You are viewing a plain text version of this content. The canonical link for it is here.

Posted to dev@tvm.apache.org by Ligeng Zhu via Apache TVM Discuss <no...@discuss.tvm.ai> on 2022/06/20 18:24:35 UTC

[Apache TVM Discuss] [Development/pre-RFC] Introducing Hexagon backend


Yep, also curious about the followup. Is the Hexagon backend fully supported now? Or SNPE is still the only toolchain we can use to compile models to Qualcomm GPU.





---
[Visit Topic](https://discuss.tvm.apache.org/t/introducing-hexagon-backend/2421/35) 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/ab4df6b9660f595a501ce54bb36fc2dadd6d50d16583f1884aaf95786baa6895).

[Apache TVM Discuss] [Development/pre-RFC] Introducing Hexagon backend

Posted by Krzysztof Parzyszek via Apache TVM Discuss <no...@discuss.tvm.ai>.


It is supported in the sense that you should be able to compile and execute any model.  There is still a lot of work we need to do to make it perform well.  Right now we're working on many infrastructural changes in TVM, and the actual code generated for Hexagon is still far from optimal.





---
[Visit Topic](https://discuss.tvm.apache.org/t/introducing-hexagon-backend/2421/36) 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/35a663335ff1f24046d43265560c853453a2ac280e6e1cc61eeb5e74bd2fa703).