You are viewing a plain text version of this content. The canonical link for it is here.
Posted to discuss-archive@tvm.apache.org by Zhiying Xu via Apache TVM Discuss <no...@discuss.tvm.ai> on 2020/10/13 05:27:25 UTC
[Apache TVM Discuss] [Questions] How to I use prefetch with GPU
codegen
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 from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/eb566255a34bf393c078b209bbff597bd93c85c06987c1bb5254b688923b510b).
[Apache TVM Discuss] [Questions] How to I use prefetch with GPU
codegen
Posted by tqchen via Apache TVM Discuss <no...@discuss.tvm.ai>.
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
---
[Visit Topic](https://discuss.tvm.apache.org/t/how-to-i-use-prefetch-with-gpu-codegen/7294/3) to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/d1949b970b3187c1d735b19784ebc72c380d717ecc79ff9ad23b9cfee69212b6).