Dual AMD Opteron 2419 EE Benchmarks – A look at Dell DCS Options
The community recently discovered several outlets selling off-lease Dell DCS chassis. In these Dell DCS C6000 chassis are generally three nodes filled with dual AMD Opteron 2419 EE processors. The AMD Opteron 2419 EE processors are 6 core Istanbul parts built on the 45nm process. They are clocked at 1.8GHz chips with a 60w TDP. Overall the AMD socket 1207 is getting a bit older. The processors sell on ebay for about $10 and complete systems with multiple nodes and RAM can sell for well under $500.
Dual AMD Opteron 2419 EE Benchmarks
We are in the process of transitioning from our 2013 STHbench benchmark suite to the Linux-Bench suite. As a result, one can see the archived STHbench data set and view different options. The new Linux-Bench data set will include relevant (unchanged) benchmarks for these processors.
Today’s benchmarks are using the old STHbench.sh script that we have used for over a year.
hardinfo is a well known Linux benchmark that has been around for years. It tests a number of CPU performance aspects. One major advantage is that one can run this out of the box from many Ubuntu installations.
The Hardinfo benchmarks show a very interesting set of results. The general trend is that the Opteron 2419 EE’s can take advantage of multi-threaded workloads. In single threaded benchmarks the low clock speeds to not help the processors’ relative performance.
UnixBench 5.1.3 Performance
UnixBench may be a defacto standard for Linux benchmarking these days. There are two main versions, one that tests single CPU performance on that tests multiple CPU performance. UnixBench segments these results. We run both sets of CPU tests. Here are the single threaded results:
In the single threaded benchmarks, the 1.8GHz clock speed is somewhat made up for by the deeper cores.
The UnixBench multi-threaded results have the dual AMD Opteron 2419 EE between the Opteron 3380 and the Intel Atom 2750.
c-ray 1.1 Performance
c-ray is a very interesting ray tracing benchmark. It provides both consistent results and some clear separation. Ray tracing is generally a great multi-threaded CPU benchmark. We did see over the course of STHbench that dual socket systems were destroying even our “hard” benchmark. The new Linux-Bench will implement a third test to stress larger systems.
With c-ray being a highly threaded benchmark, we can see performance almost in-line with an AMD Opteron 3380, a single processor platform.
Phoronix Test Suite Performance
We are using four tests from the Phoronix Test Suite: pts/stream, pts/compress-7zip, pts/openssl and pts/pybench.
- STREAM by John D. McCalpin, Ph.D. is a very well known memory benchmark benchmark.
- 7-zip compression benchmarks were a mainstay in our Windows suite so we are including it again on the Linux side as a compression benchmark.
- The pts/openssl benchmark is very dependent on the CPU architecture being used
- Python is a widely used scripting language and pyBench is a nice single-threaded Python benchmark
Our PTS tests are being removed in Linux-Bench. The OpenSSL, STREAM and 7zip tests will be recreated and expanded in the new benchmark suite.
The OpenSSL benchmark has some extremely high figures for the AMD Opteron 2419 EE that seem out of line with the other results. The other benchmarks seem more in-line with what we would expect.
Crafty Chess Performance
Crafty is a well known chess benchmark. It is also one where we saw issues last time with the Phoronix Test Suite and running on ARM CPUs. We are planning to retire this benchmark in Linux-Bench. Here are the Crafty Chess results from simply running “crafty bench”:
The 1.8GHz Opteron 2419 EE is no match for newer faster Intel processors in single threaded applications. It is however competitive with the almost 5 generations old Intel Xeon L5520 processors
Overall, the AMD Opteron 2419 EE is not the fastest processor around and that type of performance for a platform that will use a lot of power is not exactly optimal. Still, there are thousands of these systems floating around extremely inexpensively.