AMD RX Vega Rapid Packed Math: What does it mean for the console world?

PlayStation 4 Pro Enhanced Vega AMD RX Vega Rapid Packed Math: What does it mean for the console world?

Roughly around two weeks ago I’ve wrote an article on the new AMD Vega feature that is including the new cards that AMD is planning to ship very shortly, we are talking about Rapid Packed Math. Basically it’s just a fancy name for the double use of 16-bit flows, the very same feature that Mark Cerny talked about last year when the PS4 Pro was announced. He talked about this 8.4 TFLOPS of 16-bit compute power.

AMD Vega architecture also includes 64-bit floats because the games are becoming more demanding, the AI calculations and video rendering and game rendering calculations have to be so precise that even longer memory registers needs to be used. Now imagine using 16-bit floats when some games will be using 16-bit floats. This feature helps with the game rendering.

We have come though an article on Wccftech, which suggests that this new AMD’s Vega feature may actually help out to close the gap or narrow the gap between PS4 Pro and XB1X. This is one of the features that Xbox One X doesn’t have so, PS4 Pro has it Xbox One X doesn’t have it. But what that is actually?

Next-Gen Compute Units (NCUs) provide super-charged pathways for doubling processing throughput when using 16-bit data types.1 In cases where a full 32 bits of precision is not necessary to obtain the desired result, they can pack twice as much data into each register and use it to execute two parallel operations. This is ideal for a wide range of computationally intensive applications including image/video processing, ray tracing, artificial intelligence, and game rendering.

That’s official definition of what the 16-bit float is all about and then we’ve got a statement from Mark Cerny;

A few AMD roadmap features are appearing for the first time in PS4 Pro. One of the features appearing for the first time is the handling of 16-bit variables – it’s possible to perform two 16-bit operations at a time instead of one 32-bit operation. In other words, at full floats, we have 4.2 teraflops. With half-floats, it’s now double that, which is to say, 8.4 teraflops in 16-bit computation. This has the potential to radically increase performance.

16-bit computation power that just alone tells something. Do you want to build a game based on the 16-bit computation if you really want to chase the best graphics? No! that’s not possible.

Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Most Popular

Explore Latest News of Graphics cards, Video cards, GPUs , Rumors, Leaks and specifications

Copyright © 2017 By Gandhara Impex Pvt.LTD

To Top