Games run faster on SteamOS than Windows 11, Ars testing finds

> Besides, it's a cat and mouse game where the vendor is the mouse.

The goal of anti-cheat isn't to stop the world's most advanced cheaters. Those are already unstoppable because they now use Direct Memory Access over the PCI-E bus, so the cheats don't even run on the same computer anymore. However since those cheaters are few and far in-between they can be handled through player reports.

The goal is to stop the mediocre cheater who simply downloaded a known cheat from a cheating forum. If you don't stop those you'll get such a large wave of cheaters that you can't keep up with banning them quickly enough.

> Those are already unstoppable because they now use Direct Memory Access over the PCI-E bus, so the cheats don't even run on the same computer anymore.

Working on mostly server platforms, I had forgotten that IOMMU enablement (and, where relevant, enforcement) was not the default.

Consumer hardware and software is terrifying.

Not sure how that's relevant, unless you find it terrifying that owners of hardware have control over their hardware.

DMA hardware and cheats are getting more and more accessible. It's not just chosen few anymore

With the emergence of AI cheating, cheats don't even need access to memory anymore. The cheat can entirely run on mouse and screen peripherals and the computer will have totally no idea what's going on. The best you can do is behavior analysis. But it always comes with chance of misreports.

It's your IOMMU, you can do what you want with it. Maybe you need to write heaps of stuff to take advantage of it, but what's new there?

The only thing you're getting by saying "no IOMMU" is "I want any devices in my machine to be able to do anything, not just what I want them restricted to".

Direct Memory Access cheats will always perform better as they can reveal the location of an opponent before they're even visible on the screen.

Why are players who aren't on screen even in the client memory? The server shouldn't be sharing sensitive information.

You can minimize that to some degree (Valorant does this), but due to movement prediction/network latency you do have to overshare a little bit.

I imagine that most game devs just look at the incredible amount of work this takes to implement and complexity it adds, and decide to not bother. Valorant can do it because the game itself is low complexity, the developer has deep pockets, and also the added competitive integrity is valuable.

Although that looks like an obvious solution on first glance it's not really technically feasible. Things like gunshots or footstep sounds are not visible to the player, but still need to be relayed to the client.

As far as I see the only way around not sharing anything that's outside of the immediate perception of a player is to have the audio and graphics be entirely rendered server-side.

Game servers are complicated and have a lot to manage.

It's infeasible for the server to keep track of each player and do frustum and raycasting to every other player to check who can see who every frame.

Culling out of view entities also has the problematic effect of when a player spins around you now have to stream in several big chunks of world state in the few milliseconds before the user clicks to get that 180 no-scope.

How else would the game render the enemy player's sound around corners and in adjacent rooms without knowing their location for instance?

> they now use Direct Memory Access over the PCI-E bus

Do you have any good resources with keeping up with this kind of thing? Seems like a fun topic to learn about

Okay, but he's specifically brought it up in the context of a computer's owner doing something that the software vendor (and also myself as another gamer harmed by cheating) would prefer he did not.

And if they want complete control, they can choose not to use a vendor and do it themself, for all the control they could want.

Hooray, freedom!