Author Topic: Intel Makes 22nm 3-D Tri-Gate Tech for Ivy Bridge (Read 1945 times)

GoGeTa006 · « **Reply #20 on:** May 07, 2011, 04:25:34 AM »

Damn. . .that video sure opens eyes. . .

Anyways. . .I keep wondering as these things get smaller and smaller. . .anyone care to explain to me how they actually build it?
I mean to get something that size. . .its probably just some chemical reaction or laser cutting of something. . .I don't know I just cant picture something assembling a transistor that small. . .

kureshii · « **Reply #21 on:** May 07, 2011, 05:07:51 AM »

When you are your only customer, you have quite a lot of flexibility in deciding your manufacturing processes

TSMC and GF have announced the FinFET process only for the 14nm node, since it seems “FinFETs require changes in circuit design (especially analog), tools and IP throughout the whole ecosystem”, and their customers need time to make those changes in their own workflow. So for a whole year and more Intel will be the only x86 fab using FinFET. That’s pretty solid marketing material right there.

Quote from: GoGeTa006 on May 07, 2011, 04:25:34 AM

Anyways. . .I keep wondering as these things get smaller and smaller. . .anyone care to explain to me how they actually build it?

http://www.youtube.com/watch?v=_wyEjdoqNkw

GoGeTa006 · « **Reply #22 on:** May 07, 2011, 04:22:13 PM »

Quote from: kureshii on May 07, 2011, 05:07:51 AM

When you are your only customer, you have quite a lot of flexibility in deciding your manufacturing processes

TSMC and GF have announced the FinFET process only for the 14nm node, since it seems “FinFETs require changes in circuit design (especially analog), tools and IP throughout the whole ecosystem”, and their customers need time to make those changes in their own workflow. So for a whole year and more Intel will be the only x86 fab using FinFET. That’s pretty solid marketing material right there.

Quote from: GoGeTa006 on May 07, 2011, 04:25:34 AM
Anyways. . .I keep wondering as these things get smaller and smaller. . .anyone care to explain to me how they actually build it?
http://www.youtube.com/watch?v=_wyEjdoqNkw

thank you I was looking for "how transistors are made" and stuff. . .

TMRNetShark · « **Reply #23 on:** May 07, 2011, 10:53:54 PM »

Quote from: newy on May 06, 2011, 03:33:44 AM

Quote from: TMRNetShark on May 06, 2011, 12:19:41 AM
Quote from: mgz on May 05, 2011, 10:58:10 PM
Quote from: TMRNetShark on May 05, 2011, 08:19:46 PM
Good... goood... this is all working perfectly into my plan!

Oh yeah, my plan is to some day become a full on cyborg... to become one, I need Moore's Law to grow exponentially faster! I expect by 2045 that I can become fully cyberized and all thanks to corporations like Intel that will make it possible.
cuz your gay and want to have hardcore sex with men more often then your weak human body allows you to so your banking on intel

Yeah? Well you know what? Oh wait I just lost interest in what you had to say...

ON TOPIC: This will get Intel ahead of the game, but I'm wondering when this technology will hit GPUs and start lowering the amount of heat that are emitted from computers or any other technology that uses transistors. This will definitely increase usage life of CPUs... my question is, why didn't they think of this before? It seems like a simple enough concept, but I guess the technology to make such small circuits hadn't caught up yet.

This shows that you have no idea how chip/semi conductor products are made... I advise you to shut up...

What I still remember from my apprenticeship (simplified):

- Wafer (silicon e.g.)
- dope it to create a n- or p-layer (oven process)
- mask that layer
- check for errors in the mask (generally almost every structure to be checked, how many on a 21" wafer? No idea, too many to count for a human)
- etch that masked layer (that's the important step in production)
- next layer
- rinse and repeat the steps above

And now add that new 3d structure to that process and see how complicated it's going to be. Keypoints are the mask and the etching.

EDIT: If metals are needed somewhere in the middle, add another step of phyiscal deposition (sputtering), or an insulating layer/structure by oxidizing in an oven.

EDIT: This does not include the SMD (or old THD) production.

How did you get that from what I said? But no, I won't shut up because all I said was what the guy said in the video... So telling me to shut up is funny because it seems like you don't know what you are talking about. Less power needed would mean less heat that is generated. Less heat that is generated means a longer lasting product unless it was really built badly. I don't even see your argument claiming why I'm stupid, but oh well... It's the internet, people aren't always logical.

newy · « **Reply #24 on:** May 08, 2011, 03:52:21 AM »

You say it's such a simple concept. Do you work in the semi conductor industry? No? Then better shut up?

I guess even the simplified silicon chip manufacturing was still too complicated. Less power is only possible if one knows how to optimise the production and that is only possible if one knows how production works. And what I listed are just rough steps/milestones in the production... and this starts with the growing of the silicon crystal and ends with the separation of the several transistors from the wafer to be put in a case. Do you know how long that takes? No? Again, read instead of post. Only the steps I mentioned already take several days to weeks. Now combine this and the new 3d structure, how much are the several steps prolonged or how many steps need to be added? Intel knows and has managed to have them ready for market only now.

As I worked (or have been an apprentice) in that industry I'm dying to know how the several steps in that production look like but of course I will never get to know that as I will never be employed at Intel (nor do I have the intention to work in that industry).

TMRNetShark · « **Reply #25 on:** May 08, 2011, 04:38:52 AM »

Quote from: newy on May 08, 2011, 03:52:21 AM

You say it's such a simple concept. Do you work in the semi conductor industry? No? Then better shut up? I guess even the simplified silicon chip manufacturing was still too complicated. Less power is only possible if one knows how to optimise the production and that is only possible if one knows how production works. And what I listed are just rough steps/milestones in the production... and this starts with the growing of the silicon crystal and ends with the separation of the several transistors from the wafer to be put in a case. Do you know how long that takes? No? Again, read instead of post. Only the steps I mentioned already take several days to weeks. Now combine this and the new 3d structure, how much are the several steps prolonged or how many steps need to be added? Intel knows and has managed to have them ready for market only now.

As I worked (or have been an apprentice) in that industry I'm dying to know how the several steps in that production look like but of course I will never get to know that as I will never be employed at Intel (nor do I have the intention to work in that industry).

Why are you talking about production of chips? Not once in this entire thread did I start talking about production of 3D chips. I'm talking about the chip being used in a consumer fashion. Less power that that CPU needs will mean less voltage (you know, that thing called thermo-dynamics?), which in turn will have less wear and tear on those transistors. Learn to read people's posts please.

Freedom Kira · « **Reply #26 on:** May 08, 2011, 05:46:41 AM »

Quote from: TMRNetShark on May 08, 2011, 04:38:52 AM

Why are you talking about production of chips? Not once in this entire thread did I start talking about production of 3D chips.

Huh, explain this here:

Quote from: TMRNetShark on May 06, 2011, 12:19:41 AM

ON TOPIC: This will get Intel ahead of the game, but I'm wondering when this technology will hit GPUs and start lowering the amount of heat that are emitted from computers or any other technology that uses transistors. This will definitely increase usage life of CPUs... my question is, why didn't they think of this before? It seems like a simple enough concept, but I guess the technology to make such small circuits hadn't caught up yet.

--

Quote from: TMRNetShark on May 08, 2011, 04:38:52 AM

I'm talking about the chip being used in a consumer fashion. Less power that that CPU needs will mean less voltage (you know, that thing called thermo-dynamics?), which in turn will have less wear and tear on those transistors. Learn to read people's posts please.

In that case, you are off-topic, yet claiming in the previously quoted post that you were "ON TOPIC." Hmm. It'd be nice if you stopped contradicting yourself.

kureshii · « **Reply #27 on:** May 08, 2011, 11:19:34 AM »

Quote from: TMRNetShark on May 06, 2011, 12:19:41 AM

ON TOPIC: This will get Intel ahead of the game, but I'm wondering when this technology will hit GPUs and start lowering the amount of heat that are emitted from computers or any other technology that uses transistors. This will definitely increase usage life of CPUs... my question is, why didn't they think of this before? It seems like a simple enough concept, but I guess the technology to make such small circuits hadn't caught up yet.

Quote from: kureshii on May 07, 2011, 05:07:51 AM

TSMC and GF have announced the FinFET process only for the 14nm node, since it seems “FinFETs require changes in circuit design (especially analog), tools and IP throughout the whole ecosystem”, and their customers need time to make those changes in their own workflow.

Your question has already been answered anyway. 14nm is in 2014 on GF’s roadmap, and in “the foreseeable future” for TSMC’s. Since those two fabs are where most gaming GPUs are manufactured (neither Nvidia nor AMD have their own manufacturing facilities), that’s roughly when you can expect to hear news about their production. Of course, things aren’t that simple since the switch to tri-gate transistors will require changes in chip design (as mentioned above).

[edit] Silly me, I overlooked one really obvious thing: we will be seeing 22nm tri-gate transistors in Intel (integrated) GPUs on Ivy Bridge, so expect that as early as 2012

And what do you mean by “why haven’t they thought of this before?”

Quote from: Intel Newsblog

Intel will introduce a revolutionary 3-D transistor design called Tri-Gate, first disclosed by Intel in 2002, into high-volume manufacturing at the 22-nanometer (nm) node in an Intel chip codenamed "Ivy Bridge."

That was when they disclosed it, by the way; the research that went into it probably took place years earlier, and likewise the idea that led to said research. Someone already thought of this before you even knew what a processor core is! Newy’s right; his mention of chip production is relevant, even if you don’t see its relevance. Moving a chip to a smaller process node is not something one can do at the snap of one’s fingers.

Quote from: TMRNetShark on May 08, 2011, 04:38:52 AM

Not once in this entire thread did I start talking about production of 3D chips.

Nobody even mentioned 3D chips — these are “3D” transistors we’re talking about, being used in a planar chip design. 3D chips are yet to be announced on roadmaps . . .

kitamesume · « **Reply #28 on:** May 08, 2011, 12:43:39 PM »

if ever they successfully use FinFETs on GPUs we`d be seeing mainstream rated at 20watts while flagships would be rated 100watts unlike today's which are mainly 60watts-200watts.

well anyway, thats 3-5years of time to wait so i got years to save up money, i just wish they'd hurry up and quit clinging to unnecessary greediness.

kureshii · « **Reply #29 on:** May 08, 2011, 01:23:50 PM »

Quote from: kitamesume on May 08, 2011, 12:43:39 PM

if ever they successfully use FinFETs on GPUs we`d be seeing mainstream rated at 20watts while flagships would be rated 100watts unlike today's which are mainly 60watts-200watts.

I wouldn’t count on that. The trend has been for power consumption of high-end GPUs to keep heading upwards (with limited overclocking), while mainstream GPUs haven’t exactly seen power consumption numbers dropping either.

Something else is going to occupy that 20W band: integrated graphics, and low-end budget cards. IGPs already typically consume ~16W on load ( a very rough figure); Sandy Bridge graphics already consumes much more than that—something like >30W, from quick calculations based on the below graphs:

* Load figures from running Bulletstorm 1440x900. Graphs from http://techreport.com/articles.x/20728/6.

And flagship graphics cards at 100W? That sure is a nice dream. Since Nvidia GT200 (my study of GPU trends doesn't extend much before that), flagships have never dropped below the 200W mark; most attempt to creep as close to 300W, the PCIe 2.0 max power spec, as they can. PCIe 3.0 doesn't lower that power spec, so I wouldn’t expect such a trend to change.

Smaller transistors use less power, but you can cram more of them into the same die area, so power consumption of the chip doesn't always decrease.

kitamesume · « **Reply #30 on:** May 08, 2011, 01:49:04 PM »

meh, i`m saying today's mainsteam equivalent would be like 20watts and flagship equivalent would be 100watts. well it was a nice dream, would actually want to own a gtx 580 equal that uses 100watts =P

if you consider it like that, a 9500GT consumed 50watts while having 134.4GFLOPs of processing power, on those olden days they were considered mainstream, a gt5xx equivalent of that would be the newly released GT520 with 29watts while having 155.5GFLOPs of processing power. if they keep this up, we`d be seeing those as today's so called low end consuming no more than 15watts after 2years or so.

the GTX 460 SE had like 150watts rating, the GTX5xx equivalent would be the GTX 550 Ti, while being slightly slower, it still got 34watts shaved off, just think of the next GTX650 having another 30watts or so shaved off, or atleast a GT640 performing at GTX550 level and is under 100watts =P

kureshii · « **Reply #31 on:** May 08, 2011, 02:28:15 PM »

The anticipation is always sweeter than the object of desire

Were you this excited when the GTX 550 Ti, on TSMC’s 40nm, came out and displaced the GTX200 series, on TSMC’s 65nm? Wait, did you even remember that the GTX260 once existed when you heard the 560 Ti release announcement?

Even in 3 years, a graphics card quickly becomes history. You wouldn't even remember the 550 Ti by the time FinFETs-on-GPUs come out; you’d be going all “oooh 3D chips on 10nm! Can't wait to see mainstream hit 20W and flagship cards drop to 100W.”

TMRNetShark · « **Reply #32 on:** May 08, 2011, 03:41:14 PM »

(click to show/hide)

*facepalm*

Way to make youself look so so stupid.

Quote

ON TOPIC: This will get Intel ahead of the game, but I'm wondering when this technology will hit GPUs and start lowering the amount of heat that are emitted from computers or any other technology that uses transistors.

GPUs are used in a consumer settings for gaming or graphical arts... no production talk there...

Quote

This will definitely increase usage life of CPUs... my question is, why didn't they think of this before?

Once again, no production talk... only talking about the lifespan. The article even stated that lower voltages will be use which is ON topic.

Quote

It seems like a simple enough concept, but I guess the technology to make such small circuits hadn't caught up yet.

The means of making these small 3D transistors just had not caught up to the actual technology of 3D transistors... which is in accordance with the article that says Intel will be just starting mass production even though the concept was 10-20 years old. Yet again, I only talked about the mass production of it, no the developmental stages.

Now please, before you embarrass yourself even more, stay on topic? I find it paradoxical that someone tries to insult and tell me that I'm off topic when clearly I was and they themselves did not mention a single thing about the topic.

NaRu · « **Reply #33 on:** May 08, 2011, 04:43:32 PM »

When intel made a post about 3D transistors it was ready for being used in the new set of CPUs. As for development stages of future chips arent even being said in Intel post. Intel is well known not to talk about anything until they are ready to sell it in the consumer market.

kitamesume · « **Reply #34 on:** May 08, 2011, 06:50:45 PM »

well yea xD, or what if "cant wait for electricity bill to drop by 90%" now thats a woopers or maybe they should start standardizing 90% efficiency PSUs. by then, i wouldnt care even if my GPU hordes more electricity than my air conditioner.

nstgc · « **Reply #35 on:** May 09, 2011, 01:12:27 AM »

I wish Nazo would post in this thread.

Freedom Kira · « **Reply #36 on:** May 09, 2011, 02:55:49 AM »

Quote from: TMRNetShark on May 08, 2011, 03:41:14 PM

Now please, before you embarrass yourself even more, stay on topic? I find it paradoxical that someone tries to insult and tell me that I'm off topic when clearly I was and they themselves did not mention a single thing about the topic.

I think you oughta get your reading comprehension (or eyes) checked if you thought that was, in any way, an attempt at an insult.

But yes, let us stay on topic.

kureshii · « **Reply #37 on:** May 09, 2011, 03:30:34 AM »

Nazo isn’t involved in Bulldozer and won’t have anything to add that you’d be interested to read, nstgc. I’ve asked ;x

kitamesume · « **Reply #38 on:** May 09, 2011, 08:19:14 AM »

i feel like i`m gonna get disappointed about bulldozers... meh...

nstgc · « **Reply #39 on:** May 09, 2011, 03:37:39 PM »

Quote from: kureshii on May 09, 2011, 03:30:34 AM

Nazo isn’t involved in Bulldozer and won’t have anything to add that you’d be interested to read, nstgc. I’ve asked ;x

I wasn't thinking about that (Nazo's working on fusion right?), but among those on these boards who understand this stuff, he's the one that comes to mind. Besides, haven't heard from Nazo in a while.