Gaussian benchmarks

Test number 178

Input file is from Gaussian94 test suite. No modifications are made. Job is single point HF calculation with NPA population analysis. Number of basis functions is 300 and number of (direct) SCF iterations is 8.

New timing data is welcome. Results can be mailed to (Juha.Muilu@joensuu.fi)

GAUSSIAN94
Computer                Proc    MHz   time               versions 
                                /MB(* elapsed cpu+sys(*  G94    OS  F77
------------------------------------------------------------------------
CRAY C94/128                                  4:35       RevB.1 Compiled on XMP
DEC 8400 5/350          Alpha   350   6:56    6:06       RevD.1 3.2 3.8
DEC 3600/128MB          Alpha   175   18:28   18:03             3.2
DEC 3900/192MB		Alpha 	275   16:31   13:52	 RevD.1 3.2 3.8
DEC 2100  4/275/128MB   Alpha                 13:03
DEC 4000/710/256MB      Alpha                 19:06 
DEC 2000/300/64MB       Alpha         40:26   39:39
IBM RS6000 590/512MB    Power2  66             7:42      RevB.3 3.1 
IBM RS6000 380/32MB     Power2  57            19:06
IBM RS6000 370/64MB     Power2                24:49
IBM pwr3 (nighthawk)            222    4:08    3:39
SGI Power Onyx/2GB    8*R8000   75             8:42      RevB.1 5.3(**
SGI Power Indigo/128MB  R8000   75             8:02
SGI Indigo2             R10000  200            9:03      RevD.2 6.2 4.0 Compiled on R8K
SGI Challenge/64MB M    R4400   150   32:33   31:24
SGI Challenge/64MB L    R4400   100   45:26   44:18
SGI Power Indigo2       R8000   75             8:04      RevD.3 Sec.Cache 2MB
SGI Power Challenge     R8000   90             6:50      RevD.3 Sec.Cache 4MB
SGI Power Indigo2       R10000  195            7:30      RevD.3 Sec.Cache 1MB
SGI Power Challenge     R10000  195            7:08      RevD.3 Sec.Cache 1MB
SGI Power Challenge     R10000  195            5:95      RevD.3 Sec.Cache 2MB
SGI Indy                R5000   180           31:44      RecD.3 5.3 4.0
SGI Indigo2/128MB       R4400   250           20:13      RecB.3 5.3 4.0
SGI Indigo2             R4400   200           24:32      RecD.2 5.3 
SGI Indigo/32           R4000   100   52:13   50:07      RevB.3 5.3      
SGI Indigo/64           R4400   150   33:08   31:58      RevB.3 5.3 
SGI Indigo              R4600   133           47:26
SGI Indy                R4600PC 133         1:04:24
SGI Personal Iris  35   R3000    35         4:16:50 
SUN UltraSparc 170      Sparc   167           18:43      RevC.3  2.5 Solaris

(* Job CPU time from the Gaussian output file. (minutes:seconds)
(**Only one processor is used on MP machines


GAUSSIAN92
Computer                Proc    MHz     N   LP 178     G92    OS/FOR   
                                               min     ver    versions
----------------------------------------------------------------------
PC/32MB 512cache        Pentium 90      1      600
SGI Indigo/32Mb         R4000   50/100  1  16  111     RevC.3
SGI Indigo/32Mb         R4400   75/150  1  24  80      RevC.3
SGI Challenge           R8000   75      1      16
IBM RS6000 590/256MB    Power2  66      1 132  20      RevB      
IBM RS6000 590/256MB    Power2  66      1 132  17      RevG.3
IBM RS6000 390/         Power2          1      41
IBM RS6000 380/32MB     Power2  57      1  50  45      RevB
IBM RS6000 370          Power   62      1  26  57
IBM RS6000 550          Power   42      1  26  61
IBM RS6000 540          Power   30      1  19  83
IBM RS6000 32H/16MB     Power   25      1  12 134      RevB
DEC 3600 AXP/128                        1      49              3.0/3.6
DEC 3000 AXP 800/Unix   Alpha   200     1      44      RevE.2
DEC 3000 300            Alpha   150     1     144
DEC 3000 AXP 400/VMS    Alpha   133     1 26   90      RevG.2
DEC 3600 AXP            Alpha           1      59      RevG.3  2.0/3.4  
DEC 3600 AXP            Alpha           1      49      RevG.3  3.0/3.6
Cray X-MP EA/432                117     1 66   17
CRAY C90 8/256                  250     1      4.3     RevC.3
CRAY C90 8/256(incore)          250     1      1.5     RevC.3
CRAY YMP EL                     34      1      39
Convex C3840                    37      1      39


*)         Options added: -qtune=pwr2 -qarch=pwr2

Nproc) Number of processors used.
LP )   Linpack DP (100x100).

Related links

Local links...

[Use of translational symmetry...]
[ZnS cluster models]
[Visualization tools]
[Top Page]

Juha.Muilu@joensuu.fi
Last modified: Mon Nov 18 12:36:23 EET 1996