failed to legalize operation 'hal.interface.constant.load' #18487
Assignees
Labels
bug 🐞
Something isn't working
Comments
|
@pdhirajkumarprasad I am not able to get the error mentioned in the issue, for me this is failing in |
|
@nirvedhmeshram we are seeing multiple crash. original issue is masked due to nod-ai/SHARK-ModelDev#852 |
I have the IR failing with the same crash, @nirvedhmeshram. This is happening because the constant __72 does not have the right buffer size, that matches @pdhirajkumarprasad is there a specific model that produces this IR? We could be looking at a possible import issue. |
|
@pdhirajkumarprasad Unable to reproduce the issue with any of the models mentioned in nod-ai/SHARK-ModelDev#812 on the respective tracker, with latest build of IREE. |
|
Currently I am seeing crash for following simple IR module {
func.func @main_graph( %arg0: !torch.vtensor<[1],si64>, %arg1: !torch.vtensor<[2],si64> ) -> !torch.vtensor<[2,2],si64> 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"} {
%1 = torch.operator "onnx.Constant"() {torch.onnx.value = dense_resource<__74> : tensor<4xsi64>} : () -> !torch.vtensor<[4],si64>
%2 = torch.operator "onnx.ConstantOfShape"(%arg0) {torch.onnx.value = dense_resource<__75> : tensor<1xsi64>} : (!torch.vtensor<[1],si64>) -> !torch.vtensor<[0],si64>
%3 = torch.operator "onnx.Concat"(%1, %2) {torch.onnx.axis = 0 : si64} : (!torch.vtensor<[4],si64>, !torch.vtensor<[0],si64>) -> !torch.vtensor<[4],si64>
%4 = torch.operator "onnx.Reshape"(%3, %arg1) {torch.onnx.allowzero = 0 : si64} : (!torch.vtensor<[4],si64>, !torch.vtensor<[2],si64>) -> !torch.vtensor<[2,2],si64>
%5 = torch.operator "onnx.Constant"() {torch.onnx.value = dense_resource<__77> : tensor<1xsi64>} : () -> !torch.vtensor<[1],si64>
%6 = torch.operator "onnx.Slice"(%4, %5, %5, %5, %5) : (!torch.vtensor<[2,2],si64>, !torch.vtensor<[1],si64>, !torch.vtensor<[1],si64>, !torch.vtensor<[1],si64>, !torch.vtensor<[1],si64>) -> !torch.vtensor<[2,2],si64>
return %4: !torch.vtensor<[2,2],si64>
}
}
{-#
dialect_resources: {
builtin: {
__74: "0x080000000100000000000000000000000000000001000000000000000000000000000000",
__75: "0x080000000000000000000000",
__77: "0x080000000000000000000000"
}
}
#-}crash log: command : iree-compile t.mlir --iree-hal-target-backends=llvm-cpu --iree-llvmcpu-target-cpu=host iree version: IREE compiler version 3.3.0rc20250303 @ cc37664 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
What happened?
for the given IR
Getting following error:
dump with flag : '--mlir-print-ir-after-all --mlir-print-ir-before-all --mlir-disable-threading --mlir-elide-elementsattrs-if-larger=4' (due to file size restriction, initial part has been removed from log)
dump.log
Steps to reproduce your issue
command:
What component(s) does this issue relate to?
Compiler
Version information
No response
Additional context
No response
The text was updated successfully, but these errors were encountered: