Next year AMD will have 7nm server products superior in every way to Intel's offerings and it's going to remain that way for an entire year, maybe more. You have a 48 core 7nm Zen2 product versus 28 core "Cooper lake", which is just a warmed up Skylake SP and this is because Intel's 10nm process has failed so completely. It'll be 2006 all over again, when Opterons had 25% of the market.
> sort of a massive erect vomit-comet.
So, these customers are paying for the privilege of vomiting in space?
Since the Monero branch, RX Vega cards have become the best value for mining Monero, and there's no chance of getting any of those cards at MSRP
http://www.nowinstock.net/comp...
It's worth noting AMD has said that Spectre 2 is virtually impossible to exploit on the Zen architecture. Even AMD engineers were unable to create a working exploit for it. Of coarse, they still have to release a patch for it to be on the safe side.
The Chinese "Heavenly Palace" space station due to smash into the Earth within the next few hours. The ultimate April fools prank!
Multithreading is hard to implement, but you don't need to use multi-threading to get better performance. Draw calls have much lower overhead and then validation is done in a layer that is swiched off in release. That alone will get better performance. There are a lot of hidden work getting OpenGL to get performance. For instance, batching - I spent so much development time on this it's unreal. Those problems disappear in Vulkan, because of the low overhead.
Save time by start taxiing towards the runway as soon as the pilots are on board. The passengers run alongside the plane and clamber onto the boarding stairs as it moves. The taxiing is actually quite slow and if the passengers were fit enough they could easily make it before take off.
This sounds a bit like those Gilette ads. What does layer 5 do that layers 1-4 could not already achieve?
The obvious solution is to just drink beer.
count yourself lucky then
The decrease is performance only happens if you manage to update the BIOS and there's fat chance of doing that on a Haswell motherboard! It'll have reached non-support EOL long ago.
"While on some discrete workloads the performance impact from the software updates may initially be higher, additional post-deployment identification, testing and improvement of the software updates should mitigate that impact."
yeah, all you have to do is rewrite all software to avoid using system calls and the performance problem goes away
I think I understand it better now.
There are actually, 3 vulnerabilities: 2 spectre and 1 meltdown.
AMD Zen CPU's are actually affected by the first spectre vulnerability and they admit to that: https://www.amd.com/en/corpora...
The other Spectre vulnerability and the meltdown don't affect Zen. Meltdown is the vulnerability that needs the KPTI patch. Presumably there is some other patch on the way to fix spectre.
Google did not test these vulnerabilities on any Zen based CPUs. They tested only on older processors:
"AMD FX(tm)-8320, AMD PRO A8-9600 R7"
Well, they were only off by 4,539,994,000 years.
System going down in 5 minutes.
