ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper AIWareK: Compiling PyTorch Model for AI Processor Using MLIR Framework
Cited 1 time in scopus Share share facebook twitter linkedin kakaostory
Authors
Hyunjeong Kwon, Hyun Mi Kim, Chun-Gi Lyuh, Jinkyu Kim, Jinho Han, Youngsu Kwon
Issue Date
2022-06
Citation
International Conference on Artificial Intelligence Circuits and Systems (AICAS) 2022, pp.463-465
Language
English
Type
Conference Paper
DOI
https://dx.doi.org/10.1109/AICAS54282.2022.9869913
Abstract
Deep learning compiler becomes necessary with the active research on AI hardware. This work compiles PyTorch models into target hardware codes using MLIR framework. The compiler first constructs a graph from the PyTorch model using TorchScript tracing. To construct the graph, our domain-specific parser generates an abstract syntax tree using tokens generated from the lexer. Then, the graph IR (GIR) is built and lowered into the kernel IR (KIR) and the processor IR (PIR) in MLIR framework. PIR becomes the input of the backed compiler that generates target machine codes. Experimental result shows that AIWareK compiled ResNet18 in 7.67 seconds, yielding 1.16e-03 mean absolute error.
KSP Keywords
Domain-specific, Experimental Result, Machine code, Mean Absolute Error, abstract syntax tree, deep learning(DL)