[TVM Discuss] [Questions] Tvm.contrib.graph_runtime.create error

I run it on linux, a "segmentation fault" error occurs.Debug Info: ``` (gdb)bt #0 std::basic_string, std::allocator>::basic_string(std::string const&)() from /lib64/libstdc++.so.6 #1 tvm::runtime:GraphRuntime::SetupStorage() from /tvm/build/libtvm.so #2 tvm::runtime:GraphRuntime::Init(std:: str

[TVM Discuss] [Questions] [PattenLang]How to match op according to element type of input and output

I personally like `ShapePattern` and `DTypePattern` more as they are more straightforward in the pattern language, but I'd also like to see other's opinions. cc @zhiics @tqchen @masahi --- [Visit Topic](https://discuss.tvm.ai/t/pattenlang-how-to-match-op-according-to-element-type-of-inpu

[TVM Discuss] [Questions] [PattenLang]How to match op according to element type of input and output

What do you guys thing? Which would be easier to use? --- [Visit Topic](https://discuss.tvm.ai/t/pattenlang-how-to-match-op-according-to-element-type-of-input-and-output/6846/11) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [

[TVM Discuss] [Application] TVM for targetting microcontrollers/bare metal

@JakeStevens @tico make sure and check out our latest work that is now upstreamed with reproducible examples here: https://tvm.apache.org/2020/06/04/tinyml-how-tvm-is-taming-tiny And many more things to come! (eg see https://discuss.tvm.ai/t/utvm-embedded-focus-online-meetup/6908 ) --- [

[TVM Discuss] [Questions] [PattenLang]How to match op according to element type of input and output

Yeah, it's a bit complicated. The current pattern uses the tvm::ir::Type* classes, so you can match number of versions of types, but as this question reveals, we may want a finer granularity on some types. Unfortunately, since we're using a lower level Type object, we won't be able to embed

[TVM Discuss] [Questions] [PattenLang]How to match op according to element type of input and output

Make sense. The ideal interface for this case would be leveraging has_type as other type matching. We may need new patterns like AnyShape, or support Wildcard in tensor shapes (seems much harder to me). --- [Visit Topic](https://discuss.tvm.ai/t/pattenlang-how-to-match-op-according-to-ele

[TVM Discuss] [Questions] [PattenLang]How to match op according to element type of input and output

My apologies! I somehow missed this last week. Yeah, the current TypePattern is matching the full type via StructuralEqual. One possibility to clean this up slightly is to add a rule of: 1) If it's a TensorType 2) and the pattern's shape is () 3) only check the dtype That would only take a han

[TVM Discuss] [Questions] Optimizing matrix multiplication for GPU

I got very close to matching PyTorch's bmm on Vega 20 (Radeon VII) and to about to 1.5x on 1080Ti for the 1024 example (with fixed dims). One of the limiting things on the path ahead is the "-1" issue in the output configurations of course. Best regards Thomas --- [Visit Topic](https:/

[TVM Discuss] [Questions] [Solved] How is __tvm_module_startup invoked?

Hi @jinchenglee, [quote="jinchenglee, post:2, topic:6891"] TVMBackendRegisterSystemLibSymbol() function. However, I cannot find where it was invoked in TVM source tree. Thanks in advance. [/quote] In my observation, the `TVMBackendRegisterSystemLibSymbol` function is called inside the generat