Hardware Benchmarking - Results

From Tuflow
Revision as of 16:49, 24 May 2018 by Ellis Symons (talk | contribs)
Jump to navigation Jump to search

CPU 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 30m and 15m runtimes, with the fastest computers at the top of the table.
Runtimes for CPU benchmarks

Processor Name Processor Frequency (GHz)** RAM size (GB) RAM frequency (MHz) Classic 20m (mins) HPC CPU 20m (mins) Runtime Combined (mins) System Name
CPU GHz RAM RAM freq Time Time Time AAA


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.
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.
Runtimes for GPU benchmarks

Processor Name Graphic Card GPU RAM (GB) Number of CUDA Cores* Runtime 20m (mins) Runtime 10m (mins) Combined Runtime (mins) System Name
CPU GPU GPU RAM CUDA CORES Time Time Time AAA
 * 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.  

High End GPU Results


A number of additional benchmarking tests have been completed on a 5m and 2.5m model on a single GPU card.


Processor Name Graphic Card GPU RAM (GB) Number of CUDA Cores* Runtime 5m (mins) Runtime 2.5m (mins) Runtime 1.25m (mins) Combined Runtime (mins) System Name
CPU GPU GPU RAM CUDA CORES Time Time Time Time AAA
 * 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.  
Up
Go-up.png Back to TUFLOW Benchmarking