Some results on an inverter chain with 627 CMOS inverters, running for 200ns, compiled with Visual Studio professional 2008 on Windows 7 (full optimization) or gcc 4.4, SUSE Linux 11.2, -O2, on a i7 860 machine with four real cores (and 4 virtuals using hyperthreading) are shown in table 16.1.

Table 16.1: OpenMP performance

So we see a ngspice speed up of nearly a factor of two! Even on an older notebook with a dual core processor, more than 1.5x improvement using two threads was attained. Similar results are to be expected from BSIM4.