They don't have much choice, then need better iGPUs to compete and buying Nvidia is no longer an affordable option. The dGPU ambitions are just a sideshow right now.
I think I read somewhere that the pricing on their desktop GPUs will be in the same highway robbery territory as AMD and NVIDIA. And Intel has been promising a discreet GPU since at least Larrabee, back in 2008. At least their IGPs are finally advancing again, after several generations of stagnant “HD Graphics” editions.
Not to mention they will be at the mercy of AMD and Nvidia. Just consider a future where server GPUs from AMD and Nvidia use proprietary interconnect that are specific for EPYC and whatever Nvidia produces based on ARM. Intel will be thrown out of the server market or be relegated as the 3rd option.
> every decade intel decides to get into graphics and then abandons it after one lame product
This isn't even slightly true. Larrabee never shipped. Intel decided it wasn't competitive, so they switch to making compute-only products and completed TWO generations of Xeon Phi, before cancelling it.
As for their latest dGPU plans, the only thing cancelled is the non-HPC server product, which also never shipped in any quantity. The gaming-oriented Arc products are still slated for release in Q1 2022.
23 and 13 year ago business decisions are irrelevant to current market conditions. GPU is quickly becoming more important than CPU in many critical workflows. The role of the CPU is shrinking, and if Intel wants to be around, they need to diversify their compute products away from strictly CPU.
They've been selling DG1 to OEMs for over a year, IIRC. That's a PCIe card with the same 96 EU GPU as in Tiger Lake. Also, like Tiger Lake, it uses regular DDR4!
Now for that new Xe mainstream, I will see how will Intel screw up. I have my huge doubts on the driver side of things than anything else. Because there are a TON of games we have and lot of workloads we have and it has to support everything out of gate. Which is a super mighty task.
Plus thanks to Windows 10 DCH BS the drivers will be a nasty mess, just like how Nvidia's latest 493 branch has been. Sadly no more Win32 drivers from any company because M$ wants their draconian standard no matter what. NVCP was not bundled with first 493 branch and forced people to get it from Store now they added. Also reading some reports on Mining Nerf lol.
Intel also eats up TSMC 6nm overall TSMC so expect high price and low availability if ETH mining is good, add even more worse outcome.
Yeah, 6.8B NET INCOME just sucks this Q...It's so terrible to be Intel.
Then again, AMD made less then 1B NET so... What world do you live in? I live in one where ~7 is FAR larger than ~1. But hey, what do I know, these are just numbers...who cares....ROFL. ;)
3nm TSMC INTEL server/mobile incoming in 1Q. :) AMD 3nm server coming in....2024 or 2025?
People can't be this stupid. AMD is winning...AMD is winning...pfft. Ok. But at least they bought some shares back (been diluting them for 15yrs now, about time they bought a few back...LOL). AMD's Mkap is 3/4 of Intel's and Intel is making 6.8B NET in a Q while AMD is winning (making less than 1 BTW)...ROFLMAO. I take it back, people are stupid.
Select "Windows driver type" Standard. If you want to find the page from the "normal (new)" driver download page, click the utterly misleading link "BETA Drivers and Archive" down at the bottom.
"And while Xe-HPG could be called up for server use next year, unless Intel is able to tile it like Xe-HP, they won’t be able to offer the kind of performance that Xe-HP was slated to deliver."
But who even needs that kind of config?
Right now, it seems that server compute users are satisfied with diehard, cost-is-no-object accelerator designs at the very top, and repurposed PCIe gaming GPUs everywhere else. Perhaps Intel saw there was no demand for Xe HP from their customers, and therefore there's no gap to fill.
* another niche is the low power compute area that, for instance, a ton of the ML inference startups are targeting, but that doesn't seem like a good candidate for Xe HP either.
I think It's a density play, mostly. It's about packing the most amount of compute or video transcoding, etc. per rack unit.
> Perhaps Intel saw there was no demand for Xe HP from their customers, > and therefore there's no gap to fill.
That's one plausible explanation, but I think the more likely scenario is they realized their "Intel 7" fabs were overcommitted and opted to pull Xe-HP, since many of their customers could substitute in Xe-HPG or Xe-HPC. That would be far more palatable than catching a lot of bad press from Alder Lake being impossible to find in-stock, which might happen regardless.
The final explanation is that there was some technical or performance problem with how they implemented tiling, and GPU apps just didn't scale well to multiple tiles.
My bet is that they actually were going to be short on interconnect materials + capacity for their server parts. They've probably been getting orders for Sapphire Rapids in reasonably high volume since it's clearly the best Intel upgrade path.
“ In any case, Intel is clearly not giving up on their plans to break into the server GPU market” What other server GPU options are left from Intel? Also, what about those customers who sampled these? They will be skeptical next time to say the least.
> What other server GPU options are left from Intel?
There's currently a product from one of their partners which packs 4x DG1 chips on a single PCIe board. You could imagine something similar happening with DG2 (although maybe just 2x chips, due to its wider memory interface & higher power consumption).
The server market operates on longer timescales than the graphics market or the HPC market. NVIDIA is still selling T4s and V100s in servers. Providing they had the software in place, Intel could still get their foot in the door with hardware about to be surpassed.
Most likely, the reason the HP dies have been cancelled is because it's a lot harder to productize in the commercial data center space than in HPC or gaming. HPC mostly uses compiler directives for parallelization with critical pieces written in native code. Gaming relies on well-tuned drivers, but outside that it is mostly standard APIs. Commercial data center GPU compute, however, relies on tools and libraries that NVIDIA have built up over years. Customers just showed no interest in committing to Intel's OneAPI in any commercially-viable way because it would have cut their productivity severely. Intel needs to 1) prove they have a stable roadmap and 2) invest in a buildout of OneAPI first, then attract customers afterwards. They can't just build a piece of competitive hardware, a la their HP die, and expect to sell it, even if it were faster than NVIDIA's hardware coming out a few months later. The fact that it's likely slower than NVIDIA's hardware coming out a few months later is just adding dirt to the early grave.
By longer timescales I mean the sales of a particular architecture last longer. Supercomputers are being built with the A100. If it weren't for the supply shortage we wouldn't have new 20 series cards hanging around except for the low end of the market. But people still build servers with the previous generation data center GPU well after the new one is released.
Unpopular opinion, this is feeling very old AMD again. Where are the products ?
To this day I still dont understand why Raja Koduri gets all the hype like Jim Keller. We are soon 2022, and not a single discrete GPU out. Even Alder Lake is shipping.
DG1 launched exactly a year ago, and the Xe GPUs are also included in Tiger Lake and Alder Lake.
As the article said, Xe-HPC is shipping to select customers (e.g. Aurora), so that's another.
I'm not trying to defend Raja, so much as establishing the facts. I'm very much waiting to see how Xe-HPG (DG2) does. I think that and its successor will strongly suggest whether Raja has had a positive or negative impact on Intel's GPU group.
I never got why they needed that many product lines. Neither Nvidia nor AMD have multiple "fill in the blanks" like that. There's no need. Either you go consumer, or you go for AI/HPC and go as big as possible. The "inbetween" doesn't exist enough to justify investment, especially when specialized silicon like Google's video encoder already exist for the biggest potential customers, and so there's not a lot of point.
Intel didn't go "in between" gaming and data center. It went "as big as possible" with HPC and "normal" with HP. Intel's HPC "product line" (if you can call it that) is like a feast one makes for a king on his coronation. It has 47 active tiles. It uses both foveros and emib packaging technologies. It's using the TSMC's 5 nm process long before anyone else is using that for high powered chips. There's no way it can be scaled back to be a normal "HP" chip and still be considered the same product line. It makes sense for Intel to split the HPC and HP line because it wouldn't have much sales of a "normal" data center GPU, anyway. Just like AMD has never had much data center GPU sales despite having "normal" data center chips for years.
For Nvidia, the P100, V100, and A100 accelerators are their high-end machine learning & HPC offering. For AMD, their MI100 and MI200 CDNA-based products slot into basically the same tier.
Below that, they each have the gaming-oriented chips, which do double-duty being rebranded for workstations and servers.
So, you're right that Intel *was* the odd one, for having a 3rd tier that's its own distinct silicon.
I wasn't aware of Google's custom video encoding silicon. I guess it's called "Argos"? I find it surprising they found so much benefit vs. Nvidia or Intel that they deemed it worthwhile to make their own.
To get a clearer picture, consider the actual products instead of counting the number. Intel is now more of the odd one out, for now, because it is using the same architecture for its gaming and data center lines, whereas AMD and NVIDIA each have some separation between their data center chips and their gaming chips (RDNA/CDNA for AMD and the x100/all other GPUs for NVIDIA). I'm assuming Intel does not have FP64 on their HPG chips so one thing this means is that Intel's data center chips won't have FP64 (which isn't that big of a deal. the market for FP64 outside HPC seems to be small). Another oddity that was already there for Intel is that their data center and HPC chips have ray tracing. Both AMD and NVIDIA are using the same architecture for their data center and HPC chips, whereas Intel is using a different one. That oddity was there for Intel previously to this announcement and has not changed.
It feels processrelated. Could be that they don't have enough wafers to dedicate, they would prioritize CPU's on their own process since they are selling as much as they can produce and by buying more wafers from TSMC they are effectively squeezing AMD in production resources. For the moment it seems they are not competing directly with AMD on TSMC wafers, but they are limiting AMD's way forward, depending on sales and which volume they are buying of course.
Agree. And with the points Yojimbo pointed out they had a rough road ahead in data center. With limited 10 nm production capacity they probably went with the guaranteed CPU sales.
There's a sweet spot between high price @ low-volume vs. low price @ high-volume. It's not clear to me that the GPU market is in that sweet spot. That is to say that I'm sure each of those companies would like higher volume, if they could get it.
I don't know if you're trying to be funny, but I imagine no one is laughing.
Xe-HP, using Intel 7, is competing with CPU's for fab time. Seems to me current capacity isn't enough to also manufacture Xe-HP in addition to Alder Lake and Sapphire Rapids. There's no reason to believe Intel is opting out of this market, but rather just "not yet". Probably also best to focus on GPU consumer products for now and allow time for drivers to mature and see real world use.
I'm betting Intel will keep cutting GPU lines until only the consumer side is left. When that inevitably fails (again) they'll sweep it under the rug and pretend it never happened, as they do. Then in a decade they'll repeat the process, and another decade after that...
Just goes to show that no amount of money can buy talent. And no, Raja "Vega" Koduri doesn't count as talent; I'd be impressed if he could design a functional paper bag.
Intel is using their 3D manufacturing to integrate TSM GPU tiles, announced for Ponte Vecchio's compute tiles and reportedly planned for Meteor Lake's 192eu tile.
There may be enough volume in these tiles to keep their interest, which seems to be their strategy with the downscale of Ponte Vecchio's 16 tiles to 8 and 4 tile versions.
Tiger Lake's 96eu will be doubled to 192 on Meteor Lake, although it would be more interesting if they upgraded to Xe-HPG tiles.
I believe David Blythe is the chief GPU architect on Xe.
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
47 Comments
Back to Article
coburn_c - Friday, October 29, 2021 - link
They've made no progress with any of their GPU designs. Time to throw the Intel GPU on the pile with their smartphone aspirations and Itanium.Flunk - Friday, October 29, 2021 - link
They don't have much choice, then need better iGPUs to compete and buying Nvidia is no longer an affordable option. The dGPU ambitions are just a sideshow right now.Makaveli - Monday, November 1, 2021 - link
I always wonder how things would have been different if it was Intel that bought ATI. And what would the market look like now...tipoo - Wednesday, November 3, 2021 - link
Might look at Altera or Mobileye for an idea...They're still going, but not really benefitting from the mothership.MonkeyPaw - Friday, October 29, 2021 - link
I think I read somewhere that the pricing on their desktop GPUs will be in the same highway robbery territory as AMD and NVIDIA. And Intel has been promising a discreet GPU since at least Larrabee, back in 2008. At least their IGPs are finally advancing again, after several generations of stagnant “HD Graphics” editions.drexnx - Friday, October 29, 2021 - link
and before that, i740 back in 1998! that actually released though.seems like every decade intel decides to get into graphics and then abandons it after one lame product
yannigr2 - Friday, October 29, 2021 - link
Yes, but today GPU is the king. Intel will go nowhere in servers without a fast GPU.yannigr2 - Friday, October 29, 2021 - link
Not to mention they will be at the mercy of AMD and Nvidia. Just consider a future where server GPUs from AMD and Nvidia use proprietary interconnect that are specific for EPYC and whatever Nvidia produces based on ARM. Intel will be thrown out of the server market or be relegated as the 3rd option.mode_13h - Sunday, October 31, 2021 - link
> every decade intel decides to get into graphics and then abandons it after one lame productThis isn't even slightly true. Larrabee never shipped. Intel decided it wasn't competitive, so they switch to making compute-only products and completed TWO generations of Xeon Phi, before cancelling it.
As for their latest dGPU plans, the only thing cancelled is the non-HPC server product, which also never shipped in any quantity. The gaming-oriented Arc products are still slated for release in Q1 2022.
mode_13h - Sunday, October 31, 2021 - link
The irony is that it's in fact the newly-cancelled Xe-HP that was supposed to take Xeon Phi's place.mode_13h - Monday, November 1, 2021 - link
For the most part, I mean. Obviously, Xe-HPC is targeted at the high-end of Xeon Phi's market. There were a few supercomputers that used it.kwohlt - Tuesday, November 2, 2021 - link
23 and 13 year ago business decisions are irrelevant to current market conditions. GPU is quickly becoming more important than CPU in many critical workflows. The role of the CPU is shrinking, and if Intel wants to be around, they need to diversify their compute products away from strictly CPU.1998 was an entire generation ago.
hansmuff - Tuesday, November 2, 2021 - link
Hah, I had one. It was fairly awful overall, but I could play Q3 Arena with it, which is really all that mattered ;)bananaforscale - Friday, November 5, 2021 - link
"I think I heard somewhere" means exactly nothing. BTW, discrete, not discreet.YB1064 - Saturday, October 30, 2021 - link
I have yet to see a single discrete consumer GPU from INTEL on Newegg/Amazon? Is this dead?whatthe123 - Sunday, October 31, 2021 - link
they're coming out for retail next year using tsmc chipsmode_13h - Sunday, October 31, 2021 - link
They've been selling DG1 to OEMs for over a year, IIRC. That's a PCIe card with the same 96 EU GPU as in Tiger Lake. Also, like Tiger Lake, it uses regular DDR4!Silver5urfer - Friday, October 29, 2021 - link
Raja hype boys. As usual.Now for that new Xe mainstream, I will see how will Intel screw up. I have my huge doubts on the driver side of things than anything else. Because there are a TON of games we have and lot of workloads we have and it has to support everything out of gate. Which is a super mighty task.
Plus thanks to Windows 10 DCH BS the drivers will be a nasty mess, just like how Nvidia's latest 493 branch has been. Sadly no more Win32 drivers from any company because M$ wants their draconian standard no matter what. NVCP was not bundled with first 493 branch and forced people to get it from Store now they added. Also reading some reports on Mining Nerf lol.
Intel also eats up TSMC 6nm overall TSMC so expect high price and low availability if ETH mining is good, add even more worse outcome.
At this point nobody can fix the GPU market.
iranterres - Friday, October 29, 2021 - link
LOL Intel are burying theirselves again.TheJian - Saturday, October 30, 2021 - link
Yeah, 6.8B NET INCOME just sucks this Q...It's so terrible to be Intel.Then again, AMD made less then 1B NET so... What world do you live in? I live in one where ~7 is FAR larger than ~1. But hey, what do I know, these are just numbers...who cares....ROFL. ;)
3nm TSMC INTEL server/mobile incoming in 1Q. :) AMD 3nm server coming in....2024 or 2025?
People can't be this stupid. AMD is winning...AMD is winning...pfft. Ok. But at least they bought some shares back (been diluting them for 15yrs now, about time they bought a few back...LOL). AMD's Mkap is 3/4 of Intel's and Intel is making 6.8B NET in a Q while AMD is winning (making less than 1 BTW)...ROFLMAO. I take it back, people are stupid.
Lord of the Bored - Wednesday, November 3, 2021 - link
No one but you is talking about AMD.yetanotherhuman - Monday, November 1, 2021 - link
You can still download the standard drivers from NVIDIA, you just have to click about a bit.https://www.nvidia.co.uk/Download/Find.aspx
Select "Windows driver type" Standard. If you want to find the page from the "normal (new)" driver download page, click the utterly misleading link "BETA Drivers and Archive" down at the bottom.
brucethemoose - Friday, October 29, 2021 - link
"And while Xe-HPG could be called up for server use next year, unless Intel is able to tile it like Xe-HP, they won’t be able to offer the kind of performance that Xe-HP was slated to deliver."But who even needs that kind of config?
Right now, it seems that server compute users are satisfied with diehard, cost-is-no-object accelerator designs at the very top, and repurposed PCIe gaming GPUs everywhere else. Perhaps Intel saw there was no demand for Xe HP from their customers, and therefore there's no gap to fill.
brucethemoose - Friday, October 29, 2021 - link
* another niche is the low power compute area that, for instance, a ton of the ML inference startups are targeting, but that doesn't seem like a good candidate for Xe HP either.mode_13h - Sunday, October 31, 2021 - link
> But who even needs that kind of config?I think It's a density play, mostly. It's about packing the most amount of compute or video transcoding, etc. per rack unit.
> Perhaps Intel saw there was no demand for Xe HP from their customers,
> and therefore there's no gap to fill.
That's one plausible explanation, but I think the more likely scenario is they realized their "Intel 7" fabs were overcommitted and opted to pull Xe-HP, since many of their customers could substitute in Xe-HPG or Xe-HPC. That would be far more palatable than catching a lot of bad press from Alder Lake being impossible to find in-stock, which might happen regardless.
The final explanation is that there was some technical or performance problem with how they implemented tiling, and GPU apps just didn't scale well to multiple tiles.
It could also be some combination of these.
lmcd - Monday, November 1, 2021 - link
My bet is that they actually were going to be short on interconnect materials + capacity for their server parts. They've probably been getting orders for Sapphire Rapids in reasonably high volume since it's clearly the best Intel upgrade path.Teckk - Friday, October 29, 2021 - link
“ In any case, Intel is clearly not giving up on their plans to break into the server GPU market”What other server GPU options are left from Intel?
Also, what about those customers who sampled these? They will be skeptical next time to say the least.
mode_13h - Sunday, October 31, 2021 - link
> What other server GPU options are left from Intel?There's currently a product from one of their partners which packs 4x DG1 chips on a single PCIe board. You could imagine something similar happening with DG2 (although maybe just 2x chips, due to its wider memory interface & higher power consumption).
yannigr2 - Friday, October 29, 2021 - link
Failed performance? Failed manufacturing? Failed in everything?Lonyo - Saturday, October 30, 2021 - link
My guess would be manufacturing if this is the only in-house fabbed product in the stack.Yojimbo - Friday, October 29, 2021 - link
The server market operates on longer timescales than the graphics market or the HPC market. NVIDIA is still selling T4s and V100s in servers. Providing they had the software in place, Intel could still get their foot in the door with hardware about to be surpassed.Most likely, the reason the HP dies have been cancelled is because it's a lot harder to productize in the commercial data center space than in HPC or gaming. HPC mostly uses compiler directives for parallelization with critical pieces written in native code. Gaming relies on well-tuned drivers, but outside that it is mostly standard APIs. Commercial data center GPU compute, however, relies on tools and libraries that NVIDIA have built up over years. Customers just showed no interest in committing to Intel's OneAPI in any commercially-viable way because it would have cut their productivity severely. Intel needs to 1) prove they have a stable roadmap and 2) invest in a buildout of OneAPI first, then attract customers afterwards. They can't just build a piece of competitive hardware, a la their HP die, and expect to sell it, even if it were faster than NVIDIA's hardware coming out a few months later. The fact that it's likely slower than NVIDIA's hardware coming out a few months later is just adding dirt to the early grave.
Yojimbo - Friday, October 29, 2021 - link
By longer timescales I mean the sales of a particular architecture last longer. Supercomputers are being built with the A100. If it weren't for the supply shortage we wouldn't have new 20 series cards hanging around except for the low end of the market. But people still build servers with the previous generation data center GPU well after the new one is released.ksec - Friday, October 29, 2021 - link
Unpopular opinion, this is feeling very old AMD again. Where are the products ?To this day I still dont understand why Raja Koduri gets all the hype like Jim Keller. We are soon 2022, and not a single discrete GPU out. Even Alder Lake is shipping.
regsEx - Saturday, October 30, 2021 - link
There is a one. HPG are slated for Q1 2022. They depend on how TSMC ramping up N6 production capability.mode_13h - Sunday, October 31, 2021 - link
DG1 launched exactly a year ago, and the Xe GPUs are also included in Tiger Lake and Alder Lake.As the article said, Xe-HPC is shipping to select customers (e.g. Aurora), so that's another.
I'm not trying to defend Raja, so much as establishing the facts. I'm very much waiting to see how Xe-HPG (DG2) does. I think that and its successor will strongly suggest whether Raja has had a positive or negative impact on Intel's GPU group.
Frenetic Pony - Saturday, October 30, 2021 - link
I never got why they needed that many product lines. Neither Nvidia nor AMD have multiple "fill in the blanks" like that. There's no need. Either you go consumer, or you go for AI/HPC and go as big as possible. The "inbetween" doesn't exist enough to justify investment, especially when specialized silicon like Google's video encoder already exist for the biggest potential customers, and so there's not a lot of point.Yojimbo - Saturday, October 30, 2021 - link
Intel didn't go "in between" gaming and data center. It went "as big as possible" with HPC and "normal" with HP. Intel's HPC "product line" (if you can call it that) is like a feast one makes for a king on his coronation. It has 47 active tiles. It uses both foveros and emib packaging technologies. It's using the TSMC's 5 nm process long before anyone else is using that for high powered chips. There's no way it can be scaled back to be a normal "HP" chip and still be considered the same product line. It makes sense for Intel to split the HPC and HP line because it wouldn't have much sales of a "normal" data center GPU, anyway. Just like AMD has never had much data center GPU sales despite having "normal" data center chips for years.mode_13h - Monday, November 1, 2021 - link
Nvidia and AMD have basically 2 product lines.For Nvidia, the P100, V100, and A100 accelerators are their high-end machine learning & HPC offering. For AMD, their MI100 and MI200 CDNA-based products slot into basically the same tier.
Below that, they each have the gaming-oriented chips, which do double-duty being rebranded for workstations and servers.
So, you're right that Intel *was* the odd one, for having a 3rd tier that's its own distinct silicon.
I wasn't aware of Google's custom video encoding silicon. I guess it's called "Argos"? I find it surprising they found so much benefit vs. Nvidia or Intel that they deemed it worthwhile to make their own.
Yojimbo - Tuesday, November 2, 2021 - link
To get a clearer picture, consider the actual products instead of counting the number. Intel is now more of the odd one out, for now, because it is using the same architecture for its gaming and data center lines, whereas AMD and NVIDIA each have some separation between their data center chips and their gaming chips (RDNA/CDNA for AMD and the x100/all other GPUs for NVIDIA). I'm assuming Intel does not have FP64 on their HPG chips so one thing this means is that Intel's data center chips won't have FP64 (which isn't that big of a deal. the market for FP64 outside HPC seems to be small). Another oddity that was already there for Intel is that their data center and HPC chips have ray tracing. Both AMD and NVIDIA are using the same architecture for their data center and HPC chips, whereas Intel is using a different one. That oddity was there for Intel previously to this announcement and has not changed.Zoolook - Saturday, October 30, 2021 - link
It feels processrelated.Could be that they don't have enough wafers to dedicate, they would prioritize CPU's on their own process since they are selling as much as they can produce and by buying more wafers from TSMC they are effectively squeezing AMD in production resources.
For the moment it seems they are not competing directly with AMD on TSMC wafers, but they are limiting AMD's way forward, depending on sales and which volume they are buying of course.
flgt - Saturday, October 30, 2021 - link
Agree. And with the points Yojimbo pointed out they had a rough road ahead in data center. With limited 10 nm production capacity they probably went with the guaranteed CPU sales.Oxford Guy - Sunday, October 31, 2021 - link
You mean Intel is helping AMD and Nvidia keep GPU prices extremely high — so it, too, can get the big margin.mode_13h - Monday, November 1, 2021 - link
There's a sweet spot between high price @ low-volume vs. low price @ high-volume. It's not clear to me that the GPU market is in that sweet spot. That is to say that I'm sure each of those companies would like higher volume, if they could get it.I don't know if you're trying to be funny, but I imagine no one is laughing.
Oxford Guy - Monday, November 1, 2021 - link
Again with your imagination.kwohlt - Tuesday, November 2, 2021 - link
Xe-HP, using Intel 7, is competing with CPU's for fab time. Seems to me current capacity isn't enough to also manufacture Xe-HP in addition to Alder Lake and Sapphire Rapids. There's no reason to believe Intel is opting out of this market, but rather just "not yet". Probably also best to focus on GPU consumer products for now and allow time for drivers to mature and see real world use.The_Assimilator - Wednesday, November 3, 2021 - link
I'm betting Intel will keep cutting GPU lines until only the consumer side is left. When that inevitably fails (again) they'll sweep it under the rug and pretend it never happened, as they do. Then in a decade they'll repeat the process, and another decade after that...Just goes to show that no amount of money can buy talent. And no, Raja "Vega" Koduri doesn't count as talent; I'd be impressed if he could design a functional paper bag.
JayNor - Wednesday, December 15, 2021 - link
Intel is using their 3D manufacturing to integrate TSM GPU tiles, announced for Ponte Vecchio's compute tiles and reportedly planned for Meteor Lake's 192eu tile.There may be enough volume in these tiles to keep their interest, which seems to be their strategy with the downscale of Ponte Vecchio's 16 tiles to 8 and 4 tile versions.
Tiger Lake's 96eu will be doubled to 192 on Meteor Lake, although it would be more interesting if they upgraded to Xe-HPG tiles.
I believe David Blythe is the chief GPU architect on Xe.