Application & Synthetic Testing
Sandra Memory Bandwidth
Note: All systems were run in dual channel mode using timings of 16,18,18,36@1T.
Given that all of these are dual-channel systems, the results being relatively close isn’t surprising. All of the Ryzen 3000 series CPU’s all have the same memory controller, and therefore, little difference between these will be seen.
Sandra CPU Dhrystone
In this test, the Intel 9600K and AMD Ryzen 5 3600X are relatively close. The 3600X is also pretty much the same under PB2 and PBO. This wasn’t always the case as PBO often allowed the clocks to hold much longer than they would under PB2.
PCMark 10
The Ryzen 5 3600X scores very similarly using both PB2 and PBO. This is the result we have come to expect, but as you’ll see, this isn’t the case in all the tests.
WinRAR – Multithread
WinRAR is a weird test. While it does scale with additional threads, its still very much influenced by single-threaded performance. Core count matters, but it isn’t necessarily enough to sway the results towards a slower clocked CPU. You can see PBO providing a marked improvement over PB2 in this instance. AMD also shames Intel’s Core i5 9600K in this test, making it look absolutely anemic.
WinRAR – Single Thread
Oddly, in the WinRAR single-thread test, our 3600X manages to achieve some of the best results in our lineup only losing to the Core i9 9900K, which is not only twice as expensive, but runs at much higher frequencies with similar IPC.
wPrime v2.10
We see broadly similar results from our Ryzen 3000 series test systems. You can see clear advantages over the older Ryzen 7 2700X as all the 3000 series CPU’s show to be significantly faster in this test.
POV-Ray
It’s obvious that the core count matters in this test. The Core i5 9600K gets utterly destroyed by all the test systems, and the Ryzen 5 3600X is nearly at the bottom of the ladder here.