China's first 6nm GPU boots up, targets performance parity with RTX 4060
Technology
22
Beiträge
15
Kommentatoren
190
Aufrufe
-
This post did not contain any content.
I'm looking forward to getting a low cost Chinese GPU; Lets see how much time it takes for these to become competitive with Nvidia or AMD.
-
Ooh, more baseless claims of China's technological advancement.
I'll file this in the bullshit folder with the rest of their bullshit claims.
I wish their claims were true. There is not enough competition right now.
-
Big...if true. This article is long on claims but utterly bereft of proof.
As usual with very much wow inventions from China.
Not to say that they don't have clever people there doing cool stuff. It's just my experience that such articles are often overselling something which does not live up to the claims.
-
As usual with very much wow inventions from China.
Not to say that they don't have clever people there doing cool stuff. It's just my experience that such articles are often overselling something which does not live up to the claims.
Even if the hardware does....drivers matter. I'm reminded of the Moore Threads MTT S80.
-
I'm looking forward to getting a low cost Chinese GPU; Lets see how much time it takes for these to become competitive with Nvidia or AMD.
I agree, if this could make good GPU's more affordable, that would be great.
-
WTF!? OK they had the 7nm process for more than a year now, but 6nm without EUV?
I'm not an expert, but it seems to me that when China cracks EUV, which they allegedly are getting close to, then SMIC will progress fast to even better processes.
China is making very good progress, especially considering they cannot use any western equipment. Everything has to be home grown!
but 6nm without EUV?
I read elsewhere that 5nm was already done (in the lab, not on industrial levels), and they're planning on 3nm by 2026.
The workaround seems to be to use particle accelerators instead of EUV machines. More expensive and with lower yield, but it'll do the job.
-
but 6nm without EUV?
I read elsewhere that 5nm was already done (in the lab, not on industrial levels), and they're planning on 3nm by 2026.
The workaround seems to be to use particle accelerators instead of EUV machines. More expensive and with lower yield, but it'll do the job.
Yes 5nm should be ready this year, and allegedly Huawei is planning a 3nm product to be produced by SMIC already next year!
That's a very bold schedule, but maybe they expect to have something close to ASML EUV soon? -
As usual with very much wow inventions from China.
Not to say that they don't have clever people there doing cool stuff. It's just my experience that such articles are often overselling something which does not live up to the claims.
Huawei has sold a lot of phones last year based on "surprising advances" from SMIC. They have shipping AI chips that are benchmarked based on announcements that drew skepticism at the time. Not sure about this company's product or how close it is to shipping.
-
Isn't GAA one of the most advanced types?
If they can really do this next year, there is no doubt China must have their own EUV lights.So 6nm for example might just be a slightly refined 7nm node.
Absolutely true but AFAIK SMIC usually make their numbers comparable to TSMC. Even Intel changed their numbering to follow TSMC, and SAMSUNG and TSMC have always been close in their numbering.
We will have to see if the process is actually good, but I have little doubt that China will become competitive in EUV within 5 years. But if they have it already next year, that will be very fast.
GAA is the next evolution of transistor architecture from FinFET, but as far as I know has no direct link to smaller process nodes. In that (to my understanding) it doesn't require small nodes and could be used just as easily in larger ones. It's just that it is more difficult so until now there were other easier ways to make progress. However with new nodes getting more expensive and giving less scaling gaa and other things like backside power delivery are being pursued.
We will have to see if the process is actually good, but I have little doubt that China will become competitive in EUV within 5 years. But if they have it already next year, that will be very fast.
So not only do you expect China to have a working domestically produced EUV machine within 5 years, but a competitive one? Or possibly even next year?
Next year is just pure fantasy that I don't think even the most optimistic would assume. If they were anywhere close to that we would already know. They'd have shown a working prototype by now.
Euv is crazy difficult and you not only the result of a single company ASML, but many highly specialized companies that are leaders in their respective fields and all over the world like e.g. Zeiss for for the lenses. So for China to replicate it domestically they'd need to copy the whole supply chain. Which is orders of magnitude more difficult than what they've done in other industries like electric vehicles or solar panels.
Imo if they have a working prototype of a complete EUV machine within this decade it would already be impressive. But that would still be far off from mass production or wherever the industry is by then (Intel is currently trialing high na EUV). Also for reference Wikipedia says ASML had their first prototype in 2006 and we know how long it took to being that to mass production. China as a second mover might have an edge that speed things up, but just knowing how it works in theory isn't enough and there are o shortcuts.
But maybe they also pursue another technique such as nano imprint (like canon) to achieve smaller nodes. Maybe that would be easier to replicate without existing global supply chains.
-
GAA is the next evolution of transistor architecture from FinFET, but as far as I know has no direct link to smaller process nodes. In that (to my understanding) it doesn't require small nodes and could be used just as easily in larger ones. It's just that it is more difficult so until now there were other easier ways to make progress. However with new nodes getting more expensive and giving less scaling gaa and other things like backside power delivery are being pursued.
We will have to see if the process is actually good, but I have little doubt that China will become competitive in EUV within 5 years. But if they have it already next year, that will be very fast.
So not only do you expect China to have a working domestically produced EUV machine within 5 years, but a competitive one? Or possibly even next year?
Next year is just pure fantasy that I don't think even the most optimistic would assume. If they were anywhere close to that we would already know. They'd have shown a working prototype by now.
Euv is crazy difficult and you not only the result of a single company ASML, but many highly specialized companies that are leaders in their respective fields and all over the world like e.g. Zeiss for for the lenses. So for China to replicate it domestically they'd need to copy the whole supply chain. Which is orders of magnitude more difficult than what they've done in other industries like electric vehicles or solar panels.
Imo if they have a working prototype of a complete EUV machine within this decade it would already be impressive. But that would still be far off from mass production or wherever the industry is by then (Intel is currently trialing high na EUV). Also for reference Wikipedia says ASML had their first prototype in 2006 and we know how long it took to being that to mass production. China as a second mover might have an edge that speed things up, but just knowing how it works in theory isn't enough and there are o shortcuts.
But maybe they also pursue another technique such as nano imprint (like canon) to achieve smaller nodes. Maybe that would be easier to replicate without existing global supply chains.
AFAIK Canon has a process (nano imprint) that competes with EUV too, maybe not as advanced as ASML.
When I say China will have a competitive EUV system within 5 years, I don't mean competitive in how advanced it is compared to the best ASML has to offer like the new NA process TSMC hasn't even decided to buy yet.
But an EUV that allows a production process that will be competitive down to just below 2nm. Meaning competitive with the EUV process TSMC is currently using.
Depending on how much China is investing in this, they could be working on different processes in parallel.
Obviously anything as hard as this with a 5 year time span is very uncertain, we recently saw how bad things went for Intel with their 10nm process, being both multiple years delayed, and on top of that pretty bad when they finally announced it was ready.As I stated next year would be very fast, but in reality we don't know how close they are. Your claim that they would advertise it is speculation. What would be the purpose of that?
China is already competitive in 8 out of 10 key industries, and since China is prevented from even using western parts for chip making or even just buying the chips, they are pulling ressources to catch up. China will do this because they have massive talent mass and ressources, and because they have to.
-
This post did not contain any content.
Just ordered a thousand dollars worth of GPU (a single unit lol). Would i have gotten a chinese GPU for half the price if they advertised similar performance ?
No.
-
Ooh, more baseless claims of China's technological advancement.
I'll file this in the bullshit folder with the rest of their bullshit claims.
.
-
AFAIK Canon has a process (nano imprint) that competes with EUV too, maybe not as advanced as ASML.
When I say China will have a competitive EUV system within 5 years, I don't mean competitive in how advanced it is compared to the best ASML has to offer like the new NA process TSMC hasn't even decided to buy yet.
But an EUV that allows a production process that will be competitive down to just below 2nm. Meaning competitive with the EUV process TSMC is currently using.
Depending on how much China is investing in this, they could be working on different processes in parallel.
Obviously anything as hard as this with a 5 year time span is very uncertain, we recently saw how bad things went for Intel with their 10nm process, being both multiple years delayed, and on top of that pretty bad when they finally announced it was ready.As I stated next year would be very fast, but in reality we don't know how close they are. Your claim that they would advertise it is speculation. What would be the purpose of that?
China is already competitive in 8 out of 10 key industries, and since China is prevented from even using western parts for chip making or even just buying the chips, they are pulling ressources to catch up. China will do this because they have massive talent mass and ressources, and because they have to.
Your claim that they would advertise it is speculation. What would be the purpose of that?
To advertise that they can? In return what would be the purpose to hide it?
They do seem to make their advancements at least somewhat public, e.g. with their recent progress with a EUV light source.
I am probably on the pessimistic side and you maybe on the optimistic, so the reality will likely end up being somewhere in between (but only time will tell).
China will do this because they have massive talent mass and ressources, and because they have to.
Well it also was developed in the west by a large amount of talent and resources and still took a lot of time. But you are absolutely right that their hand is being forced.
Restricting exports like this imo was a huge mistake, imo especially in regard to duv. In the end it might have achieved some damage in the short/medium term, but that wasn't anything the us could capitalize on and it also directly hurt ASMLs profits (meaning less resources to advance). And regardless how the timeline ends up looking on the end (be it closer to your or my prediction), physics are the same everywhere so that can't be restricted and they will eventually be able to figure it out.
-
Your claim that they would advertise it is speculation. What would be the purpose of that?
To advertise that they can? In return what would be the purpose to hide it?
They do seem to make their advancements at least somewhat public, e.g. with their recent progress with a EUV light source.
I am probably on the pessimistic side and you maybe on the optimistic, so the reality will likely end up being somewhere in between (but only time will tell).
China will do this because they have massive talent mass and ressources, and because they have to.
Well it also was developed in the west by a large amount of talent and resources and still took a lot of time. But you are absolutely right that their hand is being forced.
Restricting exports like this imo was a huge mistake, imo especially in regard to duv. In the end it might have achieved some damage in the short/medium term, but that wasn't anything the us could capitalize on and it also directly hurt ASMLs profits (meaning less resources to advance). And regardless how the timeline ends up looking on the end (be it closer to your or my prediction), physics are the same everywhere so that can't be restricted and they will eventually be able to figure it out.
what would be the purpose to hide it?
To avoid further retaliations from USA that might prevent their progress.
And to not disclose industry secrets.I am probably on the pessimistic side and you maybe on the optimistic
True, I'm an optimist on their behalf, because China has done such impressive progress already, but I also know this is way harder than sending a man to the moon.
I agree 100% about restricting the tech is a huge mistake, and yes physics are indeed the same everywhere.
Hopefully when China figures it out, consumers everywhere will benefit. The Political implications however, is an open question. -
This post did not contain any content.
Their previous GPU used an old AMD GPU design if I recall correctly. I wonder if they have in-house stuff now.
