Weight Memory Mapping for Low-Latency Transformer Matrix Multiplication

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Generative artificial intelligence models, particularly those with a transformer structure, suffer from high latency due to limited parallelism of operations, necessitating an efficient weight memory mapping method to reduce hardware latency.

Innovation Solution

A weight memory mapping system and method that includes a weight memory, input register, and hardware operators for matrix multiplication operations, utilizing lane-level final sums and partial sum reuse to accelerate processing, and preprocessing operations using computed final sums to reduce latency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If transformer structure is used for generative AI models, then model performance is improved, but hardware latency increases due to limited parallelism of operations

Engineering Contradiction:
Improvemodel performanceVSAvoidhardware latency
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent segments the weight matrix into multiple column groups and processes them through multiple hardware operators in parallel. Each hardware operator handles a specific column group, allowing simultaneous computation of multiple partial sums. This segmentation enables the system to maintain transformer model performance while reducing hardware latency by increasing operational parallelism through divided computation paths.

Inventive Principle:
Principle #1Segmentation

2Device complexity

If conventional weight mapping method is used, then hardware structure is simple, but computational throughput is low and resource efficiency is poor

Engineering Contradiction:
Improvehardware structureVSAvoidcomputational throughput
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The patent implements preliminary action by pre-processing weight data before it enters the hardware operators. The weight data is organized into column groups and prepared in advance, allowing the hardware operators to immediately begin computation without waiting for data preparation. This preliminary organization of weight matrices enables higher computational throughput while maintaining efficient resource utilization, as the hardware structure remains relatively simple but operates at optimized speeds.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4730203A1Weight memory mapping method and system for streaming operation of massively generated artificial intelligence hardware
Publication Date: 2026.04.22 HYPERACCEL CO LTD
  • EP4730203A1 patent drawingFigure 1~2
  • EP4730203A1 patent drawingFigure 3~4
  • EP4730203A1 patent drawingFigure 5~6

AI summary

Provided are a weight memory mapping method and a system for a streaming operation of massively generated artificial intelligence hardware. A weight memory mapping system according to an embodiment may comprise: a weight memory for storing a weight matrix for a pre-trained artificial intelligence model; an input register for storing a plurality of pieces of input data; a first hardware operator for processing a matrix multiplication operation between the plurality of pieces of input data and the weight matrix, and calculating a final sum in lane units during the matrix multiplication operation by reusing a partial sum of the matrix multiplication operation; and a second hardware operator for processing, in advance, a next matrix multiplication operation during the matrix multiplication operation by using the final sum.