OSCA: End-to-End Serial Stochastic Computing Neural Acceleration with Fine-Grained Scaling and Piecewise Activation

End-to-end stochastic computing (SC) emerges as a promising paradigm for efficient neural acceleration. However, existing serial SC accelerators face serious accuracy challenges due to errors in addition, limited activation compatibility, and limited bitstream multiplication. In this paper, we propo...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Digest of technical papers - IEEE/ACM International Conference on Computer-Aided Design s. 1 - 9
Hlavní autoři: Hu, Yixuan, Jia, Yikang, Li, Meng, Wang, Yuan, Wang, Runsheng, Huang, Ru
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: ACM 27.10.2024
Témata:
Accuracy
Adders
Binary sequences
Circuit synthesis
Correlation
Design automation
End-to-end serial stochastic computing
Faces
Fine-grained scaling
Piecewise activation function
Quantization (signal)
Root mean square
ISSN:1558-2434
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:End-to-end stochastic computing (SC) emerges as a promising paradigm for efficient neural acceleration. However, existing serial SC accelerators face serious accuracy challenges due to errors in addition, limited activation compatibility, and limited bitstream multiplication. In this paper, we propose OSCA, an accurate yet efficient end-to-end serial SC accelerator. OSCA features fine-grained scaling control in the SC adder to minimize quantization error and introduces novel segment units for piecewise approximation of complex nonlinear activation functions. We also design an integerbitstream multiplier that guarantees accuracy regardless of the correlation between input bitstreams. Compared to the serial baseline accelerator of INT8 precision, we can achieve a 30.18 % reduction in root mean square error (RMSE) along with an 87.75 % area-delay product (ADP) reduction. Moreover, compared to a more accurate parallel accelerator, OSCA achieves a 92.05 % ADP reduction with a 12.54 \times improvement in area efficiency, while also increasing inference accuracy by 0.44 % and 0.86 %.
ISSN:1558-2434
DOI:10.1145/3676536.3676652