You are viewing a plain text version of this content. The canonical link for it is here.
Posted to discuss-archive@tvm.apache.org by Nick Yang via Apache TVM Discuss <no...@discuss.tvm.ai> on 2021/11/18 09:21:26 UTC
[Apache TVM Discuss] [Questions] [Error Reporting] LLVM ERROR: out of memory Aborted (core dumped)
When I tried to compile a yolov3 model for zynq following the TVM - Vitis AI YoloV3 tutorial:
https://github.com/Xilinx/Vitis-AI/blob/master/external/tvm/examples/external_yolov3_tutorial.ipynb
Met the "LLVM ERROR: out of memory Aborted (core dumped)" error, when it came to "lib.export_library('tvm_dpu_cpu.so')".
The codes as follows:
if vitis_target.startswith('DPUCZDX8G'):
# Export runtime module
temp = utils.tempdir()
lib.export_library(temp.relpath("tvm_lib.so"))
# Build and export lib for aarch64 target
tvm_target = tvm.target.arm_cpu('ultra96')
lib_kwargs = {
'fcompile': contrib.cc.create_shared,
'cc': "/usr/aarch64-linux-gnu/bin/ld"
}
build_options = {
'load_runtime_module': export_rt_mod_file
}
with tvm.transform.PassContext(opt_level=3, config={'relay.ext.vitis_ai.options': build_options}):
lib_dpuczdx8g = relay.build(mod, tvm_target, params=params)
lib_dpuczdx8g.export_library('tvm_dpu_cpu.so', **lib_kwargs)
else:
lib.export_library('tvm_dpu_cpu.so')
print("Finished storing the compiled model as tvm_dpu_cpu.so")
I tried to find a solution, but got noting help.
Is there anyone meet the same error or can help me figure out it. I would appreciate it very much~
---
[Visit Topic](https://discuss.tvm.apache.org/t/error-reporting-llvm-error-out-of-memory-aborted-core-dumped/11501/1) to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/fbb9c701e641123b4cfc819bcc59fab8d253d61f13775ff349e5617aa003faeb).