GPU ROPs Differences Between PS4 & Xbox One Don’t Reflect Practical Scenarios, eSRAM Still A Factor

At this year’s Game Developers Conference, Avalanche Studios head of research Emil Persson offered his views on the PS4 and Xbox One effectively utilizing ROPs for higher bandwidth textures. According to Persson, the PS4 could render 64 bit textures while the Xbox One could only handle 32 bit textures before it ran out of bandwidth.

GamingBolt spoke to Confetti FX founder Wolfgang Engel, who provides consulting and tech solutions to different developers besides having handled Rockstar’s RAGE technology for GTA IV in the past, about providing the same level 64 bit performance on the Xbox One.

On Persson’s figures, Engel stated, “Those are highly theoretical numbers because they don’t reflect a typical game scenario. In the game you start rendering into shadow maps which eats up memory bandwidth, then you start rendering into G-buffer for deferred lighting and then you render it into a reflection map which might be a cubed map, then you start rendering lights in a light buffer, followed by a post effects pipelines render which might require a lot of memory copies, depending on how you implement it.”

Engel also stated that the inclusion of Xbox One’s eSRAM can potentially change the figures as well since it has a high bandwidth of 204 Gb/s. “Let us take a scenario where you have 20 different render targets per frame and you render them into memory, it will be hard to say this will be faster than this one and it’s even hard to make a general assumption about something, especially with the eSRAM in the mix. It highly depends on how you use system memory and eSRAM. You will run a lot of performance captures to see what the bottleneck is, memory access or arithmetic instructions. In most cases I predict memory access patterns will be your biggest challenge.”

As we highlighted in one of recent articles, memory access patterns will play a massive role in games development. Having different paths for the CPU and GPU  to access the memory can result into big wins in the performance area. We will have an article sometime after E3 that will focus on memory access patterns.

In the meantime do you have any thoughts? Let us know below in the comments section below.