Skip to main content

Processing in memory offers major improvements to 3D rendering speeds

processing in memory 3d rendering pnnl
A researcher at the Pacific Northwest National Laboratory has developed a new architecture for 3D stacked memory. It uses the hardware’s capacity for “processing in memory” to deliver 3D rendering speeds that are up to 65 percent faster than previous methodology.

Shuaiwen Leon Song collaborated with researchers from the University of Houston to accomplish those results. The architecture was tested using video games like Doom 3 and Half-Life 2, but there are hopes that it could one day benefit scientific research thanks to its uses in terms of visualization and modeling.

A typical graphics card uses its graphical processing unit to render images from information that’s stored elsewhere. But 3D stacked memory has access to an added logic layer that it can utilize to carry some of the processing burden, which is the process that’s referred to as processing in memory.

The benefit is that less data has to be transferred from memory to GPU cores, with less congestion contributing to the 65 percent improvement in speed, according to a report published by PNNL. The researchers established that it was anisotropic filtering, the final stage in the rendering process, that caused the most congestion. They were able to produce the best improvements to performance by shifting anisotropic filtering to the first stage of the graphics pipeline, and making sure that it was being processed in memory.

“We’re pushing the boundaries of what hardware can do,” Song said of the project. “And though we tested our idea on video games, this improvement ultimately benefits science.”

This kind of research sets out to ensure that we can squeeze every last drop of performance out of currently existing hardware. Between video games, scientific applications, and the continuing rise of virtual reality, there are plenty of applications for a more efficient system of rendering 3D graphics.

Editors' Recommendations

Brad Jones
Brad is an English-born writer currently splitting his time between Edinburgh and Pennsylvania. You can find him on Twitter…
Acer launches eye-popping displays with built-in 3D tech
The Acer SpatialLabs View and SpatialLabs View Pro monitors sit side by side.

Acer has announced an expansion to its stereoscopic 3D range with the SpatialLabs View series displays. Two new portable monitors designed for the gaming segment were unveiled: the Acer SpatialLabs View and the SpatialLabs View Pro.

The former is geared toward gamers specifically, while the latter is described as a monitor for commercial audiences such as retailers (for example, kiosks).

Read more
AMD’s revolutionary 3D V-Cache chip could launch very soon
AMD Ryzen 5000G.

The launch of AMD's upcoming Ryzen 7 5800X3D processors is close, but a new leak tells us that it might be just a couple of weeks away.

According to a well-known source of hardware leaks, the processors have already started shipping. This indicates that they might hit the market by the end of this month. AMD estimates that its new processor could match up against the top chip from the Intel Alder Lake lineup.

Read more
AMD teases performance of its revolutionary 3D V-cache chip
AMD CEO holding 3D V-Cache CPU.

AMD is currently readying its new Ryzen 7 5800X3D, featuring a 3D V-cache, and it looks like we may soon have a powerful processor on our hands. AMD has teased that we can expect an up to 15% performance boost over the base Ryzen 7 5800X.

The tech giant talked about the new chip during the International Solid-State Circuits Conference (ISSSC) and revealed more information about its architecture. While the Ryzen 7 5800X3D will certainly be an improvement, will it be enough to compete with Intel's best processors?

Read more