For AMD, the use of V-Cache technology, which consists of vertically connecting an SRAM memory chip to increase the amount of cache memory, has allowed it to create the Ryzen 5800X3D and in a few weeks we will have the Ryzen 7000 X3D. Well, everything indicates that graphics cards with this technology will be available soon. Is the Radeon RX 7000 X3D with vertical cache on the horizon?
One of the general trends in the architecture of new GPUs is to integrate a large last-level cache in order to reduce memory accesses and therefore energy consumption. We first saw it in the AMD RX 6000 in the form of Infinity Cache, then we saw NVIDIA multiply the amount of cache in their RTX 40 compared to the RTX 30 sixteen times and this trend has continued. continued with the AMD RX 7000. Of course, in the latter case cutting from 128 to 96 MB in the case of the RX 7900, but increasing the bandwidth considerably.
Will we soon see RX 7000 X3D cards with V-Cache?
This must be taken into account in all processors, whether general-purpose or specific, as is the case with the central chip of a graphics card. If you have a multilevel cache hierarchy, the one with the largest size is the last level and therefore closest to memory. This is why in Ryzen adding V-Cache increases the amount of L3 and not L2 or L1.
In GPUs based on the RDNA 3 architecture and more specifically under the Navi 31 chips, used in the RX 7900, and Navi 32, for the future RX 7800, AMD decided to create a GPU split into several chips. On one side, the central chip which is the GCD and on the other several small chips called MCD. Well, the last level cache is in the latter, so the concept would be to put a V-Cache chip in each of the MCDs to increase the amount of Infinity cache.
For the moment we do not know the amount, a few months ago a rumor came out that we could see the capacity per graphics card doubled. That is to say, The RX 7900 X3D should have 192 MB of V-Cache, but these are just leaks from a few months ago and AMD may have made last minute changes. The fact is that if they use the same chips as in the Ryzen, we would be talking about 480MB Infinity Cache
How will this give more performance to our games?
The benefit of this is that it increases the chances of data being found before RAM, remember that accessing memory has 10x higher energy cost and higher latency. This allows the GPU to run at higher speeds without increasing power consumption, but that’s not the only reason for this as there are additional benefits of having a large cache.
Current AMD and NVIDIA cards work almost like a tile renderer, but with a difference, instead of using local memory to save blocks from the framebuffer, they use cache. So if there is not enough space, old data is dumped into VRAM and performance is lost. However, this is not the only advantage when facing games.
We must start from the fact that many titles today use post-processing effects, that is, they are applied to the already existing image buffer and the ideal for certain operations is to have the data in a memory close to the processor. The other reason has to do with the data structure for Ray Tracing, the BVH tree. Having it without having it in memory is a major performance boost for ray tracing.
The secret weapon to beat the RTX 40
Artificial intelligence is one of the issues that has been ignored by AMD in recent years and in which they put their batteries. An example is the addition of an NPU in their Ryzen 7000 for laptops and the ability under the RDNA 3 architecture to emulate tensor-like units. What is clear is that AMD is not going to modify the GCD of its RX 7000.
And what do the RX 7000 X3D graphics cards have to do with AI? Easy, some time ago AMD patented the concept of using V-Cache based chiplets and accelerators for AI. It described a central chip with the computing units, then a series of satellite chips with the last level cache which also integrated accelerators for machine learning. Does this setup sound familiar? Additionally, it would include the ability to convert part of the memory to local RAM instead of functioning as a cache, allowing AMD GPUs to convert a full tile renderer.