Due to high energy prices and reductions in funding, we implement a set of energy saving measures at the IT4Innovations National Supercomputer Center. The measures are selected such as to minimize the performance impact and achieve significant cost, enegy and carbon footprint reduction effect.
Due to high energy prices and reductions in funding, we have implemented a set of energy saving measures at the IT4Innovations National Supercomputer Center. The measures are selected such as to minimize the performance impact and achieve significant cost, energy, and carbon footprint reduction effect.
The energy saving measures are effective as of 1.2.2023.
The energy saving measures are effective as of **1.2.2023**.
## Karolina
...
...
@@ -19,15 +19,15 @@ Core frequency capping is implemented for the Karolina supercomputer:
### Performance Impact
The performance impact depends on the [arithmetic intensity][1] of the job.
The [arithmetic intensity][2] is a measure of floating-point operations (FLOPs) performed by a given code (or code section) relative to the amount of memory accesses (Bytes) that are required to support those operations. It is defined as a FLOP per Byte ratio (F/B). It is a characteristics of the particular computational algorithm.
The [arithmetic intensity][2] is a measure of floating-point operations (FLOPs) performed by a given code (or code section) relative to the amount of memory accesses (Bytes) that are required to support those operations. It is defined as a FLOP per Byte ratio (F/B). It is a characteristics of the particular computational algorithm.
In general, the processor frequency capping has low performance impact for memory bound computations with intensity below the [ridge point][2]. For CPU bound computations with intensity above the [ridge point][2], the impact is directly proportional to the frequency reduction.
In general, the processor frequency capping has low performance impact for memory bound computations with intensity below the [ridge point][2]. For CPU bound computations with intensity above the [ridge point][2], the impact is directly proportional to the frequency reduction.
On Karolina, relative time increase factor **up to 1.3** is observed for intensive workloads on CPU, **up to 1.1** on GPU. **No slowdown** is observed for memory bound workloads.
### Energy Saved
The enegy efficiency in floating point operations per energy unit is increased by up to 30% for CPU workloads, up to 25% for GPU workloads. The efficiency depends on the arithmetic intensity, however energy savings are always achieved.
The energy efficiency in floating point operations per energy unit is increased by up to 30% for CPU workloads, up to 25% for GPU workloads. The efficiency depends on the arithmetic intensity, however energy savings are always achieved.
