With a still 3.42% performance loss, the disadvantage in comparison to 720p on PCIe 3.0 @8 is almost halved, despite a slight CPU limit. This is still a house number compared to the run with @16. The difference in both PCIe 4.0 measurements with the Radeon RX 5700XT is, however, still clearly below one percent, which one has to impose as a measurement tolerance, at 0.14%. Since the RX 5700 XT is significantly slower by nature, a difference of only just under 4 FPS to the Quadro RTX 6000 @8 again documents this disadvantage of the halved bus very clearly.
You can see the difference quite well again on the FPS curves:
Now let’s take a look at the percentiles, because the 99th percentile is the most important one. Percentile isn’t everything. What you see is the now break-in of both cards, no matter what connection, when it is over 99. …goes out. Whereby the Radeon is still a little more affected.
At Frame Time, the fully connected Quadro RTX 6000 wins for the first time. Compared to the Radeon RX 5700XT, however, one sees again that the supposedly faster Quadro RTX 6000 @8 then takes the short straw, because the course of the Radeon is even more even. Also here I have the whole progressions later as single graphics for each map.
The evaluated variances can again illustrate this a bit more precisely, because the values of the Radeon are also now much more balanced! The two measurements on the PCIe 4.0 are virtually equal.
Individual graphics for each run as picture gallery
Kommentieren