jmdixon85:

AMD could have easily released Vega with GDDR5 if they wanted. GPU architecture doesn't dictate what memory it has to use.

If they could have easily done it, they would have done it in some form, instead of releasing Vega so terribly late. No doubt the memory controlled in the GPU has a thing or two to say about it. Of course nothing prevents them from partially remaking Polaris to support HBM2, but would they do it when they already have a design using HBM2?

The hell, men, am i Nostradamus or something? https://forums.guru3d.com/threads/why-doesnt-amd-do-this.415241/

I guess something like this would be well received by Apple.

jmdixon85:

That is like saying all GPU's must use DDR5 etc. We have seen for a long time GPU's can use different types of memory, some would come with DDR3 back in the day with the same lower cost GPU featuring DDR2. AMD could have easily released Vega with GDDR5 if they wanted. GPU architecture doesn't dictate what memory it has to use. The part number in the OpenCL information for this new CPU/GPU combination is gfx804, a polaris based chip. I really can't see AMD sharing Vega with Intel just yet. Adored makes this clear in his video [youtube=mNY5e5CFlbc]

This is Vega 11 the mainstream Vega that is rumored with 2048 shadder cores and single stack of HBM2 they are not sharing anything they are selling gpus to Intel that are still made in globalfoundaries fabs and the memory is from Samsung or hynix...

BigMaMaInHouse:

Lol I see my guess was on spot 🙂, because the die size looked ~50% of Vega 56, nice. now look how much it sa\ves comparing for 1060: http://cdn.overclock.net/c/ce/cec6b09f_MGT62VR33.jpeg its also the thickness that is saved for not needing to pace the GPU PCB on top of the MB PCB.

It's really only saved if they don't have to use the same amount of fans/heatsinks, of which it being in the same package means that: The heat all builds up in one area, but, the heat still builds up the same amount of heat, requiring the same cooling requirements And Both the CPU and GPU will heat eachother, not entirely certain that part is so great.

This is a very big deal. It's a redesign of how integrated graphics are placed on motherboards. Not only saving space, but I'm guessing power, heat, airflow. If they can get the price down I can see this being the default for mainstream computers. Especially with the processing that the video chip can do with things other than games. Which is finally catching on with crypto currency. I can see some businesses buying in to keep their administration desktops doing something with the processing while a user is doing regular office tasks or at night when a user isn't around. The computer can keep working some sort of distributed computing. And laptops/tablets should be getting thinner. This is all if the process catches on, is profitable, there is corporate buy-in. And that they continue to shrink the footprint on the motherboard. This is probably an investment gamble for buying AMD stock that would pay off in 5 years. Just like how NVidia expanded it's business with logic chips for applications other than gaming. Their stock increased because of that market expansion. Self driving car processing and other things I don't fully understand that other businesses do. It's a long road, I'm thinking 5 years of more development and integration, along with AMD/Intel being able to market and sell it successfully when it's more mature.

Well, that's the issue... more hardware on a smaller space with thinner (and lighter) laptops... I'm almost more curious about any cooling solutions than the hardware itself I have to admit.