Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Gaussian Elimination: Problem Solving01:30

Gaussian Elimination: Problem Solving

65
Systems of linear equations in several variables are pivotal in modeling complex scenarios involving multiple unknowns and constraints. Such systems are widely used in various fields to represent relationships where several conditions must be simultaneously satisfied. Each variable in the system corresponds to an unknown quantity, while each equation imposes a linear constraint, leading to a structured approach for analyzing and solving real-world problems.A system of three equations with three...
65
Parallel Processing01:20

Parallel Processing

447
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
447
Improving Translational Accuracy02:07

Improving Translational Accuracy

12.8K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
12.8K
Improving Translational Accuracy02:07

Improving Translational Accuracy

3.3K
3.3K
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

180
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
180
Ampere-Maxwell's Law: Problem-Solving01:17

Ampere-Maxwell's Law: Problem-Solving

934
A parallel-plate capacitor with capacitance C, whose plates have area A and separation distance d, is connected to a resistor R and a battery of voltage V. The current starts to flow at t = 0. What is the displacement current between the capacitor plates at time t? From the properties of the capacitor, what is the corresponding real current?
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of the...
934

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Molecular phylogeny of plant pathogenic fungi based on start codon targeted (SCoT) polymorphism.

Molecular biology reports·2023
Same author

Analysis of genetic diversity among common bean germplasm by start codon targeted (SCoT) markers.

Molecular biology reports·2022
Same author

Stochastic rounding: implementation, error analysis and applications.

Royal Society open science·2022
Same author

Monitoring of Host Suitability and Defense-Related Genes in Wheat to <i>Bipolaris sorokiniana</i>.

Journal of fungi (Basel, Switzerland)·2022
Same author

Characterization and Pathogenicity of Rhizoctonia Species Causing Root Rot and Damping-off on Sugar Beet in Turkey.

Current microbiology·2021
Same author

Numerical behavior of NVIDIA tensor cores.

PeerJ. Computer science·2021
Same journal

Computational modelling distinguishes diverse contributors to aneurysmal progression in the Marfan aorta.

Proceedings. Mathematical, physical, and engineering sciences·2025
Same journal

Inferring the shape of data: a probabilistic framework for analysing experiments in the natural sciences.

Proceedings. Mathematical, physical, and engineering sciences·2023
Same journal

The Elbert range of magnetostrophic convection. I. Linear theory.

Proceedings. Mathematical, physical, and engineering sciences·2022
Same journal

Soft wetting with (a)symmetric Shuttleworth effect.

Proceedings. Mathematical, physical, and engineering sciences·2022
Same journal

The quantum theory of time: a calculus for q-numbers.

Proceedings. Mathematical, physical, and engineering sciences·2022
Same journal

Integrable nonlinear evolution equations in three spatial dimensions.

Proceedings. Mathematical, physical, and engineering sciences·2022
See all related articles

Related Experiment Video

Updated: Nov 24, 2025

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform
06:25

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

Published on: February 12, 2014

8.7K

Mixed-precision iterative refinement using tensor cores on GPUs to accelerate solution of linear systems.

Azzam Haidar1, Harun Bayraktar1, Stanimire Tomov2

  • 1NVIDIA, Santa Clara, CA, USA.

Proceedings. Mathematical, Physical, and Engineering Sciences
|December 28, 2020
PubMed
Summary
This summary is machine-generated.

Researchers accelerated scientific simulations using mixed-precision computing on NVIDIA GPUs. This approach leverages half-precision (FP16) and single-precision (FP32) arithmetic to significantly boost performance and energy efficiency while maintaining double-precision (FP64) numerical stability.

Keywords:
GMRESGPU computingLU factorizationhalf precision arithmeticiterative refinementmixed precision solvers

More Related Videos

Optical Coherence Tomography Based Biomechanical Fluid-Structure Interaction Analysis of Coronary Atherosclerosis Progression
13:07

Optical Coherence Tomography Based Biomechanical Fluid-Structure Interaction Analysis of Coronary Atherosclerosis Progression

Published on: January 15, 2022

4.2K
Advanced Workflow for Taking High-Quality Increment Cores - New Techniques and Devices
07:40

Advanced Workflow for Taking High-Quality Increment Cores - New Techniques and Devices

Published on: March 10, 2023

2.6K

Related Experiment Videos

Last Updated: Nov 24, 2025

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform
06:25

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

Published on: February 12, 2014

8.7K
Optical Coherence Tomography Based Biomechanical Fluid-Structure Interaction Analysis of Coronary Atherosclerosis Progression
13:07

Optical Coherence Tomography Based Biomechanical Fluid-Structure Interaction Analysis of Coronary Atherosclerosis Progression

Published on: January 15, 2022

4.2K
Advanced Workflow for Taking High-Quality Increment Cores - New Techniques and Devices
07:40

Advanced Workflow for Taking High-Quality Increment Cores - New Techniques and Devices

Published on: March 10, 2023

2.6K

Area of Science:

  • High-performance computing
  • Numerical analysis
  • Scientific simulations

Background:

  • Double-precision (FP64) is the standard for scientific simulations.
  • Increasing data volumes and problem complexity necessitate optimized computational resources.
  • Machine learning has driven hardware advancements in reduced-precision arithmetic, like half-precision (FP16).

Purpose of the Study:

  • To demonstrate the effective use of reduced-precision hardware (NVIDIA Tensor Cores) for solving linear systems.
  • To accelerate computations without compromising numerical stability.
  • To improve the energy efficiency of scientific simulations.

Main Methods:

  • Exploiting FP16/FP32 Tensor Cores on NVIDIA GPUs.
  • Employing multiprecision LU factorization and preconditioned generalized minimal residual (GMRES) algorithm.
  • Utilizing scaling and auto-adaptive rounding to prevent numerical overflow.
  • Efficiently handling systems with multiple right-hand sides.

Main Results:

  • Significant performance increase on NVIDIA Quadro GV100 (Volta) GPU.
  • Achieved 5x better energy efficiency compared to standard FP64 implementations.
  • Maintained FP64 level of numerical stability throughout the computations.

Conclusions:

  • Mixed-precision techniques enable substantial acceleration and energy savings in scientific computing.
  • NVIDIA Tensor Cores can be effectively utilized for solving linear systems with reduced precision.
  • The proposed methods offer a viable path to leverage modern hardware for complex simulations.