Tuesday, September 20th 2016
AMD Vega 10, Vega 20, and Vega 11 GPUs Detailed
AMD CTO, speaking at an investors event organized by Deutsche Bank, recently announced that the company's next-generation "Vega" GPUs, its first high-end parts in close to two years, will be launched in the first half of 2017. AMD is said to have made significant performance/Watt refinements with Vega, over its current "Polaris" architecture. VideoCardz posted probable specs of three parts based on the architecture.
AMD will begin the "Vega" architecture lineup with the Vega 10, an upper-performance segment part designed to disrupt NVIDIA's high-end lineup, with a performance positioning somewhere between the GP104 and GP102. This chip is expected to be endowed with 4,096 stream processors, with up to 24 TFLOP/s 16-bit (half-precision) floating point performance. It will feature 8-16 GB of HBM2 memory with up to 512 GB/s memory bandwidth. AMD is looking at typical board power (TBP) ratings around 225W.Next up, is "Vega 20." This is one part we've never heard of today, and it's likely scheduled for much later. "Vega 20" is a die-shrink of Vega 10 to the 7 nm GF9 process being developed by GlobalFoundries. It will feature 4,096 stream processors, too, but likely at higher clocks, up to 32 GB of HBM2 memory running full-cylinders at 1 TB/s, PCI-Express gen 4.0 bus support, and a typical board power of 150W.
The "Vega 11" part is a mid-range chip designed to replace "Polaris 10" from the product-stack, and offer slightly higher performance at vastly better performance/Watt. AMD is expecting to roll out the "Navi" architecture some time in 2019, and so AMD will hold out for the next two years with "Vega." There's even talk of a dual-GPU "Vega" product featuring a pair of Vega 10 ASICs.
Source:
VideoCardz
AMD will begin the "Vega" architecture lineup with the Vega 10, an upper-performance segment part designed to disrupt NVIDIA's high-end lineup, with a performance positioning somewhere between the GP104 and GP102. This chip is expected to be endowed with 4,096 stream processors, with up to 24 TFLOP/s 16-bit (half-precision) floating point performance. It will feature 8-16 GB of HBM2 memory with up to 512 GB/s memory bandwidth. AMD is looking at typical board power (TBP) ratings around 225W.Next up, is "Vega 20." This is one part we've never heard of today, and it's likely scheduled for much later. "Vega 20" is a die-shrink of Vega 10 to the 7 nm GF9 process being developed by GlobalFoundries. It will feature 4,096 stream processors, too, but likely at higher clocks, up to 32 GB of HBM2 memory running full-cylinders at 1 TB/s, PCI-Express gen 4.0 bus support, and a typical board power of 150W.
The "Vega 11" part is a mid-range chip designed to replace "Polaris 10" from the product-stack, and offer slightly higher performance at vastly better performance/Watt. AMD is expecting to roll out the "Navi" architecture some time in 2019, and so AMD will hold out for the next two years with "Vega." There's even talk of a dual-GPU "Vega" product featuring a pair of Vega 10 ASICs.
194 Comments on AMD Vega 10, Vega 20, and Vega 11 GPUs Detailed
videocardz.com/63715/amd-vega-and-navi-roadmap
Seriously, you won't see that kind of adoption rate in 1 year.
The RX 480/470 is the card of choice in the Ethereum Mining community, where lower energy costs are crucial to profitability.
One of the main reasons Polaris is sought after by miners is the power efficiency.
etherscan.io/ether-mining-calculator
etherscan.io/ether-mining-calculator
For example I built my cousin a system 4 years ago with an i3 and 560 Ti in it, and that thing is still chugging along just fine in every game that comes. Soon he should upgrade, and throwing an RX 470 in there will be fine, but throwing a Fury or lol a 1080 would just be a complete waste. But if he had an i7 he could still take that 1080. And the 480, 470, and 460 are capturing marketshare right now. Polaris is allowing them to capture the biggest chunk of the market while they wait for API's and 14nm to mature. As AMD sees it there is no point in releasing Enthusiast cards if they won't be at their peak potential, and if developers won't fully utilize them.
From the Forum Guidelines
"If you reply to multiple posts use the "multi quote" button, that way the forum is easier to read."
www.techpowerup.com/forums/threads/forum-guidelines.197329/
Polaris is insanely bottlenecked by memory - I estimated that RX 480 should have nearly 320GB/s of bandwidth for peak performance... and it would be about 20% faster as a result. Vega 10 is 77% larger than Polaris 10, so needs that much extra bandwidth to see the GCN improvements... or about 566GB/s. With 512 GB/s, we should see about 15% better relative performance than we see with Polaris - partly eaten up by GCN scaling... but we're still looking at a card that is more than double the RX 480 with only 77% more resources... but double the bandwidth.
That means Vega 10 will range from ~40% to nearly 70% faster than the Fury X, depending on how much other hamstringing of performance AMD does (ROPs, mainly). The strongest probability cloud is nearer to 50% than to anything else. Vega 20 is a mid-range 2018 card and a test chip for 7nm. Looks like AMD plans on some pretty impressive improvements with Navi (or will tighten the gap between mid-range and the top tier). The majority of the market can now run DX12. Game developers address as much of the market as they can - with most being able to now enjoy DX12 or Vulkan, all new game engines will make use. We are already seeing nearly every new AAA title have support for one or the other. In a year's time, many top CPU-bound DX11 games will have DX12 patches and nearly every new game will have support at or shortly after launch.
Microsoft's free upgrade offer pushed a lot of people onto Windows 10 (that and their underhanded upgrade tactics...). I didn't anticipate moving to Windows 10 at all, but my ability to make it like Windows 7 (stripping most of the new Windows 10 garbage) while still benefiting from the core updates made it a worthwhile endeavor.
You did two and got called out, I did three just a few pages back and no one said anything... but I like to post really long comments, which I think changes the dynamic.
The problem that I'm seeing is that Nvidia is getting away with charging alot, imo, for the 1080 and Titan XP and most likely the 1080 Ti as well. They can do this because there is no competition from AMD for these GPUs. I see that Vega 10 is coming first half of next year (some are saying 1st quarter next year) but until then there is no competition for Nvidia. Volta will be coming near that time (some are saying Q2 2017 and if it beats Vega 10 then Volta has no competition until 2nd half 2018 if Vega 20 isn't competition for Volta then it will be 2019 for Navi is what I'm seeing.
Everybody loses in a lopsided market due to lack of competition.
There is an option to either Multi-Quote or Reply, and I chose to Reply only to what I specifically highlighted, see?
And you've now taken up a page with this nonsense...
it may also be a good opportunity at this point to suggest that a couple of pages of off topic chitchat is probably enough, this is a news thread about Vega, lets keep it that way please.
Reminds me of back in the day with the 2900XT vs the 8800GTS/ 8800GTX/Ultra.