The load average is the average of the load for a given period of time on each CPU. It takes into account the following:
Actively running processes (including each thread as an individual, separate task) on a CPU core.
Runnable processes, waiting for a CPU to become available.
Sleeping processes, for example, waiting for some kind of resource (generally disk I/O or network I/O) to become available.
Linux counts each physical CPU core and microprocessor hyper-thread as separate execution units, and refers to them as individual CPUs. Each CPU has an independent request queue. We can count the total number of system CPUs using by the following command:
$ grep "model name" /proc/cpuinfo | wc -l