Gaussian 98 A7 Compiler Comparisson (1 CPU & 2 CPU)

Job = LADH Dimer (76723 Atoms) QMMM CIS/3-21G*

Route = #p CIS=(Direct, Nstates=4,conver=3)/3-21G* Charge Nosymm

%Mem = 256MB

Compiler options used:

PGF77 (3.2-4a) Portland Blas Library (-tp p6) 256KB Cache
PGF77 (3.2-4a) Portland Blas Library -Mvect=sse -r8 (-tp p6) 256 KB Cache
PGF77 (3.2-4a) Portland Blas Library -Mvect=prefetch (-tp athlon) 256KB Cache

System Specs

Dual Intel PIII 800EB
512MB PC133 Cas3 Ram
IBM 7200RPM Deskstar 46GB HD
MSI Dual PIII Motherboard 694D Via Chipset
GeForce2 GTS 32MB Graphics Card
Redhat 7.1 (Kernel 2.4.1)

Dual AMD Athlon 1.2GHz MP
1GB PC2100 DDR Ram
10,000RPM LVD160 SCSI Drive 36GB
Tyan Thunder K7 Board
or Alternative AMD Board
Redhat Linux 7.1 (Kernel 2.4.7)


Compiler / CPUS Time (s)
P3/800 1CPU PGF77 Def 22483
P3/800 1CPU PGF77 SSE -r8 20955.6
P3/800 2CPU PGF77 Def 15523.6
P3/800 2CPU PGF77 SSE -r8 14916.5
Athlon 1.2GHMP, Tyan K7 1 CPU PGF77 Def 14400.08
Athlon 1.2GHMP, Tyan K7 1 CPU PGF77 -tpathlon -Mvect=prefetch 14491.6
Athlon 1.2GHMP, Tyan K7 1 CPU PGF77 Def 8426.6
Athlon 1.2GHMP, Tyan K7 2 CPU PGF77 -tpathlon -Mvect=prefetch 8421.3
Athlon 1.2GHMP Alt Chipset 1 CPU PGF77 -tpathlon -Mvect=prefetch 14345.7
Athlon 1.2GHMP Alt Chipset 2 CPU PGF77 -tpathlon -Mvect=prefetch 8462


Tyan K7 1 = Single processor job
Tyan K7 2 = Dual processor job
Alt Chipset 1 = Single processor job
Alt Chipset 2 =  Dual processor job


Turning on SSE extensions makes a big difference (and only changes answers in last 1 or 2 decimal places). Single Processor AMD 1.2GHz MP is slightly faster than 2 x PIII 800. and it also performs more efficiently in parallel.

The alternative Chipset motherboard makes no noticeable difference.