AMD’s CPU business has thrived in desktops, notebooks and servers due to the success of the 7nm Zen2. In the GPU, the 7nm Navi family was introduced last year, but the first generation of RDNA architecture is still insufficient, failed to overturn the flagship card market, this year to see the big Navi, AMD has confirmed that it will use the RDNA2 architecture.
Amd CFO Devinder Kumar also responded to AMD’s plans on Radeon graphics when he attended a bank meeting, referring to the big Navi graphics card, saying it would use the RDNA2 architecture, which was the first official confirmation by AMD executives, though not surprisingly.
According to data released by AMD at the Financial Analyst Conference earlier this year, the RDNA2 architecture will improve the IPC, circuit design, and clock frequency by 50% more energy efficiency than the current RDNA architecture.
Specifically, there are three major changes, as follows:
1, redesigned GPU microframe: by increasing logic functions, reduce design complexity and switching power, while improving the operating frequency, thus achieving the Improvement of IPC performance.
2, the new generation of 7nm plus process: RNDA2 GPU will be converted from 7nm process to 7nm plus process, the new process will further enhance the density of transistors, in a smaller package area to achieve higher performance, but also at the same power consumption to provide higher performance.
3, variable rate coloring VRS technology and hardware ray-tracing features added: in fact, these two technologies in the NVIDIA Turing architecture has been implemented, which is also turing GPU energy efficiency than one of the important reasons.
VRS Variable simply put sgares the GPU’s focus on rendering what the user can see, reducing the rendering accuracy of the edge area appropriately, to improve the efficiency of the GPU. According to AMD, variable rate coloring VRS technology can increase the IPC of the RDNA2 architecture by 20%.
As for the final graphics card of the big Navi core, previous leaks show that the core is approximately 505 square millimeters, integrates up to 80 cells, 5120 stream processors, doubles in size from the current RX 5700 XT, and, with a 50% energy efficiency increase, improves performance by 100-150%.
Of course, these are rough calculations, the current big Navi specifications, frequency has not been accurate data, the only thing that can be determined is that AMD’s price must be much lower than the RTX 3080 series graphics card, the price is still advantageous.
In addition, Devinder Kumar points to an important message that the next-generation graphics card, such as big Navi, will go on sale earlier than hosts such as the PS5 and XSX, essentially acknowledging the rumors that were released and launched in September, which is usually available two months after the end of the year, in November-December.