White Papers

44 Dell HPC System for Manufacturing—System Architecture and Application Performance
applications will not stress the system as much as HPL and will not consume as much power as HPL. This
is also evident from the subsequent graphs in this section. For the Implicit GPGPU building block, power
consumption was measured while running HPL on CPUs only and also while using the GPUs with a CUDA
enabled version of HPL. The values of the average and peak power measurements are shown on the
graph, with the average power displayed in the center of the average power bars and the peak power
displayed on top of the bars.
Figure 40 Building Block Power—HPL
Figure 41 plots the power consumption for one explicit building block when running a selection of ANSYS
Fluent benchmark datasets. The values reported are the power required for one building block while
running Fluent using 256 cores or eight nodes. The values of the average and peak power are shown on
the graph, with the average power displayed in the center of the average power bars and the peak power
displayed on top of the bars.
433
525 525
720
454
546 546
819
300
400
500
600
700
800
900
ExplicitBB ImplicitBB ImplicitGPGPUBB
(CPUsonly)
ImplicitGPGPUBB
(withGPUs)
PowerinWatts
BuildingBlockType
BuildingBlockPower—HPL
Peak‐Perf
Average‐Perf