How to improve performance and decrease power in neural networks.
Executing a neural network on top of an NPU requires an understanding of application requirements, such as latency and throughput, as well as the potential partitioning challenges. Sharad Chole, chief scientist and co-founder of Expedera, talks about fine-grained dependencies, why processing packets out of order can help optimize performance and power, and when to use voltage and frequency scaling versus clock gating.
[embedded content]
Ed Sperling
(all posts)
Ed Sperling is the editor in chief of Semiconductor Engineering.
- SEO Powered Content & PR Distribution. Get Amplified Today.
- PlatoData.Network Vertical Generative Ai. Empower Yourself. Access Here.
- PlatoAiStream. Web3 Intelligence. Knowledge Amplified. Access Here.
- PlatoESG. Carbon, CleanTech, Energy, Environment, Solar, Waste Management. Access Here.
- PlatoHealth. Biotech and Clinical Trials Intelligence. Access Here.
- Source: https://semiengineering.com/application-optimized-processors/
- :is
- 25
- 27
- 41
- 66
- 7
- 80
- a
- About
- All
- All Posts
- an
- and
- Application
- AS
- CAN
- challenges
- chief
- Clock
- Co-founder
- content
- decrease
- dependencies
- ed
- editor
- embedded
- Engineering
- Ether (ETH)
- Frequency
- help
- HTTPS
- improve
- in
- jpg
- Latency
- network
- networks
- Neural
- neural network
- neural networks
- of
- on
- Optimize
- order
- out
- packets
- performance
- photo
- plato
- Plato Data Intelligence
- PlatoData
- popularity
- Posts
- potential
- power
- processing
- processors
- Requirements
- requires
- ROW
- scaling
- Scientist
- semiconductor
- such
- Talks
- The
- throughput
- thumbnail
- to
- top
- understanding
- use
- Versus
- Voltage
- WELL
- when
- why
- youtube
- zephyrnet
More from Semi Engineering
Reducing Contact Resistance in Developing Transistors Based On 2D Materials
Source Node: 2008134
Time Stamp: Mar 10, 2023
Big Changes Ahead In Power Delivery, Materials, And Interconnects
Source Node: 2024182
Time Stamp: Mar 22, 2023
Agile HW Design: Fully Automatic Equivalence Checking Workflow
Source Node: 1990786
Time Stamp: Mar 3, 2023
Innovations in Device Design of The Gate-All-Around (GAA) Nanosheet FETs (IBM Research)
Source Node: 2537129
Time Stamp: Mar 23, 2023
How Attackers Can Read Data From CPU’s Memory By Analyzing Energy Consumption
Source Node: 2808650
Time Stamp: Aug 7, 2023
Covert Channel Between the CPU and An FPGA By Modulating The Usage of the Power Distribution Network
Source Node: 2553492
Time Stamp: Mar 30, 2023
