Application and Synthetic Testing
Sandra Memory Bandwidth
Note: All systems were run in dual channel or quad-channel modes where applicable. The 9900K and 3900X used timings of 16,18,18,36@1T. The 10980XE was restricted to the timings of the RAM I had on hand which were 18,19,19,39@1T. For the memory bandwidth test, the Core i9 10980XE test system was run with the memory clocked at 3800MHz.
Being the only HEDT part in the test lineup at the moment, it is not surprising that the Core i9 10980XE achieved the highest result. However, the overclocked result at 3800MHz for the RAM yielded the highest result scored on my test bench so far.
Sandra CPU Dhrystone
The Core i9 10980XE is the first system I’ve ever tested to reach 1,000GiPS. This is also a massive improvement over the stock clocks.
PCMark 10
AMD’s 3900X is simply bested by everything in this test. It’s also worth noting that as core count increases on the Cascade Lake-X system, so does the score. This is true of clocks as well. However, the 9900K achieves a higher result than all but the heavily overclocked 10980XE.
WinRAR – Multithread
This is one example where you will see our simulated 10920X outscore the 10980XE when it shouldn’t. The reason for this likely comes down to what I’ve observed with its boost behavior. When the CPU has some of its cores disabled, it seems to hold higher clocks for longer. I need to play around with this some more, but so far that seems to be the case. I do not know if an actual 10920X would behave the same way, but it might be given it’s base clocks are higher.
Also, note that the Ryzen 9 3900X is about as fast as the Core i9 10980XE without having to disable several of its cores.
WinRAR – Single Thread
Overclocking the Core i9 10980XE achieving a higher result doesn’t surprise me. However, I am surprised this CPU achieved the highest result given AMD’s IPC advantage and the i9 9900K’s higher clocks. I suspect this is due to the L3 cache of the 10980XE coming into play.
wPrime v2.10
The results surprised me a bit. I had anticipated that the Core i9 10980XE would do better here. However, the 3900X actually achieved the best result. The 10980XE was also virtually unaffected by disabling several of its cores.
POV-Ray
Given that this is a heavily multi-threaded application, the score is no surprise. It is worth noting that the 3900X also beats our Cascade Lake-X 12c easily. However, the 10980XE is the fastest system here by a wide margin.