Conference
Hybrid Performance Prediction Models for Fully-Connected Neural Networks on MPSoC
| العنوان: | Hybrid Performance Prediction Models for Fully-Connected Neural Networks on MPSoC |
|---|---|
| المؤلفون: | Dariol, Quentin, Le Nours, Sébastien, Pillement, Sébastien, Stemmer, Ralf, Helms, Domenik, Grüttner, Kim |
| المساهمون: | Institut d'Électronique et des Technologies du numéRique (IETR), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Nantes Université - pôle Sciences et technologie, Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ), German Aerospace Center (DLR) |
| المصدر: | Colloque National du GDR SOC2 ; https://hal.science/hal-03758026 ; Colloque National du GDR SOC2, Jun 2022, Strasbourg, France. , 2022 ; https://www.gdr-soc.cnrs.fr/programme-2022/ |
| بيانات النشر: | HAL CCSD |
| سنة النشر: | 2022 |
| المجموعة: | Université de Rennes 1: Publications scientifiques (HAL) |
| مصطلحات موضوعية: | Model of Performance, Multi Processor, SystemC simulation, Artificial Neural Networks, [SPI.TRON]Engineering Sciences [physics]/Electronics, [SPI.OTHER]Engineering Sciences [physics]/Other |
| جغرافية الموضوع: | Strasbourg, France |
| الوصف: | National audience ; Predicting the performance of Artificial NeuralNetworks (ANNs) on embedded multi-core platforms is tedious.Concurrent accesses to shared resources are hard to model dueto congestion effects on the shared communication medium,which affect the performance of the application. In this paperwe present a hybrid modeling environment to enable fast yetaccurate timing prediction for fully-connected ANNs deployedon multi-core platforms. The modeling flow is based on theintegration of an analytical computation time model with acommunication time model which are both calibrated throughmeasurement inside a system level simulation using SystemC. Theproposed flow enables the prediction of the end-to-end latencyfor different mappings of several fully-connected ANNs with anaverage of more than 99 % accuracy. |
| نوع الوثيقة: | conference object still image |
| اللغة: | English |
| Relation: | hal-03758026; https://hal.science/hal-03758026; https://hal.science/hal-03758026/document; https://hal.science/hal-03758026/file/2022_GDR_SOC2_juin_poster_DARIOL.pdf |
| الاتاحة: | https://hal.science/hal-03758026 https://hal.science/hal-03758026/document https://hal.science/hal-03758026/file/2022_GDR_SOC2_juin_poster_DARIOL.pdf |
| Rights: | info:eu-repo/semantics/OpenAccess |
| رقم الانضمام: | edsbas.640F9B3C |
| قاعدة البيانات: | BASE |
| الوصف غير متاح. |