Problem finding optimal configuration using Xeon cpus

[pdelteil]

My configuration has a total of 45 MB cache L3, therefore I can run up to 22 threads. Hwloc-ls tells me I have 5 physical cores and 10 threads.

I'm trying to 'accommodate' 22 threads of mining in 5 physical cores.

My results:

• 2 mining threads per physical core (10 threads total): 390 H/s
• 2 mining threads per physical core + Virtual core (HT) (2 * 10 = 20 threads): 270 H/s
• 1 mining threads per physical core + Virtual core (HT) (1 * 10 = 10 threads): 370 H/s

Config
xmr-stak 2.4.3 26a5d65
Virtual Machines on Google Cloud infrastructure.
CPU: Intel Xeon with 5 cores @2.3 Ghz.

hwloc-ls

Machine (8984MB)
Package L#0 + L3 L#0 (45MB)
L2 L#0 (256KB) + L1d L#0 (32KB) + L1i L#0 (32KB) + Core L#0
PU L#0 (P#0)
PU L#1 (P#5)
L2 L#1 (256KB) + L1d L#1 (32KB) + L1i L#1 (32KB) + Core L#1
PU L#2 (P#1)
PU L#3 (P#6)
L2 L#2 (256KB) + L1d L#2 (32KB) + L1i L#2 (32KB) + Core L#2
PU L#4 (P#2)
PU L#5 (P#7)
L2 L#3 (256KB) + L1d L#3 (32KB) + L1i L#3 (32KB) + Core L#3
PU L#6 (P#3)
PU L#7 (P#8)
L2 L#4 (256KB) + L1d L#4 (32KB) + L1i L#4 (32KB) + Core L#4
PU L#8 (P#4)
PU L#9 (P#9)
HostBridge L#0
PCI 1af4:1000

/proc/cpuinfo

processor : 0,9
vendor_id : GenuineIntel
cpu family : 6
model : 63
model name : Intel(R) Xeon(R) CPU @ 2.30GHz
stepping : 0
microcode : 0x1
cpu MHz : 2300.000
cache size : 46080 KB
physical id : 0
siblings : 10
core id : 4
cpu cores : 5
cpuid level : 13

How can I get more hashes per second?