Hardware Benchmarking - Results: Difference between revisions
Content deleted Content added
Ellis Symons (talk | contribs) m Ellis Symons moved page Hardware Benchmarking - CPU RESULTS to Hardware Benchmarking - Results |
Ellis Symons (talk | contribs) No edit summary |
||
Line 17:
|-
|}
<br>
=GPU Results=
The following table summarises the runtimes for a range of computers. More will be added when additional results are obtained. The table is ordered based on the combined 20m and 10m runtimes with the fastest computers at the top of the table.
<br>
The HPC GPU benchmark only uses a single GPU card. TUFLOW HPC GPU can be run across multiple nVidia GPU devices. However, the benefits of these are typically more noticeable for larger models with more than 1 million cells.
<br>
'''Runtimes for GPU benchmarks'''
{| align="center" class="wikitable"
! style="background-color:#005581; font-weight:bold; color:white;" width=23% | Processor Name
! style="background-color:#005581; font-weight:bold; color:white;" width=15% | Graphic Card
! style="background-color:#005581; font-weight:bold; color:white;" width=5% | GPU RAM (GB)
! style="background-color:#005581; font-weight:bold; color:white;" width=8% | Number of CUDA Cores*
! style="background-color:#005581; font-weight:bold; color:white;" width=10% | Runtime 20m (mins)
! style="background-color:#005581; font-weight:bold; color:white;" width=10% | Runtime 10m (mins)
! style="background-color:#005581; font-weight:bold; color:white;" width=10% | Combined Runtime (mins)
! style="background-color:#C5C5C5; font-weight:bold; color:white;" width=10% | System Name
|-
|CPU ||GPU||GPU RAM||CUDA CORES||Time||Time||Time||AAA
|-
|}
<pre> * it is noted that the number of CUDA cores is not provided as an output from the '''dxdiag''' command and this information has been sourced from the nvidia website.
** The output cpu.txt only provides the 'out of the box' processor speed. If you have overclocked your cpu, then please send these details through to TUFLOW Support so we can add the correct clock speed. </pre>
=High End GPU Results=
<br>
A number of additional benchmarking tests have been completed on a 5m and 2.5m model on a single GPU card.
<br>
{| align="center" class="wikitable"
! style="background-color:#005581; font-weight:bold; color:white;" width=23% | Processor Name
! style="background-color:#005581; font-weight:bold; color:white;" width=15% | Graphic Card
! style="background-color:#005581; font-weight:bold; color:white;" width=5% | GPU RAM (GB)
! style="background-color:#005581; font-weight:bold; color:white;" width=8% | Number of CUDA Cores*
! style="background-color:#005581; font-weight:bold; color:white;" width=10% | Runtime 5m (mins)
! style="background-color:#005581; font-weight:bold; color:white;" width=10% | Runtime 2.5m (mins)
! style="background-color:#005581; font-weight:bold; color:white;" width=10% | Runtime 1.25m (mins)
! style="background-color:#005581; font-weight:bold; color:white;" width=10% | Combined Runtime (mins)
! style="background-color:#C5C5C5; font-weight:bold; color:white;" width=10% | System Name
|-
|CPU ||GPU||GPU RAM||CUDA CORES||Time||Time||Time||Time||AAA
|-
|}
<pre> * it is noted that the number of CUDA cores is not provided as an output from the '''dxdiag''' command and this information has been sourced from the nvidia website.
** The output cpu.txt only provides the 'out of the box' processor speed. If you have overclocked your cpu, then please send these details through to TUFLOW Support so we can add the correct clock speed. </pre>
{{Tips Navigation
|uplink=[[TUFLOW_Benchmarking | Back to TUFLOW Benchmarking]]
}}
| |||