PRIMAL: Power Inference using Machine Learning

This paper introduces PRIMAL, a novel learning-based frame-work that enables fast and accurate power estimation for ASIC designs. PRIMAL trains machine learning (ML) models with design verification testbenches for characterizing the power of reusable circuit building blocks. The trained models can t...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of the 56th Annual Design Automation Conference 2019 s. 1 - 6
Hlavní autoři: Zhou, Yuan, Ren, Haoxing, Zhang, Yanqing, Keller, Ben, Khailany, Brucek, Zhang, Zhiru
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: ACM 01.06.2019
Témata:
Analytical models
Encoding
Estimation
Integrated circuit modeling
Logic gates
machine learning
Power estimation
Registers
Solid modeling
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This paper introduces PRIMAL, a novel learning-based frame-work that enables fast and accurate power estimation for ASIC designs. PRIMAL trains machine learning (ML) models with design verification testbenches for characterizing the power of reusable circuit building blocks. The trained models can then be used to generate detailed power profiles of the same blocks under different workloads. We evaluate the performance of several established ML models on this task, including ridge regression, gradient tree boosting, multi-layer perceptron, and convolutional neural network (CNN). For average power estimation, ML-based techniques can achieve an average error of less than 1% across a diverse set of realistic benchmarks, outperforming a commercial RTL power estimation tool in both accuracy and speed (15x faster). For cycle-by-cycle power estimation, PRIMAL is on average 50x faster than a commercial gate-level power analysis tool, with an average error less than 5%. In particular, our CNN-based method achieves a 35x speed-up and an error of 5.2% for cycle-by-cycle power estimation of a RISC-V processor core. Furthermore, our case study on a NoC router shows that PRIMAL can achieve a small estimation error of 4.5% using cycle-approximate traces from SystemC simulation.
DOI:10.1145/3316781.3317884