Flow in an Automotive Pump

Flow in an automotive pump. The case has a total of approximately 600,000 nodes (1.6 million elements, combination of tetrahedra, prisms, and pyramids) over three domains with multiple frames of reference, and solves incompressible fluid flow using the k-epsilon turbulence model.

Number of nodes 597,252
Element types Mixed: tetrahedra, prisms, and pyramids
Models k-epsilon Turbulence, Multiple Frames of Reference
Solver Coupled Implicit

Plots


Results

Results are listed alphabetically by platform.  Download

Last updated: 2013-08-01

 

Platform Cores Machines Core Solver
Rating
Core Solver
Speedup
Core Solver
Efficiency
Intel E5 2670 Processor, 2.60 GHz, RHEL 6.2 using FDR Infiniband without Turbo mode

Intel "Sandy Bridge" (16 core dual CPU) with 64 GB RAM

Download
1
1
88.0
0.91
91%
2
1
162.0
1.67
84%
4
1
285.0
2.94
74%
6
1
381.0
3.93
66%
8
1
483.0
4.99
62%
10
1
580.0
5.99
60%
12
1
691.0
7.13
59%
16
1
847.0
8.74
55%
32
2
1490.0
15.38
48%
64
4
2618.0
27.03
42%
Intel E5 2680 Processor, 2.70 GHz, CentOS 5.6

Intel "Sandy Bridge" (16 core dual CPU) with 28 GB RAM

Download
1
1
96.9
1.00
100%
2
1
180.8
1.87
93%
3
1
262.6
2.71
90%
4
1
317.6
3.28
82%
6
1
421.5
4.35
73%
8
1
533.3
5.51
69%
12
1
732.2
7.56
63%
16
1
881.6
9.10
57%
Intel X5650 Processor, 2.67 GHz, SLES 11

Intel "Gulftown / Westmere" (12 core dual CPU) with 39 GB RAM

Download
1
1
83.4
1.00
100%
2
1
149.2
1.79
89%
3
1
214.9
2.58
86%
4
1
265.0
3.18
79%
6
1
334.9
4.02
67%
8
1
407.5
4.89
61%
12
1
496.6
5.95
50%