Re:AMD Launches 12 Desktop Renoir Ryzen 4000G Series APUs: B...
by pmalynin on Tuesday July 21, 2020 @03:47PM
(#23910226)
I was an ML engineer in a previous life.
For most ML and GPGPU workloads the bottleneck is memory bandwidth. It’s normal to hit 2TB/s because of all the caches, memory banks and the wide memory bus. I wouldn’t expect the APU to perform nearly as well as even an entry level GPU (say 1660) but I would be curious to see.
For most ML and GPGPU workloads the bottleneck is memory bandwidth. It’s normal to hit 2TB/s because of all the caches, memory banks and the wide memory bus. I wouldn’t expect the APU to perform nearly as well as even an entry level GPU (say 1660) but I would be curious to see.