I have found writing CUDA code is much simpler than writing correct multi-threaded AVX2/AVX-512 code.
Which other hardware vendor provides the level of performance that Nvidia's GPU provide? Wasnt the benevolence on single (or couple) manufacturer(s) true in 90s, 2020s?
The network topology is the same, no modules are removed, etc. Of course it will be optimized to run on Ampere
I have found writing CUDA code is much simpler than writing correct multi-threaded AVX2/AVX-512 code.
Which other hardware vendor provides the level of performance that Nvidia's GPU provide? Wasnt the benevolence on single (or couple) manufacturer(s) true in 90s, 2020s?
The network topology is the same, no modules are removed, etc. Of course it will be optimized to run on Ampere