With AMD Zen 4, It's Surprisingly Not Worthwhile Disabling CPU Security Mitigations

[NobodyXu]

Everyone seems to have a theory on what this is. I can only speculate (pun intended) that maybe AMD found an elegant solution and just baked it into the CPU design. Until Lisa herself says it, AMD probably will keep hush hush. I'm going with they baked it in somehow. Occam's razor?

Lisa is not involved in the development of new CPUs as much as the engineers.
She is a CEO, a CEO does not have much time to deal with these stuff.

[NobodyXu]

With browsers you have one nearly complete machine either interpreting or performing a JIT on untrusted code that

It's not the only software doing this, jvm for Java and some JIT interpreter for Python or other PLs also do this.

it then passes on to the operating system. The OS then takes that and tells the hardware what to do.

Nope, most operations does not pass to operating system and can be done in userspace.
It's only the syscalls (I/O) that needs to pass to the operating system.

A lot of mitigations go into preventing that untrusted code from doing anything nefarious to the rest of the system, so it's not surprising there's operations common to all the browsers and in the kernel and system libraries that AMD is optimizing at the processor level.

When you know you're going to reach Z by path X, then it makes sense to review the path X takes in your hardware then optimize X's road surface as much as realistically possible. Known question always results in known answer via proven path. Proven path has certain inefficiencies. Remove inefficiencies. Proven path is then traversed more quickly, say 2 instructions rather than 4 or 5.

Performing such optimization on the migration code...Looks like a good way to introduce yet another specter-like CVE.

[Turbine]

Wow! I feel like that's the first real reason I've seen that's actually compelling me to want to upgrade my Zen 2 system outside of Newer, Better, and Faster. At the same time these results make me curious how fast Zen 4 and the Intel equivalents would be if there weren't hardware and firmware mitigations in place.

I've done enough grammar edits today that this article is triggering me. That last sentence starts with But and also uses but to make it a compound sentence.

Well performance really. Zen 2 was on par with mid range Intel's at the time. Couldn't keep up with overclocked high-end intels.

[CochainComplex]

This is witchcraft!1!

so lets burn down the stack ...ehh stake

[andrebrait]

I would have expected corrections and optimizations on the CPU design to cause mitigations=on to still perform worse (but negligibly at best) than mitigations=off. The reason being whatever is accomplished by mitigations=on would be accomplished at the hardware level and thus mitigations=off would be as secure but perform better.

I can't think of anything in the hardware design that would make software explicitly working around those flaws run faster. The same? Sure. But faster? Significantly so, on top of that?

Anyone has any comments from AMD on this?

[abu_shawarib]

LOL, Ubuntu. Where up is down and down is up. You should stick to real distros Michael, not these play things.

Michael tested distros countless times. The only distro that is consistently faster is Clear Linux by a small margin. Don't spew trash about things you're completely ignorant about.

[creative]

Michael tested distros countless times. The only distro that is consistently faster is Clear Linux by a small margin. Don't spew trash about things you're completely ignorant about.

Ubuntu is one hell of an OS, I use Manjaro. Plenty of people talk about it the same like Ubuntu. What some people don't know is some Ubuntu lovers out there have been using Linux since its' inception.

Been using linux personally for 21 years.

[Anux]

I can't think of anything in the hardware design that would make software explicitly working around those flaws run faster. The same? Sure. But faster? Significantly so, on top of that?

Maybe you're looking at it from the wrong angle. If they build in hardware mitigations for unsave code these hardware instructions might run slower. All that is masked by just being faster overall.
And someone above already mentioned branch prediction.

[coder]

Ubuntu is one hell of an OS, I use Manjaro. Plenty of people talk about it the same like Ubuntu. What some people don't know is some Ubuntu lovers out there have been using Linux since its' inception.

How much of what's good about Ubuntu really just due to Debian, upstream?

My first revelation was using Raspbian on my first gen Pi. Before that, I hadn't realized how much of the core stuff in Ubuntu was simply inherited from Debian.

Given that I use Kubuntu, I imagine it wouldn't be too hard for me to move upstream or to another Debian derivative.

BTW, I also use Ubuntu 20.04 on my ODROID N2. However, what's odd about that is the kernel (and possibly other packages) are much older than on the desktop.

[coder]

Maybe you're looking at it from the wrong angle. If they build in hardware mitigations for unsave code these hardware instructions might run slower. All that is masked by just being faster overall.

In one sense, possibly things like maybe flushing cache or branch predictor state on context-switch, that's probably what they're doing. However, the software mitigations often require extra CPU instructions to accomplish these things and optimizing those down to nothing would be pretty impressive.

It does make me wonder how much of AMD's purported IPC gains would remain, if comparing against unmitigated Zen 3. No doubt some, but I'll bet it would eat into their margin. Same for Intel.