onnxruntime/tools/ci_build/github/azure-pipelines
Adrian Tsai 4090d0d0de
Add DirectML Execution Provider (#2057)
This change adds a new execution provider powered by [DirectML](https://aka.ms/DirectML).

DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning on Windows. DirectML provides GPU acceleration for common machine learning tasks across a broad range of supported hardware and drivers.

The DirectML execution provider is capable of greatly improving evaluation time of models using commodity GPU hardware, without sacrificing broad hardware support or requiring vendor-specific extensions to be installed.

**Note** that the DML EP code was moved verbatim from the existing WindowsAI project, which is why it doesn't yet conform to the onnxruntime coding style. This is something that can be fixed later; we would like to keep formatting/whitespace changes to a minimum for the time being to make it easier to port fixes from WindowsAI to ORT during this transition.

Summary of changes:
* Initial commit of DML EP files under onnxruntime/core/providers/dml
* Add cmake entries for building the DML EP and for pulling down the DirectML redist using nuget
* Add a submodule dependency on the Windows Implementation Library (WIL)
* Add docs under docs/execution_providers/DirectML-ExecutionProvider.md
* Add support for DML EP to provider tests and perf tests
* Add support for DML EP to fns_candy_style_transfer sample
* Add entries to the C ABI for instantiating the DML EP
2019-10-15 06:13:07 -07:00
..
nuget C# end to end test fix, and make end to end tests mandatory (#2079) 2019-10-10 19:23:43 -07:00
templates Add DirectML Execution Provider (#2057) 2019-10-15 06:13:07 -07:00
android-x86_64-crosscompile-ci-pipeline.yml Android CI (#1600) 2019-10-04 17:39:51 -07:00
azure-pipelines-py-packaging.yml Downgrade python gpu package to CUDA 10.0 (#2086) 2019-10-10 18:31:24 -07:00
c-api-packaging-pipelines.yml Downgrade python gpu package to CUDA 10.0 (#2086) 2019-10-10 18:31:24 -07:00
centos-ci-pipeline.yml CentOS CI (#1998) 2019-10-04 10:48:43 -07:00
linux-ci-pipeline.yml Enable Nuphar docker build, and reinstate Nuphar tests (#1757) 2019-09-05 08:50:48 -07:00
linux-gpu-ci-pipeline-cuda9.yml Avoid downloading test data into C:\ (#1562) 2019-08-05 19:53:15 -07:00
linux-gpu-ci-pipeline.yml Refactor CI pipelines - add GPU NuGet pipelines and ESRP code signing steps (#1247) 2019-06-20 19:41:30 -07:00
linux-gpu-tensorrt-ci-pipeline.yml Update TensorRT to version 6.0.1.5 (#1966) 2019-10-06 10:40:53 -07:00
linux-multi-gpu-ci-pipeline.yml Enable Gpu multi-device test for CUDA EP and Trt EP 2019-10-14 11:16:34 -07:00
linux-multi-gpu-tensorrt-ci-pipeline.yml Enable Gpu multi-device test for CUDA EP and Trt EP 2019-10-14 11:16:34 -07:00
linux-ngraph-ci-pipeline.yml Avoid downloading test data into C:\ (#1562) 2019-08-05 19:53:15 -07:00
linux-nocontribops-ci-pipeline.yml Avoid downloading test data into C:\ (#1562) 2019-08-05 19:53:15 -07:00
linux-openvino-ci-pipeline.yml Enable Openvino nightly build on edge device (#1684) 2019-09-11 16:36:12 -07:00
linux-openvino-nightly-pipeline.yml Enable Openvino nightly build on edge device (#1684) 2019-09-11 16:36:12 -07:00
linux-ort-srv-ci-pipeline.yml Avoid downloading test data into C:\ (#1562) 2019-08-05 19:53:15 -07:00
linux-ort-srv-nightly-pipeline.yml Avoid downloading test data into C:\ (#1562) 2019-08-05 19:53:15 -07:00
linux-x86-ci-pipeline.yml Refactor CI pipelines, and add YAML NuGet package generation pipelines ( for CPU, MKLML, NoContribOps) (#1223) 2019-06-14 14:51:03 -07:00
linux-x86-nocontribops-ci-pipeline.yml Avoid downloading test data into C:\ (#1562) 2019-08-05 19:53:15 -07:00
mac-ci-pipeline.yml Add AutoML to 3 main builds. (#1631) 2019-08-16 18:06:16 -07:00
mac-nocontribops-ci-pipeline.yml Avoid downloading test data into C:\ (#1562) 2019-08-05 19:53:15 -07:00
post-merge-jobs.yml Set job timeout for code coverage pipeline to 120min(#1563) 2019-08-06 07:49:31 -07:00
win-arm-crosscompile-ci-pipeline.yml Relax timeout in CI system (#1394) 2019-07-15 15:10:08 -07:00
win-arm64-crosscompile-ci-pipeline.yml Relax timeout in CI system (#1394) 2019-07-15 15:10:08 -07:00
win-ci-pipeline.yml Add AutoML to 3 main builds. (#1631) 2019-08-16 18:06:16 -07:00
win-gpu-ci-pipeline-cuda9.yml
win-gpu-ci-pipeline.yml Add DirectML Execution Provider (#2057) 2019-10-15 06:13:07 -07:00
win-gpu-tensorrt-ci-pipeline.yml Update TensorRT to version 6.0.1.5 (#1966) 2019-10-06 10:40:53 -07:00
win-mklml-ci-pipeline.yml Conditionally export execution provider apis in chsarp (#1724) 2019-09-09 11:17:44 -07:00
win-ngraph-ci-pipeline.yml removed --gen_doc (#1633) 2019-08-16 09:52:36 -07:00
win-nocontribops-ci-pipeline.yml Avoid downloading test data into C:\ (#1562) 2019-08-05 19:53:15 -07:00
win-x86-ci-pipeline.yml Avoid downloading test data into C:\ (#1562) 2019-08-05 19:53:15 -07:00
win-x86-nocontribops-ci-pipeline.yml Avoid downloading test data into C:\ (#1562) 2019-08-05 19:53:15 -07:00