torch-mlir/lib/RefBackend/Runtime
Sean Silva 0b7c443256 [RefBackend] Properly initialize refbackrt::Tensor refcount.
Although `refCount` is initialized as `std::atomic<int> refCount{0};` in
the definition of Tensor, our tail-allocating malloc would ignore it,
resulting in bogus values that led to leaks.

Caught with LeakSanitizer, but I added an assertion that the refcount is
non-negative to begin with, which should catch this bug in the future
fairly consistently (assuming the garbage refcount is negative half the
time).
2020-11-24 12:01:35 -08:00
..
CMakeLists.txt Start reworking towards a shared library build. 2020-10-09 16:02:58 -07:00
CompilerDataStructures.h [RefBackend] Use std.global_memref instead of homegrown thing 2020-11-13 18:43:50 -08:00
CompilerRuntime.cpp [RefBackend] Use std.global_memref instead of homegrown thing 2020-11-13 18:43:50 -08:00
Runtime.cpp [RefBackend] Properly initialize refbackrt::Tensor refcount. 2020-11-24 12:01:35 -08:00
unix_version.script [RefBackend] Move runtime related code under npcomp/RefBackend/ 2020-10-08 09:07:00 -07:00