Add support inference on SYCL devices #9800
Conversation
| - conda-forge | ||
| - intel | ||
| dependencies: | ||
| - python=3.8 |
There was a problem hiding this comment.
should be it 3.8 or higher?
There was a problem hiding this comment.
Have used the same config, as is already used for cpu
Co-authored-by: Nikolay Petrov <[email protected]>
Co-authored-by: Nikolay Petrov <[email protected]>
| @@ -262,7 +269,6 @@ struct Context : public XGBoostParameter<Context> { | |||
| */ | |||
| template <typename CPUFn, typename CUDAFn, typename SYCLFn> | |||
| decltype(auto) DispatchDevice(CPUFn&& cpu_fn, CUDAFn&& cuda_fn, SYCLFn&& sycl_fn) const { | |||
| static_assert(std::is_same_v<std::invoke_result_t<CPUFn>, std::invoke_result_t<CUDAFn>>); | |||
There was a problem hiding this comment.
In case of non-sycl device, the DispatchDevice with this assert will be called. So, it was just a duplicated assert.
| #include "xgboost/context.h" | ||
|
|
||
| namespace xgboost { | ||
| namespace sycl { |
There was a problem hiding this comment.
Are you sure you want to use sycl namespace in the first PR? In the future, you will have to keep doing ::sycl for the global sycl namespace.
There was a problem hiding this comment.
Yes. This option is not perfect, but looks like the best one.
Co-authored-by: Alexandra <[email protected]>
Co-authored-by: Alexandra <[email protected]>
Co-authored-by: Alexandra <[email protected]>
Co-authored-by: Alexandra <[email protected]>
Co-authored-by: Alexandra <[email protected]>
Co-authored-by: Alexandra <[email protected]>
plugin/sycl/README.md
Outdated
| ``` | ||
|
|
||
| ## Dependencies | ||
| To build the plugin, install [Intel® oneAPI DPC++/C++ Compiler](https://www.intel.com/content/www/us/en/developer/tools/oneapi/dpc-compiler.html). |
There was a problem hiding this comment.
I think we also should mention that once build - for running plugin you have to resolve DPC compiler runtime + drivers
|
Hi, could you please help take a look into the CI errors? |
working on it right now. Will fix it asap. |
|
no worries, we trigger AWS workers for the CI manually. It was just a friendly reminder that the CI has been triggered. |
|
In continuation of #9691
This PR adds experimental support of prediction with SYCL devices.
The key changes are:
sycl_predictor, which is calling if SYCL device parameter is specified.PredictBatchmethod has a native SYCL implementation.-DPLUGIN_SYCL=ONforcmake.