Assertion `isValid' failed

[pdhirajkumarprasad]

for the give IR

module {
  func.func @main_graph( ) -> !torch.vtensor<[7,7],f32>   attributes {torch.onnx_meta.ir_version = 8 : si64, torch.onnx_meta.opset_version = 17 : si64, torch.onnx_meta.producer_name = "pytorch", torch.onnx_meta.producer_version = "2.1.0"} {
    %416 = torch.operator "onnx.Constant"() {torch.onnx.value = dense_resource<__72> : tensor<7x7xf32>} : () -> !torch.vtensor<[7,7],f32> 
    return %416: !torch.vtensor<[7,7],f32>
  }
}

{-#
  dialect_resources: {
    builtin: {
      __72: "0x080000000000803F0000803F0000803F0000803F000080"
    }
  }
#-}

getting crash due to change in LLVM

iree-compile: /proj/rdi/staff/dhirajp/localBuild/iree/third_party/llvm-project/mlir/lib/IR/BuiltinAttributes.cpp:1352: static mlir::DenseElementsAttr mlir::DenseIntOrFPElementsAttr::getRaw(mlir::ShapedType, ArrayRef<char>): Assertion `isValid' failed.
Please report issues to https://github.com/iree-org/iree/issues and include the crash backtrace.
Stack dump:
0.	Program arguments: iree-compile --iree-input-type=auto --iree-vm-bytecode-module-output-format=flatbuffer-binary --iree-hal-target-backends=rocm --mlir-print-debuginfo --mlir-print-op-on-diagnostic=false --iree-hip-target=gfx942 t1.mlir
 #0 0x00007f0c1f4ad8f7 llvm::sys::PrintStackTrace(llvm::raw_ostream&, int) /proj/xhdhdstaff6/dhirajp/localBuild/iree/third_party/llvm-project/llvm/lib/Support/Unix/Signals.inc:723:13
 #1 0x00007f0c1f4abb30 llvm::sys::RunSignalHandlers() /proj/xhdhdstaff6/dhirajp/localBuild/iree/third_party/llvm-project/llvm/lib/Support/Signals.cpp:106:18
 #2 0x00007f0c1f4adfba SignalHandler(int) /proj/xhdhdstaff6/dhirajp/localBuild/iree/third_party/llvm-project/llvm/lib/Support/Unix/Signals.inc:413:1
 #3 0x00007f0c18ba2520 (/lib/x86_64-linux-gnu/libc.so.6+0x42520)

command:

iree-compile --iree-input-type=auto --iree-vm-bytecode-module-output-format=flatbuffer-binary --iree-hal-target-backends=llvm-cpu --mlir-print-debuginfo --mlir-print-op-on-diagnostic=false t1.mlir

[jinchen62]

I don't see this issue from the models of iree-org/iree#18468.

[jinchen62]

@vinayakdsci Could you run the models of iree-org/iree#18487 to try to reproduce it? I think these are the models

Natural_Language_Processing/funnelbase_Opset16_transformers
Natural_Language_Processing/funnelbase_Opset16_transformers