Question for IT cels?

[gassers]

How do they cram more cores in processors every year?

How does that even work if you have limited space on chips?

And how are they successful doing that every year? What if they fail and get stuck at some point?

@NoBacon

@Lamont & Tonelli

@admin

 

[DMbA]

they make them smaller every year

now they are using 4nm(nigger moment) chips

i remember me first family pc was a pentium IIPE

 

[CorradoSoprano4]

With the weekly windows 10 updates, I've had to have my OS reinstalled TWICE due to compatibility issues. Now, $200 geek squad dollars later, I've eliminated that mess but I get this pop-up scam, when I take the computer out of sleep mode, that has a window that won't close and audio of some limey twunt telling me that my computer's been infected by a virus from a malicious porn site and that I need to call the number on the screen because all of my personal info including Passwords for banking, social media sites, credit cards, etc... etc... have been compromised. Most asshats would shit themselves hearing this blaring from their computer speakers, as the very official looking screen blinks an 1-888 number and implores you to call it to work with their "windows professionals" to eliminate this infection. If this happens to you, do the following: Hold Control, alt, delete simultaneously. Choose "task manager" from the resulting menu, and close your browser. It disappears. I'm not sure if it'll happen again, but for Christ's sake... DON'T call the number and play ball with these mongrel terrorists. The only infection your computer has is some fucker slipped in that pop up in the form of a familiar email with a link you (and I) mistakenly clicked. Go to "remove program" in your control panel and look for one of these. Delete it, problem solved. THANKS FOR YOUR USELESS SECURITY UPDATES WINDOWS 10!!!!!!

 

[quark]

Transistors, dog. You spend all day reading about how women are evil on incel forums. Instead, read about transistors for the next day or two and have your mind blown.

 

[ShutYourCakeHorn]

Transistors, dog. You spend all day reading about how women are evil on incel forums. Instead, read about transistors for the next day or two and have your mind blown.

I'm working on @gassers getting his dick blown, but in the meantime he can get his mind blown by transistors.

 

[Sex Offender Joe]

How do they cram more cores in processors every year?

How does that even work if you have limited space on chips?

And how are they successful doing that every year? What if they fail and get stuck at some point?

@NoBacon

@Lamont & Tonelli

@admin

Faggot

 

[soulbrotherman#1]

 

[Stent]

Moore's Law. Uh-oh spaghetti-o.

 

[NoBacon]

Satanic black magic. Sick shit.

 

[StlakerFatti]

This shit is 30 year old technology anyway.

 

[SoloJoeAcousticShow]

To answer OP:
they will fail at some point. Moore's law is just about computational power in total, not individual CPUs.
<2nm will, as far as my high school understanding goes, bring some physical challenges we can't solve yet because of Quantum Mechanics.

CPU frequency scaling hasn't done much for performance since early 2000s, and more transistors or cores also not really since the 70s.
The problem's always been memory accesses from the CPU to a much much slower either RAM or even slower disk. Multi-core processors, scaling frequencies and a lot of innovation in CPU/DRAM architecture have mitigated it some, but these also seem to have hard limitations.

A lot of the applications you're using probably aren't even utilizing multiple cores because it wouldn't improve memory accessing speed.
There are developments in the traditional sense that will improve things for years to come.

But long-term there should be huge changes coming still. I think they will have to do with quantum computing, distributed computing, close-to-memory computation, D2A mechanisms to compute in memory, other decentralized strategies to address the problems of shared memory.

Some neat graphs that explain some of the inherent limitations in Von Neumann architecture:

 

[guest]

To answer OP:
they will fail at some point. Moore's law is just about computational power in total, not individual CPUs.
<2nm will, as far as my high school understanding goes, bring some physical challenges we can't solve yet because of Quantum Mechanics.

CPU frequency scaling hasn't done much for performance since early 2000s, and more transistors or cores also not really since the 70s.
The problem's always been memory accesses from the CPU to a much much slower either RAM or even slower disk. Multi-core processors, scaling frequencies and a lot of innovation in CPU/DRAM architecture have mitigated it some, but these also seem to have hard limitations.

A lot of the applications you're using probably aren't even utilizing multiple cores because it wouldn't improve memory accessing speed.
There are developments in the traditional sense that will improve things for years to come.

But long-term there should be huge changes coming still. I think they will have to do with quantum computing, distributed computing, close-to-memory computation, D2A mechanisms to compute in memory, other decentralized strategies to address the problems of shared memory.

Some neat graphs that explain some of the inherent limitations in Von Neumann architecture:

View attachment 170393
View attachment 170396

so dat explains why we got sooooo many more listeners on da doggy channel, right?
like da technology is just sooo fawkin advanced over dare, compared to like, regular radio, from like, da fawkin 50's..
i mean, technology is just fawkin amazing, I still tink about da 8 track player i had at geneseo... im riffin man.. I'm feelin old... lil bit lil bit

 

[Leonard Rhomberg]

I know the answer but I’m not telling you

 

[gassers]

To answer OP:
they will fail at some point. Moore's law is just about computational power in total, not individual CPUs.
<2nm will, as far as my high school understanding goes, bring some physical challenges we can't solve yet because of Quantum Mechanics.

CPU frequency scaling hasn't done much for performance since early 2000s, and more transistors or cores also not really since the 70s.
The problem's always been memory accesses from the CPU to a much much slower either RAM or even slower disk. Multi-core processors, scaling frequencies and a lot of innovation in CPU/DRAM architecture have mitigated it some, but these also seem to have hard limitations.

A lot of the applications you're using probably aren't even utilizing multiple cores because it wouldn't improve memory accessing speed.
There are developments in the traditional sense that will improve things for years to come.

But long-term there should be huge changes coming still. I think they will have to do with quantum computing, distributed computing, close-to-memory computation, D2A mechanisms to compute in memory, other decentralized strategies to address the problems of shared memory.

Some neat graphs that explain some of the inherent limitations in Von Neumann architecture:

View attachment 170393
View attachment 170396

Thanks for answering sincerely, this is what i was asking.

 

[1073waaf]

You see, processor cores are like a river…