- Joined
- Sep 28, 2005
- Messages
- 3,160 (0.47/day)
- Location
- Canada
System Name | PCGR |
---|---|
Processor | 12400f |
Motherboard | Asus ROG STRIX B660-I |
Cooling | Stock Intel Cooler |
Memory | 2x16GB DDR5 5600 Corsair |
Video Card(s) | Dell RTX 3080 |
Storage | 1x 512GB Mmoment PCIe 3 NVME 1x 2TB Corsair S70 |
Display(s) | LG 32" 1440p |
Case | Phanteks Evolve itx |
Audio Device(s) | Onboard |
Power Supply | 750W Cooler Master sfx |
Software | Windows 11 |
it looks like directml is hardware agnostic
whatever it does for rdna2 it'll do for rdna1,turing and even older
I updated my post with this:
Inside Xbox Series X: the full specs
This is it. After months of teaser trailers, blog posts and even the occasional leak, we can finally reveal firm, hard …
www.eurogamer.net
It was an impressive showing for a game that hasn't even begun to access the next generation features of the new GPU. Right now, it's difficult to accurately quantify the kind of improvement to visual quality and performance we'll see over time, because while there are obvious parallels to current-gen machines, the mixture of new hardware and new APIs allows for very different workloads to run on the GPU. Machine learning is a feature we've discussed in the past, most notably with Nvidia's Turing architecture and the firm's DLSS AI upscaling. The RDNA 2 architecture used in Series X does not have tensor core equivalents, but Microsoft and AMD have come up with a novel, efficient solution based on the standard shader cores. With over 12 teraflops of FP32 compute, RDNA 2 also allows for double that with FP16 (yes, rapid-packed math is back). However, machine learning workloads often use much lower precision than that, so the RDNA 2 shaders were adapted still further.
"We knew that many inference algorithms need only 8-bit and 4-bit integer positions for weights and the math operations involving those weights comprise the bulk of the performance overhead for those algorithms," says Andrew Goossen. "So we added special hardware support for this specific scenario. The result is that Series X offers 49 TOPS for 8-bit integer operations and 97 TOPS for 4-bit integer operations. Note that the weights are integers, so those are TOPS and not TFLOPs. The net result is that Series X offers unparalleled intelligence for machine learning."
Other forward-looking features also make the cut. Again, similar to Nvidia's existing Turing architecture, mesh shaders are incorporated into RDNA 2, allowing for a potentially explosive improvement in geometric detail.
"As GPUs have gotten wider and computing performance has increased, geometry processing has become more and more bound on the fixed function vertex issue triangle setup and tessellation blocks of the GPU," reveals Goossen. "Mesh shading allows developers to completely bypass those fixed function bottlenecks by providing an optional alternative to the existing parts of the GPU pipeline. In addition to performance, mesh shading offers developers flexibility and memory savings. Mesh shading will allow game developers to increase detail in the shapes and animations of objects and render more complex scenes with no sacrifice to frame-rate."
There is more. Much more. For example, the Series X GPU allows for work to be shared between shaders without involvement from the CPU, saving a large amount of work for the Zen 2 cores, with data remaining on the GPU. However, the big innovation is clearly the addition of hardware accelerated ray tracing. This is hugely exciting and at Digital Foundry, we've been tracking the evolution of this new technology via the DXR and Vulkan-powered games we've seen running on Nvidia's RTX cards and the console implementation of RT is more ambitious than we believed possible.