Numerical computing on the web: benchmarking for the future

Herrera, David; Chen, Hanfeng; Lavoie, Erick; Hendren, Laurie

doi:10.1145/3276945.3276968

Cited by 17 publications

(12 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The smartphone is a Samsung, model S8+ (), with an octacore Exynos 8895 system-on-chip (4 × 2.3 GHz M2 Mongoose & 4 × 1.7 GHz Cortex-A53 ‘GTS’) and 4 GB of LPDDR4 RAM 1794 MHz. This smartphone has been used previously in IoT approaches and numerical computing [29]. The computation was performed by using its internal storage of 64 GB UFS 2.1.…”

Section: Methodsmentioning

confidence: 99%

On the Possibility of Predicting Glycaemia ‘On the Fly’ with Constrained IoT Devices in Type 1 Diabetes Mellitus Patients

Rodríguez‐Rodríguez

Rodríguez

Chatzigiannakis

et al. 2019

Sensors

View full text Add to dashboard Cite

Type 1 Diabetes Mellitus (DM1) patients are used to checking their blood glucose levels several times per day through finger sticks and, by subjectively handling this information, to try to predict their future glycaemia in order to choose a proper strategy to keep their glucose levels under control, in terms of insulin dosages and other factors. However, recent Internet of Things (IoT) devices and novel biosensors have allowed the continuous collection of the value of the glucose level by means of Continuous Glucose Monitoring (CGM) so that, with the proper Machine Learning (ML) algorithms, glucose evolution can be modeled, thus permitting a forecast of this variable. On the other hand, glycaemia dynamics require that such a model be user-centric and should be recalculated continuously in order to reflect the exact status of the patient, i.e., an ‘on-the-fly’ approach. In order to avoid, for example, the risk of being disconnected from the Internet, it would be ideal if this task could be performed locally in constrained devices like smartphones, but this would only be feasible if the execution times were fast enough. Therefore, in order to analyze if such a possibility is viable or not, an extensive, passive, CGM study has been carried out with 25 DM1 patients in order to build a solid dataset. Then, some well-known univariate algorithms have been executed in a desktop computer (as a reference) and two constrained devices: a smartphone and a Raspberry Pi, taking into account only past glycaemia data to forecast glucose levels. The results indicate that it is possible to forecast, in a smartphone, a 15-min horizon with a Root Mean Squared Error (RMSE) of 11.65 mg/dL in just 16.15 s, employing a 10-min sampling of the past 6 h of data and the Random Forest algorithm. With the Raspberry Pi, the computational effort increases to 56.49 s assuming the previously mentioned parameters, but this can be improved to 34.89 s if Support Vector Machines are applied, achieving in this case an RMSE of 19.90 mg/dL. Thus, this paper concludes that local on-the-fly forecasting of glycaemia would be affordable with constrained devices.

show abstract

Section: Methodsmentioning

confidence: 99%

On the Possibility of Predicting Glycaemia ‘On the Fly’ with Constrained IoT Devices in Type 1 Diabetes Mellitus Patients

Rodríguez‐Rodríguez

Rodríguez

Chatzigiannakis

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Our focus in developing Pando has been to easily tap into the computing power of personal devices already owned by the general public. The collective performance of personal devices has previously been shown to be significant both when considering the collection of devices owned by individuals and the aggregate performance of mobile devices of co-workers [52,70]. The design of Pando has also been shown to scale up to at least a thousand browsers when combined with a fat-tree overlay [71] but had not yet been tested on wide-area network deployments.…”

Section: Discussionmentioning

confidence: 99%

“…First, they are compatible with a wide number of personal devices, from smartphones and embedded devices to tablets, laptop, and desktops computers (DP2). Second, virtual machines in modern browsers execute numerical applications in JavaScript at a speed within a factor of 3 of equivalent numerical code written in C [52,57]. A large variety of native applications, as represented by the SPEC CPU2006 and CPU2017 benchmarks and originally written in C for Unix systems, can also be executed in browsers supporting WebAssembly [50] without modification to the original source code by using Browsix-WASM [54]: the applications then run with an average slowdown of only 45% to 55% and peak slowdown of 2.5x compared to a native execution.…”

Section: Technology Choicesmentioning

confidence: 99%

“…These devices represent a wide variety of CPU and OS choices, as well as a computing performance. We favoured the use of close versions of Firefox on laptops for consistency so the experiments would focus on the variations on CPU speed and because it is generally the fastest on numerical benchmarks [52]. We also used the minimum number of cores that provided close to the maximum performance, shown between brackets in Table 2; using more cores typically did not significantly increase the total throughput.…”

Section: Lan: Personal Devicesmentioning

confidence: 99%

“…More than 1.5 billion smartphones were sold in the world in 2018 [25] and the computing power of the highest-end devices today rivals that of desktops and laptops [52]. They collectively represent an immense source of largely untapped computing power.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Pando: Personal Volunteer Computing in Browsers

Lavoie,

Hendren,

Desprez

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

The large penetration and continued growth in ownership of personal electronic devices represents a freely available and largely untapped source of computing power. To leverage those, we present Pando, a new volunteer computing tool based on a declarative concurrent programming model and implemented using JavaScript, WebRTC, and WebSockets. This tool enables a dynamically varying number of failure-prone personal devices contributed by volunteers to parallelize the application of a function on a stream of values, by using the devices' browsers. We show that Pando can provide throughput improvements compared to a single personal device, on a variety of compute-bound applications including animation rendering and image processing. We also show the flexibility of our approach by deploying Pando on personal devices connected over a local network, on Grid5000, a French-wide computing grid in a virtual private network, and seven PlanetLab nodes distributed in a wide area network over Europe. CCS Concepts• Computing methodologies → Distributed computing methodologies; • Software and its engineering → Development frameworks and environments;

show abstract

Face Recognition Efficiency Enhancements Using Tensorflow and WebAssembly: A Practical Approach

Manso

Gallardo

2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

Numerical computing on the web: benchmarking for the future

Cited by 17 publications

References 18 publications

On the Possibility of Predicting Glycaemia ‘On the Fly’ with Constrained IoT Devices in Type 1 Diabetes Mellitus Patients

On the Possibility of Predicting Glycaemia ‘On the Fly’ with Constrained IoT Devices in Type 1 Diabetes Mellitus Patients

Pando: Personal Volunteer Computing in Browsers

Face Recognition Efficiency Enhancements Using Tensorflow and WebAssembly: A Practical Approach

Contact Info

Product

Resources

About