On 9/14/05, Raghu Vadapalli <iprsvp@xxxxxxxxx> wrote: > AFAIU, > > UMA --- CPU to Memory bank access times are same. > > NUMA -- CPU to memory bank access times are different for different cpus. > > So you always want to allocate from the memory bank which is near to you. Yes, that is pretty much the basic difference. Consider (hypothetically), a shared bank of memory between two CPUs, designed to provide the same access time to both. That would be UMA (pretty straightforward and common). Consider (again hypothetically), 2 nodes, where each node is effectively a self-contained machine, i.e. 1 CPU, own bank of memory, etc. However, CPU0 can access CPU1's memory and v.v. This would be NUMA, though, as the access time to go off-node and back is *significantly* higher than that for on-node memory. Thanks, Nish -- Kernelnewbies: Help each other learn about the Linux kernel. Archive: http://mail.nl.linux.org/kernelnewbies/ FAQ: http://kernelnewbies.org/faq/
