@zhiics Yep, we have an option to turn off the default method generation and
allow user to fill their customized code snippets.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/rfc-tvm-object-schema-dsl/7930/8) to
respond.
You are receiving this because you enabled mailing list mode.
Hi @jcf94,
[quote="jcf94, post:5, topic:7930"]
IMHO, advanced users who may benefit from it are more likely to write their C++
code directly, while other users may not really have a requirement on this.
[/quote]
First, this is not only for C++ code generation. In the future, we will extend
it
Yeah, this could be a useful tool to generate the generic templates or the code
with the fixed pattern which is actually the major part of a node. For some
other members, e.g. SEqualReduce and SHashReduce, we may still need users to
manually check/add since they are not always `Equal(this->a,
Thanks, this is really an interesting work! For those who have a requirement to
add their own modifications to use TVM, it will be very helpful!
I'm just thinking about how frequently will this new feature be used. IMHO,
advanced users who may benefit from it are more likely to write their C++
I did some tests, and the result is that tvm cannot exceed MNN.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/strassen-algorithm-for-dense/2661/5) to
respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discus
Thanks for the clarification :) So this is more like a tool to facilitate the
development process. After the C++ code has been generated, we can continue
working on it as always.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/rfc-tvm-object-schema-dsl/7930/4) to
respond.
You are re
Hi @comaniac,
[quote="comaniac, post:2, topic:7930"]
* Are the generated .h and .cc files supposed to be tracked in the repo, or
they are more like the build files?
[/quote]
They will be tracked in the repo. But user should write the tschema for objects
instead of writing the cpp files direct
Thanks for the RFC and it looks super useful! I have two questions from the RFC:
1. Are the generated .h and .cc files supposed to be tracked in the repo, or
they are more like the build files?
2. For the in-place modification, I am a bit confused about the example of
customized C++ code (the
## Introduction
[TVM Object
system]([https://tvm.apache.org/docs/dev/runtime.html#tvm-object-and-compiler-stack](https://tvm.apache.org/docs/dev/runtime.html#tvm-object-and-compiler-stack))
provides a convenient and decent way to share objects between backend (C++)
and frontend (Python/Java/R
Graph of TF OD is much larger than PT OD.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/vm-slow-compilation-of-tf-object-detection-models/7479/10)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discus
You can first register a target using `TVM_REGISTER_TARGET_KIND` macro in
`https://github.com/apache/incubator-tvm/blob/master/src/target/target_kind.cc`.
Then register OpenCL codegen as your backend.
This doc can help you get familiar with the compilation flow, and you can add
corresponding
We have a custom accelerator that uses the OpenCL frontend. We want to include
this as a custom type like the aocl within the TVM pipeline. How do we go about
introducing a new target for the same? (we aim to give our custom accelerator
as the target parameter for tvm.context)
---
[Visit
@FrozenGene，do you have any updates about this topic？
---
[Visit
Topic](https://discuss.tvm.apache.org/t/strassen-algorithm-for-dense/2661/4) to
respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.apac
13 matches
Mail list logo
