onnxruntime/include/onnxruntime/core
Jeff Daily c8789d3047
[ROCm] static re-hipify of CUDA EP to ROCm EP, now a shared provider (#8877)
* re-hipify all rocm EP sources

* fix all other files affected by re-hipify

* add cuda_provider_factory.h to amd_hipify.py

* do not use cudnn_conv_algo_search in ROCm EP, missing reduce min registration

* Fix ReduceConsts template specialization introduced in #9101.

Fixes the error when building for ROCm 4.3.1:

error: too many template headers for onnxruntime::rocm::ReduceConsts<__half>::One (should be 0)

* fix flake8 error in amd_hipify.py

* speed up hipify with concurrent.futures

* flake8 fix in amd_hipify.py
2021-10-14 15:15:51 -07:00
..
common Make onnxruntime::Status nodiscard (#9279) 2021-10-08 17:10:31 -07:00
eager support register external ep lib information (#8897) 2021-08-31 20:51:22 -07:00
framework Execution Provider Profiler (#8406) 2021-09-28 13:59:52 -07:00
graph Remove unused NodeArgs in Graph::Resolve (#9213) 2021-10-01 11:44:26 -07:00
optimizer Added new fp16 allow/safe opcodes in PropagateCastOps (#8964) 2021-09-10 11:53:26 -07:00
platform Downgrade Eigen (#8817) 2021-08-23 18:06:23 -07:00
providers [ROCm] static re-hipify of CUDA EP to ROCm EP, now a shared provider (#8877) 2021-10-14 15:15:51 -07:00
session [ROCm] static re-hipify of CUDA EP to ROCm EP, now a shared provider (#8877) 2021-10-14 15:15:51 -07:00