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

Improving Translational Accuracy02:07

Improving Translational Accuracy

8.6K
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...
8.6K
Parallel Processing01:20

Parallel Processing

145
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...
145
Ampere-Maxwell's Law: Problem-Solving01:17

Ampere-Maxwell's Law: Problem-Solving

531
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...
531
Reducing Line Loss01:18

Reducing Line Loss

143
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
143
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

39
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...
39
Machines: Problem Solving II01:30

Machines: Problem Solving II

293
Machines are complex structures consisting of movable, pin-connected multi-force members that work together to transmit forces. Consider a lifting tong carrying a 100 kg load. It comprises movable sections DAF and CBG linked together with member AB.
293

You might also read

Related Articles

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

Sort by
Same author

Traumatic pseudophacocele with subconjunctival PCIOL and fractured haptic.

Eye (London, England)·2026
Same author

Giant facial congenital melanocytic naevus causing mechanical ptosis.

Eye (London, England)·2026
Same author

Elucidating the Role of Pelargonidin-3-O-Glucoside on <i>C1QL3</i>, <i>CYBB</i>, and <i>CYTIP</i> Involved in Glucose Metabolism: An <i>In Silico</i> Approach.

Journal of pharmacy & bioallied sciences·2024
Same author

Feedforward and feedback interactions between visual cortical areas use different population activity patterns.

Nature communications·2022
Same author

Decision Signals in the Local Field Potentials of Early and Mid-Level Macaque Visual Cortex.

Cerebral cortex (New York, N.Y. : 1991)·2020
Same author

Particulate Study on NeoProfen, a Neonatal Injectable Product.

PDA journal of pharmaceutical science and technology·2016

Related Experiment Video

Updated: Jun 2, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

494

AxLaM: energy-efficient accelerator design for language models for edge computing.

Tom Glint1, Bhumika Mittal2, Santripta Sharma2

  • 1Forschungszentrum Jülich, Jülich, Germany.

Philosophical Transactions. Series A, Mathematical, Physical, and Engineering Sciences
|January 16, 2025
PubMed
Summary

This study introduces AxLaM, an energy-efficient hardware accelerator for modern language models. AxLaM significantly reduces power consumption and improves performance, enabling advanced AI on edge devices.

Keywords:
hardware acceleratorlanguage model BERTtransformer accelerator

More Related Videos

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

482
P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
06:09

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Published on: September 8, 2023

491

Related Experiment Videos

Last Updated: Jun 2, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

494
Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

482
P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
06:09

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Published on: September 8, 2023

491

Area of Science:

  • Computer Engineering
  • Artificial Intelligence
  • Hardware Acceleration

Background:

  • Modern language models, like Bidirectional Encoder Representations from Transformers, excel at Natural Language Processing (NLP) but are power-hungry.
  • Their high computational demands hinder deployment on resource-constrained edge devices.

Purpose of the Study:

  • To design an energy-efficient hardware accelerator for encoder-based language models.
  • To enable the integration of advanced NLP capabilities into mobile and edge computing platforms.

Main Methods:

  • Developed a data-flow-aware hardware accelerator, AxLaM, inspired by the Simba architecture.
  • Incorporated approximate fixed-point POSIT-based multipliers and High Bandwidth Memory (HBM).

Main Results:

  • AxLaM achieved a ninefold energy reduction, 58% area reduction, and 1.2x improved latency compared to Simba.
  • Demonstrated an energy efficiency of 1.8 TOPS/W, surpassing FACT by 65%.

Conclusions:

  • AxLaM offers a viable solution for deploying computationally intensive language models on edge devices.
  • The design significantly enhances computational efficiency and reduces power consumption for edge AI applications.