TransLib: A Library to Explore Transprecision Floating-Point Arithmetic on Multi-Core IoT End-Nodes


METADATA ONLY
Loading...

Date

2023

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Reduced-precision floating-point (FP) arithmetic is being widely adopted to reduce memory footprint and execution time on battery-powered Internet of Things (IoT) end-nodes. However, reduced precision computations must meet end-do-end precision constraints to be acceptable at the application level. This work introduces TransLib(1), an open-source kernel library based on transprecision computing principles, which provides knobs to exploit different FP data types (i.e., float, float16, and bfloat16), also considering the trade-off between homogeneous and mixed-precision solutions. We demonstrate the capabilities of the proposed library on PULP, a 32-bit microcontroller (MCU) coupled with a parallel, programmable accelerator. On average, TransLib kernels achieve an IPC of 0.94 and a speed-up of 1.64x using 16-bit vectorization. The parallel variants achieve a speed-up of 1.97x, 3.91x, and 7.59x on 2, 4, and 8 cores, respectively. The memory footprint reduction is between 25% and 50%. Finally, we show that mixed-precision variants increase the accuracy by 30x at the cost of 2.09x execution time and 1.35x memory footprint compared to float16 vectorized.

Publication status

published

Editor

Book title

2023 Design, Automation & Test in Europe Conference & Exhibition (DATE)

Journal / series

Volume

Pages / Article No.

10136916

Publisher

IEEE

Event

26th Design, Automation and Test in Europe Conference and Exhibition (DATE 2023)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Transprecision computing; IoT end-nodes; Parallel programming; SIMD vectorization

Organisational unit

03996 - Benini, Luca / Benini, Luca check_circle

Notes

Funding

Related publications and datasets