Normally, when a GPU developer creates a laptop SKU, they re-use the desktop branding, add an M at the end, but release a very different, significantly slower part. This changed with the GTX 980, as NVIDIA cherry-picked the heck out of their production to find chips that could operate full-speed at a lower-than-usual TDP. With less power (and cooling) to consider, they were sent to laptop manufacturers and integrated into high-end designs.
They still had the lower-performance 980M, though, which was confusing for potential customers. You needed to know to avoid the M, and trust the product page to correctly add the M as applicable. This is where PCGamer's scoop comes into play. Apparently, NVIDIA will stop “producing separate M versions of its desktop GPUs”. Also, they are expected to release their 10-series desktop GPUs to their laptop partners by late-summer.
Whatttttt?
Last time, NVIDIA took almost a year to bin enough GPUs for laptops. While we don't know how long they've been stockpiling GP104 GPUs, this, if the rumors are true, would just be about three months of lead-time for the desktop SKUs. Granted, Pascal is significantly more efficient than Maxwell. Maxwell tried to squeeze extra performance out of an existing fabrication node, while Pascal is a relatively smaller chip, benefiting from the industry's double-shrink in process technology. It's possible that they didn't need to drop the TDP threshold that far below what they accept for desktop.
For us desktop users, this also suggests that NVIDIA is not having too many issues with yield in general. I mean, if they were expecting GPU shortages to persist for months, you wouldn't expect that they would cut their supply further with a new product segment, particularly one that should require both decent volume and well-binned chips. This, again, might mean that we'll see desktop GPUs restock soon. Either that, or NVIDIA significantly miscalculated demand for new GPUs, and they needed to fulfill partner obligations that they made before reality struck.
Call it wishful thinking, but I don't think it's the latter.
talking about stock, i wonder
talking about stock, i wonder how Nvidia will respond to AMD, and how big of a problem the 480 could become.
AMD is making 2chips, a 100mm² and 200mm², have 1bil$ worth of wafer in glofo, and have a partnership with samsung for 14nm, they took their time to get the stock to push a 199$ gpu, Nvidia started with a 300mm² chip, while they need to compete with another chip that could make their 950-970-980 obselete, so add another 200mm² chip(1060), so the 1060 need to be priced well and stay at it, my guess one of the chips need to have priority probably the 1060-1050, and the other could see a shortage, dont even want to add the gp100 with 600mm².
We’ll see. I told a friend,
We'll see. I told a friend, who was just about to buy a new, mid-range video card, to wait and see for AMD's RX 480 to arrive. It could be interesting, especially if there's no clear, universal winner — just a bunch of "is the winner, but…"s.
there is always a winner lol,
there is always a winner lol, no one feels good with a participation medal 😀
I like the idea of a 1080p
I like the idea of a 1080p getting released at the price of a 1080, and the other two cards just dropping in price. Then that still leaves the option for a 1080ti later.
Is the mobile part going to
Is the mobile part going to be at a lower clock? I could see Nvidia having a large amount of stock that doesn’t clock high enough to be a 1070 or 1080. Just because review samples seem to ha able to clock quite high doesn’t mean that all of Nvidia’s production can reach those speeds. I am curious as to whether 16 nm (or 14 nm) will have more variation in achievable clock speeds than 28 nm.
I still don’t see any 1080s
I still don’t see any 1080s available for founders edition MSRP. How long does that have to continue until it is considered a paper launch? I have to wonder if this “laptop chips coming soon” is just marketing to try to get people to wait for Nvidia parts, even if competing laptops are available sooner. With how much AMD has talked about lower power consumption, I have assumed that they are targeted by the mobile market more than the desktop market, so hopefully AMD will have mobile parts available quickly after release also.
I suspect Nvidia rushed the
I suspect Nvidia rushed the launch of the 1080 and 1070 to make sure they got review samples out before AMD could. The whole founders edition BS seems to indicate very limited supply also. They may have massive supply available, just not yet. That effectively makes the 1080/1070 launch a paper launch. That isn’t that big of an issue if they actually have mass availability relatively soon and, of course, the mass availability parts actually match the review samples.
Having only 2 different parts for a single die, if the mobile parts are the same as the desktop parts, isn’t that good for making efficient use of production. With having slightly more cut down parts for mobile, this allows them to get around 4 different parts per die. So you would have the 1070M, 1070, 1080M, and 1080. All of these would be different salvaged parts with varying number of active units, which makes good use of parts with varying number of defects that would need to be binned as 1070s or scrapped otherwise. Perhaps Nvidia has a lot of parts that are just completely unusable or in the 1080 range, with little in between. They could also differentiate more based on clock speed but that makes these effectively different parts also. It may be a case where the form factor will limit the clock, so you will have to be careful to buy a laptop that supports the full TDP if you want the full clocks. That will be confusing for the end user though.