies < start_jiffies+1)
* start = read_current_timer();
* will not do. As we don't really know whether jiffy switch
* happened first or timer_value was read first. And some asynchronous
* event can happen between these two events introducing errors in lpj.
*
* So, we do
* 1. pre_start <- When we are sure that jiffy switch hasn't happened
* 2. check jiffy switch
* 3. start <- timer value before or after jiffy switch
* 4. post_start <- When we are sure that jiffy switch has happened
*
* Note, we don't know anything about order of 2 and 3.
* Now, by looking at post_start and pre_start difference, we can
* check whether any asynchronous event happened or not
*/
</nowiki></pre>

<code>loops_per_jiffy</code> 用于实现 <code>udelay</code>（微秒级延时）和 <code>ndelay</code>（纳秒级延时）函数。某些驱动程序需要这些函数来等待硬件操作完成。这里采用了[[忙等待]]（busy waiting）方法，所以在执行 <code>ndelay</code> 或 <code>udelay</code> 函数期间，内核实际上处于阻塞状态。对于i386结构，<code>delay_loop</code> 的实现在 <code>/usr/src/linux/arch/i386/lib/delay.c</code> 中，如下所示：
<syntaxhighlight lang="c">
/* simple loop based delay: */
static void delay_loop(unsigned long loops)
{
int d0;

__asm__ __volatile__(
"\tjmp 1f\n"
".align 16\n"
"1:\tjmp 2f\n"
".align 16\n"
"2:\tdecl %0\n\tjns 2b"
:"=&a" (d0)
:"0" (loops));
}
</syntaxhighlight>

用C语言重写的代码如下：
<syntaxhighlight lang="c">
static void delay_loop(long loops)
{
long d0 = loops;
do {
--d0;
} while (d0 >= 0);
}
</syntaxhighlight>

关于BogoMips更丰富更全的信息和数百篇相关文章可参见 BogoMips mini-Howto.<ref name=howto/>

==参考==
{{Reflist}}

== 外部链接 ==
* [http://www.clifton.nl/bogomips.html BogoMips Mini-Howto, V38]{{Wayback|url=http://www.clifton.nl/bogomips.html |date=20130530163229 }}

{{DEFAULTSORT:Bogomips}}

[[Category:Linux內核]]
[[Category:计算机性能测试]]

BogoMips - 版本历史

imported>KrisTHL181：​修正笔误

imported>KrisTHL181：修正笔误