It is workable. The VM can gather the workloads and pack them as a single
dynamic-shape workload and forward it to DietCode. DietCode does the
auto-scheduling and send the generated code back to the VM.
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm-rfcs/pul
### This issue is to track progress for DietCode
- [ ] Code Generation Support
- Local Padding
- Loop Partitioning
- [ ] Meta-Scheduler
- Frontend Interface
- Sketch Generation
- Random Annotations
- Program Measurer
- Micro-Kernel Cost Model
- Evolutionary Search
- [ ] Decision-Tr
@areusch @cgerum Thank you for your feedback. I have addressed your feedback.
Please review it again.
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm-rfcs/pull/72#issuecomment-1141453752
You are receiving this because you are subscribed to this thread.
Messag
@areusch BTW, may I ask whether there is anything I should prepare for the
meeting? Alternatively, any particular thing that the community might be
interested in? How much time am I given for the presentation?
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm-r
@areusch Thank you for the reminder. I have put that on my calendar.
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm-rfcs/pull/72#issuecomment-1136243463
You are receiving this because you are subscribed to this thread.
Message ID:
@areusch @comaniac Sure. I would be happy to. I will be traveling on 6/1 so
5/25 looks good.
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm-rfcs/pull/72#issuecomment-1130348204
You are receiving this because you are subscribed to this thread.
Message ID:
