It looks like AMD’s high-end Radeon RX Navi 21 GPU specifications have started to leak out with reports from the Far East claiming that the next-generation GPU could be twice as fast as Navi 10. According to the folks over at the Taiwanese based PTT platform, a high-end Navi GPU has been taped out and is headed for launch next year in 2020.
AMD’s High-End Radeon RX Graphics Card With Navi 21 GPU Rumored To Be Twice As Fast As Navi 10 – Features 505mm2 Die Size & GDDR6 Memory
The details were posted by a Chinese Forum member who lists down several key specifications of the upcoming high-end Navi GPU. We know that AMD’s current Radeon RX lineup is based on the 7nm process node and is part of the first generation RDNA family. The 2nd generation RDNA family is expected to make use of the advanced 7nm+ process node which should offer leverages in the overall performance efficiency while allowing even more dense designs to be made possible.
The rumor states that AMD’s high-end Navi GPU, which is being referred to as the Navi 21 GPU, has been taped out. The chip has a die size of 505mm2 which is twice as big as Navi 10 which has a die size of 251mm2. This is even bigger than AMD’s Vega 20 GPU which had a die size of 331mm2, so it could mean that we are looking at a powerhouse of a chip which should definitely be faster than anything AMD has released yet. The AMD Vega 20 GPU featured 13.2 Billion transistors so the Navi 21 GPU could exceed 15-16 Billion transistors which would make the chip far denser than anything else on the market.
In terms of performance, the Navi 21 GPU is said to be at least twice as fast as the Navi 10 GPU. The Radeon RX 5700 XT is the best case for the Navi 10 GPU and it comes close to the GeForce RTX 2070 SUPER, so the Navi 21 GPU could exceed the RTX 2080 SUPER’s performance and even end up coming close to the RTX 2080 Ti. This might explain why we were hearing rumors of NVIDIA’s RTX 2080 Ti SUPER in the works.
With that said, the clock speeds have not been stated yet which would play a bigger role in determining the final performance of the card. Also, it should be said that a GPU of this size would consume a lot of power and a TDP around 275-300W is a given since the Navi 10 GPU has a TDP of 225W.
It is also stated that given the huge die size of the GPU itself, the card would end up not using HBM memory but would rather rely on GDDR6 memory. This would mean that we are likely to get a 384 or 512-bit memory interface which should either give us 12 GB or 16 GB memory. AMD could go one step ahead and offer 24 or even 32 GB of GDDR6 products since this would end up being their flagship 2020 graphics product. Some of the features to expect from 2nd Generation rDNA Navi GPUs would be:
Optimized 7nm+ process node
Enthusiast-grade desktop graphics card options
Hardware-Level Ray Tracing Support
A mix of GDDR6 and HBM2 graphics cards
More power-efficient than First-Gen Navi GPUs
Nothing else is stated, but from the looks of it, this could be a very powerful graphics card, marking AMD’s proper return in the enthusiast high-end desktop GPU space. We also know for a fact that AMD is planning to introduce hardware-accelerated ray tracing as a primary featured of their next-generation RDNA powered GPUs. With that said, the information is based on a rumor so treat it with a grain of salt, but if it is true, then we might get to hear at least some form of confirmation from AMD at CES 2020 aside from the expected Radeon RX 5600 XT announcement.