The transprecision computing paradigm: Concept, design, and applications

Malossi, A. Cristiano I.; Schaffner, Michael; Molnos, Anca; Gammaitoni, L.; Tagliavini, Giuseppe; Emerson, Andrew; Tomás, Andrés E.; Nikolopoulos, Dimitrios S.; Flamand, Éric; Wehn, Norbert

doi:10.23919/date.2018.8342176

Cited by 61 publications

(38 citation statements)

References 12 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…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.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Novel Arithmetics to Accelerate Machine Learning Classifiers in Autonomous Driving Applications

Cococcioni

Rossi

Ruffaldi³

et al. 2019

2019 26th IEEE International Conference on Electronics, Circuits and Systems (ICECS)

View full text Add to dashboard Cite

Autonomous driving techniques frequently need the clustering and the classification of data coming from several input sensors, like cameras, radar and lidars. These sub-tasks need to be implemented0020in real-time in embedded on-board computing units. The trend for data classification and clustering in the signal processing community is moving towards machine learning (ML) algorithms. One of them, which plays a central role, is the k-nearest neighbors (k-NN) algorithm. To meet stringent requirements in terms of real-time computing capability and circuit/memory complexity, ML accelerators are needed. Innovation is required in terms of computing arithmetic since classic integer numbers lead to low classification accuracy with respect to the needs of safety critical applications like autonomous driving. Instead, floating numbers require too much circuit and memory. To overcome these issues the paper shows that the use of a new format, called Posit, implemented in a new cppPosit software library, can lead to a k-NN implementation having the same accuracy of floats, but with halved bit-size. This means that a Posit Processing Unit (PPU) reduces by a factor higher than 2 the data transfer and storage complexity of ML accelerators. We also prove that a LUTbased complete tabulated implementation of a PPU for a 8-bit requires just 64 kB storage size, compliant with memoryconstrained devices.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Transprecision computing for DNN is also proposed in state of art by academia [14] and industry, e.g. IBM and Greenwaves in [15]. Signal processing sparsity has been exploited recently [16,17] to achieve a compression of ML complexity to reach real-time computing on edge devices.…”

Section: Introductionmentioning

confidence: 99%

Novel Arithmetics to Accelerate Machine Learning Classifiers in Autonomous Driving Applications

Cococcioni

Rossi

Ruffaldi³

et al. 2019

2019 26th IEEE International Conference on Electronics, Circuits and Systems (ICECS)

View full text Add to dashboard Cite

show abstract

“…Approximation techniques. During the last years, the most promising approaches to achieve performance gains are represented by the trade-off with application accuracy [30], [31]. Algorithm-level approximate computing techniques are well-known in literature [32], [33], [3], and represent also an important challenge for in HPC applica-tions [34], [35].…”

Section: Related Workmentioning

confidence: 99%

Tunable approximations to control time-to-solution in an HPC molecular docking Mini-App

et al. 2020

View full text Add to dashboard Cite

The drug discovery process involves several tasks to be performed in vivo, in vitro and in silico. Molecular docking is a task typically performed in silico. It aims at finding the three-dimensional pose of a given molecule when it interacts with the target protein binding site. This task is often done for virtual screening a huge set of molecules to find the most promising ones, which will be forwarded to the later stages of the drug discovery process. Given the huge complexity of the problem, molecular docking cannot be solved by exploring the entire space of the ligand poses. State-of-the-art approaches face the problem by sampling the space of the ligand poses to generate results in a reasonable time budget. In this work, we improve the geometric approach to molecular docking by introducing tunable approximations. In particular, we analyzed and enriched the original implementation with tunable software knobs to explore and control the performance-accuracy tradeoffs. We modeled time-to-solution of the virtual screening task as a function of software knobs, input data features, and available computational resources. Therefore, the application can autotune its configuration according to a user-defined time budget. We used a Mini-App derived by LiGenDock -a state-of-the-art molecular docking application -to validate the proposed approach. We run the enhanced Mini-App on an HPC system by using a very large database of pockets and ligands. The proposed approach exposes a time-to-solution interval spanning more than one order of magnitude with accuracy degradation up to 30%, more in general providing different accuracy levels according to the needs of the virtual screening campaign.

show abstract

“…Great examples of compact formats are Brain Floats (BFLOAT) and Flexpoint [4,5] that consist in an optimized version of the 16-bit standard floating point number IEEE 754) used by Google for their TPU (tensor processing unit) engines. Other formats also come from the concept of transprecision computing [6,7] (NVIDIA Turing architectures allow computation with 4-, 8-, and 32-bit integers and with 16-and 32-bit floats). The up-and-coming Posit format has been theoretically [8][9][10] and practically [11] proven to be a perfect replacement for IEEE float numbers when applied to DNNs in terms of efficiency and accuracy.…”

Section: Introductionmentioning

confidence: 99%

Fast Approximations of Activation Functions in Deep Neural Networks when using Posit Arithmetic

Cococcioni

Rossi

Ruffaldi³

et al. 2020

Sensors

View full text Add to dashboard Cite

With increasing real-time constraints being put on the use of Deep Neural Networks (DNNs) by real-time scenarios, there is the need to review information representation. A very challenging path is to employ an encoding that allows a fast processing and hardware-friendly representation of information. Among the proposed alternatives to the IEEE 754 standard regarding floating point representation of real numbers, the recently introduced Posit format has been theoretically proven to be really promising in satisfying the mentioned requirements. However, with the absence of proper hardware support for this novel type, this evaluation can be conducted only through a software emulation. While waiting for the widespread availability of the Posit Processing Units (the equivalent of the Floating Point Unit (FPU)), we can already exploit the Posit representation and the currently available Arithmetic-Logic Unit (ALU) to speed up DNNs by manipulating the low-level bit string representations of Posits. As a first step, in this paper, we present new arithmetic properties of the Posit number system with a focus on the configuration with 0 exponent bits. In particular, we propose a new class of Posit operators called L1 operators, which consists of fast and approximated versions of existing arithmetic operations or functions (e.g., hyperbolic tangent (TANH) and extended linear unit (ELU)) only using integer arithmetic. These operators introduce very interesting properties and results: (i) faster evaluation than the exact counterpart with a negligible accuracy degradation; (ii) an efficient ALU emulation of a number of Posits operations; and (iii) the possibility to vectorize operations in Posits, using existing ALU vectorized operations (such as the scalable vector extension of ARM CPUs or advanced vector extensions on Intel CPUs). As a second step, we test the proposed activation function on Posit-based DNNs, showing how 16-bit down to 10-bit Posits represent an exact replacement for 32-bit floats while 8-bit Posits could be an interesting alternative to 32-bit floats since their performances are a bit lower but their high speed and low storage properties are very appealing (leading to a lower bandwidth demand and more cache-friendly code). Finally, we point out how small Posits (i.e., up to 14 bits long) are very interesting while PPUs become widespread, since Posit operations can be tabulated in a very efficient way (see details in the text).

show abstract

The transprecision computing paradigm: Concept, design, and applications

Cited by 61 publications

References 12 publications

Novel Arithmetics to Accelerate Machine Learning Classifiers in Autonomous Driving Applications

Novel Arithmetics to Accelerate Machine Learning Classifiers in Autonomous Driving Applications

Tunable approximations to control time-to-solution in an HPC molecular docking Mini-App

Fast Approximations of Activation Functions in Deep Neural Networks when using Posit Arithmetic

Contact Info

Product

Resources

About