[GPU]: 'arith.extui' op operand type 'i64' and result type 'i32' are cast incompatible

[pdhirajkumarprasad]

What happened?

For the given IR

module {
  func.func @main_graph(%arg0: !torch.vtensor<[?],i1>, %arg1: !torch.vtensor<[?,?],i1>) -> !torch.vtensor<[?],si64>  attributes {torch.onnx_meta.ir_version = 7 : si64, torch.onnx_meta.opset_version = 21 : si64, torch.onnx_meta.producer_name = "pytorch", torch.onnx_meta.producer_version = "2.4.0"} {
    %1 = torch.operator "onnx.And"(%arg0, %arg1) : (!torch.vtensor<[?],i1>, !torch.vtensor<[?,?],i1>) -> !torch.vtensor<[?,?],i1> 
    %2 = torch.operator "onnx.Cast"(%1) {torch.onnx.to = 7 : si64} : (!torch.vtensor<[?,?],i1>) -> !torch.vtensor<[?,?],si64> 
    %3 = torch.operator "onnx.Constant"() {torch.onnx.value = dense_resource<__4> : tensor<1xsi64>} : () -> !torch.vtensor<[1],si64> 
    %4 = torch.operator "onnx.ReduceSum"(%2, %3) {torch.onnx.keepdims = 0 : si64} : (!torch.vtensor<[?,?],si64>, !torch.vtensor<[1],si64>) -> !torch.vtensor<[?],si64> 
    return %4 : !torch.vtensor<[?],si64>
  }
}

{-#
  dialect_resources: {
    builtin: {
      __4: "0x08000000FFFFFFFFFFFFFFFF"
    }
  }
#-}

getting error as

model.torch_onnx.mlir:6:10: error: 'arith.extui' op operand type 'i64' and result type 'i32' are cast incompatible
    %4 = torch.operator "onnx.ReduceSum"(%2, %3) {torch.onnx.keepdims = 0 : si64} : (!torch.vtensor<[?,?],si64>, !torch.vtensor<[1],si64>) -> !torch.vtensor<[?],si64> 
         ^

The same model works fine in CPU

Steps to reproduce your issue

command:

iree-compile --iree-hal-target-backends=rocm --iree-hip-target=gfx942 -o abc.vmfb model.torch_onnx.mlir

Version : IREE compiler version 3.0.0rc20241117 @ 29c451b

Detail log:
dump.log

What component(s) does this issue relate to?

Compiler

Version information

No response

Additional context

No response