简体   繁体   English

Power8处理器上有多少个NUMA节点

[英]How many NUMA nodes on a Power8 processor

I am using Ubuntu 15.04 on a two sockets Power8 machine, each socket has 10 cores. 我在两个插座的Power8机器上使用Ubuntu 15.04,每个插槽有10个内核。 "numactl -H" outputs: “numactl -H”输出:

available: 4 nodes (0-3)
node 0 cpus: 0 8 16 24 32
node 0 size: 30359 MB
node 0 free: 26501 MB
node 1 cpus: 40 48 56 64 72
node 1 size: 0 MB
node 1 free: 0 MB
node 2 cpus: 80 88 96 104 112
node 2 size: 30425 MB
node 2 free: 27884 MB
node 3 cpus: 120 128 136 144 152
node 3 size: 0 MB
node 3 free: 0 MB
node distances:
node   0   1   2   3 
  0:  10  20  40  40 
  1:  20  10  40  40 
  2:  40  40  10  20 
  3:  40  40  20  10 

The problem is, are there two NUMA nodes on each Power8 processor? 问题是,每个Power8处理器上有两个NUMA节点吗? Any why one has memory but the other one has nothing. 为什么一个人有记忆而另一个人什么都没有。 I can't find any document about this. 我找不到任何关于此的文件。 Any information would be appreciated. 任何信息,将不胜感激。

A further question, if there are two nodes on a socket, then are their last level cache shared like NUMA nodes(a data can reside in all of the caches) or like on the same socket(only one copy can exist). 另一个问题是,如果套接字上有两个节点,那么它们的最后一级缓存就像NUMA节点一样共享(数据可以驻留在所有缓存中)或者类似于同一套接字(只能存在一个副本)。

Scale-out POWER8 systems use Dual-Chip Modules (DCMs). 横向扩展POWER8系统使用双芯片模块(DCM)。 As the name suggests, a DCM packages two multi-core chips with some additional logic within the same physical package. 顾名思义,DCM在同一物理封装中封装了两个多核芯片和一些额外的逻辑。 There is an on-package cache-coherent 32 GBps interconnect (misleadingly called an SMP bus) between the two chips and two separate paths to the external memory buffers, one for each chip. 两个芯片之间有一个封装缓存一致的32 GBps互连(误导性地称为SMP总线)和两个到外部存储缓冲器的独立路径,每个芯片一个。 Thus, each socket is a dual-node NUMA system itself, similar to eg, the multi-module AMD Opterons. 因此,每个插座本身是双节点NUMA系统,类似于例如多模块AMD Opterons。 In your case, all of the memory local to a given socket is probably installed in the slots belonging to the first chip of that socket only, therefore the second NUMA domain shows up as 0 MB. 在您的情况下,给定套接字本地的所有内存可能只安装在属于该套接字的第一个芯片的插槽中,因此第二个NUMA域显示为0 MB。

Both the on-package (X bus) and inter-package (A bus) interconnects are cache-coherent, ie the L3 caches are kept in sync. 封装(X总线)和封装间(A总线)互连都是高速缓存一致的,即L3高速缓存保持同步。 Within a multi-core chip, each core is directly connected to a region of L3 cache and through the chip interconnect has access to all other L3 caches of the same chip, ie a NUCA (Non-Uniform Cache Architecture). 在多核芯片内,每个核心直接连接到L3高速缓存的区域,并且通过芯片互连可以访问同一芯片的所有其他L3高速缓存,即NUCA(非统一高速缓存架构)。

For more information, see the logical diagram of an S824 system in this Redpaper . 有关更多信息,请参阅本红皮书中 S824系统的逻辑图。

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM