>Last time Intel decided to go all out on a new CPU design

>>60158682
>My Heart Will Go On And Off

>>60158682
>It keeps happening

"It will be a lean mean, x86-on a diet where backward compatibility is no longer assured."

http://wccftech.com/intel-developing-new-x86-uarch-succeed-core-generation/

My 4690k will last until then, hopefully!

glad i picked the best arch!
>ddr3 is cheap
>one of four gens that aren't housefires (ivy, haswell, and skylake DELID HOUSEFIRES BTFO XDD)
>i can deal with being a corelet for another 3 years
how's it feel haswellbros?

File: pjmxjlsm9muy.jpg (26KB, 512x384px) Image search: [Google]

26KB, 512x384px

>>60158788
kabylale* not skylake, got my memes wrong
pls no bully

>>60158682
>>60158732
Oh, they never learn. Another round of VLIW memes with x86-64 emulation layer? Sasuga Intel.

>>60158788
>ddr3 is cheap
until they start reducing production capacity for it at which point it'll start going up

>>60158812
still, look at how much ddr4 is right now compared to ddr3! i'll grab some 8gb stick at some point, be a 16gb memer, and by the time i need more my processor will be ancient!

>>60158854
>not stocking up on DDR3 now to jew people in 5 years time

>>60158805
So Intel's SHINY NEW architecture is already DoA?
;_;

>>60158892
Yes unless they'll suddenly found and hired fuckton of actually competent non-meme engineers.

>>60158812
DDR3 is still more expensive than it was just last year.

>>60158788
>haslel
Ditched my 4570 for an R5 1600 last week. Couldn't be happier. Runs cooler, faster, and after I sold my old shit (mobo, CPU and RAM) to some Intel memer, the upgrade set me back 200 euros.
Don't miss Haslel at all.

>>60158966

Shit CPU though, my 4690k is still faster than your 1600 meme CPU at 4,6Ghz

>>60158931
my bad, looks like the price for ddr3 is the same. damn, i was really flaunting my meme superiority!
>>60158966
>he can't into devil's canyon
did i say hascucks could be here? devil's canyon bulls only

>>60158971
So your CPU that is more expansive than mine is 2% better in single thread with a heavy OC against my stock, and gets anally devastated in anything that uses more than 4 threads. Wow, you sure told me ;^)

>>60158788
>ddr3 is cheap

Was cheap. I picked up a 2 x 8 GB pair (GSKILL Sniper 1866) for $48 delivered last Fall. Lucky to find that for under $110 now.

If you are paying attention to speed and low timings for quality DDR3, most often it's more expensive than DDR4 right now. I don't see the price dropping from here on out. You will never again get a decent 16 GB kit for under $60, and I have doubts that it will ever happen again for under ~$80.

I'm personally fortunate in that I acquired all the DDR3 my systems will ever practically need for the remainder of my life. I'll probably skip DDR4 RAM completely before I need to replace my current systems.

>>60158892
>2021
>AMD is now on Zen revision 4
>Intel's ancient arch has fallen behind
>Delayed nu-x86 arch finally comes out
>Performance is worse on most software
>Shitty compatibility layer written by diversity hires
>"J-just wait for Intel(tm) Compiler to use all the new features!"
>15% better performance at last

>>60159008
>15% better performance at last*
>still behind Zen4

>>60159002
yeah, my info was outdated for sure; i already have 8 gigs so i'll just grab another corsair kit and curse my wretched luck
>>60158966
forgot to add, grats on the upgrade! enjoy!

>>60158788
Just jump on the AM4 platform now IMO.

>>60159138
the 4690k is serving me fine right now, and i'm building a dedicated rendering server on the side anyways for hobby purposes, and since for now i don't need magic smoke powers to gayme, talk to friends, and watch a movie at the same time, i'm gonna wait a few generations

>>60158805
It's more like x86 with parts of it chopped off and done in emulation. How old or nessecary these parts are remains to be seen. Apparently they're targeting "Legacy SIMDs" which can be done by other SIMDs.

>>60159180
If it's another IA-64 tier memery Intel's done for. AMD and ARM are not going to wait.

>>60159205
I don't think it's going to be like that.

>>60158788
Haswell-E still feels nice no need to upgrade in the coming years

>>60159229
thats cause haswell-E is just broadwell-E with a smaller number my guy

>>60158682
It was more hp fault then anything desu

File: 73812main_Altix_front.jpg (303KB, 2964x1656px) Image search: [Google]

303KB, 2964x1656px

>>60158682
It was an alright supercomputer chip for a while, at least. Then they stopped giving a shit about it altogether.

File: landscape-1466520354-trump-hat-2.jpg (28KB, 640x320px) Image search: [Google]

28KB, 640x320px

>intel shifts to a new architecture and drags the industry with them
>amd can't license the new architecture
>intel gets broken up in an anti-trust lawsuit
>VIA becomes the last desktop chip company

>>60159008
>2021
>With Zen4 India is finally a Superpower

>>60162516
>unironically looking forward to a future of shitty Centaur designs

while searching I uncovered interesting
https://www.pcgamesn.com/intel/intel-new-stacked-cpu-design
>Intel have just announced the future of their CPU design will be built around the new embedded multi-die interconnect bridge (EMIB), a technology which will allow chips from different generations to be stitched into the same package. This may also be how AMD GPU silicon finds its way into Intel processors.
>the new heterogeneous CPU design made possible by this new EMIB interface.
>This new design will mean 22nm, 14nm and 10nm silicon could all sit within the same processor
>The idea is for Intel to be able to rapidly move from generation to generation without necessarily having to completely overhaul the entire architecture. Non-performance realted components could then remain on the previous generation’s lithography while only the high-performance parts of a CPU design would need to be on the latest, lower-yield process node.
>This sounds an awful lot like a patent application Intel filed back in 2014
>The patent covers the method for stacking multiple cores in a single package and covers the potential cost reductions of going for smaller 3D stacked designs over larger monolithic layouts, and how it will at least halve the time to market of Intel’s complex server CPUs. It will potentially also allow Intel to quickly ramp up the core-count of their client processors too.
>It also paves the way for different silicon designs to talk to each other at speeds necessary for them to make a viable alternative to large monolithic designs. And that means, if the rumours of Intel licensing actual AMD GPU silicon and not just IP are true, this could be how they can jam a Radeon chip into an Intel package.
>“This Lego-like ability to incorporate big and small cores, graphics, FPGAs and custom accelerators,” says the patent, ”provides an unprecedented flexibility to customize server processors at assembly time for specific OEM workloads and compute requirements.”

>>60162516
It's still x86.

>>60162624
"The idea is for Intel to be able to rapidly move from generation to generation without necessarily having to completely overhaul the entire architecture. Non-performance realted components could then remain on the previous generation’s lithography while only the high-performance parts of a CPU design would need to be on the latest, lower-yield process node."

So basically, they can put out more pointless refreshes that don't provide enough of a reason to upgrade at a faster rate. Wow, it's fucking nothing.

File: Intel stacked CPU design.jpg (69KB, 590x332px) Image search: [Google]

69KB, 590x332px

>>60162624
>3D stacked design

How are they going to cool this shit? Spoilers: It's gonna be a housefire no matter what kind of cooling you use.

>>60162624
>22nm, 14nm and 10nm silicon could all sit within the same processor
>this could be how they can jam a Radeon chip into an Intel package
DUDE JUST SHOEHORN ALL KINDS OF CPU AND GPU ARCHITECTURES IN JUST ONE COMPUTER CHIP LOL

>>60162624
I dont know if it's related to OP.
But this does seem much more relevant to OP
http://wccftech.com/intel-developing-new-x86-uarch-succeed-core-generation/
>Intel really hasn’t shifted from its primary one in ages. As the inventor of the x86 architecture, it has a cross-licensing agreement with AMD to utilize the x86_64 extension of the same architecture (which is basically the 64-bit implementation of x86). It’s a funny state of affairs since Intel cannot offer 64-bit compatibility without licensing x86_64 from AMD and the latter cannot ship 64-bit processors unless it has licensed the base x86 from Intel.
>All this time, and through the generations, however, Intel processors have remained 100% backward compatible with all previous iterations. The same basic architecture expanded over and over with new features with time. Every new Intel architecture is essentially the same underlying x86 architecture expanded with new features with every iteration. For the first time, however, and if this rumor turns out to be true, things might actually change. Intel might introduce an x86 architecture that we can consider to be truly different from what we have seen so far. The reason? It will be a lean mean, x86-on a diet where backward compatibility is no longer assured.
>The reason for doing so is simple, by no longer guaranteeing backward compatibility, Intel could save precious die space by removing the hardware for legacy SIMDs and other legacy features. The result would be a much leaner and more efficient x86 architecture that can deliver a bigger bang for lower resources on-die. According to the source, the architecture will be used to replace the current Core series on the Desktop and Enterprise market.
>Tiger Lake would be the last iteration of the current x86 architecture from Intel Corporation. This is expected to arrive sometime in 2019 so we can expect the brand new x86 implementation to land by 2020 approximately.

>>60162762
https://www.overclock3d.net/news/cpu_mainboard/intel_is_reportedly_working_on_a_new_x86_architecture/1
>One of the biggest changes that Intel plans on making with this new core design is removing some older/unused SIMD and Hardware reminders, removing full x86 backwards compatibility but creating a more streamlined power friendly CPU design.
>While the removal of these old features may seem like a huge problem, they can be rectified in software via emulation. Right now Intel is working hard to emulate x86 on ARM and vice versa, so a lot of these issues may have already been solved in-house.
>This new architecture may be an attempt from Intel to create something that will finally be suitable for both the ultra-mobile market and desktop/servers, with increased performance-per-watt and a streamlined, cheaper to produce design.
>Intel's new architecture is expected to release in late 2019 or 2020, after Intel's Tigerlake series CPUs.

Wow so intel really didn't have anything planned against ryzen and are just duck taping all sorts of house fires together, lol

>>60162386
>>60162498
I still kek at how HP is forcing Intel to keep to their end of the bargain.

>>60162762
Nah Tiger Lake +1 was already confirmed x86, news is still out on +2

>>60162853
POOTEL DUCT-TAPED HOUSEFIRES

>>60162853

but /g/ told me Intel was sitting on years worth of finished designs just ready to be manufacturered the second ryzen looked good!

File: Itanium_Sales_Forecasts_edit.png (36KB, 1042x708px) Image search: [Google]

36KB, 1042x708px

>>60158682

>>60162799
so this is like when AMD removed 3D now! but they're removing even more instruction sets?

>>60163222
Yeah right

>>60162516
VIA still exists? I only remember them because they made the CPUs in the OQOs

>>60163222
Just wait(tm). They haven't hit the big red "In case of AMD" button yet.

Why did Itanium fail anyway?

File: 1488599027939.webm (3MB, 960x540px) Image search: [Google]

3MB, 960x540px

>>60163532
Can they even do that?
If yes, what?
I can't imagine them removing something like MMX without breaking literally everything.

>>60164339
http://www.eejournal.com/article/20130306-itanium/

>>60164470
Thanks!

Did anyone of you here ever use an Itanium machine, and why?

>>60164485
I don't think there was ever an Itanium desktop CPU.

File: 1425083600921.png (181KB, 280x273px) Image search: [Google]

181KB, 280x273px

>>60164354
>tfw they go full retarded and remove MMX and SSE2/3/4.1

>>60164667
Should just start coming up with joke names for it now already.

>gimp86
>axed86

>>60163024
They spent years and billions on it, I would do the same thing too if after all that the shitheads who shit the bed on it decided they weren't into it anymore and wanted to shitcan it after only a few years.
>>60164339
They spent years overhyping it as the release date pushed further and further back, by the time Merced came out it was hopelessly under-performing, and even Intel couldn't write a decent compiler that yielded its full potential. Combine that with its expensive price tag, a general slump in the high-end market and the fucking terrible x86 emulation that made transitioning over while waiting for the software base to come about impossible and you had a recipe for disaster. And the systems based on it were lackluster outside of HP's own offerings, basically just overpriced commodity shitboxes with a different CPU.

Later versions were a little better, but the Itanium failed to do what Intel ultimately intended it to do, and instead it ended up just becoming another expensive chip for HPC and mission-critical systems with very little mainstream exposure.
>>60164508
There were workstations, mostly from HP and SGI. I've got a quad-1.3 rackmount in my garage I'm going to do something with eventually.