NVIDIA GeForce RTX 3080 Compute Performance Nearly 70 Percent Better Than RTX 2080 SUPER

The FPS Review may receive a commission if you purchase something after clicking a link in this article.

Image: NVIDIA

VideoCardz has spotted new NVIDIA GeForce RTX 3080 benchmarks on CompuBench, which tease the flagship GPU’s potential CUDA and Open CL performance. According to the averages calculated from 20 separate tests (e.g., Ocean Surface Simulation, Subsurface Scattering), the GeForce RTX 3080 is nearly 70 percent better than the GeForce RTX 2080 SUPER in compute. It’s also 38 to 41 percent better than the GeForce RTX 2080 Ti in that respect.

“The GeForce RTX 3080 graphics card has been tested using 456.16 drivers,” VideoCardz noted. “The OpenCL info page reveals its a 10GB variant with 68 Compute Units (Streaming Multiprocessors) and 1710 MHz boost frequency. This is either the Founders Edition model tested by one of the reviewers or a custom variant featuring the same clock speed. The CUDA info page confirms its a 320-bit memory configuration with 19 Gbps modules.”

VideoCardz also points out that these tests are compute oriented, which means that they shouldn’t be used to gauge gaming performance. NVIDIA has already teased us with benchmarks and videos that suggest the GeForce RTX 3080 blows away its predecessor in practically every regard, however.

Tsing Mui
News poster at The FPS Review.

Recent News