Ask HN: Can competitors catch up to Apple Silicon?

Re:Ask HN: Can competitors catch up to Apple Silicon? by pclmulqdq on Monday July 04, 2022 @01:49PM (#31979890)

ROCm is pretty mature, but harder to support than CUDA. Its BLAS library works well. PyTorch and TensorFlow are likely getting a lot more help from Nvidia than from AMD on compatibility. The ROCm ecosystem is a lot smaller, too, so there are many fewer examples to copy.

Still, if you want to do floating point math with high performance for a lot cheaper than Nvidia, investing the time in ROCm is probably worth it.

[ Parent | on HN ]

Re:Ask HN: Can competitors catch up to Apple Silicon? by fxtentacle on Tuesday July 05, 2022 @02:44AM (#31985111)

In our case, we train on NVIDIA and then port to C++ with AVX. It's a bit more work, but deployment on AMD CPUs is even cheaper than on AMD GPUs.

[ Parent | on HN ]