Cargando…
Inference of ML models on Intel GPU with SYCL and Intel OneAPI using SOFIE
<!--HTML-->TMVA provides a fast interference system that takes an ONNX model as input and produces compilation-ready standalone C++ scripts as output which can be compiled and executed on CPU architectures. The idea of this project is to extend this capability to generate from the TMVA SOFIE m...
| Autor principal: | |
|---|---|
| Lenguaje: | eng |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | http://cds.cern.ch/record/2869215 |
| _version_ | 1780978268368797696 |
|---|---|
| author | Panagou, Ioanna Maria |
| author_facet | Panagou, Ioanna Maria |
| author_sort | Panagou, Ioanna Maria |
| collection | CERN |
| description | <!--HTML-->TMVA provides a fast interference system that takes an ONNX model as input and produces compilation-ready standalone C++ scripts as output which can be compiled and executed on CPU architectures. The idea of this project is to extend this capability to generate from the TMVA SOFIE model representation code that can be run also on Intel GPU using both SYCL and Intel OneAPI libraries. These will allow for a more efficient evaluation of these models on Intel accelerator hardware. |
| id | cern-2869215 |
| institution | Organización Europea para la Investigación Nuclear |
| language | eng |
| publishDate | 2023 |
| record_format | invenio |
| spelling | cern-28692152023-09-02T19:47:12Zhttp://cds.cern.ch/record/2869215engPanagou, Ioanna MariaInference of ML models on Intel GPU with SYCL and Intel OneAPI using SOFIECERN openlab Summer Student Lightning Talks (2/2)CERN openlab Summer Student Programme 2023<!--HTML-->TMVA provides a fast interference system that takes an ONNX model as input and produces compilation-ready standalone C++ scripts as output which can be compiled and executed on CPU architectures. The idea of this project is to extend this capability to generate from the TMVA SOFIE model representation code that can be run also on Intel GPU using both SYCL and Intel OneAPI libraries. These will allow for a more efficient evaluation of these models on Intel accelerator hardware.oai:cds.cern.ch:28692152023 |
| spellingShingle | CERN openlab Summer Student Programme 2023 Panagou, Ioanna Maria Inference of ML models on Intel GPU with SYCL and Intel OneAPI using SOFIE |
| title | Inference of ML models on Intel GPU with SYCL and Intel OneAPI using SOFIE |
| title_full | Inference of ML models on Intel GPU with SYCL and Intel OneAPI using SOFIE |
| title_fullStr | Inference of ML models on Intel GPU with SYCL and Intel OneAPI using SOFIE |
| title_full_unstemmed | Inference of ML models on Intel GPU with SYCL and Intel OneAPI using SOFIE |
| title_short | Inference of ML models on Intel GPU with SYCL and Intel OneAPI using SOFIE |
| title_sort | inference of ml models on intel gpu with sycl and intel oneapi using sofie |
| topic | CERN openlab Summer Student Programme 2023 |
| url | http://cds.cern.ch/record/2869215 |
| work_keys_str_mv | AT panagouioannamaria inferenceofmlmodelsonintelgpuwithsyclandinteloneapiusingsofie AT panagouioannamaria cernopenlabsummerstudentlightningtalks22 |