onnxruntime/docs/execution_providers
mikecaraman 358b517d49 [v2] Add ACL (Arm Compute Library) execution provider (#2258)
* Guard unused parameter

Guard unused parameter for Linux Arm and other cases.

* Add ACL (Arm Compute Library) execution provider

Add a new execution provider targeting Arm architecture based on Arm Compute Library.
Validated on NXP i.MX8QM CPU with ResNet50, MobileNetv2 and VGG models.
All unit tests are passing.

Comparative performance improvements for ResNet50v1 model obtained with
onnxruntime_perf_test:
		A72	2xA72	A53	4xA53
ACL vs CPU  	16%	9%	21%	13%

Usage documentation available in ACL-ExecutionProvider.

* Fix eigen unused parameter

Fix eigen unused parameter error for Arm cross-compilation.
2019-10-31 12:25:36 -07:00
..
images MKL-DNN Subgraphs (#1116) 2019-06-10 20:18:56 -07:00
ACL-ExecutionProvider.md [v2] Add ACL (Arm Compute Library) execution provider (#2258) 2019-10-31 12:25:36 -07:00
DirectML-ExecutionProvider.md Add DirectML Execution Provider (#2057) 2019-10-15 06:13:07 -07:00
MKL-DNN-ExecutionProvider.md Documentation Refresh (#1990) 2019-10-15 15:58:02 -07:00
MKL-DNN-Subgraphs.md MKL-DNN Subgraphs (#1116) 2019-06-10 20:18:56 -07:00
nGraph-ExecutionProvider.md Documentation Refresh (#1990) 2019-10-15 15:58:02 -07:00
Nuphar-ExecutionProvider.md Documentation Refresh (#1990) 2019-10-15 15:58:02 -07:00
OpenVINO-ExecutionProvider.md Updated documentation for VAD-F (#2248) 2019-10-24 14:31:44 -07:00
TensorRT-ExecutionProvider.md Fixed node index remapping issue in TensorRT graph partitioning (#2155) 2019-10-19 20:31:56 -07:00