Machine learning isn't the only useful thing to run on "GPU"s (these can't do graphics workloads anymore; they're basically just vector processors).
AMD isn't attempting to complete on f16 perf. They're completing where Nvidia's perf is abysmal: f64.
Having programmed AMDGPUs at a lower level than HIP/Rocm, they are actually much better than Nvidia (and in fact I'm able to do cool things like pcie large bar/p2p even on RDNA1 GPUs) in terms of flexibility. The HIP/CUDA API (nevermind OpenCL) doesn't do them justice, CUDA's enormous ecosystem and vender lock-in notwithstanding.
AMD isn't attempting to complete on f16 perf. They're completing where Nvidia's perf is abysmal: f64.
Having programmed AMDGPUs at a lower level than HIP/Rocm, they are actually much better than Nvidia (and in fact I'm able to do cool things like pcie large bar/p2p even on RDNA1 GPUs) in terms of flexibility. The HIP/CUDA API (nevermind OpenCL) doesn't do them justice, CUDA's enormous ecosystem and vender lock-in notwithstanding.