This set includes only 32-bit results --- i.e. results based on either 32-bit data elements or 32-bit arithmetic. Many of the 64-bit results actually move data in 32-bit chunks, but as long as the operands and operations are 64-bit, those cases remain in the other tables.
Revised to Sun May 12 12:45:54 EDT 1996 ---------------------------------------------------------- ---------------------------------------------------------- ---------------------------------------------------------- All results are in MFLOPS --- 1 MFLOPS=10^6 FP OPS/sec Alliant_VFX80 3 2.0 2.1 2.1 Convex_C1XP 1 5.2 5.4 5.4 Convex_C3210 1 7.7 9.1 9.1 Convex_C3220 2 14.8 17.6 17.4 Convex_C3410 1 12.6 13.1 12.9 Convex_C3420 2 19.9 22.0 21.7 DEC_4000-710 1 6.7 6.6 6.6 DEC_5000-200 1 1.7 1.8 1.5 FPS_510_EA_scalar 1 1.0 1.1 1.0 FPS_511_EA_vector 1 6.9 7.8 7.8 FPS_511_SPARC_scalar 1 2.6 2.3 2.2 FPS_511_SPARC_vector 1 7.1 7.9 7.9 FPS_MCP104 1 8.6 9.7 7.8 FPS_MCP728 7 39.8 32.8 32.9 HP_9000-720 1 3.9 4.0 4.3 HP_9000-730 1 3.1 3.8 3.3 IBM_3090J-VF 1 13.9 14.4 14.5 IBM_3090J_scalar 1 4.7 6.0 5.7 IBM_RS-6000-250 1 4.3 4.4 4.4 IBM_RS6000-320 1 2.8 3.3 3.3 IBM_RS6000-320H 1 3.3 4.5 4.5 IBM_RS6000-355 1 7.0 7.1 7.1 IBM_RS6000-530 1 3.7 5.1 5.0 IBM_RS6000-580 1 11.9 15.6 13.9 IBM_RS6000-950 1 6.2 8.5 8.3 Machine ID ncpus SCALE ADD TRIAD NEC_SX3-12 1 319.6 416.2 416.2 NeXTStation_68040 1 0.6 0.9 0.7 Omron_Luna88k 1 1.1 1.3 1.1 SGI_4D-240 1 1.2 1.5 1.3 SGI_4D-25 1 0.8 0.8 0.8 SGI_4D-35 1 2.4 3.1 2.1 SGI_Challenge_100 1 3.9 4.2 4.0 SGI_Challenge_150 1 5.6 5.6 5.3 SGI_Crimson 1 4.5 4.5 4.4 SGI_Indigo 1 1.8 2.2 2.2 STREAM Memory MFLOPS --- John D. McCalpin, mccalpin@udel.edu Sun_4-490 1 1.2 1.9 1.3 Sun_670 1 1.8 1.8 2.0 Sun_SS1- 1 0.7 1.0 0.7 Sun_SS10-30 1 3.5 3.2 2.8 Sun_SS10-41 1 3.2 3.1 3.2 Sun_SS2_(4-75) 1 1.4 1.6 1.7 TMC_CM-5E 32 587.9 670.3 669.7 VAX_9000-420 1 6.9 6.5 6.5