P006Filed

Cache-Aware Ternary Inference on NPU

Precision shifts on the fly — full power when needed, whisper-quiet when not.

AU Application
2023900006
Filing Date
10 February 2023
Index Number
P006
Figures
13 figures
Batch / Category
Core 1

Explore the Vision

Discover this technology through five complementary perspectives — from technical architecture to partnership outcomes. Each layer reveals a different aspect of how this innovation creates value.

Precision shifts on the fly — full power when needed, whisper-quiet when not.

What It IS

Technical Vision

The architectural essence — what makes this technology work

A neural network breathing — expanding to higher precision for complex decisions, contracting to ultra-efficient ternary for routine inference. The chip pulses between states like a living organism managing its energy. Computational respiration.

1/5
Explore the buyer's journey across 5 perspectives

Abstract

Methods for optimizing data locality and cache utilization in ternary neural network inference on Binary NPU architectures, reducing memory bandwidth pressure.

Visual Essence

A neural network breathing — expanding to higher precision for complex decisions, contracting to ultra-efficient ternary for routine inference. The chip pulses between states like a living organism managing its energy. Computational respiration.

Visual Family:silicon-awakening

Technology Domains

Related Patents

From the silicon-awakening visual family