Structured Sparse Matrix Compression for Systolic Array Acceleration

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing AI workloads, particularly those involving large language models, face challenges in efficiently processing sparse data due to limited techniques for accelerating fine-grained and structured fine-grained sparsity, leading to computational inefficiencies and trade-offs in hardware resources.

Innovation Solution

A hardware accelerator is designed to compress sparse input matrices based on sparsity factors, using multiplexor circuits and index arrays to generate multiplier matrices, while supporting block-scaled data formats, thereby reducing data streaming and enabling efficient matrix multiplication without loss of accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If techniques are used to accelerate fine-grained and structured fine-grained sparse workloads, then processing speed for sparse data is improved, but hardware resources and computational efficiency deteriorate due to limited acceleration techniques and specific sparsity factor requirements

Engineering Contradiction:
Improveprocessing speed for sparse workloadsVSAvoidhardware resource requirements
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The hardware accelerator is designed with a universal architecture that can handle multiple types of workloads (dense, coarse-grained sparse, fine-grained sparse, and structured fine-grained sparse) using the same data path and computational units. The system uses configurable sparsity handling mechanisms that can be adjusted based on the input data characteristics, eliminating the need for separate dedicated hardware for each workload type.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The accelerator employs dynamic sparsity detection and handling mechanisms that adapt to the actual sparsity patterns in the input data. The system can dynamically switch between different processing modes (dense mode, sparse mode with various sparsity factors) based on the detected characteristics of the incoming workload, optimizing resource utilization for each specific case.

Inventive Principle:
Principle #15Dynamics

2Quantity of substance

If sparse data compression is applied, then data streaming requirements are reduced, but processing complexity increases due to the need for multiplexor circuits and index arrays

Engineering Contradiction:
Improvedata volume for streamingVSAvoidcircuit complexity for compression
Core Design Contradiction:
Quantity of substanceVSDevice complexity

Solution Approach 1:

The system performs preliminary compression of sparse data before it enters the main computation pipeline. By pre-compressing the input matrices and pre-computing index arrays that map compressed elements to their original positions, the system reduces the data volume that needs to be streamed and processed, while the compression overhead is paid once before the main acceleration benefit is realized.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

Index arrays serve as intermediary structures that bridge the compressed data format and the original data layout required for computation. These index arrays enable the hardware to efficiently access and process only the non-zero elements of sparse matrices without requiring complex decompression circuits, by directly mapping compressed element positions to their computational roles.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Quantity of substance

If block quantization is used to represent data, then memory efficiency is improved, but precision is reduced due to lossy approximation

Engineering Contradiction:
Improvememory storage requirementsVSAvoiddata precision
Core Design Contradiction:
Quantity of substanceVSMeasurement precision

Solution Approach 1:

The system changes the precision parameter of data representation by applying block quantization, where blocks of floating-point values are approximated using lower-precision formats (such as INT8 or INT4) with shared scaling factors. This parameter change reduces memory storage requirements and increases data throughput, while the lossy approximation is managed through careful scaling factor selection and post-processing to minimize accuracy degradation.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4629105A1Structured sparse matrix acceleration in systolic arrays
Publication Date: 2025.10.08 GOOGLE LLC
  • EP4629105A1 patent drawingFigure 1
  • EP4629105A1 patent drawingFigure 2A
  • EP4629105A1 patent drawingFigure 2B

AI summary

Methods, systems, and apparatus, including computer-readable storage media for hardware-accelerated fine-grained sparse computation. The accelerator provides for improved performance for structured fine-grained sparse AI workloads, for example by accelerating sparse matrix multiplication required to execute or train AI models. Sparse data is compressed to remove zero-valued elements before being streamed into a matrix multiplication unit (MXU) of the accelerator. The accelerator stores a gains matrix, which can be the matrix for multiplying with the received input matrix. The accelerator uses an index array mapping locations of elements in the compressed matrix with locations of elements in the matrix's precompressed form, to generate a multiplier matrix from the gains matrix. Aspects of the disclosure also provide for accelerated gains matrix loading in a hardware accelerator or other type of processor. The accelerator can load the gains matrix more efficiently in a compressed form, and then un-compress the matrix once loaded.