Fetching the paper…

Reading the bibliography…

2017

A Transprecision Floating-Point Platform for Ultra-Low Power Computing

Tagliavini, Giuseppe, Mach, Stefan, Rossi, Davide et al.

Original
PDF
Post on X

Understand

In modern low-power embedded platforms, floating-point (FP) operations emerge as a major contributor to the energy consumption of compute-intensive applications with large dynamic range.

Experimental evidence shows that 50% of the energy consumed by a core and its data memory is related to FP computations.
The adoption of FP formats requiring a lower number of bits is an interesting opportunity to reduce energy consumption, since it allows to simplify the arithmetic circuitry and to reduce the memory bandwidth between memory and registers by enabling vectorization.
From a theoretical point of view, the adoption of multiple FP types perfectly fits with the principle of transprecision computing, allowing fine-grained control of approximation while meeting specified constraints on the precision of final results.

A Transprecision Floating-Point Platform for Ultra-Low Power Computing · Around

Built on

J. R. Hauser, “Handling floating-point exceptions in numeric programs,”
1996
Earlier work this paper cites.
J. Y. F. Tong
2000
Earlier work this paper cites.
D. H. Bailey
2002
Earlier work this paper cites.
H. Brönnimann
2006
Earlier work this paper cites.
L. Fousse
2007
Earlier work this paper cites.
D. Zuras
2008
Earlier work this paper cites.

Similar

C. Bekas
2012
Cited alongside, same era.
C. Rubio-González
2013
Cited alongside, same era.
P. Klavík
2014
Cited alongside, same era.
S. Graillat
2016
Cited alongside, same era.
M. M. Trompouki and L. Kosmidis, “Towards general purpose computations on low-end mobile GPUs,” in
2016
Cited alongside, same era.
W.-F. Chiang
2017
Cited alongside, same era.

Then

M. Gautschi
2017
Closest in time.
——, “Near-Threshold RISC-V Core With DSP Extensions for Scalable IoT Endpoint Devices,”
2017
Closest in time.
N.-M. Ho
2017
Closest in time.
M. Moscato
2017
Closest in time.
T. Rzayev
2017
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…