8000 [iree][llvm]error in converting an linalg mlir into llvm using nvvm · Issue #20635 · iree-org/iree · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

[iree][llvm]error in converting an linalg mlir into llvm using nvvm #20635

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
piyushhingu opened this issue Apr 25, 2025 · 1 comment
Open
Labels
bug 🐞 Something isn't working

Comments

@piyushhingu
Copy link
piyushhingu commented Apr 25, 2025

What happened?

0.	Program arguments: /workspace/docker/mlir_venv/lib/python3.10/site-packages/iree/compiler/tools/../_mlir_libs/iree-opt --iree-convert-to-nvvm
 #0 0x000071c5463c2448 llvm::sys::PrintStackTrace(llvm::raw_ostream&, int) (/workspace/docker/mlir_venv/lib/python3.10/site-packages/iree/compiler/_mlir_libs/libIREECompiler.so+0x57c2448)
 #1 0x000071c5463c01ee llvm::sys::RunSignalHandlers() (/workspace/docker/mlir_venv/lib/python3.10/site-packages/iree/compiler/_mlir_libs/libIREECompiler.so+0x57c01ee)
 #2 0x000071c5463c2af6 SignalHandler(int, siginfo_t*, void*) Signals.cpp:0:0
 #3 0x000071c540a19520 (/usr/lib/x86_64-linux-gnu/libc.so.6+0x42520)
 #4 0x000071c5465ae9f8 mlir::iree_compiler::IREE::GPU::TargetAttr::getCUDAComputeCapability() const IREEGPUAttrs.cpp:0:0
 #5 0x000071c54805a424 mlir::iree_compiler::(anonymous namespace)::ConvertToNVVMPass::runOnOperation() ConvertToNVVM.cpp:0:0
 #6 0x000071c54660dfdb mlir::detail::OpToOpPassAdaptor::run(mlir::Pass*, mlir::Operation*, mlir::AnalysisManager, bool, unsigned int) (/workspace/docker/mlir_venv/lib/python3.10/site-packages/iree/compiler/_mlir_libs/libIREECompiler.so+0x5a0dfdb)
 #7 0x000071c546611eeb mlir::PassManager::run(mlir::Operation*) (/workspace/docker/mlir_venv/lib/python3.10/site-packages/iree/compiler/_mlir_libs/libIREECompiler.so+0x5a11eeb)
 #8 0x000071c54660591e performActions(llvm::raw_ostream&, std::shared_ptr<llvm::SourceMgr> const&, mlir::MLIRContext*, mlir::MlirOptMainConfig const&) MlirOptMain.cpp:0:0
 #9 0x000071c54660559c llvm::LogicalResult llvm::function_ref<llvm::LogicalResult (std::unique_ptr<llvm::MemoryBuffer, std::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&)>::callback_fn<mlir::MlirOptMain(llvm::raw_ostream&, std::unique_ptr<llvm::MemoryBuffer, std::default_delete<llvm::MemoryBuffer>>, mlir::DialectRegistry&, mlir::MlirOptMainConfig const&)::$_0>(long, std::unique_ptr<llvm::MemoryBuffer, std::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&) MlirOptMain.cpp:0:0
#10 0x000071c5466074f2 mlir::splitAndProcessBuffer(std::unique_ptr<llvm::MemoryBuffer, std::default_delete<llvm::MemoryBuffer>>, llvm::function_ref<llvm::LogicalResult (std::unique_ptr<llvm::MemoryBuffer, std::default_delete<llvm::MemoryBuffer>>, llvm::raw_ostream&)>, llvm::raw_ostream&, llvm::StringRef, llvm::StringRef) (/workspace/docker/mlir_venv/lib/python3.10/site-packages/iree/compiler/_mlir_libs/libIREECompiler.so+0x5a074f2)
#11 0x000071c5466004b2 mlir::MlirOptMain(llvm::raw_ostream&, std::unique_ptr<llvm::MemoryBuffer, std::default_delete<llvm::MemoryBuffer>>, mlir::DialectRegistry&, mlir::MlirOptMainConfig const&) (/workspace/docker/mlir_venv/lib/python3.10/site-packages/iree/compiler/_mlir_libs/libIREECompiler.so+0x5a004b2)
#12 0x000071c54632376d ireeOptRunMain (/workspace/docker/mlir_venv/lib/python3.10/site-packages/iree/compiler/_mlir_libs/libIREECompiler.so+0x572376d)
#13 0x000071c540a00d90 __libc_start_call_main ./csu/../sysdeps/nptl/libc_start_call_main.h:58:16
#14 0x000071c540a00e40 call_init ./csu/../csu/libc-start.c:128:20
#15 0x000071c540a00e40 __libc_start_main ./csu/../csu/libc-start.c:379:5
#16 0x000000000020169e _start (/workspace/docker/mlir_venv/lib/python3.10/site-packages/iree/compiler/tools/../_mlir_libs/iree-opt+0x20169e)

Steps to reproduce your issue

convert an model into onnx
use this command to convert into linalg
$ iree-opt iree_onnx.mlir --torch-onnx-to-torch-backend-pipeline --torch-backend-to-linalg-on-tensors-backend-pipeline -o iree_linalg.mlir
convert this linalg into llvm using this
mlir-opt iree_linalg.mlir --linalg-generalize-named-ops | iree-opt -pass-pipeline="builtin.module(convert-func-to-spirv,torch-func-backend-type-conversion,iree-codegen-iree-bufferize-constants,iree-convert-to-llvm)" | iree-opt --iree-convert-to-nvvm

What component(s) does this issue relate to?

No response

Version information

No response

Additional context

No response

@piyushhingu piyushhingu added the bug 🐞 Something isn't working label Apr 25, 2025
@krzysz00
Copy link
Contributor

First note: you've got conversion to spir-v in your pipeline while you're going to LLVM. Try removing that

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug 🐞 Something isn't working
Projects
None yet
Development

No branches or pull requests

2 participants
0