Visualizing the world’s largest turbulence simulation

Cielo, Salvatore; Iapichino, Luigi; Günther, Johannes; Federrath, Christoph; Mayer, Elisabeth; Wiedemann, Michael

doi:10.1016/j.parco.2021.102758

Cited by 4 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…OSPRay installations have shown massive improvements over GL or Mesa, especially for real-time interactive visualization and when performing large tasks on KNL and Intel Xeon architecture [43]. While this is an appealing solution, its investigation will be left to future studies [44]. For the moment we conclude that the Mesa version of VISIT can already take a huge advantage Fig.…”

Section: B Visit: Discussion On Cpu-defined Performancementioning

confidence: 86%

Honing and proofing Astrophysical codes on the road to Exascale. Experiences from code modernization on many-core systems

Cielo,

Iapichino,

Baruffa

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

The complexity of modern and upcoming computing architectures poses severe challenges for code developers and application specialists, and forces them to expose the highest possible degree of parallelism, in order to make the best use of the available hardware. The Intel R Xeon Phi TM of second generation (code-named Knights Landing, henceforth KNL) is the latest many-core system, which implements several interesting hardware features like for example a large number of cores per node (up to 72), the 512 bits-wide vector registers and the high-bandwidth memory. The unique features of KNL make this platform a powerful testbed for modern HPC applications. The performance of codes on KNL is therefore a useful proxy of their readiness for future architectures. In this work we describe the lessons learnt during the optimisation of the widely used codes for computational astrophysics P-GADGET3, FLASH and ECHO. Moreover, we present results for the visualisation and analysis tools VISIT and yt. These examples show that modern architectures benefit from code optimisation at different levels, even more than traditional multi-core systems. However, the level of modernisation of typical community codes still needs improvements, for them to fully utilise resources of novel architectures.

show abstract

Section: B Visit: Discussion On Cpu-defined Performancementioning

confidence: 86%

Honing and proofing Astrophysical codes on the road to Exascale. Experiences from code modernization on many-core systems

Cielo,

Iapichino,

Baruffa

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Game engines had previously been used in CAVE systems [15], in that case, however, the CAVE did not support stereoscopy and was not equipped with a tracking system. With the development of the nDisplay plugin 4 , it was possible to use UE4 4 https://docs.unrealengine.com/4.27/en-US/ for a CAVE and a Powerwall display setup, which only required the addition of tracking via VRPN [26].…”

Section: Phasementioning

confidence: 99%

Ten years Center for Immersive Visualizations - Past, Present, and Future

Mayer

Hernández²,

Kolb

et al. 2023

2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW)

Self Cite

View full text Add to dashboard Cite

Virtual Reality (VR) can be found in many fields. A majority of the time this involves the use of Head-Mounted Displays (HMDs). Their alternatives, large-scale immersive 3D screens and CAVE systems, can also be found in research and offer researchers high visual quality and collaborative VR experiences. This report covers the operation and learnings from maintaining a visualization center with large-scale immersive installations over the course of ten years.

show abstract

“…Accelerators are also a very good example to illustrate why accounting models should not be directly linked with peak performance. Modern GPU accelerators' double precision floating point (DP FLOPs) performance is 200x higher compared to DP FLOPS performance of single cores of modern CPU architectures 1 . If we were to base the GPU charging rate on the ratio between GPU peak performance and the one of a single CPU core, then we would be using a factor that high.…”

Section: B System Architecturementioning

confidence: 99%

“…The CSC's Puhti node sharing accounting model discussed in previous subsection is an interesting heterogeneous model which provides a good introduction to our model. Puhti is based on Intel Xeon Gold 6230 "Cascade Lake" and NVIDIA 1 Comparing NVIDIA A100 architecture (9.7 DP TFLOPs) with AMD EPYC 64-core Milan 7763 (2.5 DP TFLOPs). 2 OLCF's Summit system achieves 74% of peak performance on High Performance Linpack benchmark [13] V100 with NVLink architectures.…”

Section: B System Architecturementioning

confidence: 99%

“…Computer-enabled investigations such as simulations and big data analysis count an ever-increasing number of calculations, requiring an outstanding amount of resources to execute [1]. Two items make up the cost for a researcher to run computations: the time required for the computation to run to completion and the compute bandwidth of the system employed.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Energy-based Accounting Model for Heterogeneous Supercomputers

Pietrantonio¹,

Harris²,

Cytowski³

2021

Preprint

View full text Add to dashboard Cite

In this paper we present a new accounting model for heterogeneous supercomputers. An increasing number of supercomputing centres adopt heterogeneous architectures consisting of CPUs and hardware accelerators for their systems. Accounting models using the core hour as unit of measure are redefined to provide an appropriate charging rate based on the computing performance of different processing elements, as well as their energy efficiency and purchase price. In this paper we provide an overview of existing models and define a new model that, while retaining the core hour as a fundamental concept, takes into account the interplay among resources such as CPUs and RAM, and that bases the GPU charging rate on energy consumption. We believe that this model, designed for Pawsey Supercomputing Research Centre's (Pawsey) next supercomputer Setonix, has a lot of advantages compared to other models, introducing carbon footprint as a primary driver in determining the allocation of computational workflow on heterogeneous resources.

show abstract

Visualizing the world’s largest turbulence simulation

Cited by 4 publications

References 21 publications

Honing and proofing Astrophysical codes on the road to Exascale. Experiences from code modernization on many-core systems

Honing and proofing Astrophysical codes on the road to Exascale. Experiences from code modernization on many-core systems

Ten years Center for Immersive Visualizations - Past, Present, and Future

Energy-based Accounting Model for Heterogeneous Supercomputers

Contact Info

Product

Resources

About