onnxruntime/include/onnxruntime/core
kile0 f367fd921c
Use a custom allocator for temporary buffers in reduction_ops.cc (#2775)
* port the mimalloc allocator

* hook mimalloc opt into common.h and reduction ops

* repurpose USE_MIMALLOC to only denote subbing in of default allocator with mimalloc and some refactoring

* fix unintended cherry pick diffs

* polish alloctor_mimalloc

* explicitly disable mimalloc where it already had been disabled

* update mimalloc to pull in stl allocator

* switch mimalloc stl allocator to use mimalloc library version

* turn mimalloc on by default (only the stl changes are enabled, the python interacting ones are off already and shall remain so)

* move FastAllocVector into cpu specific code

* separate out defines into arena and stl changes

* the rest of the define renames

* bfc arena allocator

* some typos and rename the bfc arena allocator to fit existing class naming conventions

* adjustments in response to comments

* different template instantiations are friends
2020-02-23 16:04:30 +10:00
..
common Use a custom allocator for temporary buffers in reduction_ops.cc (#2775) 2020-02-23 16:04:30 +10:00
framework Use a custom allocator for temporary buffers in reduction_ops.cc (#2775) 2020-02-23 16:04:30 +10:00
graph Use CUDA 10.1 for Linux build (#3057) 2020-02-21 11:55:32 -08:00
optimizer Add a transformer to use Gelu approximation for cuda provider (#2480) 2019-11-27 10:15:50 -08:00
platform Remove USE_NSYNC macro (#3052) 2020-02-20 13:29:19 -08:00
providers Merge windowsai (winml layering) into master (#2956) 2020-02-04 17:12:19 -08:00
session Support a few new C/C++ APIs (#2794) 2020-02-10 16:18:42 -08:00