AMD Radeon 800M iGPUs Achieve Over 3600 Points in 3DMark Time Spy, Approaching RTX 2050 Performance

AMD’s upcoming Radeon 800M iGPUs for Ryzen AI 300 APUs, featuring RDNA 3.5 technology, are expected to significantly enhance graphics performance.

AMD Radeon 800M “RDNA 3.5” iGPUs Rival NVIDIA’s RTX 2050 in 3DMark Time Spy, Optimized Drivers for Enhanced Performance

The latest updates on AMD’s RDNA 3.5 “Radeon 800M” iGPUs come from Golden Pig Upgrade on Bilibili. According to insider information, based on tests conducted on MSI’s Ryzen AI 300-powered laptops at Computex 2024, the next-generation integrated GPU will be a substantial improvement over the RDNA 3 “Radeon 700M” series.

It’s confirmed that the MSI laptops showcased at Computex 2024 were not final designs and were using engineering silicon of the AMD Ryzen AI 300 chips. Most of these laptops feature the Ryzen AI 9 HX 370 CPU, which is the flagship model with 12 cores based on the Zen 5 architecture, 24 threads, and the top Radeon 890M iGPU with 16 CUs (compute units).

Based on the measurements, the AMD Radeon 800M (890M) with 16 compute units clocked at around 2900 MHz scored over 3600 points in the 3DMark Time Spy Graphics test. Additionally, the Cinebench R23 tests showed the CPU scoring over 2000 points in single-core and over 20,000 points in the multi-threaded test. Overall, CPU performance has improved by more than 20% compared to the previous generation, although no TDP details were mentioned.

3DMark Time Spy Graphics (Higher is Better)

Score Scale:

• 5400
• 4500
• 3600
• 2700
• 1800
• 900
• 0

A score of over 3600 points positions the AMD Radeon 890M iGPU close to the NVIDIA GeForce RTX 2050 (Laptop) GPU. Given that this is an early ES chip and there is no information about the TDP, it’s likely that the final performance will be even higher.

We previously reported that the high-end iGPUs could potentially exceed 4000 points in the same 3DMark Time Spy tests. Overall, these are impressive gains for a refreshed architecture, and the additional compute units should contribute to better gaming performance. These improvements are ideal for applications such as thin and light laptops, Mini PCs, and handheld devices.