I have conducted some experiments with STREAM benchmarks on the following servers and observed unexpected trends:
Characteristics of Machine A:
It is a dual socket machine.
Intel(R) Xeon(R) Gold 6126 CPU @ 2.60GHz (Codename: Skylake)
Cores per socket = 12; L3 cache = 19.25 MB; TDP=125W; Powercap range: [65W to 125W]
Total RAM at machine A = 192GB (96 GB per socket)
Characteristics of Machine B:
It is a quad socket machine.
Intel(R) Xeon(R) Gold 5318H CPU @ 2.50GHz (Codename: Cooperlake)
Cores per socket = 18; L3 cache =24.75 MB; TDP=150W; Powercap range: [82W to 150W]
Total RAM at machine B = 256GB (64 GB per socket).
Characteristics of Machine C:
It is a dual socket machine.
Intel(R) Xeon(R) Gold 5418Y CPU @ 2.0GHz (Codename: Sapphire)
Cores per socket = 24; L3 cache = 45 MB; TDP=185W; Powercap range: [115W to 185W]
Total RAM at machine C = 192GB (96 GB per socket)
I ran the STREAM benchmark, where the total memory usage is 2.2 GB. I observed that the execution time on machine A decreases when we increase the power cap. However, the execution time remains constant on machines B and C when we increase the power cap from MIN to MAX.
I ran another version of STREAM, where the total memory usage is quite low (22 MB). The execution time decreases on machines A, B, and C when we increase the power cap. This suggests that we can observe certain trends when DRAM access is negligible or when pages fit into the cache.
I am unable to understand why machines B and C produce the lowest performance for the STREAM benchmark, even though B and C are of a newer generation compared to machine A.
