And now you list one of the disadvantages of HBM lol.
NVidia have not used HBM on the 1080 either and that is not a cheap card. Could this be due to HBMs other limitations ?
-
Competitor rules
Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.
Radeon RX 480 "Polaris" Launched at $199
- Thread starter Kaapstad
- Start date
And now you list one of the disadvantages of HBM lol.
NVidia have not used HBM on the 1080 either and that is not a cheap card. Could this be due to HBMs other limitations ?
Your argument about heat. It just blew my mind and I couldn't treat it as a serious comment given that it's grounded in bull poop.
The 1080 and 1070 are released now and available now, get over it and move on and let the RX 480 thread carry on with the hype.
Just to add to the HBM discussion i believe 4gb of HBM1 was pointless for the fury cards except for saleability / first to market, which worked reasonably well as the actual fury cards were not bad but just overpriced due to the 4gb of HBM.
Pre sold 5000 cards, shipped 200
Have you got a link for 200 shipped?
That's most likely because HBM2 isn't quite full production ready yet, and it would also require a different memory controller, meaning you couldn't use a simple cut down version with GDDR5(X).
Not that they would have definitely used HBM2. I'm sure there's cost benefits to GDDR5X, while still giving entirely adequate performance.
Workstation cards have never scaled to desktop cards but I think that's beside the point really. There's nothing especially astounding or unusual about this generations die sizes. nVidia have opened with an equivalent class of card as AMD opened their last generation node with (7970), while AMD are opening this generation with a more pitcairn (7870) like card, which they explained was because they were going for volume. Both approaches make sense and by avoiding each other they both get some much needed income.
No it's because the chips memory controller & arch can't SATURATE HBM. Please keep up.
Soldato
- Joined
- 28 May 2007
- Posts
- 10,207
Google paper launch. It's the exact definition of a paper launch. Simply it's when the cards have been reviewed and you can't buy the product. The cards were reviewed and all was known about them yet you couldn't buy for 2 weeks. Paper launch.
It is just a theory but quite a reasonable one.
If you have the GPU and memory chips in the same place with the memory actually working like lagging around the GPU then yes there will be a higher heat build up. Warm running memory chips will do nothing to make the GPU run cooler now will it lol.
He is right - the Pascal cores are small and high frequency which produces a lot of heat in a concentrated small area which produces a challenging in respect to cooling - cramming HBM packages into that same area would increase the amount of heat you are trying to remove - in that situation you want a larger area to remove heat over which having the memory chips further away allows you to do.
Last edited:
The image of Lisa Su laying down a fat cigar, turning away from showering strippers with money and saying to her staff: "This better be &&&&*** good" is certainly a striking image, I will give your post that.
So you are telling me AMD made a mistake fitting the Fiji chips with HBM, I think you may be onto something here.
Erm how did these people have them?
Date 31/05/2016, Make Zotac Founders Edition, ToastedChip, Link
Date 29/05/2016, Make Gigabyte Founders Edition, kitkat9933, Link
Date 28/05/2016, Make EVGA Founders Edition, X-Mikuru_Beam-X, Link
Date 28/05/2016, Make Gigabyte Founders Edition, dvs8, Link
Date 28/05/2016, Make EVGA Founders Edition, passey89, Link
Date 28/05/2016, Make MSI Founders Edition, Biomorphs, Link
Date 28/05/2016, Make EVGA Founders Edition, RichardH754, Link
I dont know why people get so nitpicky arguing over whether something is technically a 'paper' launch or not. Apparently, that's become something of a negative term or something? Cuz it shouldn't be. I really dont know what is wrong with having reviews of something available before you can buy it. Gives users plenty of time to become informed before making a decision.
But people can buy the product the context of a paper launch is where the supply coming into the retailer is non-existent - there are atleast a dozen you can buy right now from OcUK and somewhere else has around 50 pieces (or did before the weekend) of one model and around 6-7 of another. Pre-orders are also being fulfilled at varying rates depending on the model but they are being fulfilled at a moderate rate.
Soldato
- Joined
- 28 May 2007
- Posts
- 10,207
Erm the cards were reviewed on the 17th around 2 weeks before. Your point lol.
Yes, but he could stay quiet. He didn't hype the Fury launch. The 1080 is selling itself because it's the fastest single gpu available - it's an easy sale, end of.
Soldato
- Joined
- 28 May 2007
- Posts
- 10,207
No its not. In real life it's like somebody giving you all the hard facts on paper and showing you a product working yet you can't buy it. Paper Launch.
The card launched 2 weeks before it was on sale. That's a paper launch. I am not denying there was stock when it went on sale but all the paper facts were known weeks before when it launched on paper.
Look Kaap, keep going around in circles, the only person making himself look daft is you. Plenty of people understand the issues with memory capacity for first gen HBM and where the issues are with fiji performance, yet you keep up this little act since you have to be right about it when you are not.
And the same again with GP104, it is all about cost that go beyond the part itself such as sorting out production lines. Which is why their HBM2 efforts are going towards GP100 since it is their first HBM based part alike fiji was AMD's HBM/Interposer pipe cleaner. mainly since Nvidia can charge an arm and a leg for it and recover those production setup costs etc since they have had less time to get this done in comparison to AMD who have had years of R&D time to get it right.
Paper launch would mean that nvidia released the cards on the 17th. and none were available to buy, they didn't they were released on the 27th = no paper launch.