How do our products compare to the computers that are typically used by energy simulation professionals? We have tested a range of desktop and laptop computers using the jEPlus benchmark model set. Two metrics are used here: the single-core performance of the processors, and the overall computing speed of the computers when all processor cores are used.
Single-thread Processor Performance
By making the tested computer run one simulation job at a time, the average simulation time of the benchmark models is a good measure of the speed of the processor itself. This also gives a good estimation of the best simulation speed achievable on the hardware. In general, the main factors determining the processor's speed are its architecture and frequency. The latest Intel Core i7 processors are normally the best performers.
Figure 1 Processor chart
The ENSIMS K890 and K870 tested here are based on the Intel Core i7 4790K and 3770K, respectively. Our performance tuning ensures that it is at least 10% faster than the standard configurations. The X3200 (X3290 as tested) is based on the Intel Xeon E5-2600 processors. They are designed for handling parallel workloads, but still shows a decent single core performance in this test.
Overall (Multi-thread) Computer Speed
The overall computer speed test uses all available processor cores to run the benchmark set. This puts strains on not only the processor(s), but also the memory and storage components. The benchmark result is a good measure of the raw “crunching” power of the computer platform.
Figure 2 Computer chart
* Performance of the AWS EC2 instances other than the C3.8xLarge are variable. The results reported here are from single experiments that may not represent the average performance.