![]() We'll start with the CPU benchmarks which was gathered using the RTX 4090 and we've only been able to test Zen 4 and Raptor Lake CPUs.ĪMD's Zen 4 processors were tested with DDR5-6000 memory and Intel's Raptor Lake with DDR5-6400, as those are the optimal kits we have for each platform right now, and they're similar in terms of pricing. What all of this means is, testing the hardware configurations that we did, took at least as long as all the testing we did for Modern Warfare 2 using the built-in benchmark – but for 44 graphics cards.įor this Warzone 2.0 testing, loads of time was lost just waiting for games, eventually loading into a game and getting to the section used for testing, and on numerous occasions we were killed while testing, invalidating the results forcing us to start over.įor this testing we've covered 1080p, 1440p and 4K resolutions, using the "Ultra" and "Minimum" quality presets. What we did notice is that scaling was similar for the hardware configurations we checked, so the margins between the various CPU and GPUs tested should remain the same. ![]() The potential downside to benchmarking a quieter section of the map is that the performance can be a bit higher than what you'll typically see in the busier sections of the map, and we did look into this, noticing that performance was often ~10% better for the benchmark pass.īut there's very little we can do about this as you won't often complete even a 20 second pass in the busy area, let alone a 60 second pass. Speaking of which, we decided to conduct our testing in a central location as this would allow us to land with relative ease every time, regardless of the flight path and the landing zone. We were only able to test this a few times as it required a late game circle. We also found that realistically you can only execute a single pass per game, not only because we were getting killed at the end of the test almost every single time, but because as the match progresses, the frame rate generally increases as there are fewer players.įor example, with just 30 players left we saw 1% lows increase by 25%, though the average frame rate was only boosted by ~6%, suggesting that there was a lot less stress on the CPU in late game. ![]() This is because no two matches play out the same way, with players dropping in different locations, system load can vary, and you also need to land in the same location to carry out the path for the benchmark pass and ideally you want to do this somewhere where you won't often end up being killed, so good luck with that. Gathering accurate data is a real mission and super time consuming. But how do you test a multiplayer battle royale game like Warzone 2.0? It's never easy, especially if you want to test more than one or two hardware configurations.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |