Apple M1 Max’s 32-core GPU defeats AMD Radeon Pro W6900X in Affinity benchmark

The Cupertino giant has already launched its next-generation M1 Pro and M1 Max chips across the globe, debuting on its new-age 14-inch and 16-inch MacBook Pros. Shown in the launch…

By Raunak Saha

October 27, 2021

2 min read

Comments

The Cupertino giant has already launched its next-generation M1 Pro and M1 Max chips across the globe, debuting on its new-age 14-inch and 16-inch MacBook Pros. Shown in the launch event, these efficient chips promises phenomenal productivity performance we have never seen on a laptop.

A new benchmark leak has emerged that shows the new M1 Max with a 32-core GPU defeats the top-of-the-line AMD Radeon Pro W6900X graphics card in the Affinity benchmark. Yes, this is a flagship-level GPU by AMD used on Mac Pro and is easily a GPU that can tear apart the competition.

Though Affinity benchmark is not a good synthetic benchmark for comparison, however, if a laptop GPU can give similar performance in some tests like this is a great achievement. The tests were conducted by Andy Somerfield, the lead developer of the popular image editor Affinity Photo.

#M1Pro and #M1Max certainly sound like they have UMA GPUs with similar compute performance and on-chip bandwidth to high end discrete GPUs right? Let’s see what difference that makes then.. let’s see what this “ideal” GPU we designed our apps for way back in 2009 actually scores.
— Andy Somerfield (@andysomerfield) October 25, 2021

In a Twitter thread, Somerfield has detailed how the Affinity team has been optimizing its software for Apple Silicon chips since the first version of Affinity Photo for iPad. Obviously, developers like Somerfield have seen the evolution of these Apple chips and the new MacBook Pro with M1 Max could be game-changing.

The M1 Max as you probably know boasts a huge 400GB/s memory bandwidth, thanks to the 64GB unified memory, the developer explains that Affinity Photo runs best with a GPU that has high compute performance, fast on-chip bandwidth, and fast transfer on and off the GPU.

This means productivity apps like Affinity will instantly benefit from Apple’s onboard SoC that a unique design, draws far less power, gives best results even in battery mode. Not by any surprise, the fastest GPU that the Affinity team had ever tested in their benchmark tool was AMD’s Radeon Pro W6900X that costs around $6000.

Thanks to its 32GB of GDDR6 memory, it delivers up to 512GB/s of memory bandwidth, now this GPU has been beaten by Apple’s M1 Max GPU with 32 cores and 400GB/s of unified memory bandwidth.

via 9To5Mac