Articles de revistahttp://hdl.handle.net/2117/31242024-03-28T15:51:27Z2024-03-28T15:51:27ZThe MAMe dataset: On the relevance of high resolution and variable shape image propertiesParés Pont, FerranArias Duart, AnnaGarcía Gasulla, DarioCampo Francés, GemaViladrich Iglesias, NinaAyguadé Parra, EduardLabarta Mancho, Jesús Joséhttp://hdl.handle.net/2117/4023632024-02-26T13:15:15Z2024-02-21T09:41:14ZThe MAMe dataset: On the relevance of high resolution and variable shape image properties
Parés Pont, Ferran; Arias Duart, Anna; García Gasulla, Dario; Campo Francés, Gema; Viladrich Iglesias, Nina; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José
The mostcommon approach in image classification tasks is to resize all images in the dataset to a unique shape, while reducing their resolution to a size that makes experimentation at scale easier. This practice has benefits from a computational perspective, but it entails negative side-effects on performance due to loss of information and image deformation. In this work we introduce the MAMe dataset, an image classification dataset with remarkable properties of high resolution and variable shape. The goal of MAMe is to provide a tool for studying the impact of such properties in image classification, while motivating research in the topic. The MAMe dataset contains thousands of artworks from three different museums, and proposes a classification task consisting on differentiating between 29 mediums (i.e., materials and techniques) supervised by art experts. After analyzing the novelty of MAMe in the context of the current image classification tasks, a thorough description of the task is provided, along with statistics of the dataset. Experiments are conducted to evaluate the impact of using high resolution images, variable shape inputs, as well as both properties at the same time. Results illustrate the positive impact in performance when using high resolution images, while highlighting the lack of solutions to exploit variable shapes. An additional experiment exposes the distinctiveness between the MAMe dataset and the prototypical ImageNet dataset, showing that performance improves due to information gain and resolution gain. Finally, the baselines are inspected using explainability methods and expert knowledge, in order to gain insights about the challenges that remain ahead.
2024-02-21T09:41:14ZParés Pont, FerranArias Duart, AnnaGarcía Gasulla, DarioCampo Francés, GemaViladrich Iglesias, NinaAyguadé Parra, EduardLabarta Mancho, Jesús JoséThe mostcommon approach in image classification tasks is to resize all images in the dataset to a unique shape, while reducing their resolution to a size that makes experimentation at scale easier. This practice has benefits from a computational perspective, but it entails negative side-effects on performance due to loss of information and image deformation. In this work we introduce the MAMe dataset, an image classification dataset with remarkable properties of high resolution and variable shape. The goal of MAMe is to provide a tool for studying the impact of such properties in image classification, while motivating research in the topic. The MAMe dataset contains thousands of artworks from three different museums, and proposes a classification task consisting on differentiating between 29 mediums (i.e., materials and techniques) supervised by art experts. After analyzing the novelty of MAMe in the context of the current image classification tasks, a thorough description of the task is provided, along with statistics of the dataset. Experiments are conducted to evaluate the impact of using high resolution images, variable shape inputs, as well as both properties at the same time. Results illustrate the positive impact in performance when using high resolution images, while highlighting the lack of solutions to exploit variable shapes. An additional experiment exposes the distinctiveness between the MAMe dataset and the prototypical ImageNet dataset, showing that performance improves due to information gain and resolution gain. Finally, the baselines are inspected using explainability methods and expert knowledge, in order to gain insights about the challenges that remain ahead.Can we trust undervolting in FPGA-based deep learning designs at harsh conditions?Koc, FahrettinSalami, BehzadErgin, OguzUnsal, Osman SabriCristal Kestelman, Adriánhttp://hdl.handle.net/2117/3961952023-11-13T09:27:55Z2023-11-09T13:20:44ZCan we trust undervolting in FPGA-based deep learning designs at harsh conditions?
Koc, Fahrettin; Salami, Behzad; Ergin, Oguz; Unsal, Osman Sabri; Cristal Kestelman, Adrián
As more Neural Networks on Field Programmable Gate Arrays (FPGAs) are used in a wider context, the importance of power efficiency increases. However, the focus on power should never compromise application accuracy. One technique to increase power efficiency is reducing the FPGAs' supply voltage ("undervolting"), which can cause accuracy problems. Therefore, careful design-time considerations are required for correct configuration without hindering the target accuracy. This fact becomes especially important for autonomous systems, edge-computing, or data-centers. This study reveals the impact of undervolting in harsh environmental conditions on the accuracy and power efficiency of the convolutional neural network benchmarks. We perform the comprehensive testing in a calibrated infrastructure at controlled temperatures (between -40C and 50C) and four distinct humidity levels (40%, 50%, 70%, 80%) for off-the-shelf FPGAs. We show the voltage guard-band shift with temperature is linear and propose new reliable undervolting designs providing a 65% increase in power efficiency (GOPS/W).
2023-11-09T13:20:44ZKoc, FahrettinSalami, BehzadErgin, OguzUnsal, Osman SabriCristal Kestelman, AdriánAs more Neural Networks on Field Programmable Gate Arrays (FPGAs) are used in a wider context, the importance of power efficiency increases. However, the focus on power should never compromise application accuracy. One technique to increase power efficiency is reducing the FPGAs' supply voltage ("undervolting"), which can cause accuracy problems. Therefore, careful design-time considerations are required for correct configuration without hindering the target accuracy. This fact becomes especially important for autonomous systems, edge-computing, or data-centers. This study reveals the impact of undervolting in harsh environmental conditions on the accuracy and power efficiency of the convolutional neural network benchmarks. We perform the comprehensive testing in a calibrated infrastructure at controlled temperatures (between -40C and 50C) and four distinct humidity levels (40%, 50%, 70%, 80%) for off-the-shelf FPGAs. We show the voltage guard-band shift with temperature is linear and propose new reliable undervolting designs providing a 65% increase in power efficiency (GOPS/W).Towards EXtreme scale technologies and accelerators for euROhpc hw/Sw supercomputing applications for exascale: The TEXTAROSSA approachAgosta, GiovanniAldinucci, MarcoÁlvarez Martínez, CarlosAmmendola, RobertoArfat, YasirBeaumont, OlivierBernaschi, MassimoFilgueras Izquierdo, AntonioMartorell Bofill, XavierVidal, Miquelhttp://hdl.handle.net/2117/3747062022-10-30T05:45:37Z2022-10-20T07:45:14ZTowards EXtreme scale technologies and accelerators for euROhpc hw/Sw supercomputing applications for exascale: The TEXTAROSSA approach
Agosta, Giovanni; Aldinucci, Marco; Álvarez Martínez, Carlos; Ammendola, Roberto; Arfat, Yasir; Beaumont, Olivier; Bernaschi, Massimo; Filgueras Izquierdo, Antonio; Martorell Bofill, Xavier; Vidal, Miquel
In the near future, Exascale systems will need to bridge three technology gaps to achieve high performance while remaining under tight power constraints: energy efficiency and thermal control; extreme computation efficiency via HW acceleration and new arithmetic; methods and tools for seamless integration of reconfigurable accelerators in heterogeneous HPC multi-node platforms. TEXTAROSSA addresses these gaps through a co-design approach to heterogeneous HPC solutions, supported by the integration and extension of HW and SW IPs, programming models, and tools derived from European research.
2022-10-20T07:45:14ZAgosta, GiovanniAldinucci, MarcoÁlvarez Martínez, CarlosAmmendola, RobertoArfat, YasirBeaumont, OlivierBernaschi, MassimoFilgueras Izquierdo, AntonioMartorell Bofill, XavierVidal, MiquelIn the near future, Exascale systems will need to bridge three technology gaps to achieve high performance while remaining under tight power constraints: energy efficiency and thermal control; extreme computation efficiency via HW acceleration and new arithmetic; methods and tools for seamless integration of reconfigurable accelerators in heterogeneous HPC multi-node platforms. TEXTAROSSA addresses these gaps through a co-design approach to heterogeneous HPC solutions, supported by the integration and extension of HW and SW IPs, programming models, and tools derived from European research.Vector extensions in COTS processors to increase guaranteed performance in real-time systemsPujol Torramorell, RogerJorba Jorba, JosepTabani, HamidKosmidis, LeonidasMezzetti, EnricoAbella Ferrer, JaumeCazorla Almeida, Francisco Javierhttp://hdl.handle.net/2117/3739082023-10-15T04:03:29Z2022-10-04T10:06:05ZVector extensions in COTS processors to increase guaranteed performance in real-time systems
Pujol Torramorell, Roger; Jorba Jorba, Josep; Tabani, Hamid; Kosmidis, Leonidas; Mezzetti, Enrico; Abella Ferrer, Jaume; Cazorla Almeida, Francisco Javier
The need for increased application performance in high-integrity systems like those in avionics is on the rise as software continues to implement more complex functionalities. The prevalent computing solution for future high-integrity embedded products are multi-processors systems-on-chip (MPSoC) processors. MPSoCs include CPU multicores that enable improving performance via thread-level parallelism. MPSoCs also include generic accelerators (GPUs) and application-specific accelerators. However, the data processing approach (DPA) required to exploit each of these underlying parallel hardware blocks carries several open challenges to enable the safe deployment in high-integrity domains. The main challenges include the qualification of its associated runtime system and the difficulties in analyzing programs deploying the DPA with out-of-the-box timing analysis and code coverage tools. In this work, we perform a thorough analysis of vector extensions (VExt) in current COTS processors for high-integrity systems. We show that VExt prevent many of the challenges arising with parallel programming models and GPUs. Unlike other DPAs, VExt require no runtime support, prevent by design race conditions that might arise with parallel programming models, and have minimum impact on the software ecosystem enabling the use of existing code coverage and timing analysis tools. We develop vectorized versions of neural network kernels and show that the NVIDIA Xavier VExt provide a reasonable increase in guaranteed application performance of up to 2.7x. Our analysis contends that VExt are the DPA approach with arguably the fastest path for adoption in high-integrity systems.
2022-10-04T10:06:05ZPujol Torramorell, RogerJorba Jorba, JosepTabani, HamidKosmidis, LeonidasMezzetti, EnricoAbella Ferrer, JaumeCazorla Almeida, Francisco JavierThe need for increased application performance in high-integrity systems like those in avionics is on the rise as software continues to implement more complex functionalities. The prevalent computing solution for future high-integrity embedded products are multi-processors systems-on-chip (MPSoC) processors. MPSoCs include CPU multicores that enable improving performance via thread-level parallelism. MPSoCs also include generic accelerators (GPUs) and application-specific accelerators. However, the data processing approach (DPA) required to exploit each of these underlying parallel hardware blocks carries several open challenges to enable the safe deployment in high-integrity domains. The main challenges include the qualification of its associated runtime system and the difficulties in analyzing programs deploying the DPA with out-of-the-box timing analysis and code coverage tools. In this work, we perform a thorough analysis of vector extensions (VExt) in current COTS processors for high-integrity systems. We show that VExt prevent many of the challenges arising with parallel programming models and GPUs. Unlike other DPAs, VExt require no runtime support, prevent by design race conditions that might arise with parallel programming models, and have minimum impact on the software ecosystem enabling the use of existing code coverage and timing analysis tools. We develop vectorized versions of neural network kernels and show that the NVIDIA Xavier VExt provide a reasonable increase in guaranteed application performance of up to 2.7x. Our analysis contends that VExt are the DPA approach with arguably the fastest path for adoption in high-integrity systems.A closer look at referring expressions for video object segmentationBellver Bueno, MíriamVentura Royo, CarlesSilberer, CarinaKazakos, IoannisTorres Viñals, JordiGiró Nieto, Xavierhttp://hdl.handle.net/2117/3736422023-01-11T12:44:57Z2022-09-29T09:45:51ZA closer look at referring expressions for video object segmentation
Bellver Bueno, Míriam; Ventura Royo, Carles; Silberer, Carina; Kazakos, Ioannis; Torres Viñals, Jordi; Giró Nieto, Xavier
The task of Language-guided Video Object Segmentation (LVOS) aims at generating binary masks for an object referred by a linguistic expression. When this expression unambiguously describes an object in the scene, it is named referring expression (RE). Our work argues that existing benchmarks used for LVOS are mainly composed of trivial cases, in which referents can be identified with simple phrases. Our analysis relies on a new categorization of the referring expressions in the DAVIS-2017 and Actor-Action datasets into trivial and non-trivial REs, where the non-trivial REs are further annotated with seven RE semantic categories. We leverage these data to analyze the performance of RefVOS, a novel neural network that obtains competitive results for the task of language-guided image segmentation and state of the art results for LVOS. Our study indicates that the major challenges for the task are related to understanding motion and static actions.
2022-09-29T09:45:51ZBellver Bueno, MíriamVentura Royo, CarlesSilberer, CarinaKazakos, IoannisTorres Viñals, JordiGiró Nieto, XavierThe task of Language-guided Video Object Segmentation (LVOS) aims at generating binary masks for an object referred by a linguistic expression. When this expression unambiguously describes an object in the scene, it is named referring expression (RE). Our work argues that existing benchmarks used for LVOS are mainly composed of trivial cases, in which referents can be identified with simple phrases. Our analysis relies on a new categorization of the referring expressions in the DAVIS-2017 and Actor-Action datasets into trivial and non-trivial REs, where the non-trivial REs are further annotated with seven RE semantic categories. We leverage these data to analyze the performance of RefVOS, a novel neural network that obtains competitive results for the task of language-guided image segmentation and state of the art results for LVOS. Our study indicates that the major challenges for the task are related to understanding motion and static actions.The holistic perspective of the INCISIVE Project: artificial intelligence in screening mammographyLazic, IvanAgulló López, FerranAussó Trias, SusannaAlves, BrunoBarelle, CarolineBerral García, Josep LluísBizopoulos, PaschalisBunduc, OanaGutiérrez Torre, Albertohttp://hdl.handle.net/2117/3736372022-12-11T01:54:12Z2022-09-29T09:12:46ZThe holistic perspective of the INCISIVE Project: artificial intelligence in screening mammography
Lazic, Ivan; Agulló López, Ferran; Aussó Trias, Susanna; Alves, Bruno; Barelle, Caroline; Berral García, Josep Lluís; Bizopoulos, Paschalis; Bunduc, Oana; Gutiérrez Torre, Alberto
Finding new ways to cost-effectively facilitate population screening and improve cancer diagnoses at an early stage supported by data-driven AI models provides unprecedented opportunities to reduce cancer related mortality. This work presents the INCISIVE project initiative towards enhancing AI solutions for health imaging by unifying, harmonizing, and securely sharing scattered cancer-related data to ensure large datasets which are critically needed to develop and evaluate trustworthy AI models. The adopted solutions of the INCISIVE project have been outlined in terms of data collection, harmonization, data sharing, and federated data storage in compliance with legal, ethical, and FAIR principles. Experiences and examples feature breast cancer data integration and mammography collection, indicating the current progress, challenges, and future directions.
2022-09-29T09:12:46ZLazic, IvanAgulló López, FerranAussó Trias, SusannaAlves, BrunoBarelle, CarolineBerral García, Josep LluísBizopoulos, PaschalisBunduc, OanaGutiérrez Torre, AlbertoFinding new ways to cost-effectively facilitate population screening and improve cancer diagnoses at an early stage supported by data-driven AI models provides unprecedented opportunities to reduce cancer related mortality. This work presents the INCISIVE project initiative towards enhancing AI solutions for health imaging by unifying, harmonizing, and securely sharing scattered cancer-related data to ensure large datasets which are critically needed to develop and evaluate trustworthy AI models. The adopted solutions of the INCISIVE project have been outlined in terms of data collection, harmonization, data sharing, and federated data storage in compliance with legal, ethical, and FAIR principles. Experiences and examples feature breast cancer data integration and mammography collection, indicating the current progress, challenges, and future directions.A BF16 FMA is all you need for DNN trainingOsorio Ríos, John HaiberArmejach Sanosa, AdriàPetit, EricHenry, GregCasas, Marchttp://hdl.handle.net/2117/3736142023-12-24T03:52:16Z2022-09-29T08:12:58ZA BF16 FMA is all you need for DNN training
Osorio Ríos, John Haiber; Armejach Sanosa, Adrià; Petit, Eric; Henry, Greg; Casas, Marc
Fused Multiply-Add (FMA) functional units constitute a fundamental hardware component to train Deep Neural Networks (DNNs). Its silicon area grows quadratically with the mantissa bit count of the computer number format, which has motivated the adoption of the BrainFloat16 format (BF16). BF16 features 1 sign, 8 exponent and 7 explicit mantissa bits. Some approaches to train DNNs achieve significant performance benefits by using the BF16 format. However, these approaches must combine BF16 with the standard IEEE 754 Floating-Point 32-bit (FP32) format to achieve state-of-the-art training accuracy, which limits the impact of adopting BF16. This article proposes the first approach able to train complex DNNs entirely using the BF16 format. We propose a new class of FMA operators, FMAbf16 n m, that entirely rely on BF16 FMA hardware instructions and deliver the same accuracy as FP32. FMAbf16 n m operators achieve performance improvements within the 1.28-
1.35X range on ResNet101 with respect to FP32. FMAbf16 n m enables training complex DNNs on simple low-end hardware devices without requiring expensive FP32 FMA functional units.
2022-09-29T08:12:58ZOsorio Ríos, John HaiberArmejach Sanosa, AdriàPetit, EricHenry, GregCasas, MarcFused Multiply-Add (FMA) functional units constitute a fundamental hardware component to train Deep Neural Networks (DNNs). Its silicon area grows quadratically with the mantissa bit count of the computer number format, which has motivated the adoption of the BrainFloat16 format (BF16). BF16 features 1 sign, 8 exponent and 7 explicit mantissa bits. Some approaches to train DNNs achieve significant performance benefits by using the BF16 format. However, these approaches must combine BF16 with the standard IEEE 754 Floating-Point 32-bit (FP32) format to achieve state-of-the-art training accuracy, which limits the impact of adopting BF16. This article proposes the first approach able to train complex DNNs entirely using the BF16 format. We propose a new class of FMA operators, FMAbf16 n m, that entirely rely on BF16 FMA hardware instructions and deliver the same accuracy as FP32. FMAbf16 n m operators achieve performance improvements within the 1.28-
1.35X range on ResNet101 with respect to FP32. FMAbf16 n m enables training complex DNNs on simple low-end hardware devices without requiring expensive FP32 FMA functional units.TunaOil: A tuning algorithm strategy for reservoir simulation workloadsAlbuquerque Portella, FelipeBuchaca Prats, DavidRodrigues, José RobertoBerral García, Josep Lluíshttp://hdl.handle.net/2117/3732952022-09-25T18:58:34Z2022-09-22T08:57:30ZTunaOil: A tuning algorithm strategy for reservoir simulation workloads
Albuquerque Portella, Felipe; Buchaca Prats, David; Rodrigues, José Roberto; Berral García, Josep Lluís
Reservoir simulations for petroleum fields and seismic imaging are known as the most demanding workloads for high-performance computing (HPC) in the oil and gas (O&G) industry. The optimization of the simulator numerical parameters plays a vital role as it could save considerable computational efforts. State-of-the-art optimization techniques are based on running numerous simulations, specific for that purpose, to find good parameter candidates. However, using such an approach is highly costly in terms of time and computing resources. This work presents TunaOil, a new methodology to enhance the search for optimal numerical parameters of reservoir flow simulations using a performance model. In the O&G industry, it is common to use ensembles of models in different workflows to reduce the uncertainty associated with forecasting O&G production. We leverage the runs of those ensembles in such workflows to extract information from each simulation and optimize the numerical parameters in their subsequent runs. To validate the methodology, we implemented it in a history matching (HM) process that uses a Kalman filter algorithm to adjust an ensemble of reservoir models to match the observed data from the real field. We mine past execution logs from many simulations with different numerical configurations and build a machine learning model based on extracted features from the data. These features include properties of the reservoir models themselves, such as the number of active cells, to statistics of the simulation’s behavior, such as the number of iterations of the linear solver. A sampling technique is used to query the oracle to find the numerical parameters that can reduce the elapsed time without significantly impacting the quality of the results. Our experiments show that the predictions can improve the overall HM workflow runtime on average by 31%.
2022-09-22T08:57:30ZAlbuquerque Portella, FelipeBuchaca Prats, DavidRodrigues, José RobertoBerral García, Josep LluísReservoir simulations for petroleum fields and seismic imaging are known as the most demanding workloads for high-performance computing (HPC) in the oil and gas (O&G) industry. The optimization of the simulator numerical parameters plays a vital role as it could save considerable computational efforts. State-of-the-art optimization techniques are based on running numerous simulations, specific for that purpose, to find good parameter candidates. However, using such an approach is highly costly in terms of time and computing resources. This work presents TunaOil, a new methodology to enhance the search for optimal numerical parameters of reservoir flow simulations using a performance model. In the O&G industry, it is common to use ensembles of models in different workflows to reduce the uncertainty associated with forecasting O&G production. We leverage the runs of those ensembles in such workflows to extract information from each simulation and optimize the numerical parameters in their subsequent runs. To validate the methodology, we implemented it in a history matching (HM) process that uses a Kalman filter algorithm to adjust an ensemble of reservoir models to match the observed data from the real field. We mine past execution logs from many simulations with different numerical configurations and build a machine learning model based on extracted features from the data. These features include properties of the reservoir models themselves, such as the number of active cells, to statistics of the simulation’s behavior, such as the number of iterations of the linear solver. A sampling technique is used to query the oracle to find the numerical parameters that can reduce the elapsed time without significantly impacting the quality of the results. Our experiments show that the predictions can improve the overall HM workflow runtime on average by 31%.Burst-aware predictive autoscaling for containerized microservicesAbdullah, MuhammadIqbal, WaheedBerral García, Josep LluísPolo Bardés, JordaCarrera Pérez, Davidhttp://hdl.handle.net/2117/3732912022-09-25T18:58:04Z2022-09-22T07:14:45ZBurst-aware predictive autoscaling for containerized microservices
Abdullah, Muhammad; Iqbal, Waheed; Berral García, Josep Lluís; Polo Bardés, Jorda; Carrera Pérez, David
Autoscaling methods are used for cloud-hosted applications to dynamically scale the allocated resources for guaranteeing Quality-of-Service (QoS). The public-facing application serves dynamic workloads, which contain bursts and pose challenges for autoscaling methods to ensure application performance. Existing State-of-the-art autoscaling methods are burst-oblivious to determine and provision the appropriate resources. For dynamic workloads, it is hard to detect and handle bursts online for maintaining application performance. In this article, we propose a novel burst-aware autoscaling method which detects burst in dynamic workloads using workload forecasting, resource prediction, and scaling decision making while minimizing response time service-level objectives (SLO) violations. We evaluated our approach through a trace-driven simulation, using multiple synthetic and realistic bursty workloads for containerized microservices, improving performance when comparing against existing state-of-the-art autoscaling methods. Such experiments show an increase of × 1.09 in total processed requests, a reduction of × 5.17 for SLO violations, and an increase of × 0.767 cost as compared to the baseline method.
2022-09-22T07:14:45ZAbdullah, MuhammadIqbal, WaheedBerral García, Josep LluísPolo Bardés, JordaCarrera Pérez, DavidAutoscaling methods are used for cloud-hosted applications to dynamically scale the allocated resources for guaranteeing Quality-of-Service (QoS). The public-facing application serves dynamic workloads, which contain bursts and pose challenges for autoscaling methods to ensure application performance. Existing State-of-the-art autoscaling methods are burst-oblivious to determine and provision the appropriate resources. For dynamic workloads, it is hard to detect and handle bursts online for maintaining application performance. In this article, we propose a novel burst-aware autoscaling method which detects burst in dynamic workloads using workload forecasting, resource prediction, and scaling decision making while minimizing response time service-level objectives (SLO) violations. We evaluated our approach through a trace-driven simulation, using multiple synthetic and realistic bursty workloads for containerized microservices, improving performance when comparing against existing state-of-the-art autoscaling methods. Such experiments show an increase of × 1.09 in total processed requests, a reduction of × 5.17 for SLO violations, and an increase of × 0.767 cost as compared to the baseline method.A holistic scalability strategy for time series databases following cascading polyglot persistenceGarcía Calatrava, CarlosBecerra Fontal, YolandaCucchietti, Fernandohttp://hdl.handle.net/2117/3728292023-01-01T03:46:09Z2022-09-15T08:07:21ZA holistic scalability strategy for time series databases following cascading polyglot persistence
García Calatrava, Carlos; Becerra Fontal, Yolanda; Cucchietti, Fernando
Time series databases aim to handle big amounts of data in a fast way, both when introducing new data to the system, and when retrieving it later on. However, depending on the scenario in which these databases participate, reducing the number of requested resources becomes a further requirement. Following this goal, NagareDB and its Cascading Polyglot Persistence approach were born. They were not just intended to provide a fast time series solution, but also to find a great cost-efficiency balance. However, although they provided outstanding results, they lacked a natural way of scaling out in a cluster fashion. Consequently, monolithic approaches could extract the maximum value from the solution but distributed ones had to rely on general scalability approaches. In this research, we proposed a holistic approach specially tailored for databases following Cascading Polyglot Persistence to further maximize its inherent resource-saving goals. The proposed approach reduced the cluster size by 33%, in a setup with just three ingestion nodes and up to 50% in a setup with 10 ingestion nodes. Moreover, the evaluation shows that our scaling method is able to provide efficient cluster growth, offering scalability speedups greater than 85% in comparison to a theoretically 100% perfect scaling, while also ensuring data safety via data replication.
2022-09-15T08:07:21ZGarcía Calatrava, CarlosBecerra Fontal, YolandaCucchietti, FernandoTime series databases aim to handle big amounts of data in a fast way, both when introducing new data to the system, and when retrieving it later on. However, depending on the scenario in which these databases participate, reducing the number of requested resources becomes a further requirement. Following this goal, NagareDB and its Cascading Polyglot Persistence approach were born. They were not just intended to provide a fast time series solution, but also to find a great cost-efficiency balance. However, although they provided outstanding results, they lacked a natural way of scaling out in a cluster fashion. Consequently, monolithic approaches could extract the maximum value from the solution but distributed ones had to rely on general scalability approaches. In this research, we proposed a holistic approach specially tailored for databases following Cascading Polyglot Persistence to further maximize its inherent resource-saving goals. The proposed approach reduced the cluster size by 33%, in a setup with just three ingestion nodes and up to 50% in a setup with 10 ingestion nodes. Moreover, the evaluation shows that our scaling method is able to provide efficient cluster growth, offering scalability speedups greater than 85% in comparison to a theoretically 100% perfect scaling, while also ensuring data safety via data replication.