cfaed Publications

BASE2: An IR for Binary Numeral Types

Reference

Karl F. A. Friebel, Jiahong Bi, Jeronimo Castrillon, "BASE2: An IR for Binary Numeral Types", In Proceeding: 13th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies (HEART 2023), Association for Computing Machinery, pp. 19–26, New York, NY, USA, Jun 2023. [doi]

Abstract

Custom data types and arbitrary-precision arithmetic are often key for efficient hardware designs on Field Programmable Gate Array (FPGA) platforms. Current end-to-end flows incorporating quantization are not only domain-specific, but also tightly integrated and not repurposable. Abstractions for arbitrary-precision arithmetic are generally vendor-specific, and results are hardly portable across platforms. In this work, we present a new Intermediate Representation (IR), base2, to address the programmability issues of custom data types in reconfigurable hardware. We contextualize our proposal in the greater LLVM (llvm) ecosystem, where we show how existing abstractions can be simplified and unified. We implement base2 in Multi-Level Intermediate Representation (MLIR), which allows it to be used in a variety of existing and future target-agnostic front-ends. We demonstrate the power of our model by applying it to sample kernels and evaluating the accuracy of the result. For these samples, we achieve interoperability with an existing end-to-end High-Level Synthesis (HLS) flow.

Bibtex

@InProceedings{friebel_heart23,
author = {Karl F. A. Friebel and Jiahong Bi and Jeronimo Castrillon},
booktitle = {13th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies (HEART 2023)},
title = {{BASE2}: An {IR} for Binary Numeral Types},
doi = {10.1145/3597031.3597048},
isbn = {9798400700439},
location = {Kusatsu, Japan},
pages = {19--26},
publisher = {Association for Computing Machinery},
series = {HEART2023},
url = {https://doi.org/10.1145/3597031.3597048},
abstract = {Custom data types and arbitrary-precision arithmetic are often key for efficient hardware designs on Field Programmable Gate Array (FPGA) platforms. Current end-to-end flows incorporating quantization are not only domain-specific, but also tightly integrated and not repurposable. Abstractions for arbitrary-precision arithmetic are generally vendor-specific, and results are hardly portable across platforms. In this work, we present a new Intermediate Representation (IR), base2, to address the programmability issues of custom data types in reconfigurable hardware. We contextualize our proposal in the greater LLVM (llvm) ecosystem, where we show how existing abstractions can be simplified and unified. We implement base2 in Multi-Level Intermediate Representation (MLIR), which allows it to be used in a variety of existing and future target-agnostic front-ends. We demonstrate the power of our model by applying it to sample kernels and evaluating the accuracy of the result. For these samples, we achieve interoperability with an existing end-to-end High-Level Synthesis (HLS) flow.},
address = {New York, NY, USA},
month = jun,
numpages = {8},
year = {2023},
}

Downloads

2306_Friebel_HEART [PDF]

Permalink

https://esim-project.eu/publications?pubId=3554


Go back to publications list