TY - GEN
T1 - Towards Rapid Exploration of Heterogeneous TinyML Systems using Virtual Platforms and TVM's UMA
AU - Ahmadifarsani, Samira
AU - Stahl, Rafael
AU - Van Kempen, Philipp
AU - Mueller-Gritschneder, Daniel
AU - Schlichtmann, Ulf
N1 - Publisher Copyright:
© 2023 is held by the owner/author(s). Publication rights licensed to ACM.
PY - 2023/9/21
Y1 - 2023/9/21
N2 - The rapid setup of deep learning compilation toolchains for heterogeneous TinyML systems with a processor and dedicated ML accelerator is still at an early stage. Here, achieving the most optimal combination of targets for a TinyML application on ultra-low-power edge devices demands additional benchmarking solutions to estimate the final performance.Apache TVM's Universal Modular Accelerator (UMA) interface as an easy-to-use API is a promising speed-up approach to this scope. In this paper, we integrate a simple custom dedicated accelerator into TVM using UMA to offload the quantized convolution operators in order to demonstrate such an approach. Furthermore, we leverage MLonMCU tool and its capability of virtual prototyping to estimate and explore the performance improvement achieved by the accelerator.
AB - The rapid setup of deep learning compilation toolchains for heterogeneous TinyML systems with a processor and dedicated ML accelerator is still at an early stage. Here, achieving the most optimal combination of targets for a TinyML application on ultra-low-power edge devices demands additional benchmarking solutions to estimate the final performance.Apache TVM's Universal Modular Accelerator (UMA) interface as an easy-to-use API is a promising speed-up approach to this scope. In this paper, we integrate a simple custom dedicated accelerator into TVM using UMA to offload the quantized convolution operators in order to demonstrate such an approach. Furthermore, we leverage MLonMCU tool and its capability of virtual prototyping to estimate and explore the performance improvement achieved by the accelerator.
KW - TinyML
KW - TVM
KW - UMA
KW - virtual prototyping
UR - http://www.scopus.com/inward/record.url?scp=85196357234&partnerID=8YFLogxK
U2 - 10.1145/3615338.3618121
DO - 10.1145/3615338.3618121
M3 - Conference contribution
AN - SCOPUS:85196357234
T3 - Proceedings - 2023 IEEE/ACM International Workshop on Compilers, Deployment, and Tooling for Edge AI, CODAI 2023
SP - 6
EP - 10
BT - Proceedings - 2023 IEEE/ACM International Workshop on Compilers, Deployment, and Tooling for Edge AI, CODAI 2023
PB - Association for Computing Machinery, Inc
T2 - 2023 IEEE/ACM International Workshop on Compilers, Deployment, and Tooling for Edge AI, CODAI 2023
Y2 - 21 September 2023
ER -