When using ONNX Runtime (which has PyTorch cpuinfo as a static dependency) with a Linux program built with LeakSanitizer/AddressSanitizer, memory leaks are reported:
=================================================================
==11753==ERROR: LeakSanitizer: detected memory leaks
Direct leak of 576 byte(s) in 1 object(s) allocated from:
#0 0x2b11dd429917 in __interceptor_calloc (/path/to/libasan.so.6+0xb4917)
#1 0x2b11e45064b6 in cpuinfo_x86_linux_init (/path/to/libonnxruntime.so.1.14.1+0x8684b6)
Direct leak of 576 byte(s) in 1 object(s) allocated from:
#0 0x2b11dd429917 in __interceptor_calloc (/path/to/libasan.so.6+0xb4917)
#1 0x2b11e4506496 in cpuinfo_x86_linux_init (/path/to/libonnxruntime.so.1.14.1+0x868496)
SUMMARY: AddressSanitizer: 1152 byte(s) leaked in 2 allocation(s).
ONNX Runtime doesn't call cpuinfo_deinitialize, but on the other hand that wouldn't help since the implementation is empty.
It would be nice if cpuinfo_deinitialize could be implemented so that ONNX Runtime and other users can call it to deallocate the resources.
When using ONNX Runtime (which has PyTorch cpuinfo as a static dependency) with a Linux program built with LeakSanitizer/AddressSanitizer, memory leaks are reported:
ONNX Runtime doesn't call
cpuinfo_deinitialize
, but on the other hand that wouldn't help since the implementation is empty.It would be nice if
cpuinfo_deinitialize
could be implemented so that ONNX Runtime and other users can call it to deallocate the resources.