[ad_1]
We haven’t even gotten to talk about the results of features like AMD’s intelligent access memory, and Team Red’s competitors are already lining up to promise support for an equivalent feature. SAM is AMD’s first method to take advantage of the fact that it owns its entire IP stack: CPU, GPU, and platform. According to AMD, you can use this fact to increase system performance when you combine an RDNA2 card and Ryzen CPU with an X570 motherboard.
Specifically, AMD claims that it can give the CPU full access to the GPU RAM instead of limiting the system to a 256MB opening window for data transfers. We don’t know if the large Infinity Cache built into RDNA2 plays a role in this. No one has crammed a 128MB cache into a GPU before, so the idea that it could play a role in boosting data transfers in and out of VRAM isn’t crazy, especially since cache latency is presumably quite a bit lower than the time it takes to go out to GDDR6.
According to GamersNexus, Nvidia is capable of doing something similar:
It’s hard to fit into a tweet, but basically, they are working to enable the same feature as AMD Smart Access memory (AMD GPU + CPU = performance boost) at both Intel and AMD. No ETA yet. It doesn’t look like it’s ready before the RX 6000 launch, but we’ll keep an eye on development.
– GamersNexus (@GamersNexus) November 12, 2020
Nvidia claims that the feature is part of the PCIe specification, that it has the ability to work internally, and that it is already getting similar performance results. There is no ETA on when the feature might be available in the controller.
AMD has not publicly disclosed whether smart access memory relies on features beyond the ability to adjust the size of this aperture (Intel refers to this as the IGD aperture size), or if it is further enhanced with Zen’s capabilities. 3 or B550 / X570. chipset. It would definitely change the framing of the feature if Nvidia were able to enable it on Intel and AMD systems, but if it is, the likely end result would be AMD to enable the capability for Intel systems as well.
Historically, for capabilities to become common, both GPU manufacturers must agree to use a common standard. Nvidia introduced ray tracing using Microsoft’s DXR, for example, but it was only when AMD added the capability to next-gen consoles and its own GPUs that it really started to take off in the mass market. If Nvidia and Intel can take advantage of a feature that AMD currently only enables for AMD customers, the company is likely to enable it on Intel platforms as well or risk losing clashes with its biggest rival.
AMD is unlikely to want to risk that outcome. It is one thing for the company to allow additional performance by leveraging the commonalities within its own ecosystem, and another to artificially limit performance on competing platforms.
However, whatever happens, the end result appears to be a gain for the consumer. If Nvidia successfully adds this feature, game performance increases for Nvidia customers. If AMD responds by enabling it for Intel as well, performance increases for AMD + Intel customers. If, on the other hand, Nvidia (or hypothetically, Intel) can’t match AMD’s core gains or capabilities, we’ll have evidence that the company is really leveraging its cross-product IP in interesting new ways.
Now read:
[ad_2]
