News Posts matching #Asynchronous Compute

Return to Keyword Browsing

"Navi 31" RDNA3 Sees AMD Double Down on Chiplets: As Many as 7

Way back in January 2021, we heard a spectacular rumor about "Navi 31," the next-generation big GPU by AMD, being the company's first logic-MCM GPU (a GPU with more than one logic die). The company has a legacy of MCM GPUs, but those have been a single logic die surrounded by memory stacks. The RDNA3 graphics architecture that the "Navi 31" is based on, sees AMD fragment the logic die into smaller chiplets, with the goal of ensuring that only those specific components that benefit from the TSMC N5 node (6 nm), such as the number crunching machinery, are built on the node, while ancillary components, such as memory controllers, display controllers, or even media accelerators, are confined to chiplets built on an older node, such as the TSMC N6 (6 nm). AMD had taken this approach with its EPYC and Ryzen processors, where the chiplets with the CPU cores got the better node, and the other logic components got an older one.

Greymon55 predicts an interesting division of labor on the "Navi 31" MCM. Apparently, the number-crunching machinery is spread across two GCD (Graphics Complex Dies?). These dies pack the Shader Engines with their RDNA3 compute units (CU), Command Processor, Geometry Processor, Asynchronous Compute Engines (ACEs), Rendering Backends, etc. These are things that can benefit from the advanced 5 nm node, enabling AMD to the CUs at higher engine clocks. There's also sound logic behind building a big GPU with two such GCDs instead of a single large GCD, as smaller GPUs can be made with a single such GCD (exactly why we have two 8-core chiplets making up a 16-core Ryzen processors, and the one of these being used to create 8-core and 6-core SKUs). The smaller GCD would result in better yields per wafer, and minimize the need for separate wafer orders for a larger die (such as in the case of the Navi 21).

The Coalition's Gears 5 Is Filled to the Brim With AMD DNA, System Requirements Outed

Gears 5, the next upcoming installment in the Gears of War series of video games, is launching this September 10th. In anticipation, developer The Coalition has announced the games' close partnership development with AMD, optimizing it for the company's cadre of GPU and CPU solutions. The game will make extensive use of Asynchronous Compute - one of AMD's most relevant technologies in gaining the upper hand against NVIDIA on performance terms. According to the developer, post-processing effects are being run exclusively on Asynchronous Compute, which means that the games' rendering is being run as close to a clockwork as possible. FidelityFX also makes an appearance again, as one of the latest AMD technologies for improving visual fidelity and sharpness. Multithreaded Command Buffering is the technical implementation for a system that improves AMD's Ryzen CPUs' processing of the game, specifically geared towards taking advantage of that CPU architecture's strong points.

The game seems to be a pretty scalable affair, with minimum requirements making do with just 2 GB of VRAM and an AMD RX 560 or NVIDIA GTX 1050. The ideal system requirements, however, call for a much beefier setup, with an AMD Radeon VII or NVIDIA RTX 2080 being called for, including 16 GB of system memory and a whopping 100 GB+ install footprint - preferably on an SSD. The game, like Gears of War 4, has been developed with the PC market in mind - there are more than 35 different graphical options for users to tweak. Here's hoping the games' writing is as much a technical achievement as its engine development seems to be.
Return to Keyword Browsing
Apr 25th, 2024 22:59 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts