STREAM "Experimental & Nonstandard" results

This is the "Experimental & Nonstandard" set of STREAM benchmark results.

This set includes only the following categories:

Assembly language results.
Other hand-coded results.
Simulated results.
Results from experimental or non-production hardware.
Results from "partially depopulated" systems (i.e., results based on the use of a subset of a system's processors, where the processors are "spread around" to decrease contention).

STREAM Machine Balance --- John D. McCalpin, mccalpin@cs.virginia.edu
Revised to Tue Apr 15 17:23:56 CDT 2008

Balance is Peak MFLOPS divided by Triad Bandwidth in MW/s
------------------------------------------------------------------
Machine ID                              Peak       BW    Machine		
Machine ID                      ncpus  MFLOPS    (MW/s)  Balance		
------------------------------------------------------------------
Azul_Vega2_7280                  768    92160.0  11424.3      8.1 data
Cray_J98                           4      800.0    543.2      1.5
Cray_J98                           2      400.0    304.1      1.3
Cray_J98                           1      200.0    151.5      1.3
Cray_J98                           1      200.0    159.4      1.3
IBM_eServer_p680                  24    28800.0    629.5     45.7 data
IBM_eServer_p680                  24    28800.0    849.6     33.9 data
IBM_eServer_p680                  22    26400.0    625.5     42.2 data
IBM_eServer_p680                  20    24000.0    576.7     41.6 data
IBM_eServer_p680                  18    21600.0    560.4     38.5 data
IBM_eServer_p680                  16    19200.0    494.3     38.8 data
IBM_eServer_p680                  14    16800.0    458.7     36.6 data
IBM_eServer_p680                  12    14400.0    375.5     38.3 data
IBM_eServer_p680                  10    12000.0    349.4     34.3 data
IBM_eServer_p680                   8     9600.0    264.1     36.4 data
IBM_eServer_p680                   6     7200.0    216.7     33.2 data
IBM_eServer_p680                   4     4800.0    145.7     33.0 data
IBM_eServer_p680                   2     2400.0     78.2     30.7 data
IBM_eServer_p680                   1     1200.0     39.2     30.6 data
IBM_eServer_p680                   1     1200.0     50.4     23.8 data
SGI_Origin2000-195_1_per_node     32    12480.0   1179.4     10.6
SGI_Origin2000-195_1_per_node     16     6240.0    608.9     10.2
SGI_Origin2000-195_1_per_node      8     3120.0    293.4     10.6
SGI_Origin2000-195_1_per_node      4     1560.0    160.4      9.7
SGI_Origin2000-250_1_per_node     32    16000.0   1362.5     11.7
SGI_Origin2000-250_1_per_node     16     8000.0    655.0     12.2
SGI_Origin2000-250_1_per_node      8     4000.0    342.5     11.7
SGI_Origin2000-250_1_per_node      4     2000.0    188.8     10.6
SGI_Origin2000-250_1_per_node      2     1000.0     89.2     11.2
Sun_UE_10000_400_1_per_node       16    12800.0    348.6     36.7
Sun_UE_10000_400_2_per_node       32    25600.0    647.5     39.5
Sun_UE_10000_400_2_per_node       16    12800.0    430.7     29.7
Sun_UE_10000_400_3_per_node       48    38400.0    903.7     42.5
TMC_CM-200_64k_10               2048    40960.0   5653.2      7.2
TMC_CM-200__8k_10_MHz            256     5120.0    706.6      7.2
TMC_CM-2_64k_7_MHz              2048    28672.0   3494.8      8.2
TMC_CM-2_64k_8_MHz              2048    32768.0   4000.0      8.2
TMC_CM-2__8k_7_MHz               256     3584.0    436.9      8.2
TMC_CM-2__8k_8_MHz               256     4096.0    500.0      8.2
Tera_MTA_simulated                16    14400.0   3813.7      3.8
Tera_MTA_simulated                 8     7200.0   1905.1      3.8
Tera_MTA_simulated                 4     3600.0    975.0      3.7
Tera_MTA_simulated                 2     1800.0    507.8      3.5
Tera_MTA_simulated                 1      900.0    261.4      3.4
------------------------------------------------------------