prefetch is not supported in most GPUs. Most cases cache prefetching happens
automatically and you can use cache_read to get the data into shared meory, see
examples in
https://tvm.apache.org/docs/tutorials/optimize/opt_conv_cuda.html#sphx-glr-tutorials-optimize-opt-conv-cuda-py
---
[Visi
I am facing the same problem with prefetching data from shared mem to registers.
Did you solve this?
---
[Visit
Topic](https://discuss.tvm.apache.org/t/how-to-i-use-prefetch-with-gpu-codegen/7294/2)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe
