AMD RX Vega has been delayed time and time again and we are still waiting for the release of the GPUs because they will use HBM2 memory instead of GDDR5, that Nvidia is using. HBM2 technology is not quite ready for mass production that is why we are being forced to wait this long. AMD has said that they will be releasing the Vega GPUs in a month or true.
It has been confirmed that we will be able to see AMD RX Vega GPUs at Computex 2017 and there have been reports that we will be able to see custom AMD Vega GPUs at the event as well. Now reports are coming in regarding the cost of HBM2 memory and reports claim that a 4 GB HBM2 stack costs $80. Why is that important you ask?
AMD Vega GPUs will use 8 GB HBM2 memory and this means that there will be two stacks used so this means that the cost of producing this will be $160. Comparing this to GDDR5, it is very expensive indeed. AMD is also using HBM2 memory for their corporate customers and the GPUs are custom made according to needed requirements of the customer.
It is important to note here that the price is a rough guideline and the cost can go up and down a fair but depending upon what the customer needs. No matter how you look at it, it is clear that GDDR5 is still less expensive to mass produce and the technology needed is readily available. Even GDDR5X which is used in the 1080 Ti is less expensive to make.
As of right now, there is nothing that we know for sure about the pricing and availability of AMD Vega GPUs, neither do we know about the performance of these upcoming cards.
Let us know what you think about this cost that AMD will have to deal with when releasing the upcoming AMD RX Vega GPUs.