• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

Jim Keller Resigns from Intel

Is x86 dead with reached IPC wall once and forever?

If this years Ryzen releases have anything to say about it, no.

Mesh is a hot garbage mess.

Mesh honestly works fine, it's just that it has higher latency, kinda like Ryzen chips. That's not the end all but it does hurt their "best gaming" claims because well, Ryzen already has them beat on every other front.
 
also interconnect says hi :)
Ringbus doesn't scale.
Mesh is a hot garbage mess.

Good thing Intel 10th series is the last (Sky Lake) and finally done.

Q1 2021
11th gen (Rocket Lake) Willows Cove is the last 14nm++

Intel new 16 Cores big.Little architecture on new H6 LGA 1700 socket.

Now moves too...10nm++
Q4 2021
12th gen (Alder Lake) Golden Cove

Q4 2022
Which brings us to Jim Keller Ocean Cove project on 13th generation (Meteor Lake) 7nm+

Basically Intel Meteor Lake is Intel Zen2 aka version....

13th gen (Meteor Lake) is the coming fix to what everyone is complaining about... Ultra low power, double Cores, 7nm+, Ultra IPC.... More than 80 IPC Gain over 10th generation SkyLake IPC.

I'm really curious how far Jim Keller Ocean cove project is right now...
 
Last edited:
If this years Ryzen releases have anything to say about it, no.

Zen 3 should be one of the last and final attempts in the development of x86-64 and the PC platform in this shape and form.
Zen 3 started its development at least 3-5 years ago, JK resigns today. There is quite a difference in the time frame.

The Sony PlayStation 5 development and design shows just how primitive the x86 is, where they needed a ton of new specialised functions and dedicated hardware sets in order to replace the missing x86 instructions which they need and the extremely slow execution on the Zen 2 cores if they didn't include these new specialised hardware functions in order to accelerate the gaming experience as they wish.

Try running a Celeron with an HDD on Windows 10.
You will see how painfully slow it is.
A simple update takes dozens of minutes or hours.

My Ryzen system with an SSD took longer than an hour to update from 19 09 to 20 04. This is just unacceptable and I will take the very first opportunity to get rid of x86 system in favour of RISC ARM which is a mignitude of times FASTER.

You will never see, even the slowest Android smartphone to update in hours. :kookoo::rolleyes:
 
Zen 3 should be one of the last and final attempts in the development of x86-64 and the PC platform in this shape and form.
Zen 3 started its development at least 3-5 years ago, JK resigns today. There is quite a difference in the time frame.

The Sony PlayStation 5 development and design shows just how primitive the x86 is, where they needed a ton of new specialised functions and dedicated hardware sets in order to replace the missing x86 instructions which they need and the extremely slow execution on the Zen 2 cores if they didn't include these new specialised hardware functions in order to accelerate the gaming experience as they wish.

Try running a Celeron with an HDD on Windows 10.
You will see how painfully slow it is.
A simple update takes dozens of minutes or hours.

My Ryzen system with an SSD took longer than an hour to update from 19 09 to 20 04. This is just unacceptable and I will take the very first opportunity to get rid of x86 system in favour of RISC ARM which is a mignitude of times FASTER.

You will never see, even the slowest Android smartphone to update in hours. :kookoo::rolleyes:

LMAO.

Your ignorance is showing again.
 
My Ryzen system with an SSD took longer than an hour to update from 19 09 to 20 04.
This is just unacceptable and I will take the very first opportunity to get rid of x86 system in favour of RISC ARM which is a mignitude of times FASTER.

You will never see, even the slowest Android smartphone to update in hours. :kookoo::rolleyes:
You know what, get a better SSD. How about the upcoming true gen4 980 pro from Sammy?

Depends on the handset & the size of the update.

I dunno, you seem to fluctuate from anywhere between Tucker Carlson on one end of the spectrum to John Oliver at the other. If you get what I mean :rolleyes:
See the source image
 
You know what, get a better SSD.

The problem is these forums are too many anti-objective employees of corporations working with x86, thus shilling and trolling in favour of their job.
Completely ignoring the global users' experiences, and more importantly - the huge list of disadvantages of their own achievements.

My SSD Western Digital Blue 3D NAND M.2 SSD 500GB is already the best SATA3 SSD on the market. Can't get better than it and it's not the problem..
 
My Ryzen system with an SSD took longer than an hour to update from 19 09 to 20 04. This is just unacceptable and I will take the very first opportunity to get rid of x86 system in favour of RISC ARM which is a mignitude of times FASTER.

You will never see, even the slowest Android smartphone to update in hours
it took me ~5-10 mins including the DL all the way to 'first' boot. Sounds like a personal issue. :)

Funny how you're comparing phone os upgrades to pc's tho...the size of the upgrade packages are a lot smaller. A couple/few GB vs couple hundo MB? Even the much slower arm processors and a phone will chew through it. That said, I've had a few OS updates on my s9+ and the first on the s20+ also took 10 mins...and these are both high-end units with, at the time, the fastest snapdragons(?) on them.
 
it took me ~5-10 mins including the DL all the way to 'first' boot. Sounds like a personal issue. :)

Funny how you're comparing phone os upgrades to pc's tho...the size of the upgrade packages are a lot smaller. A couple/few GB vs couple hundo MB? Even the much slower arm processors and a phone will chew through it. That said, I've had a few OS updates on my s9+ and the first on the s20+ also took 10 mins...and these are both high-end units with, at the time, the fastest snapdragons(?) on them.


:confused:

Well, the SSD's speeds are 560 MB/s reads , 530 MB/s writes as at https://shop.westerndigital.com/en-ie/products/internal-drives/wd-blue-3d-nand-sata-ssd#WDS250G2B0A

1592138724745.png


Now, my tests show:
From HDD1 to SSD1 where the Windows is:

1592138773107.png


Copy - paste in the same SSD folder:

1592138809609.png



What can the "personal" issue be ? Platform defect on the Acer Nitro AN515-42 ?
 
Not sure, ARF. Just telling you my experiences with my system (16c/16t cpu, pcie 3.0 nvme m.2) and phones. I'll add to that my son's 2700x system with sata ssd for OS took a bit longer, but nowhere near how long yours did. Same with my 7900x + sata ssd system. No way the latter took 20 mins...60 mins is, seemingly, a problem and not normal.
 
Last edited:
Well, the SSD's speeds are 560 MB/s reads , 530 MB/s writes as at https://shop.westerndigital.com/en-ie/products/internal-drives/wd-blue-3d-nand-sata-ssd#WDS250G2B0A
Now, my tests show:
From HDD1 to SSD1 where the Windows is:
Copy - paste in the same SSD folder:
First one - you are copying from an HDD. The speed is limited by speed of data source read - that is HDD speed.
Second one - small enough files? Small-ish file overhead eats speed more than anything, especially on the same drive.
 
Last edited:
You know what, get a better SSD. How about the upcoming true gen4 980 pro from Sammy?

Depends on the handset & the size of the update.

I dunno, you seem to fluctuate from anywhere between Tucker Carlson on one end of the spectrum to John Oliver at the other. If you get what I mean :rolleyes:
See the source image
Don't drag poor Tucker into this. LOL.

But "personal reasons" for a resignation in this day and age is prolly the fact he was busted with stuff he shouldn't and he took some plea deal.... I smell shenanigans.

Just like how Bob iger and disney are.... basement bob is still on training wheels and sippy cups for disney stuff.. while iger still has the whips.

Same shit pattern. So where's Intel's basement bob?
 
Not sure, ARF. Just telling you my experiences with my system (16c/16t cpu, pcie 3.0 nvme m.2) and phones. I'll add to that my son's 2700x system with sata ssd for OS took a bit longer, but nowhere near how long yours did. Same with my 7900x + sata ssd system. No way the latter took 20 mins...60 mins is, seemingly, a problem and not normal.


First one - you are copying from an HDD. The speed is limited by speed of data source read - that is HDD speed.
Second one - small enough files? Small-ish file overhead eats speed more than anything, especially on the same drive.


Copying ISO Office and Windows files is very fast - an ISO office file of 0.9 GB happens instantly.
Windows ISO file that is larger begins with 1.1 GB/s and ends with around 430 MB/s...

That means that the problem is NOT in the SSD but in Windows itself. Updating is slower than new fresh installation.
Updating is very slow, it's like decompressing by the CPU that eats dozens of minutes, and then copying and pasting very small files.
 
So because Windows updates slowly, x86 is the problem?

Amazing logic there. Absolutely flawless. Impeccable even.


There are two very important words there that you seem incapable of reading:

UP TO.
 
The "up to" is wrong. It goes up to all the way up to 1.1 - 1.2 GB/s copying and pasting in the same folder.
 
The "up to" is wrong. It goes up to all the way up to 1.1 - 1.2 GB/s copying and pasting in the same folder.
No that is not true. :laugh:
It`s read speeds up to 560MB/s and sequential write speeds up to 530MB/s.
 
That means that the problem is NOT in the SSD but in Windows itself. Updating is slower than new fresh installation
for you, perhaps. Installing windows from a 10 Gbps USB takes around 10-15 mins on nvme drive... the update from DL to boot was, as I said, less than 10 mins.
 
Last edited:
No that is not true. :laugh:
It`s read speeds up to 560MB/s and sequential write speeds up to 530MB/s.


I have just said that I observe higher speeds and you say it's untrue?

These are just speeds around the saturation of the SATA3 bus (which is by the way 600 MB/s, if you don't know) and no where it's written under what exactly circumstances and conditions a user would observe them.
 
I have just said that I observe higher speeds and you say it's untrue?

These are just speeds around the saturation of the SATA3 bus (which is by the way 600 MB/s, if you don't know) and no where it's written under what exactly circumstances and conditions a user would observe them.
So... if the limit of the bus is 600 MB/s, and with overhead etc its more realistically 560 MB/s as you see most sata drives top out at, you saw double this speed? I'm not sure what you're trying to defend.

Would that be cache/burst? Either way, I dont care.. its off topic, lol.
 
Last edited:
Am I missing something? I'm not sure what microprocessor architecture, be it x86, ARM or whatever, has to do with data throughput speeds...
 
Say on topic please!

We are talking about "Jim Keller" and his Ocean Cove project at Intel he leaving.

Talking about load times is a losing battle with technology changing rapidly over the next few years.

Both companies...have new sockets with higher bus speeds huge bandwidth increases with PCIe 5.0 coming. AMD AM5 and Intel H6 LGA 1700 sockets every thing is changing... PCIe 5.0, DDR5, USB4, technology's make all you guys load times irrelevant with the technology that "Jim Keller" was working on...

This is near future stuff....Jim Keller Ocean cove is second generation big.Little...

Intel is moving to 16/32 Cores big.Little architecture and unifying mobile and desktop together under Alder Lake / Meteor Lake over the next few years. This is PCIe 4.0 to PCIe 5.0 and 10nm++ to 7nm+ on 16/32 Cores big.LITTLE

Jim Keller will get more famous once Ocean Cove technology gets in our hands. This is the technology that Jim Keller was working on at Intel.

Power efficiency, IPC increase, Bandwidth, Prices....all fixed with Meteor Lake.
 
Am I missing something? I'm not sure what microprocessor architecture, be it x86, ARM or whatever, has to do with data throughput speeds...
I think those are more related to storage than CPU??
 
One of the chips is so fast that accelerates as if 9 Zen 2 cores ! :eek:
You do realize this is an ASIC running hardware implementation of whichever compression they are using? It has little to do with the specific processor in the system.

Kraken compression range generally falls in the 2-7x range. basically there is a 3-4GB/s NVMe drive underneath and then there is a hardware compressor/decompressor on the machine side of things. I kind of wonder how long will it take for motherboard manufacturers and/or Intel/AMD to implement something similar if it proves useful to generic use cases. From the descriptions so far, both Sony's and Microsoft solutions seem to be heavily aimed towards texture compression.
 
Last edited:
Back
Top