Can't schedule instances using greater than 12 pinned vCPUs on a compute node with 40 threads available

Issue

• 1 compute node has been set aside for use in testing CPU pinning and NUMA topology awareness This compute node has 2 physical CPUs with hyper-threading turned on, yielding 12 physical cores and 24 threads per physical CPU (total of 24 physical cores and 48 threads per compute node). 8 threads given to physical machine hence 40 threads are available for instances.
• The RAM available to the compute node is 128GB, split into two NUMA cells of ~64GB each;

available: 2 nodes (0-1)
node 0 cpus: 0 2 4 6 8 10 12 14 16 18 20 22 24 26 28 30 32 34 36 38 40 42 44 46
node 0 size: 65439 MB
node 0 free: 58074 MB
node 1 cpus: 1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33 35 37 39 41 43 45 47
node 1 size: 65536 MB
node 1 free: 62156 MB
node distances:
node   0   1 
  0:  10  21 
  1:  21  10