Follow along with the video below to see how to install our site as a web app on your home screen.
Note: This feature may not be available in some browsers.
You weren't slower? just the thumbnail isn't a long enough test
The linux kernel fix for Spectre attack on Zen CPUs consists on disabling branch prediction
https://lists.opensuse.org/opensuse-security-announce/2018-01/msg00004.html
Oh man how nice would it be if Intel would step up to the plate, fix the issue in the chips and allow you to cross ship RMA your affected chip(s) as stock on the new version of the processor becomes available.
Could take 18+ months for a new CPU to be developed and tested. And its not like they could replace every CPU sold in the last 25 years. Although good thing the users have thrown their old systems out..
1. Who named these and why these names?
I know it's wishful thinking, but it would be cool if this could be addressed in microcode. Then all we'd need would be a new bios.
The problem with BIOS update is that I doubt older platform will be taken care of... I mean I still use a 2500K on an ASUS board.
I'm scared I'll need to replace my perfectly working computer because they decided to patch until "most" of last 5 years... which doesn't even mention the motherboard part...
On the other hand, I might be one of the early Zen refresh adopter...
Then convert the old CPU to a Linux box? My understanding (which very well could be wrong) is that on Linux microcode doesn't depend on the BIOS, but can be loaded into ram at the time of boot by the OS.
I believe Windows loads microcode updates at boot as well.
If it's fixable by a microcode update, why didn't Intel state so?So? Are they experts in the micro-architecture of high-performance microprocessors? Are they experts in the particulars of Intel x86 microprocessors? Do they have clue-1 as to what Intel's microcode patching system is and isn't capable of? Have they published the analysis behind their conclusions?
The answer to at least some and perhaps all of those questions is probably NO.
And if that isn't causing the needle to move on your BS detector, better get it checked.
Just yesterday everyone was saying Spectre was unpatchable.
Which is it?
Is it patchable, but only on Zen and with the extreme measures of completely disabling branch prediction?
So? Are they experts in the micro-architecture of high-performance microprocessors? Are they experts in the particulars of Intel x86 microprocessors? Do they have clue-1 as to what Intel's microcode patching system is and isn't capable of? Have they published the analysis behind their conclusions?
The answer to at least some and perhaps all of those questions is probably NO.
And if that isn't causing the needle to move on your BS detector, better get it checked.
"These vulnerabilities are particularly troubling as they are not due to a bug in a particular processor implementation, but are a consequence of the widespread technique of speculative execution. Many generations of processors with different ISAs and from several different manufacturers are susceptible to the attacks, which exploit the fact that instructions speculatively executed on incorrectly predicted code paths can leave observable changes in micro-architectural state even though the instructions' architectural state changes will be undone once the branch prediction is found incorrect." -- https://riscv.org/2018/01/more-secure-world-risc-v-isa/
Just as I thought.
"These vulnerabilities are particularly troubling as they are not due to a bug in a particular processor implementation, but are a consequence of the widespread technique of speculative execution. Many generations of processors with different ISAs and from several different manufacturers are susceptible to the attacks, which exploit the fact that instructions speculatively executed on incorrectly predicted code paths can leave observable changes in micro-architectural state even though the instructions' architectural state changes will be undone once the branch prediction is found incorrect." -- https://riscv.org/2018/01/more-secure-world-risc-v-isa/
Just as I thought.
Perhaps if you would bother reading the actual whitepapers you would understand more... But I guess you are an expert so you don't need to bother with the direct facts and information, you can just say stuff on conjecture and accuse people of fake news even when the news comes directly from the source. It is also nice how you can just consistently assume the experience level of everyone without knowing anything about them...
You don't understand what the RISC-V people posted, do you?Explain how that is "Just as you thought"? What does RISC-V have to do with Intel and AMD x86 ISA?
Yada yada yada. I read the GPZ reports. What evidence do you have that I didn't?
And your experience level is indicated by what you post. You're just mindlessly regurgitating after misunderstanding what you read.
In essence, you're puking up random stuff from the Internet in manner inconsistent with the proposition that you have substantial experience with the subject matter.
You don't understand what the RISC-V people posted, do you?
Think hard about these parts of it: "speculative execution ... micro-architectural state ... architectural state." Google them if you must, because if you don't understand exactly what those terms mean, you understand nothing about these exploits.
Resume of attacks and table of affecter vendors
https://www.kb.cert.org/vuls/id/584653
IBM is missing in that table. Already confirmed by Red Hat than Power and Z-series are also affected
The linux kernel fix for Spectre attack on Zen CPUs consists on disabling branch prediction
https://lists.opensuse.org/opensuse-security-announce/2018-01/msg00004.html
RISC-V is not x86 architecture. It is completely different. Not to mention if you look at the title of that page it literally says more secure world RISC V..
I am also convinced you do not even know what that quote means, since it is stating there is a problem on many different processors.
You are ignorant. This exploit is micro-architectural, not architectural. That's why it isn't on all x86 processors, and is on some non-x86 processors.
Since you apparently don't know the difference between architecture and micro-architecture, you are completely unqualified to discuss this topic.
I have complete confidence that within the next two week, events will demonstrate that you are totally wrong.
You realize that using red, consistently trying to put people's experience down that you don't know, and trying to use various classifications to confuse people, and trying to put things all in bold doesn't make your points anymore valid. So far you have provided zero evidence behind anything you have said, yet are trying to invalidate things people have said backed by direct evidence. In fact the one page you did try to use as evidence pretty much showed you actually didn't even understand what was written on it...
I am also still not sure what your angle is here, or why you seem to be calling what I am saying fake news without actually trying to say what it is you specifically disagree with about it? I am waiting for you to eventually get to some kind of point...but I am just left waiting. So far you have validated things I have said, like the fact it is a problem on many different processors and that it is a design flaw.
Also trying to say that what happens in the next 2 weeks somehow proves I am wrong shows that all you are doing is trying personal attacks. Because all I have said is what is literally in the reports from the researchers who found the flaw. Perhaps they are wrong, but that doesn't make me wrong about pointing to the researcher's evidence and being wary of early claims about complete immunity to the attacks based on rushed patches... If the patches do work, then great. That doesn't fix the design flaw, because now there is apparently a performance hit. If they have a fix in two weeks that doesn't include a performance hit and completely fixes the problem, even better.
So, you really don't understand that "architecture" and "micro-architecture" are completely different things, do you?... trying to use various classifications to confuse people ...
I guess no one ever taught you that only you can make a fool out of you on the Internet.
Or was that your goal?
And there's all we need to know about your ability to reason logically: you can't.Considering Juanrga is liking his post. I would ignore the troll.
You and NoOther don't actually understand that article, as far as I can tell. All I see is puked-up excerpts posted by people who don't understand the technical terms being used.after reading the article you linked....I think you might need to look in the "internet" mirror about who is making a fool of themselves.
So, you really don't understand that "architecture" and "micro-architecture" are completely different things, do you?
They are, and an expert in one can be non-expert in the other -- they are that different, and both are complicated.
I was more involved in micro-architecture, myself.
So now you resort to criticizing my formating, because you don't have anything more valid to say?
Wow, that's lower than a spelling flame.
I guess no one ever taught you that only you can make a fool out of you on the Internet.
Or was that your goal?
And there's all we need to know about your ability to reason logically: you can't.
You and NoOther don't actually understand that article, as far as I can tell. All I see is puked-up excerpts posted by people who don't understand the technical terms being used.
I have complete confidence that within the next two week, events will demonstrate that you and 'noOther' are totally wrong.
And there's all we need to know about your ability to reason logically: you can't.
You and NoOther don't actually understand that article, as far as I can tell. All I see is puked-up excerpts posted by people who don't understand the technical terms being used.
I have complete confidence that within the next two week, events will demonstrate that you and 'noOther' are totally wrong.
Reading comprehension and logic don't seem to be your strong suits. Or your buddy Brackle's for that matter.So yet again, what is it you are actually trying to say?
You wouldn't understand the explanation, and I don't have time or inclination to teach you the 12 graduate-level credit-hours worth of processor hardware design knowledge you'd need.Please, explain how the researchers who posted the flaws and their conclusions are wrong if you are so confident?
I don't care, as long as you're gone for two weeks, it's a win for the Forums.I will in 2 weeks come back to this post. If am I wrong I will admit it,
I don't care, as long as you're gone for two weeks, it's a win for the Forums.
So much for you saying you'd come back in two weeks. You couldn't stay away five minutes, could you?considering I have been around since 2003. You lost the battle.
Reading comprehension and logic don't seem to be your strong suits. Or your buddy Brackle's for that matter.
You wouldn't understand the explanation, and I don't have time or inclination to teach you the 12 graduate-level credit-hours worth of processor hardware design knowledge you'd need.