DARTS.5.1.4.pdf
- Filesize: 298 kB
- 3 pages
Document
API Comparison of CPU-To-GPU Command Offloading Latency on Embedded Platforms (Artifact)
Authors
Nicola Capodieci 
,
Marco Solieri ,
Marko Bertogna
-
Part of:
Issue:
Special Issue of the 31st Euromicro Conference on Real-Time Systems (ECRTS 2019)
Volume: DARTS, Volume 5 (ECOOP 2019)
Conference: Euromicro Conference on Real-Time Systems (ECRTS)
Journal: Dagstuhl Artifacts Series (DARTS) - License:
Creative Commons Attribution 3.0 Germany license
- Publication Date: 2019-07-08
Artifact Description
Document Identifiers
Author Details
Cite As Get BibTex
Roberto Cavicchioli, Nicola Capodieci, Marco Solieri, and Marko Bertogna. API Comparison of CPU-To-GPU Command Offloading Latency on Embedded Platforms (Artifact). In Special Issue of the 31st Euromicro Conference on Real-Time Systems (ECRTS 2019). Dagstuhl Artifacts Series (DARTS), Volume 5, Issue 1, pp. 4:1-4:3, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)
https://doi.org/10.4230/DARTS.5.1.4
Artifact
DARTS-5-1-4-artifact-3978b2398eab0687e51009e681c0ada9.tgz
(Filesize: 37 kB)
MD5 Sum:
3978b2398eab0687e51009e681c0ada9
(Get MD5 Sum)
Abstract
High-performance heterogeneous embedded platforms allow offloading of parallel workloads to an integrated accelerator, such as General Purpose-Graphic Processing Units (GP-GPUs). A time-predictable characterization of task submission is a must in real-time applications. We provide a profiler of the time spent by the CPU for submitting stereotypical GP-GPU workload shaped as a Deep Neural Network of parameterized complexity. The submission is performed using the latest API available: NVIDIA CUDA, including its various techniques, and Vulkan. Complete automation for the test on Jetson Xavier is also provided by scripts that install software dependencies, run the experiments, and collect results in a PDF report.
Subject Classification
ACM Subject Classification
- Computer systems organization → System on a chip
- Computer systems organization → Real-time system architecture
Keywords
- GPU
- Applications
- Heterogeneus systems
Metrics
- Access Statistics
-
Total Accesses (updated on a weekly basis)
0PDF Downloads