Huge real world performance impact, they didn't say how much but it looks like close to 100%.
I smell a class action lawsuit coming.
I smell a class action lawsuit coming.
[0] https://www.joelonsoftware.com/2002/11/11/the-law-of-leaky-a...
The other percentages we've been offered have been in terms of performance reduction. We were told to expect a range of 5-30%; this is about 60%.
Somewhere a sysadmin's hair has started smoldering.
We write a lot of code that needs to run as fast as possible (processing, post-processing, generating real-time weather/satellite data) and I’m concerned about time windows and whether we’ll be able to meet requirements.
You'll probably see a wide variety of benchmark results anything from no impact to things like above. So just make sure you measure carefully with your own workload.
It really only affects workloads where high performance is important. The average user might not see an impact but if you need fast IO God help you. The solution is to 'make less syscalls' but the problem is that syscalls have always been slow and the people making a lot of them are only doing so because they absolutely have to
You're right. Most people who just surf the Netflix and download the YouTubes will not notice. But it's still a form of fraud, even to those who never max out CPU. I think fraud is a strong word knowing that this wasn't intentional. But they sold a lesser product than they advertised and need to make customers whole. Otherwise it pretty much is fraud.
Do you think browser vendors have been pushing JIT research forward, investing in webasm, and building things like servo because websites are so fast and light on CPU?
If anything, for big shops like this one, I wouldn't be surprised if we saw a move away from hosted providers (the "cloud" .. god I still hate it when people use that word), and return to co-located setups.
At least for people who need immediately performance needs, AMD might make a lot of short term sales right now.
It's not just the cost of the processors, but everything that contains them. Truly 'fixing' all the affected products would bankrupt a county but we should get a refund for the CPU's at the least
No one saw this coming. Things happen. It's impossible to predict every contingency.
They acted in good faith.
Also, heh, users are funny: "all other games i have work fin by the way so there must be a problem whit fortnite."
Of course you can't predict every contingency, but some of them you pay for.
Yes.
They showcased benchmarks and paid people to benchmark/review their product along similar lines.
https://ark.intel.com/products/96900/Intel-Xeon-Processor-E7...
etc.
That's new for a company, and it's not indicated by their PR spin right now.
What I think happened : a company produced a product with a problem. Probably not out of malice, but ignorance.
One of two things happened after, which can kill the 'good faith' argument ; the problem was found internally and hushed, or the problem was found externally and minimized to reduce financial burden arising from fixing the problem and the PR related.
We have no way of knowing how well it was known about internally, but we can all see the PR going on from Intel right now, and I hope i'm not the only one who reads into those press releases to establish intent.
Modern processors are insanely complex systems. Branch prediction, out of order execution, hardware virtual memory management, hardware virtualization, etc. Not to mention that these are side-channel attacks. It's not a direct vulnerability, it requires executing some code and measuring timing very precisely; similar to and oscilloscope and a very expensive safe.
Of course Intel is going to be spinning this however they can for damage control. That's what PR departments do. I still doubt engineers at Intel really thought this attack was plausible, or else they wouldn't have been engineering chips this way for the past decade.
And until we align their market incentives properly, silicon vendors are going to continue to ignore this fact when it comes to verification. Intel is especially bad here; they’ve had an unreasonable number of hardware bugs in recent years.
Right now, I think the problem started out of ignorance - but they have abused Google's policy of responsible disclosure to hide the flaw as long as they could and take advantage of their market position while the unknowing public kept buying their products. Now they are pulling the four D's of propaganda in their PR statements all while we are seeing huge performance deltas in graphs from Epic and more?
This is straight up deceptive, I'm glad I switched back to AMD with my new gaming rig and I already have plans in the works to purchase multiple EPYC servers with our datacenter move starting next month.
The PR spin and misdirection games isn't in good faith which completely demolishes this line of defense.
Normally I'd agree but not in this case. Notice that besides latest ARM it seems no other architecture is susceptible to Meltdown - s390x, SPARC, POWER, AMD etc.
Speculatively loading and executing code across protection boundary is something someone should have thought twice about. Doesn't mean other vendors knew or had PoC examples, but they could have had an instinctive hunch.
I've given this example before, say I have some sensitive data on a server. I could install a bunch of services and API endpoints on it, to access it faster, inspect it, extract it various formats etc. Or I could decide to lock it down and just install only the minimum number of needed things, locked everything down. Doesn't mean I knew all those additional APIs or services had vulnerabilities, but it's just a good practice.
If the server gets hacked and someone looks back, I think they would be justified asking "What the hell were you thinking installing all that crap you didn't need on it".
I'm not sure about this. At any large company like Intel, the cost of potential - even predicted - lawsuits are already factored into their budgets.
I remember reading something about how rich people can get 'everything else's insurance that's basically applicable to anything bad that could happen to them. Maybe its the same with companies?
So really, in this case insurance is just another word for “more lawyers to drag through the courts for people years, with uncertain results.”
They were aware of the problem for a couple of years: https://twitter.com/TheSimha/status/949361495468642304
I don't see how a class action could apply here, by IANAL
To this date I can still buy broken Intel CPUs....
They knew about the flaw in June. Yet they still kept selling Coffee Lake CPUs.
If my 8700k wouldn't still be significantly faster than Amd Ryzen (or I wouldn't have to also return the MB), I would have switched to an Amd in a heart beat.
With this they need to add even more tests before they can start on attacking the issues with the design.
It's understandable that they may not have been able to mitigate it in the 8th gen CPUs in just a few months, but they also put those CPUs out on the market, advertised them, and sold them, all the while they knew of their design flaw, without saying anything about it to the unsuspecting customer.
Moreover it would be hard to say "everyone is doing it" because it seems so far besides the latest ARM processors, most of the other CPU architectures don't do it.
Not really: http://www.daemonology.net/hyperthreading-considered-harmful...
That was in 2005. It might be an over-generalization, but one could say that Intel made that same mistake (at least) twice.
IIRC almost nobody took them up on the offer. But today there is far more cloud computing, so datacenters might.
But since the USA have the highest lawyer-per-citizen ratio in the world, it would be very interesting to see what happened if, say, Google sued Intel because from one day to the next, Google's electricity bills rise steeply, their servers crash, because the AC cannot handle the extra heat, ... , and Google demanded Intel pay for their damages.
We live in very interesting times, indeed.