I am active.
I am trying to move all memory access to the remote NUMA node(i.e., node1), using numatop or other tools, if possible. However, seems to me the Numpy that uses OpenBLAS internally does not go to node1.
This is the workload I am testing, just a simple matrix multiplication. Running...
I'm working on a NUMA-related benchmark and got an issue troubling me for a week.
I use numactl to pin a metrics multiplication workload to use node0's CPU and node1's memory like this:
However, I observe tons of memory access still goes to node0 (throughput is high), either using pcm or...
This is the second time I crashed our department servers. :-( Really don't know why.
The previous configuration was: We had a persistent memory namespace (/dev/pmem0) that was mounted at /mnt/pmem. We wanted to change it to Mixed Mode. So we unmounted this file directory ($ umount /mnt/pmem)...