"Meanwhile, between mobile, desktop, and workstation products, Intel is expecting to ship over 4 million" So if I understand this correctly , if you subtract like OEM(laptop/desktop/workstation) , wouldn't this mean like AIB Intel GPU's to like almost nothing?
Yeah I was also hoping for DG2 in Q4/2021 as then we could see a quick follow up of DG3 in Q4/2022 and DG4 in Q4/2023 to H1/2024... Especially since originally DG2 was expected for H2/2021 with some hoping for Q3/2021...
Intel has to catch up so a fast cadence is expected. Also there should be a lots of low hanging fruits. With DG3 we already should see significant increases as most bugs are fixed and they might move to TSMC N4 and maybe already go for chiplets... By DG4 I would say intel managed chiplet GPU designs as well as drivers and node so they could really go head to head with AMD and Nvidia.
But I guess since DG2 is deayed and Corona reminded us how fast things can change they also became more careful with roadmaps...
I would hope we see MeteorLake Mobile by Q4/2022 or Q1/2023 parallel to RaptorLake Mobile while keep desktop mainly on RaptorLake. They did same with IceLake and CometLake...
Especially on mobile the new node and packaging combined with updated arch should provide significant advantages. And against Zen4 on TSMC5 this would be well needed...
By late 2023 we could see ArrowLake as successor for the whole lineup from Desktop to Mobile. Intel 4 / 3 should be mature by then as well as their chiplet and packaging technologies. And again this is also needed if AMD brings a big+little Zen5 on TSMC N3...
Interesting how Intel and TSMC are interacting here. Intel never used to fab for anyone else and scoffed at the market. Then they aquired a few companies which did fab for external partners and they remained a second class citizen. With the continued growth of TSMC, Intel is seeing fabing for external partners as more and more of a future revenue system. That's fine.
But, what I find interesting is how Intel is buying up TSMC capacity (legitimently because they don't currently have the capacity for some of thier parts) while they ramp up their own fabs. But what's the next step? After Intel elbows out TSMCs clients--while they ramped up fab capacity--they leave TSMC with excess fab capacity. All the while Intel has been siphoning off clients from the fab starved TSMC. Now we live in a world with excess capacity and is that a battle TSMC can win against Intel?
Intel is funding TSMC to improve their manufacturing process and get even further ahead of intel. If anything you have ask if Intel can acheive the scale to match TSMC or even Samsung.
Not in the least bit surprised that they're going for laptops first.
For one thing, they have existing relationships with the laptop manufacturers to leverage, shall we say, in the same way as Intel persuaded the manufacturers to sell laptops with spinning rust and ~16 GB of Optane memory. For another, the contracts that will be in place mean Intel already have a good idea how many chips they can sell (imagine if they started with desktop boards and the community decided they were trash: how embarrassing not to be able to sell GPUs in the current market!)
Also, it's two decades since we've had a proper low-end competitor in the graphics market. Many of the influencers and reviewers who are going to pronounce judgment on Arc will be of the mindset that if it doesn't compete with Nvidia's most expensive card, and work as well as them, it's pointless.
Releasing into the laptop market first means, at least, that the initial Arc offering will be compared with laptop GPUs.
Finally, the desktop market would almost entirely be gamers. There seems to be room in the market for all-round laptops where discrete graphics are nice to have, but users spend less time gaming (and are much less hard-core gamers) so are less likely to be so critical of issues with particular games.
Another argument is power scaling. Intel's chips probably do well in the 50-100W range with diminishing returns, Nvidia got the 3k series to be "fast" by upping the power, performance per watt hasn't improved between 2k and 3k. Used to be the 1k series laptop/desktop equivalent were pretty close (finally), but you can't put a 250W part in a laptop.
"it’s a notable departure from the traditional top-to-bottom, desktop-then-laptop style launches that current GPU titans NVIDIA and AMD have favored."
I don't find this surprising at all. Intel is already shipping GPUs in the mobile space. They already have customers lined up to buy their latest and best mobile GPU. An Intel Arc mobile customer is already an Intel Xe mobile customer.
Releasing mobile first also gives them a differentiating opportunity. While Nvidia is going to win for top performer without question, the mobile space isn't as competitive or clearly dominated. Intel stands a chance of being the "fastest mobile GPU'. A crown they stand no chance to take in the desktop space right now.
With Ryzen 6xxx's much improved RDNA integrated solution I don't really see intel's Alchemist GPUs being in anything other than OEMs or business laptops. I welcome the competition but it's unlikely going to be anything noteworthy
the math is wrong in this article. With its initial release Intel will offer up to 2M units per quarter supposing they launch that they launch at the end of Q2 as planned. The current offer is of arround 10 M per Q. So with intels new offering there will be a 20% increase in the total offer and Intel is targeting an initial 16,666% market share.
Nope...mobile is launching 1Q, and the 4mm target is inclusive of mobile, and in all likelihood even after desktop launches the vast majority of the volume will be in mobile still. So AT's math is correct.
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
Facebook
Twitter
RSS
13 Comments
Back to Article
plopke - Thursday, February 17, 2022 - link
"Meanwhile, between mobile, desktop, and workstation products, Intel is expecting to ship over 4 million" So if I understand this correctly , if you subtract like OEM(laptop/desktop/workstation) , wouldn't this mean like AIB Intel GPU's to like almost nothing?Achaios - Thursday, February 17, 2022 - link
In the beginning they implied "ARC GPUs rdy by Q4 2021" then they went to early Q1 2022 now it's "not rdy until (end of ) Q2 2022".Summer 2022 for desktop GPUs at the earliest, Fall or Winter 2022 more likely IMO.
Matthias B V - Thursday, February 17, 2022 - link
Yeah I was also hoping for DG2 in Q4/2021 as then we could see a quick follow up of DG3 in Q4/2022 and DG4 in Q4/2023 to H1/2024... Especially since originally DG2 was expected for H2/2021 with some hoping for Q3/2021...Intel has to catch up so a fast cadence is expected. Also there should be a lots of low hanging fruits. With DG3 we already should see significant increases as most bugs are fixed and they might move to TSMC N4 and maybe already go for chiplets... By DG4 I would say intel managed chiplet GPU designs as well as drivers and node so they could really go head to head with AMD and Nvidia.
But I guess since DG2 is deayed and Corona reminded us how fast things can change they also became more careful with roadmaps...
Matthias B V - Thursday, February 17, 2022 - link
I would hope we see MeteorLake Mobile by Q4/2022 or Q1/2023 parallel to RaptorLake Mobile while keep desktop mainly on RaptorLake. They did same with IceLake and CometLake...Especially on mobile the new node and packaging combined with updated arch should provide significant advantages. And against Zen4 on TSMC5 this would be well needed...
By late 2023 we could see ArrowLake as successor for the whole lineup from Desktop to Mobile. Intel 4 / 3 should be mature by then as well as their chiplet and packaging technologies. And again this is also needed if AMD brings a big+little Zen5 on TSMC N3...
JimRamK - Wednesday, March 30, 2022 - link
Thats way too optimistic for Meteor Lake. I don't think it's coming before Q2 2023 if not later.dwillmore - Thursday, February 17, 2022 - link
Interesting how Intel and TSMC are interacting here. Intel never used to fab for anyone else and scoffed at the market. Then they aquired a few companies which did fab for external partners and they remained a second class citizen. With the continued growth of TSMC, Intel is seeing fabing for external partners as more and more of a future revenue system. That's fine.But, what I find interesting is how Intel is buying up TSMC capacity (legitimently because they don't currently have the capacity for some of thier parts) while they ramp up their own fabs. But what's the next step? After Intel elbows out TSMCs clients--while they ramped up fab capacity--they leave TSMC with excess fab capacity. All the while Intel has been siphoning off clients from the fab starved TSMC. Now we live in a world with excess capacity and is that a battle TSMC can win against Intel?
Templewolf - Friday, March 4, 2022 - link
Intel is funding TSMC to improve their manufacturing process and get even further ahead of intel. If anything you have ask if Intel can acheive the scale to match TSMC or even Samsung.jamesindevon - Thursday, February 17, 2022 - link
Not in the least bit surprised that they're going for laptops first.For one thing, they have existing relationships with the laptop manufacturers to leverage, shall we say, in the same way as Intel persuaded the manufacturers to sell laptops with spinning rust and ~16 GB of Optane memory. For another, the contracts that will be in place mean Intel already have a good idea how many chips they can sell (imagine if they started with desktop boards and the community decided they were trash: how embarrassing not to be able to sell GPUs in the current market!)
Also, it's two decades since we've had a proper low-end competitor in the graphics market. Many of the influencers and reviewers who are going to pronounce judgment on Arc will be of the mindset that if it doesn't compete with Nvidia's most expensive card, and work as well as them, it's pointless.
Releasing into the laptop market first means, at least, that the initial Arc offering will be compared with laptop GPUs.
Finally, the desktop market would almost entirely be gamers. There seems to be room in the market for all-round laptops where discrete graphics are nice to have, but users spend less time gaming (and are much less hard-core gamers) so are less likely to be so critical of issues with particular games.
RSAUser - Wednesday, March 2, 2022 - link
Another argument is power scaling. Intel's chips probably do well in the 50-100W range with diminishing returns, Nvidia got the 3k series to be "fast" by upping the power, performance per watt hasn't improved between 2k and 3k. Used to be the 1k series laptop/desktop equivalent were pretty close (finally), but you can't put a 250W part in a laptop.im.thatoneguy - Thursday, February 17, 2022 - link
"it’s a notable departure from the traditional top-to-bottom, desktop-then-laptop style launches that current GPU titans NVIDIA and AMD have favored."I don't find this surprising at all. Intel is already shipping GPUs in the mobile space. They already have customers lined up to buy their latest and best mobile GPU. An Intel Arc mobile customer is already an Intel Xe mobile customer.
Releasing mobile first also gives them a differentiating opportunity. While Nvidia is going to win for top performer without question, the mobile space isn't as competitive or clearly dominated. Intel stands a chance of being the "fastest mobile GPU'. A crown they stand no chance to take in the desktop space right now.
tkSteveFOX - Friday, February 18, 2022 - link
With Ryzen 6xxx's much improved RDNA integrated solution I don't really see intel's Alchemist GPUs being in anything other than OEMs or business laptops.I welcome the competition but it's unlikely going to be anything noteworthy
BloodshedPanda - Saturday, February 19, 2022 - link
the math is wrong in this article. With its initial release Intel will offer up to 2M units per quarter supposing they launch that they launch at the end of Q2 as planned. The current offer is of arround 10 M per Q. So with intels new offering there will be a 20% increase in the total offer and Intel is targeting an initial 16,666% market share.warreo - Tuesday, March 8, 2022 - link
Nope...mobile is launching 1Q, and the 4mm target is inclusive of mobile, and in all likelihood even after desktop launches the vast majority of the volume will be in mobile still. So AT's math is correct.