Inspur Systems NF5280M5 Power Consumption
Our Inspur NF5280M5 test server used a dual 550W power supply configuration. The PSUs were LiteOn 80Plus Platinum level units.
We needed to use both PSUs in order to power our test configuration. Inspur offers higher-wattage PSUs, up to 1.6kW, which we would recommend if you are using heavy accelerators, storage, or Intel Xeon Platinum CPUs like the Platinum 8280 processors we used.
- Idle: 103W
- STH CPU 70% Load: 361W
- 100% Load AVX2 (GROMACS): 609W
- Maximum Observed: 652W
Note these results were taken using a 208V Schneider Electric / APC PDU at 17.7C and 72% RH. Our testing window shown here had a +/- 0.3C and +/- 2% RH variance.
STH Server Spider: Inspur NF5280M5
In the second half of 2018, we introduced the STH Server Spider as a quick reference to where a server system’s aptitude lies. Our goal is to start giving a quick visual depiction of the types of parameters that a server is targeted at.
The Inspur NF5280M5 is designed to be an all-around solid performer. It is not as customized for getting the highest compute density or the most accelerators in a system. For example, the Inspur Systems NF8260M5 is a 2U 4-socket server that has more CPU and memory in the same 2U of space. We also reviewed the Inspur Systems NF5468M5 4U 8x GPU Server that is focused on higher accelerator density. The company and the market offer higher density solutions for storage as well. At the same time, there are a lot of organizations willing to sacrifice density to have a 2U server building block that can be configured to support a number of different roles, thereby simplifying the architecture. Those are the types of roles that the Inspur NF5280M5 is designed to fill.
In every major server vendor’s portfolio, there is a 2U server offering that has flexible PCIe expansion as well as different storage configurations. These platforms are immensely popular since they offer so much deployment flexibility. Systems like the Inspur NF5280M5 are popular well beyond the traditional datacenter. These systems, configured with FPGAs and GPUs like the NVIDIA Tesla T4, have become extremely popular as edge video analytics platforms. As an example, for deploying video analytics in a store.
The flexible expansion, flexible CPU and memory, and storage help make these excellent all-around platforms. In Inspur’s server portfolio, this is perhaps the one platform you could use to do anything from AI inferencing to hyper-converged storage all using a common 2U platform.