SEC Filing Reveals NVIDIA Now Using Samsung for Some Manufacturing

Subject: General Tech | March 21, 2015 - 12:09 AM |
Tagged: TSMC, SoC, Semiconductor, Samsung, process node, nvidia, gpu, fab

Want to liven up your weekend? Forget college basketball, we all know that few things are more exciting than SEC filings - and oh boy do we have a great read for you! (OK, this one is actually interesting!)

10K.png

Ah, legal documents...

NVIDIA has disclosed in their latest 10-K filing that none other than Samsung is manufacturing some of the company’s chips. TSMC has been the source of GPUs for both AMD and NVIDIA for some time, but this filing (the full document is available from the SEC website) has a very interesting mention of the suppliers of their silicon under the “Manufacturing” section:

"We utilize industry-leading suppliers, such as Taiwan Semiconductor Manufacturing Company Limited and Samsung Electronics Co. Ltd, to produce our semiconductor wafers."

Back in December NVIDIA commented on its lawsuit against Samsung for alleged IP theft, which only makes this partnership seem more unlikely. However even Apple (which has their own famous legal history with Samsung, of course) has relied on Samsung for some of the production of their A-series SoCs, including the current crop of A8 chips.  Business is business, and Samsung Foundry has been a reliable source of silicon for multiple manufacturers - particularly during times when TSMC has struggled to meet demand at smaller process nodes.

Process_Tech.png

Samsung's Current Semiconductor Offering

It is unclear at this point whether the wafers produced by Samsung Semiconductor are for NVIDIA’s mobile parts exclusively, or if any of the desktop GPUs were produced there rather than at TSMC. The partnership could also be attributed simply to scale, just as Apple has augmented A8 SoC supply with their rival’s fab while primarily relying on TSMC. It will be interesting to see just how pervasive the chips produced by Samsung are within the NVIDIA lineup, and what future products might be manufactured with their newest 14nm FinFET process technology.

Source: SEC

TSMC Begins 16nm FinFET-based 3D Chip Production

Subject: General Tech, Processors | December 14, 2013 - 03:08 AM |
Tagged: TSMC, process node, 16nm

Taiwan Semiconductor (TSMC) is one of the few chip fabrication companies in the world (especially when you omit the memory producers, etc.). Their customers include: AMD, NVIDIA, Qualcomm, Broadcom, and even a few Intel Atom processors have come out of their lines at one point. They will take money from just about anyone who wants a chip.

tsmc.jpg

According to Bit-Tech, a few customers will even have access to 16nm before the end of the year.

The catch, which of course there is one, is that production runs will be very small. We would love to see a gigantic run of new AMD or NVIDIA GPUs based on 16nm but that will not be the case (and not just because Volcanic Islands and Maxwell are both 2Xnm products). The first customers, while otherwise anonymous, will be interested in mobile systems-on-a-chip (SoCs).

On the plus side, when future 1Xnm designs come out, TSMC's production could be reasonably caught up to make a smooth launch.

Intel, the current leader in the fabrication world, targeted a slightly smaller 14nm process and have already begun producing a few odds and ends at that level. Full production has not even really started yet.

Just so you can get an idea of the complexity we are dealing with: 16nm fabrication creates details that are just ~32 atoms in width.

Source: Bit-Tech

TSMC Suffers 28 nm Woes

Subject: Editorial | March 9, 2012 - 11:45 AM |
Tagged: TSMC, tahiti, process node, nvidia, kepler, amd, 28 nm

 Charlie over at Semiaccurate is reporting that TSMC has closed down their entire 28 nm line.  Shut down.  Not running wafers.  This obviously cannot be good.

Apparently TSMC stopped the entire line about three weeks ago and have not restarted it.  This type of thing does not happen very often, and when it does, things are really out of whack.  Going back we have heard mixed reviews of TSMC’s 28 nm process.  NVIDIA was quoted as saying that yields still were not very good, but at least were better than what they experienced with their first 40 nm part (GTX 400 series).  Now, part of NVIDIA’s problem was that the design was as much of an issue as the 40 nm process was.  AMD at the time was churning out HD 5000 series parts at a pretty good rate, and they said their yields were within expectations.

tsmc_logo.jpg

AMD so far is one of the first customers out of the gate with a large volume of 28 nm parts.  The HD 7900 series has been out since the second week of January, the HD 7700 series since mid-February, and the recently released HD 7800 series will reach market in about 2 weeks.  Charlie has done some more digging and has found out that AMD has enough product in terms of finished boards and packaged chips that they will be able to handle the shutdown from TSMC.  Things will get tight at the end, but apparently the wafers in the middle of being processed have not been thrown out or destroyed.  So once production starts again, AMD and the other customers will not have to wait 16 to 20 weeks before getting finished product.

NVIDIA will likely not fare nearly as well.  The bulk of the stoppage occurred during the real “meat and potatoes” manufacturing cycle for the company.  NVIDIA expects to launch the first round of Kepler based products this month, but if production has been stopped for the past three weeks then we can bet that there are a lot of NVIDIA wafers just sitting in the middle of production.  Charlie also claims that the NVIDIA launch will not be a hard one, and NVIDIA expects retail products to be available several weeks after the introduction.

The potential reasons for this could be legion.  Was there some kind of toxic spill that resulted in a massive cleanup that required the entire line to be shut down?  Was there some kind of contamination that was present while installing the line, but was not discovered until well after production started?  Or was something glossed over during installation that ballooned into a bigger problem that just needed to be rectified (a stitch in time saves nine)?

Source: SemiAccurate