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

Posted to dev@tvm.apache.org by "Leandro Nunes (Arm) via TVM Discuss" <no...@discuss.tvm.ai> on 2020/08/24 15:30:34 UTC

[TVM Discuss] [Development/RFC] [RFC] TVM Target Specification


[quote="comaniac, post:9, topic:6844"]
I like the idea of composite target and believe it would be useful for BYOC. We could ask the developers to first register a target ID and create a specialized tag to specify the desire usage of the customized codegen (e.g., 1) offload to DNNL and fallback to LLVM if not suppport; 2) offload to TensorRT and fallback to CUDA if not support; 3) offload to an accelerator, fallback to DNNL or LLVM if not support.)
[/quote]

I'm interested to understand how would the JSON would look like for case 3 (above). Also, could you expand a little on how you see this working, specifically who would oversee the graph partitioning process (and call the expected passes in the expected order) ?





---
[Visit Topic](https://discuss.tvm.ai/t/rfc-tvm-target-specification/6844/52) to respond.

You are receiving this because you enabled mailing list mode.

To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/5fed1ff78dd8af0a62e732b6cedfc0a49eba6c6d745bb8d4de75909c20cc3de2).

[TVM Discuss] [Development/RFC] [RFC] TVM Target Specification

Posted by "Leandro Nunes (Arm) via TVM Discuss" <no...@discuss.tvm.ai>.


[quote="leandron, post:52, topic:6844"]
I’m interested to understand how would the JSON would look like for case 3 (above). Also, could you expand a little on how you see this working, specifically who would oversee the graph partitioning process (and call the expected passes in the expected order) ?
[/quote]

For completeness, @comaniac posted a follow-up RFC to cover Composite Targets -> https://discuss.tvm.ai/t/rfc-composite-target/7744





---
[Visit Topic](https://discuss.tvm.ai/t/rfc-tvm-target-specification/6844/53) to respond.

You are receiving this because you enabled mailing list mode.

To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/dcf20351a36510c4b298dcf51e7de85b6a6740cbf572eb668f125e16f1ac88d2).