FlexFloat: A Software Library for Transprecision Computing

Abstract

In recent years approximate computing has been extensively explored as a paradigm to design hardware and software solutions that save energy by trading off on the quality of the computed results. In applications that involve numerical computations with wide dynamic range, precision tuning of floating-point (FP) variables is a key knob to leverage the energy/quality trade-off of program results. This aspect assumes maximum relevance in the transprecision computing scenario, where accuracy of data is tuned at fine grain in application code. Performing precision tuning at fine grain requires a software development flow that streamlines the assessment of which variables have "precision slack" within an application. In this paper we introduce FlexFloat, an open-source software library that has been expressly designed to aid the development of transprecision applications. FlexFloat provides a C/C++ interface for supporting multiple FP formats. Unlike alternative libraries, FlexFloat enables to control the bit-width of mantissa and exponent fields and provides advanced features for the collection of runtime statistics, reducing the FP emulation time compared to the state-of-the-art solutions. Its design allows to emulate the behavior of standard IEEE FP types and custom extensions for reduced-precision computation. This makes the library suitable for adoption in multiple contexts, from manual exploration to integration into automatic tools. Experimental findings demonstrate that our approach can be used to perform a complete precision analysis from which deriving multiple program versions depending on the energy/quality trade-off. Furthermore, we show that the adoption of our methodology can lead to a significant reduction of energy consumption even on current commercial hardware (an embedded GPGPU).

Novel Arithmetics to Accelerate Machine Learning Classifiers in Autonomous Driving Applications

“…This topic is also the core of the automotive stream in the H2020 European Processor Initiative (embedded HPC for autonomous driving with BMW as main technology end-user [9,10]) funding this work. To address the above issues new computing arithmetic styles are appearing in research [11][12][13][14][15][16][17][18][19][20] overcoming the classic fixed-point (INT) vs. IEEE-754 floating-point duality in case of embedded DNN (Deep Neural Networks) signal processing. Just as an example, Intel is proposing BFLOAT16 (Brain Floating Point), that has same number of exponent bits of the single-precision floating point allowing in this way to replace binary32 in practical uses although with less precision.…”

“…The Tesla FSD chip exploits a neural processing units using 8-bit by 8-bit integer multiply and a 32-bit integer addition. Transprecision computing for DNN is also proposed in state of art by academia [14] and industry, e.g. IBM and Greenwaves in [15].…”

HOBFLOPS for CNNs: Hardware Optimized Bitslice-Parallel Floating-Point Operations for Convolutional Neural Networks

“…The Flexfloat C++ library of Tagliavini et al, [23], offers alternative FP formats with variable bit-width mantissa and exponents. They demonstrate Flexfloat is up to 2.8× and 2.4× faster than MPFR and SoftFloat, respectively for various benchmarks.…”

“…To address custom-fp in central processing units (CPUs), FP simulators, such as the Flexfloat [23], and Berkeley's SoftFP [13], are available. These simulators support arbitrary or custom range and precision FP such as 16-, 32-, 64-, 80-and 128-bit with corresponding fixed-width mantissa and exponents respectively.…”

Novel Arithmetics in Deep Neural Networks Signal Processing for Autonomous Driving: Challenges and Opportunities

“…The Tesla FSD chip exploits a neural processing units using 8-bit by 8-bit integer multiply and a 32-bit integer addition. Transprecision computing for DNN is also proposed in state of art by academia [20] and industry, e.g. IBM and Greenwaves in [21].…”