@JammyZhou The runtime part is actually OS independent. I refer to Zephyr RTOS
as an example of OS that provides MISRA-C compliance. As Zephyr RTOS is
designed to be architecture independent, I worked on building the runtime with
Zephyr RTOS on top of qemu_x86, so that the complete system would
> Coming from a PL perspective, this is obvious.
The solution is in fact _not_ obvious even from a PL perspective. [Xavier
Leroy](https://xavierleroy.org/talks/compilation-agay.pdf), famous for his work
on OCaml, outlines multiple closure representations including their handling of
recursive an
Please share your thoughts about the RFC. this RFC will open for a week, if
there are no further comments, we will harden it by bringing it as a part of
tvm official document.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
# Workload record storage proposal
This is a migration and summation of the discussion
https://discuss.tvm.ai/t/rfc-benchmark-performance-log-format/4610/15. Please
head over there to put in your two cents. This is a WIP issue maintained for
visibility.
We propose a column-based data storage
@u99127 Good idea, will add.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/incubator-tvm/issues/4259#issuecomment-552540902
Should we have a known issues section ?
These are some initial thoughts from the top of my head over the last 5
minutes. I am sure that there are more.
- Tflite rounding vs tvm rounding causing differences in accuracy and
potentially off by 1 errors. For reference
https://github.com/apache/in
