The impact of these vulnerabilities, according to Chipzilla.

This last sentence is missing a huge chunk of it. Also, yeah, Intel can't catch a break. Won't stop me going intel still though...

eh by time I actual build new PC STP on AMD should be well 2000-2200 hopefull and by that time STP performance will be less important, so it looking my next system my be AMD after refusing have personal system from them for decades, they still cheaper then INTEL as far as cores go and as now actual on par or faster. Though Wattage really went up with all that cores, which IS to be expected but I still like my CPU to stay under 100 watts I dont wany my CPU running as hot and my GPU does hah

No wonder Intel chips have been so fast over the last 5-6 years. They left all the doors open and took a lot of shortcuts. By the look of it those shortcuts are being found weekly and patched. I wonder how slow a CPU will become after all these software holes are filled in.

Reddoguk:

No wonder Intel chips have been so fast over the last 5-6 years. They left all the doors open and took a lot of shortcuts. By the look of it those shortcuts are being found weekly and patched. I wonder how slow a CPU will become after all these software holes are filled in.

This patch doesn't seem to affect performance though, which is good. There was a Windows 10 patch for this yesterday: https://support.microsoft.com/en-gb/help/4343909/windows-10-update-kb4343909 I can confirm no performance hit using latest microcode C6 for Skylake combined with the patch above. This is in Cinebench R15 / 3DMark / Timespy / Battlefield 1 testing. (I'm assuming that the protection is turned on automatically if you're running the latest microcode & this Windows patch.)

austin865a:

I have read that alot of the problems they been having lately was do to them using tech from a old 686 Cyrix CPU way back in the day or something.

All of the "tech" involved in a Cyrix processor was licensed from Intel and AMD. There was never a point where Intel or AMD could gain anything from Cyrix.

I have not heard cyrix name in long time, I remember having got few of them that "upgrade" the cpu's Only thing good about them cryix chips was there name, I remember them needing drivers to be installed in dos to just work correctly, unless I remeber man I wish I could forget about most this stuff, Atlest the Computer crap IF didnt remember most of it is 1 thing that stressed me would no longer exist Rest stuff I cant avoid, and keep getting told to just "deal with it" last time I "deal with it" someone was lucky they were not in hospitable...

Reddoguk:

No wonder Intel chips have been so fast over the last 5-6 years. They left all the doors open and took a lot of shortcuts. By the look of it those shortcuts are being found weekly and patched. I wonder how slow a CPU will become after all these software holes are filled in.

I would say now it will actually matter which gen CPU you have, i.e. spectre and meltdown, newer gen have more advanced caches, bigger buffers, registers, etc and it took smaller or not really noticeable performance hit, while older gen without those extra tweaks like by Sandy, Ivybridge (7branch pipeline vs 5) a lot more. And now this L1 is the fastest by Intel, if this fix cripples its bandwidth then it won't look so good across all generations.

The gift that keeps on giving..... Any INTEL share holders sell that stock while it's still worth something. A good analogy is if INTEL made a car and AMD made a car INTEL would on paper look better and test wise be faster then AMD in lap times...... But when you opened the door on the INTEL car you notice everything is made of cardboard. You notice no air bags, no safety bumper shocks that get absorbed during impacts, hollow doors, no spare tire and jack no powered seats no radio. You notice the body of the car is made of soda can aluminum. I never like INTEL's business practices and monopoly shadiness. Sorry for being rude on here but it's funny how INTEL is nothing special and people claim their products are the best in the universe. It's the image that fools people and they really were nothing special. INTEL is like a bully, looks all tough but you quickly find it's weakness and INTEL riding it's gravy train is slowly going to loose steam.

Dimitrios1983:

The gift that keeps on giving..... Any INTEL share holders sell that stock while it's still worth something.

Actually it stands to reason that Intel is going to sell more CPUs now, as people replace the current ones with new ones that come with built-in support for vulnerability mitigations (at a much lower perf hit.) Maybe this will turn out to work in Intel's favor.

RealNC:

Actually it stands to reason that Intel is going to sell more CPUs now, as people replace the current ones with new ones that come with built-in support for vulnerability mitigations (at a much lower perf hit.) Maybe this will turn out to work in Intel's favor.

eh i don't think so, intel already had market dominance , surely people will be more inclined to replace old hardware, but ultimately they have options other than intel, they may sell some chips, but they will lose market share in the process. And frankly intel intends to use its dirty hacks for the next couple of uarches, all you have to look at is their "enhanced" IBRS patches. Remember its not a bug its a feature!

@user1 People are not always so logical, me included. Perhaps a better business model would be to change architectures more often, though that would cost more $$.

And another two. https://marc.info/?l=openbsd-tech&m=153504937925732&w=2

Two recently disclosed hardware bugs affected Intel cpus: - TLBleed - T1TF (the name "Foreshadow" refers to 1 of 3 aspects of this bug, more aspects are surely on the way) Solving these bugs requires new cpu microcode, a coding workaround, *AND* the disabling of SMT / Hyperthreading. SMT is fundamentally broken because it shares resources between the two cpu instances and those shared resources lack security differentiators. Some of these side channel attacks aren't trivial, but we can expect most of them to eventually work and leak kernel or cross-VM memory in common usage circumstances, even such as javascript directly in a browser. There will be more hardware bugs and artifacts disclosed. Due to the way SMT interacts with speculative execution on Intel cpus, I expect SMT to exacerbate most of the future problems. A few months back, I urged people to disable hyperthreading on all Intel cpus. I need to repeat that: DISABLE HYPERTHREADING ON ALL YOUR INTEL MACHINES IN THE BIOS. Also, update your BIOS firmware, if you can. OpenBSD -current (and therefore 6.4) will not use hyperthreading if it is enabled, and will update the cpu microcode if possible. But what about 6.2 and 6.3? The situation is very complex, continually evolving, and is taking too much manpower away from other tasks. Furthermore, Intel isn't telling us what is coming next, and are doing a terrible job by not publically documenting what operating systems must do to resolve the problems. We are having to do research by reading other operating systems. There is no time left to backport the changes -- we will not be issuing a complete set of errata and syspatches against 6.2 and 6.3 because it is turning into a distraction. Rather than working on every required patch for 6.2/6.3, we will re-focus manpower and make sure 6.4 contains the best solutions possible. So please try take responsibility for your own machines: Disable SMT in the BIOS menu, and upgrade your BIOS if you can. I'm going to spend my money at a more trustworthy vendor in the future.

Solving these bugs requires new cpu microcode, a coding workaround, *AND* the disabling of SMT / Hyperthreading.

That can't be good.

OpenBSD -current (and therefore 6.4) will not use hyperthreading if it is enabled, and will update the cpu microcode if possible.

And neither can that, both performance wise and how serious it must be if it's off by default as this distribution update. Wonder how that's going to work out, hardware wise it seems HT/SMT just has to go even if it gets software patched because it's just broken security wise from one of these exploits and that can't be good at all. EDIT:

There will be more hardware bugs and artifacts disclosed.

And that's a bit of a [censored] too isn't it, also tying into SMT/HT even more.

Yeah I think this is mostly Intel, they're just grouping together hyper-threading and simultaneous multi-threading. Need to read up more about these things although my knowledge on CPU and their hardware is not very good but it's sounding pretty problematic and even if it might be specialized exploits and not very common the amount of them is starting to add up now particularly for Intel's CPU hardware although we might see more on AMD's side too as this continues. Sounds like a mess so far though but I only understand a small part of it though if it's a hardware bug or design issue then that's pretty significant unless it can be patched around or otherwise solved and that too could incur a performance hit. Hah although I guess with my own fairly old CPU now there's already a bit of a overhead from the current exploit patches if left enabled. Should see about looking up more info on this last round of exploits and patches overall but of course just after the last hotfix was released on Windows another exploit pops up.