Live data from Hacker News

Disabling Intel ME 11 via undocumented mode

blog.ptsecurity.com

221–228 of 228 posts

Re: Disabling Intel ME 11 via undocumented mode

#221
post #38

Earlier quoted context omitted.

You missed the point. It was added for people with big money. I promise you - it is supported. Just not for you. You need to be backdoorable. They don't

ME itself was added for people with big money. I'm not an engineer experienced in this kind of work, but I fail to see how a company whose core business is manufacturing chips would develop an entire computer (comprising an x86 CPU, its own RAM, MINIX OS, and access to all kinds of I/O) hidden inside each one of their chips and made largely inaccessible to regular users and developers. Unless they are paid very well…

Maybe this was due to a sympathetic engineers actions in Intel?

Re: Disabling Intel ME 11 via undocumented mode

#222
post #165

Earlier quoted context omitted.

> The last 3 chinese super computers have used home grown FeiTeng RISC processors which were binary compatible to Itanium, but for new models their using OpenSPARC. Where did you get that information? https://en.wikipedia.org/wiki/SW26010 doesn't claim any of that.

China's newest supercomputers are based on Sunway like you linked, but newer FeiTeng models (post-Itanium) were indeed OpenSPARC: https://en.wikipedia.org/wiki/FeiTeng_(processor)

I don't understand what the SPARC "front end" actually is, but the Tianhe-2 Top 500 figure comes from Intel processors " rel="nofollow">https://www.top500.org/system/177999>.

Re: Disabling Intel ME 11 via undocumented mode

#223

Earlier quoted context omitted.

I wish there were OpenSPARC super computers in the US...

Ehh, SPARC was a great architecture for ancient process nodes, but doesn't really line up with today's needs IMO.

Well, there are half a dozen SPARC systems in the Top 500, most notably " rel="nofollow">https://www.top500.org/system/177232>, with substantial longevity and currently top place in the HPCG benchmark list. They reflect needs in my area, at least. See also Fujitsu's M series?

Re: Disabling Intel ME 11 via undocumented mode

#224
post #212
post #172

What happened to 3rd party chipsets? Seems like VIA, ALi, SiS, Nvidia nForce, all stopped making them for Intel processors around 2008. If there were alternative chipsets still around, we would see more motherboard makers adopting something like openBMC with an alternative chipset and using it. No Intel PCH, no Intel ME.

I believe Intel stopped releasing the documentation required to make them around that timeframe.

If the EU or US regulators can force Google and Microsoft to unbundle and provide APIs, surely unbundling chipsets fit in the same category. Making chipsets was a successful business for quite a few companies, too bad the FTC didn't force Intel to provide enough documentation, like it mandated the number of PCI-E lanes.

Now if the NSA got to the FTC, that would be different.

Re: Disabling Intel ME 11 via undocumented mode

#225
post #149
post #84

Earlier quoted context omitted.

Why not?

Register windows and delay slots. These turned out to be not such a great idea.

What, specifically, about register windows and delay slots makes them unsuitable for today's needs?

PS: read my profile description.

Re: Disabling Intel ME 11 via undocumented mode

#226
post #83

Earlier quoted context omitted.

So what chips does the US government use for classified purposes?

We know that Amazon had Intel create custom chips specially for them, like the E5-2666 v3. So of course Uncle Sam have their own top secret bespoke Intel SKUs.

Amazon buys a significant fraction of the chips produced by Intel. I don't know how many security-sensitive chips the US government needs, but I'd be willing to bet it's a drop in the ocean.

Re: Disabling Intel ME 11 via undocumented mode

#227

This is why I support Power/MIPS/RISC development going forward. It's just a shame that we allowed intel and amd to both put in cpu backdoors at such an obvious level (I like x86 but it's not the cpu of the future unless it's open). I highly suspect some national security letter type shit is going on in the background, ala Promis and William A. Hamilton who has claimed on Bruce Schneiers blog they (intel agencies) we…

> I like x86 but it's not the cpu of the future unless it's open

SPARC has been open for years FYI.

Re: Disabling Intel ME 11 via undocumented mode

#228
post #225
post #149

Earlier quoted context omitted.

Register windows and delay slots. These turned out to be not such a great idea.

What, specifically, about register windows and delay slots makes them unsuitable for today's needs? PS: read my profile description.

They complicate OoO core design.
Post reply on HN