Thanks for your reply, assuming that there is no layout transformation, I want
to develop a
function to collect all CallNode and Function input output layout in a model,
any advice ?
---
[Visit
Topic](https://discuss.tvm.apache.org/t/how-to-get-layout-of-relay-callnode-and-relay-functio
Hi, I have a question about the layout, does tvm has a method to get every
relay::callnode
and relay::function's input, output, weights layout. Thanks!
---
[Visit
Topic](https://discuss.tvm.apache.org/t/how-to-get-layout-of-relay-callnode-and-relay-function/11721/1)
to respond.
You are
No, I didn't solve the problem, but I have found that it is llvm's problem, its
support about riscv need to be improved.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/cant-link-soft-float-modules-with-double-float-modules/10140/3)
to respond.
You are receiving this because you enabl
If you use llvm as your codegenerator, it will not generate double-float object
file for riscv, I don't know why, but it can't, even though you add
`-mfloat-abi=hard`, the workaround is
save the code as a text assembly code and then call your cross compiler to
generate object file.
for exampl
I have a question about function `export_library`, Here is my target
```
tgt = "llvm -mtriple=riscv64-unknown-linux-gnu -mcpu=generic-rv64
-mfloat-abi=hard"
```
and `export_library` use:
```
specialized =
cc.cross_compiler("soft/riscv/new_install/bin/riscv64-unknown-linux-gnu-g++",
["-mabi=lp
hi @Julien ,
With the help of @areusch , I have tried to make `tvm/tests/micro/qemu` work on
`qemu_riscv32`, and one month ago, it works for `test_compile_runtime` and
`test_relay` in `test_zephyr.py`, here is my
[code](https://github.com/Dream-math/Riscv-backend). But I find tvm code has
cha
Hi, everyone ! I have a few questions about the following code in
`include/tvm/tir/stmt_functor.h`
```
template
TSelf& set_dispatch(FPointer f) { // NOLINT(*)
uint32_t tindex = TNode::RuntimeTypeIndex();
if (func_.size() <= tindex) {
func_.resize(tindex + 1, nullptr);
}
